From acde70bc67355bee573377655dd1386acfb203af Mon Sep 17 00:00:00 2001
From: Alexander Froch <Alexander.Froch@cern.ch>
Date: Mon, 22 Jun 2026 16:04:14 +0200
Subject: [PATCH 01/13] Honour configured jets_name in remaining stages

Several stages assumed the literal "jets" group instead of the configured
jets_name, breaking object-agnostic preprocessing for non-"jets" object names.

- split_containers: use config.jets_name for batch access; pass jets_name to
  the H5Reader/H5Writer calls that previously defaulted to "jets".
- rw_merge: use config.jets_name for attr_to_write and variables keys; thread
  jets_name through do_merge_with_weights into its H5Reader/H5Writer.
- reweight: pass jets_name to the input H5Reader and the fallback all_vars key.
- download_and_prepare: pass jets_name to the metadata H5Reader.

Add an end-to-end integration test (and fixture) that renames the mock object
group to "objects" and runs split -> weights -> merge with jets_name: objects,
asserting the output uses "objects" and no hardcoded "jets" group remains.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---
 .../fixtures/test_config_rw_custom_name.yaml  | 94 +++++++++++++++++++
 tests/integration/test_run_rw.py              | 41 ++++++++
 tests/unit/stages/test_reweight.py            |  1 +
 upp/grid/download_and_prepare.py              |  1 +
 upp/stages/reweight.py                        |  5 +-
 upp/stages/rw_merge.py                        | 19 +++-
 upp/stages/split_containers.py                | 24 +++--
 7 files changed, 171 insertions(+), 14 deletions(-)
 create mode 100644 tests/integration/fixtures/test_config_rw_custom_name.yaml

diff --git a/tests/integration/fixtures/test_config_rw_custom_name.yaml b/tests/integration/fixtures/test_config_rw_custom_name.yaml
new file mode 100644
index 0000000..b6fb4c0
--- /dev/null
+++ b/tests/integration/fixtures/test_config_rw_custom_name.yaml
@@ -0,0 +1,94 @@
+variables:
+  objects:
+    inputs:
+      - pt
+      - eta
+    labels:
+      - mass
+      - eventNumber
+
+  tracks:
+    inputs:
+      - dphi
+      - deta
+      - qOverP
+    labels:
+      - qOverP
+      - leptonID
+global_cuts: !include GN3V01/simple-split.yaml
+
+ttbar: &ttbar
+  name: ttbar
+  equal_jets: False
+  pattern:
+    - "data1.h5"
+    - "data2.h5"
+
+zprime: &zprime
+  name: zprime
+  equal_jets: False
+  pattern:
+    - "data3.h5"
+
+lowpt: &lowpt
+  name: lowpt
+  cuts:
+    - [pt, ">", 20_000]
+    - [pt, "<", 250_000]
+    - [eta, "<", 2.5]
+    - [eta, ">", -2.5]
+
+highpt: &highpt
+  name: highpt
+  cuts:
+    - [pt, ">", 250_000]
+    - [pt, "<", 6_000_000]
+    - [eta, "<", 2.5]
+    - [eta, ">", -2.5]
+
+components:
+  - region:
+      <<: *lowpt
+    sample:
+      <<: *ttbar
+    flavours: [bjets, cjets, ujets, taujets]
+    num_jets: -1
+
+  - region:
+      <<: *highpt
+    sample:
+      <<: *zprime
+    flavours: [bjets, cjets, ujets, taujets]
+    num_jets: -1
+
+reweighting:
+  num_jets_estimate: 200
+  merge_num_proc: 1
+  reweights:
+    - group: objects
+      reweight_vars: [pt, eta]
+      bins:
+        pt:
+          [
+            [20_000, 250_000, 50],
+            [250_000, 1_000_000, 50],
+            [1_000_000, 6_000_000, 50],
+          ]
+        eta: [[-2.5, 2.5, 40]]
+      class_var: flavour_label
+      class_target: mean
+    - group: tracks
+      reweight_vars: [deta]
+      bins:
+        deta: [[-1.0, 1.0, 50]]
+      class_var: leptonID
+      class_target: mean
+
+# note: sensible defaults are defined in the PreprocessingConfig constructor
+global:
+  jets_name: objects
+  batch_size: 1_000_000
+  num_jets_estimate: 25_000_000
+  base_dir: tmp/upp-tests/integration/temp_workspace/
+  out_dir: test_out
+  ntuple_dir: ntuples
diff --git a/tests/integration/test_run_rw.py b/tests/integration/test_run_rw.py
index 1c07c8c..a074473 100644
--- a/tests/integration/test_run_rw.py
+++ b/tests/integration/test_run_rw.py
@@ -127,6 +127,47 @@ def test_rw(self):
         self._calculate_weights()
         self._rw_merge()
 
+    def _rename_mock_group(self, fname, old="jets", new="objects"):
+        """Rename the main object group in a mock file (jets -> objects)."""
+        with h5py.File(fname, "a") as f:
+            f.move(old, new)
+
+    def test_rw_custom_object_name(self):
+        """End-to-end reweighting with a non-"jets" object group name.
+
+        Guards against hardcoded "jets" references: the input group is renamed
+        to "objects" and the config sets jets_name: objects. Every stage must
+        honour the configured name rather than assuming "jets".
+        """
+        for container in ["data1.h5", "data2.h5", "data3.h5"]:
+            self._rename_mock_group(f"tmp/upp-tests/integration/temp_workspace/ntuples/{container}")
+
+        config = str(Path(this_dir / "fixtures/test_config_rw_custom_name.yaml"))
+
+        # Split
+        main(["--config", config, "--split", "train", "--split-components", *self.no])
+
+        # Calculate weights
+        main(["--config", config, "--rw", *self.no])
+        hist_file = Path("tmp/upp-tests/integration/temp_workspace/test_out/histograms.h5")
+        with h5py.File(hist_file, "r") as f:
+            assert f.keys() == {"objects", "tracks"}, (
+                f"Expected 'objects'/'tracks' groups, found {f.keys()}"
+            )
+
+        # Merge with weights
+        for split in ["train", "val", "test"]:
+            main(["--config", config, "--rwm", "--split", split, *self.no])
+            outfile = Path(
+                f"tmp/upp-tests/integration/temp_workspace/test_out/pp_output_{split}_vds.h5"
+            )
+            assert outfile.exists()
+            with h5py.File(outfile, "r") as f:
+                assert "objects" in f, "Expected 'objects' group in output file"
+                assert "jets" not in f, "Output must not contain a hardcoded 'jets' group"
+                assert "flavour_label" in f["objects"].attrs
+                assert "flavour_label" in f["objects"].dtype.names
+
     def test_rw_unequal_jets(self):
         """Test reweighting when a file has fewer jets than num_jets_estimate.
 
diff --git a/tests/unit/stages/test_reweight.py b/tests/unit/stages/test_reweight.py
index 59b33f3..8c409e0 100644
--- a/tests/unit/stages/test_reweight.py
+++ b/tests/unit/stages/test_reweight.py
@@ -39,6 +39,7 @@ def _make_reweight_obj(tmpdir, jets_per_flavour, num_jets_estimate, batch_size=1
     config = MagicMock()
     config.batch_size = batch_size
     config.base_dir = str(tmpdir)
+    config.jets_name = "jets"
 
     rw_config = SimpleNamespace(num_jets_estimate=num_jets_estimate, reweights=[])
 
diff --git a/upp/grid/download_and_prepare.py b/upp/grid/download_and_prepare.py
index 9abe1b3..fe74a5d 100644
--- a/upp/grid/download_and_prepare.py
+++ b/upp/grid/download_and_prepare.py
@@ -134,6 +134,7 @@ def create_meta_data(
         split: {
             flavour: H5Reader(
                 files_by_component[split][flavour],
+                jets_name=pp_config.jets_name,
             ).num_jets
             for flavour in files_by_component[split]
         }
diff --git a/upp/stages/reweight.py b/upp/stages/reweight.py
index 99ff3b2..03019fe 100644
--- a/upp/stages/reweight.py
+++ b/upp/stages/reweight.py
@@ -48,6 +48,7 @@ def get_input_readers(self):
             f: H5Reader(
                 files_by_flavour[f],
                 batch_size=self.config.batch_size,
+                jets_name=self.config.jets_name,
             )
             for f in files_by_flavour
         }
@@ -116,8 +117,8 @@ def calculate_weights(
             all_vars[rw_group].extend(rw.reweight_vars)
             if "valid" in existing_vars[rw_group]:
                 all_vars[rw_group] += ["valid"]
-        if "jets" not in all_vars:
-            all_vars["jets"] = ["pt"]
+        if self.config.jets_name not in all_vars:
+            all_vars[self.config.jets_name] = ["pt"]
         all_vars = {k: list(set(v)) for k, v in all_vars.items()}
         num_in_hists = {}
         all_histograms = {}
diff --git a/upp/stages/rw_merge.py b/upp/stages/rw_merge.py
index 36f9576..6965858 100644
--- a/upp/stages/rw_merge.py
+++ b/upp/stages/rw_merge.py
@@ -39,7 +39,7 @@ def __init__(self, config, outfile_idx_range=None):
 
         num_jets = sum(organised_components["num_jets"][self.config.split].values())
         self.attr_to_write = {
-            "jets": {
+            self.config.jets_name: {
                 "flavour_label": [f.name for f in self.config.components.flavours],
             },
             None: {
@@ -70,6 +70,7 @@ def run(self):
             "fname": all_files,
             "batch_size": batch_size,
             "shuffle": False,
+            "jets_name": self.config.jets_name,
         }
         output_dir = self.config.out_dir / self.config.split
         output_dir.mkdir(parents=True, exist_ok=True)
@@ -82,7 +83,7 @@ def run(self):
 
         variables = self.config.variables.combined() if self.config.split != "test" else None
         if variables and "flavour_label" not in variables:
-            variables["jets"] += ["flavour_label"]
+            variables[self.config.jets_name] += ["flavour_label"]
         args_list = []
         for i, bi in enumerate(range(0, num_batches, batches_per_file)):
             args_list.append(
@@ -98,6 +99,7 @@ def run(self):
                     if (bi + batches_per_file) < num_batches
                     else (num_batches - bi),
                     self.attr_to_write,
+                    self.config.jets_name,
                 )
             )
         print("Running with ", self.rw_config.merge_num_proc, "processes")
@@ -206,6 +208,7 @@ def do_merge_with_weights(
         writer_id=0,
         limit_batches=False,
         attrs=None,
+        jets_name="jets",
     ):
         """Take a series of input files and merge them into a single final output file.
 
@@ -252,7 +255,8 @@ def do_merge_with_weights(
 
         for i, batch in enumerate(reader.stream(variables, skip_batches=skip_batches)):
             print(
-                f"Writer {writer_id} Combined batch {i} has {len(batch['jets'])} jets", flush=True
+                f"Writer {writer_id} Combined batch {i} has {len(batch[jets_name])} jets",
+                flush=True,
             )
             all_sample_weights = RWMerge.get_sample_weights(batch, weights)
             to_write = {}
@@ -263,7 +267,14 @@ def do_merge_with_weights(
                     to_write[key] = batch[key]
             if writer is None:
                 shapes = {k: (None,) + v.shape[1:] for k, v in to_write.items()}
-                writer = H5Writer(output_file, dtypes, shapes, shuffle=True, compression="gzip")
+                writer = H5Writer(
+                    output_file,
+                    dtypes,
+                    shapes,
+                    shuffle=True,
+                    compression="gzip",
+                    jets_name=jets_name,
+                )
                 for group, g_attrs in attrs.items():
                     for attr, value in g_attrs.items():
                         writer.add_attr(attr, value, group)
diff --git a/upp/stages/split_containers.py b/upp/stages/split_containers.py
index efff193..c04f0f6 100644
--- a/upp/stages/split_containers.py
+++ b/upp/stages/split_containers.py
@@ -130,6 +130,7 @@ def split_file(
     ):
         if isinstance(input_file, str):
             input_file = Path(input_file)
+        jets_name = self.config.jets_name
         add_flavour_label = flavour_label_list is not None
         # All variables for test file
         all_variables = get_all_datasets(input_file)
@@ -140,7 +141,9 @@ def split_file(
         )
         print("parsed variables: ", parsed_variables, flush=True)
         start = time.time()
-        reader = H5Reader(input_file, batch_size=batch_size, shuffle=False)
+        reader = H5Reader(
+            input_file, batch_size=batch_size, shuffle=False, jets_name=self.config.jets_name
+        )
         if output_name is None:
             output_name = input_file.name
         num_jets = reader.num_jets
@@ -173,6 +176,7 @@ def split_file(
                 variables=all_variables if "test" in split else parsed_variables,
                 compression="gzip",
                 add_flavour_label=add_flavour_label,
+                jets_name=jets_name,
             )
             cuts_by_sample_components[split] = component_cuts
             print(f"Creating writer for {split} saved to {output_file}", flush=True)
@@ -198,28 +202,28 @@ def split_file(
             for sample_component in sample_components:
                 writer = writers_by_sample_components[sample_component]
                 cuts = cuts_by_sample_components[sample_component]
-                sel_idx = cuts(batch["jets"]).idx
+                sel_idx = cuts(batch[jets_name]).idx
                 sel_batch = {k: v[sel_idx] for k, v in batch.items()}
                 if add_flavour_label:
                     this_flavour_label = flavour_label_by_component[sample_component]
                     tfl_arr = (
-                        np.ones(sel_batch["jets"].shape[0], dtype=np.int32) * this_flavour_label
+                        np.ones(sel_batch[jets_name].shape[0], dtype=np.int32) * this_flavour_label
                     )
 
                     # I think this is only going to happen during tests, as the mock file has
                     # flavour_label in, but we wont
-                    if "flavour_label" in sel_batch["jets"].dtype.names:
+                    if "flavour_label" in sel_batch[jets_name].dtype.names:
                         if i == 0:
                             print(
                                 f"Warning: {sample_component} already has a flavour label. "
                                 "We will overwrite it now.",
                                 flush=True,
                             )
-                        sel_batch["jets"]["flavour_label"] = tfl_arr
+                        sel_batch[jets_name]["flavour_label"] = tfl_arr
                     else:
                         # Get the
-                        sel_batch["jets"] = rfn.append_fields(
-                            sel_batch["jets"],
+                        sel_batch[jets_name] = rfn.append_fields(
+                            sel_batch[jets_name],
                             "flavour_label",
                             tfl_arr,
                             usemask=False,
@@ -279,6 +283,7 @@ def _make_tmp_vds(self, files: list[str] | str | Path) -> Generator[Path, None,
             create_virtual_file(str(tmp_dir / "*.h5"), tmp_out_path, overwrite=True)
             h5vds = H5Reader(
                 tmp_out_path,
+                jets_name=self.config.jets_name,
             )
             print(
                 f"Created combined virtual dataset with {h5vds.num_jets} jets at {tmp_out_path}",
@@ -368,7 +373,10 @@ def create_meta_data(self):
                     files[split][flavour].append(str(file[0]))
 
         num_jets = {
-            split: {flavour: H5Reader(files[split][flavour]).num_jets for flavour in files[split]}
+            split: {
+                flavour: H5Reader(files[split][flavour], jets_name=self.config.jets_name).num_jets
+                for flavour in files[split]
+            }
             for split in files
         }
         metadata = {

From 6633708f0d0ce4026c29b226fb4c910a044776bc Mon Sep 17 00:00:00 2001
From: Alexander Froch <Alexander.Froch@cern.ch>
Date: Mon, 22 Jun 2026 16:07:34 +0200
Subject: [PATCH 02/13] Add changelog entry for jets_name fix

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---
 changelog.md | 2 ++
 1 file changed, 2 insertions(+)

diff --git a/changelog.md b/changelog.md
index f084858..95ffe9e 100644
--- a/changelog.md
+++ b/changelog.md
@@ -2,6 +2,8 @@
 
 ### [Latest]
 
+- Honour the configured `jets_name` in the split, reweighting and merge stages so preprocessing works with object groups not named "jets" [#156](https://github.com/umami-hep/umami-preprocessing/pull/156)
+
 ### [v0.3.1](https://github.com/umami-hep/umami-preprocessing/releases/tag/v0.3.1) (19.06.2026)
 
 - Make skip-resampling work end-to-end; support `num_jets: -1` to write all jets passing cuts, and record the resampling method in the output metadata [#153](https://github.com/umami-hep/umami-preprocessing/pull/153)

From 06066be798b6f485a5d4ad4556d2646ac42330e8 Mon Sep 17 00:00:00 2001
From: Alexander Froch <Alexander.Froch@cern.ch>
Date: Mon, 22 Jun 2026 17:03:29 +0200
Subject: [PATCH 03/13] Rename jets_name config option to global_name

Generalise the framework beyond jets: the config key that names the main
per-object dataset is renamed from jets_name to global_name, along with all
internal attributes/parameters and the {jets_name} ylabel placeholder.

The external ftag H5Reader/H5Writer keyword (jets_name=) and reader.jets_name
attribute are kept as-is, since they belong to the ftag library API; call
sites now pass jets_name=<config>.global_name.

Breaking change: existing configs must rename the global: jets_name key to
global_name. All in-repo configs, docs, tests and the {global_name} ylabel
placeholder are updated accordingly.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
---
 changelog.md                                  |  3 +-
 docs/configuration.md                         |  2 +-
 .../integration/fixtures/test_config_rw.yaml  |  2 +-
 .../fixtures/test_config_rw_custom_name.yaml  |  2 +-
 tests/integration/test_run_rw.py              |  2 +-
 tests/unit/fixtures/test_config_rw.yaml       |  2 +-
 tests/unit/stages/test_merging.py             |  6 ++--
 tests/unit/stages/test_plotting.py            |  8 ++---
 tests/unit/stages/test_reweight.py            |  2 +-
 tests/unit/utils/test_check_input_samples.py  | 12 ++++----
 upp/classes/components.py                     | 12 ++++----
 upp/classes/plotting_config.py                |  6 ++--
 upp/classes/preprocessing_config.py           | 11 +++----
 upp/classes/variable_config.py                | 10 ++++---
 upp/configs/GN3EPCMV01/GN3EPCMV01.yaml        |  2 +-
 upp/configs/GN3V00/dr.yaml                    |  2 +-
 upp/configs/GN3V00/ghost-highstat.yaml        |  2 +-
 upp/configs/GN3V00/ghost.yaml                 |  2 +-
 upp/configs/GN3V01/GN3V01-RW.yaml             |  2 +-
 upp/configs/GN3V01/GN3V01.yaml                |  2 +-
 upp/configs/extended_labels.yaml              |  2 +-
 upp/configs/open-dataset.yaml                 |  2 +-
 upp/configs/plit_electron.yaml                |  2 +-
 upp/configs/plit_muon.yaml                    |  2 +-
 upp/configs/single-b-upgrade.yaml             |  2 +-
 upp/configs/single-b.yaml                     |  2 +-
 upp/configs/xbb-rw.yaml                       |  2 +-
 upp/grid/download_and_prepare.py              |  2 +-
 upp/stages/hist.py                            |  2 +-
 upp/stages/merging.py                         | 30 +++++++++----------
 upp/stages/normalisation.py                   | 18 +++++------
 upp/stages/plot.py                            | 18 +++++------
 upp/stages/resampling.py                      | 14 ++++-----
 upp/stages/reweight.py                        |  6 ++--
 upp/stages/rw_merge.py                        | 14 ++++-----
 upp/stages/split_containers.py                | 23 +++++++-------
 upp/utils/check_input_samples.py              |  2 +-
 37 files changed, 120 insertions(+), 115 deletions(-)

diff --git a/changelog.md b/changelog.md
index 95ffe9e..2e49846 100644
--- a/changelog.md
+++ b/changelog.md
@@ -2,7 +2,8 @@
 
 ### [Latest]
 
-- Honour the configured `jets_name` in the split, reweighting and merge stages so preprocessing works with object groups not named "jets" [#156](https://github.com/umami-hep/umami-preprocessing/pull/156)
+- Honour the configured global object name in the split, reweighting and merge stages so preprocessing works with object groups not named "jets" [#156](https://github.com/umami-hep/umami-preprocessing/pull/156)
+- Rename the `jets_name` config option to `global_name` to generalise the framework beyond jets (breaking: update existing configs) [#156](https://github.com/umami-hep/umami-preprocessing/pull/156)
 
 ### [v0.3.1](https://github.com/umami-hep/umami-preprocessing/releases/tag/v0.3.1) (19.06.2026)
 
diff --git a/docs/configuration.md b/docs/configuration.md
index 2be9d80..99f4ad6 100644
--- a/docs/configuration.md
+++ b/docs/configuration.md
@@ -273,7 +273,7 @@ plotting:
   output_directory: plots
 ```
 
-The `ylabel` setting supports a `{jets_name}` placeholder. Histogram normalisation and overflow handling can be controlled with `norm` and `underoverflow`.
+The `ylabel` setting supports a `{global_name}` placeholder. Histogram normalisation and overflow handling can be controlled with `norm` and `underoverflow`.
 
 ::: upp.classes.plotting_config.PlottingConfig
 
diff --git a/tests/integration/fixtures/test_config_rw.yaml b/tests/integration/fixtures/test_config_rw.yaml
index 6b3a334..ee1a86e 100644
--- a/tests/integration/fixtures/test_config_rw.yaml
+++ b/tests/integration/fixtures/test_config_rw.yaml
@@ -146,7 +146,7 @@ reweighting:
 
 # note: sensible defaults are defined in the PreprocessingConfig constructor
 global:
-  jets_name: jets
+  global_name: jets
   batch_size: 1_000_000
   num_jets_estimate: 25_000_000
   base_dir: tmp/upp-tests/integration/temp_workspace/
diff --git a/tests/integration/fixtures/test_config_rw_custom_name.yaml b/tests/integration/fixtures/test_config_rw_custom_name.yaml
index b6fb4c0..0187f5e 100644
--- a/tests/integration/fixtures/test_config_rw_custom_name.yaml
+++ b/tests/integration/fixtures/test_config_rw_custom_name.yaml
@@ -86,7 +86,7 @@ reweighting:
 
 # note: sensible defaults are defined in the PreprocessingConfig constructor
 global:
-  jets_name: objects
+  global_name: objects
   batch_size: 1_000_000
   num_jets_estimate: 25_000_000
   base_dir: tmp/upp-tests/integration/temp_workspace/
diff --git a/tests/integration/test_run_rw.py b/tests/integration/test_run_rw.py
index a074473..44ff733 100644
--- a/tests/integration/test_run_rw.py
+++ b/tests/integration/test_run_rw.py
@@ -136,7 +136,7 @@ def test_rw_custom_object_name(self):
         """End-to-end reweighting with a non-"jets" object group name.
 
         Guards against hardcoded "jets" references: the input group is renamed
-        to "objects" and the config sets jets_name: objects. Every stage must
+        to "objects" and the config sets global_name: objects. Every stage must
         honour the configured name rather than assuming "jets".
         """
         for container in ["data1.h5", "data2.h5", "data3.h5"]:
diff --git a/tests/unit/fixtures/test_config_rw.yaml b/tests/unit/fixtures/test_config_rw.yaml
index 217ee59..e204297 100644
--- a/tests/unit/fixtures/test_config_rw.yaml
+++ b/tests/unit/fixtures/test_config_rw.yaml
@@ -69,7 +69,7 @@ reweighting:
 
 # note: sensible defaults are defined in the PreprocessingConfig constructor
 global:
-  jets_name: jets
+  global_name: jets
   batch_size: 1_000_000
   num_jets_estimate: 25_000_000
   base_dir: /tmp/upp-tests/integration/temp_workspace/
diff --git a/tests/unit/stages/test_merging.py b/tests/unit/stages/test_merging.py
index 4687f51..371a27b 100644
--- a/tests/unit/stages/test_merging.py
+++ b/tests/unit/stages/test_merging.py
@@ -104,7 +104,7 @@ def _minimal_merging(monkeypatch, jets_per_file=10) -> merging_mod.Merging:
         components=SimpleNamespace(flavours=[Flavours["bjets"]]),
         variables=variables,
         batch_size=100,
-        jets_name="jets",
+        global_name="jets",
         num_jets_per_output_file=jets_per_file,
         file_tag="split",
         out_fname=Path("/tmp/merged.h5"),
@@ -338,7 +338,7 @@ def _mk_merge_for_path(monkeypatch, out_path: Path, jets_per_file=5):
         components=SimpleNamespace(flavours=[Flavours["bjets"]]),
         variables=variables,
         batch_size=100,
-        jets_name="jets",
+        global_name="jets",
         num_jets_per_output_file=jets_per_file,
         file_tag="split",
         out_fname=out_path,
@@ -704,7 +704,7 @@ def groupby_sample(self):
         components=FakeComponents(),
         variables=variables,
         batch_size=100,
-        jets_name="jets",
+        global_name="jets",
         num_jets_per_output_file=10,
         file_tag="split",
         out_fname=tmp_path / "merged.h5",
diff --git a/tests/unit/stages/test_plotting.py b/tests/unit/stages/test_plotting.py
index 54420d9..024c23e 100644
--- a/tests/unit/stages/test_plotting.py
+++ b/tests/unit/stages/test_plotting.py
@@ -38,19 +38,19 @@ def setup_method(self, method):
             "test": H5Reader(
                 fname=self.fname1,
                 batch_size=self.config.batch_size,
-                jets_name=self.config.jets_name,
+                jets_name=self.config.global_name,
                 shuffle=False,
                 equal_jets=True,
             ).load(
                 {
-                    self.config.jets_name: [
+                    self.config.global_name: [
                         "pt",
                         "abs_eta",
                         "mass",
                         "HadronConeExclTruthLabelID",
                     ]
                 }
-            )[self.config.jets_name]
+            )[self.config.global_name]
         }
         print(f"setup_method, method: {method.__name__}")
 
@@ -241,7 +241,7 @@ def groupby_region(self):
             bins={"pt": [[20_000, 250_000, 5]]},
         ),
         components=FakeComponents(),
-        jets_name="jets",
+        global_name="jets",
         batch_size=100,
         out_dir=tmp_path,
     )
diff --git a/tests/unit/stages/test_reweight.py b/tests/unit/stages/test_reweight.py
index 8c409e0..6b2982a 100644
--- a/tests/unit/stages/test_reweight.py
+++ b/tests/unit/stages/test_reweight.py
@@ -39,7 +39,7 @@ def _make_reweight_obj(tmpdir, jets_per_flavour, num_jets_estimate, batch_size=1
     config = MagicMock()
     config.batch_size = batch_size
     config.base_dir = str(tmpdir)
-    config.jets_name = "jets"
+    config.global_name = "jets"
 
     rw_config = SimpleNamespace(num_jets_estimate=num_jets_estimate, reweights=[])
 
diff --git a/tests/unit/utils/test_check_input_samples.py b/tests/unit/utils/test_check_input_samples.py
index 983d359..9d858eb 100644
--- a/tests/unit/utils/test_check_input_samples.py
+++ b/tests/unit/utils/test_check_input_samples.py
@@ -52,7 +52,7 @@ def __init__(self, ntuple_dir: Path):
             self.config = {"blockX": {"pattern": [missing_dsid, missing_rtag, missing_both]}}
             self.ntuple_dir = ntuple_dir
             self.batch_size = 1
-            self.jets_name = "jets"
+            self.global_name = "jets"
             self.vds_dir = None
 
     cfg = _Cfg(tmp_path)
@@ -89,7 +89,7 @@ def __init__(self, ntuple_dir: Path):
             self.config = {"blockY": {"pattern": {"oops": "dict-not-supported"}}}
             self.ntuple_dir = ntuple_dir
             self.batch_size = 1
-            self.jets_name = "jets"
+            self.global_name = "jets"
             self.vds_dir = None
 
     cfg = _Cfg(tmp_path)
@@ -112,7 +112,7 @@ def __init__(self):  # minimal attributes used by run_input_sample_check stub
             self.config = {}
             self.ntuple_dir = tmp_path
             self.batch_size = 1
-            self.jets_name = "jets"
+            self.global_name = "jets"
             self.vds_dir = None
 
     called = {"run": False, "cfg": None, "df": None, "v": None}
@@ -178,7 +178,7 @@ def __init__(self, ntuple_dir: Path):
             self.config = {"block": {"pattern": ["x.123456.y_r13167.z.h5"]}}
             self.ntuple_dir = ntuple_dir
             self.batch_size = 1
-            self.jets_name = "jets"
+            self.global_name = "jets"
             self.vds_dir = None
 
     cfg = _Cfg(tmp_path)
@@ -224,7 +224,7 @@ def __init__(self, ntuple_dir: Path):
             self.config = {"block": {"pattern": [sample]}}
             self.ntuple_dir = ntuple_dir
             self.batch_size = 1
-            self.jets_name = "jets"
+            self.global_name = "jets"
             self.vds_dir = None
 
     cfg = _Cfg(tmp_path)
@@ -258,7 +258,7 @@ def __init__(self):
             self.config = {}
             self.ntuple_dir = tmp_path
             self.batch_size = 1
-            self.jets_name = "jets"
+            self.global_name = "jets"
             self.vds_dir = None
 
         @classmethod
diff --git a/upp/classes/components.py b/upp/classes/components.py
index 62d6021..a9d94bd 100644
--- a/upp/classes/components.py
+++ b/upp/classes/components.py
@@ -66,7 +66,7 @@ def __post_init__(self):
     def setup_reader(
         self,
         batch_size: int,
-        jets_name: str = "jets",
+        global_name: str = "jets",
         fname: Path | str | list[Path | str] | None = None,
         **kwargs,
     ) -> None:
@@ -76,7 +76,7 @@ def setup_reader(
         ----------
         batch_size : int
             Batch size that is used for loading from file
-        jets_name : str, optional
+        global_name : str, optional
             Name of the group in which the jets are stored, by default "jets"
         fname : Path | str | list[Path | str] | None, optional
             Filename of the file(s) from which the jets are loaded, by default None
@@ -92,26 +92,26 @@ def setup_reader(
         self.reader = H5Reader(
             fname=fname,
             batch_size=batch_size,
-            jets_name=jets_name,
+            jets_name=global_name,
             equal_jets=self.equal_jets,
             **kwargs,
         )
         log.debug(f"Setup component reader at: {fname}")
 
-    def setup_writer(self, variables: VariableConfig, jets_name: str = "jets") -> None:
+    def setup_writer(self, variables: VariableConfig, global_name: str = "jets") -> None:
         """Set up the writer of the jets to file.
 
         Parameters
         ----------
         variables : VariableConfig
             Instance of VariableConfig in which the variables are stored.
-        jets_name : str, optional
+        global_name : str, optional
             Name of the group in which the jets are stored, by default "jets"
         """
         dtypes = self.reader.dtypes(variables.combined())
         # num_jets == -1 ("write all") -> 0 leading dim so the writer grows dynamically
         shapes = self.reader.shapes(max(self.num_jets, 0), variables.keys())
-        self.writer = H5Writer(self.out_path, dtypes, shapes, jets_name=jets_name)
+        self.writer = H5Writer(self.out_path, dtypes, shapes, jets_name=global_name)
         log.debug(f"Setup component writer at: {self.out_path}")
 
     @property
diff --git a/upp/classes/plotting_config.py b/upp/classes/plotting_config.py
index d87ed36..7dff1da 100644
--- a/upp/classes/plotting_config.py
+++ b/upp/classes/plotting_config.py
@@ -39,8 +39,8 @@ class PlottingConfig:
         Display labels for input samples. User-provided labels are merged with the
         default ttbar and zprime labels.
     ylabel : str, optional
-        Label for the y-axis. The `{jets_name}` placeholder is replaced with the
-        configured jet dataset name. By default "Normalised Number of {jets_name}".
+        Label for the y-axis. The `{global_name}` placeholder is replaced with the
+        configured global object name. By default "Normalised Number of {global_name}".
     atlas_first_tag : str, optional
         First ATLAS plot label. By default "Simulation Internal".
     atlas_second_tag : str, optional
@@ -79,7 +79,7 @@ class PlottingConfig:
     num_jets_plotting: int | None = None
     variable_labels: dict[str, str] = field(default_factory=_default_variable_labels)
     sample_labels: dict[str, str] = field(default_factory=_default_sample_labels)
-    ylabel: str = "Normalised Number of {jets_name}"
+    ylabel: str = "Normalised Number of {global_name}"
     atlas_first_tag: str = "Simulation Internal"
     atlas_second_tag: str = "$\\sqrt{s} = 13/13.6\\,\\mathrm{TeV}$"
     show_num_jets: bool = True
diff --git a/upp/classes/preprocessing_config.py b/upp/classes/preprocessing_config.py
index 1a7b0a9..550d30f 100644
--- a/upp/classes/preprocessing_config.py
+++ b/upp/classes/preprocessing_config.py
@@ -47,7 +47,7 @@ class PreprocessingConfig:
     For example:
     ```yaml
     global:
-        jets_name: jets
+        global_name: jets
         batch_size: 1_000_000
         num_jets_estimate: 5_000_000
         base_dir: /my/stuff/
@@ -104,8 +104,9 @@ class PreprocessingConfig:
         Is equal to num_jets_estimate by default.
     merge_test_samples : bool, optional
         Merge the test samples of the different processes into one file. By default False.
-    jets_name : str, optional
-        Name of the jets dataset in the input file. By default "jets".
+    global_name : str, optional
+        Name of the global (per-object) dataset in the input file, e.g. the jets.
+        By default "jets".
     flavour_config : Path | None, optional
         Flavour config yaml file which is to be used. By default None
     flavour_category : str, optional
@@ -141,7 +142,7 @@ class PreprocessingConfig:
     num_jets_estimate_norm: int | None = None
     num_jets_estimate_plotting: int | None = None
     merge_test_samples: bool = False
-    jets_name: str = "jets"
+    global_name: str = "jets"
     flavour_config: Path | None = None
     flavour_category: str = "standard"
     num_jets_per_output_file: int | None = None
@@ -209,7 +210,7 @@ def __post_init__(self):
 
         # configure variables
         self.variables = VariableConfig(
-            self.config["variables"], self.jets_name, self.is_test, selectors
+            self.config["variables"], self.global_name, self.is_test, selectors
         )
         if self.sampl_cfg is not None and self.sampl_cfg.variables:
             self.variables = self.variables.add_jet_vars(
diff --git a/upp/classes/variable_config.py b/upp/classes/variable_config.py
index 023ebab..f76d37d 100644
--- a/upp/classes/variable_config.py
+++ b/upp/classes/variable_config.py
@@ -9,7 +9,7 @@
 @dataclass(frozen=True)
 class VariableConfig:
     variables: dict[str, dict[str, list[str]]]
-    jets_name: str = "jets"
+    global_name: str = "jets"
     keep_all: bool = False
     selectors: dict[str, TrackSelector] | None = None
 
@@ -28,15 +28,17 @@ def combined(self):
 
     @property
     def jets(self):
-        return self[self.jets_name]
+        return self[self.global_name]
 
     @property
     def tracks(self):
-        return {name: var for name, var in self.variables.items() if name != self.jets_name}
+        return {name: var for name, var in self.variables.items() if name != self.global_name}
 
     def add_jet_vars(self, variables: list[str], kind: str = "inputs") -> VariableConfig:
         """Return a new VariableConfig instance."""
-        vc = VariableConfig(deepcopy(self.variables), self.jets_name, self.keep_all, self.selectors)
+        vc = VariableConfig(
+            deepcopy(self.variables), self.global_name, self.keep_all, self.selectors
+        )
         vc.jets[kind] = list(dict.fromkeys(vc.jets[kind] + variables))
         return vc
 
diff --git a/upp/configs/GN3EPCMV01/GN3EPCMV01.yaml b/upp/configs/GN3EPCMV01/GN3EPCMV01.yaml
index 2be01a9..4b52d22 100644
--- a/upp/configs/GN3EPCMV01/GN3EPCMV01.yaml
+++ b/upp/configs/GN3EPCMV01/GN3EPCMV01.yaml
@@ -153,7 +153,7 @@ resampling:
 
 # note: sensible defaults are defined in the PreprocessingConfig constructor
 global:
-  jets_name: jets
+  global_name: jets
   batch_size: 1_000_000
   num_jets_estimate: 50_000_000
   num_jets_estimate_plotting: 10_000_000
diff --git a/upp/configs/GN3V00/dr.yaml b/upp/configs/GN3V00/dr.yaml
index a1ec283..36fc70f 100644
--- a/upp/configs/GN3V00/dr.yaml
+++ b/upp/configs/GN3V00/dr.yaml
@@ -72,7 +72,7 @@ resampling:
 
 # note: sensible defaults are defined in the PreprocessingConfig constructor
 global:
-  jets_name: jets
+  global_name: jets
   batch_size: 1_000_000
   num_jets_estimate: 2_000_000
   base_dir: /unix/atlastracking/samples/gn3v00/dr/
diff --git a/upp/configs/GN3V00/ghost-highstat.yaml b/upp/configs/GN3V00/ghost-highstat.yaml
index d630d01..5148203 100644
--- a/upp/configs/GN3V00/ghost-highstat.yaml
+++ b/upp/configs/GN3V00/ghost-highstat.yaml
@@ -137,7 +137,7 @@ resampling:
 
 # note: sensible defaults are defined in the PreprocessingConfig constructor
 global:
-  jets_name: jets
+  global_name: jets
   batch_size: 1_000_000
   num_jets_estimate: 25_000_000
   base_dir: /unix/atlas2/weilai/datasets/atlas/upp_outs/ghost_high_stat_full
diff --git a/upp/configs/GN3V00/ghost.yaml b/upp/configs/GN3V00/ghost.yaml
index e7583a1..9c2ece6 100644
--- a/upp/configs/GN3V00/ghost.yaml
+++ b/upp/configs/GN3V00/ghost.yaml
@@ -73,7 +73,7 @@ resampling:
 
 # note: sensible defaults are defined in the PreprocessingConfig constructor
 global:
-  jets_name: jets
+  global_name: jets
   batch_size: 1_000_000
   num_jets_estimate: 2_000_000
   base_dir: /unix/atlas2/weilai/datasets/atlas/upp_outs/ghost_correct
diff --git a/upp/configs/GN3V01/GN3V01-RW.yaml b/upp/configs/GN3V01/GN3V01-RW.yaml
index 216a677..a4bbf6b 100644
--- a/upp/configs/GN3V01/GN3V01-RW.yaml
+++ b/upp/configs/GN3V01/GN3V01-RW.yaml
@@ -65,7 +65,7 @@ components:
 
 # note: sensible defaults are defined in the PreprocessingConfig constructor
 global:
-  jets_name: jets
+  global_name: jets
   batch_size: 1_000_000
   num_jets_estimate: 25_000_000
   num_jets_per_output_file: 25_000_000
diff --git a/upp/configs/GN3V01/GN3V01.yaml b/upp/configs/GN3V01/GN3V01.yaml
index eccd90f..8289060 100644
--- a/upp/configs/GN3V01/GN3V01.yaml
+++ b/upp/configs/GN3V01/GN3V01.yaml
@@ -137,7 +137,7 @@ resampling:
 
 # note: sensible defaults are defined in the PreprocessingConfig constructor
 global:
-  jets_name: jets
+  global_name: jets
   batch_size: 1_000_000
   num_jets_estimate: 25_000_000
   base_dir: GN3V01_Training_preprocessed/
diff --git a/upp/configs/extended_labels.yaml b/upp/configs/extended_labels.yaml
index f97a8fa..8de3c94 100644
--- a/upp/configs/extended_labels.yaml
+++ b/upp/configs/extended_labels.yaml
@@ -64,7 +64,7 @@ resampling:
 
 # note: sensible defaults are defined in the PreprocessingConfig constructor
 global:
-  jets_name: nominal_Loose
+  global_name: nominal_Loose
   batch_size: 1_000_000
   num_jets_estimate: 5_000_000
   base_dir: /nfs/dust/atlas/user/nkumari/UPP_latest/umami-preprocessing/upp/configs/prep
diff --git a/upp/configs/open-dataset.yaml b/upp/configs/open-dataset.yaml
index 3198004..41f1a87 100644
--- a/upp/configs/open-dataset.yaml
+++ b/upp/configs/open-dataset.yaml
@@ -92,7 +92,7 @@ resampling:
 
 # note: sensible defaults are defined in the PreprocessingConfig constructor
 global:
-  jets_name: jets
+  global_name: jets
   batch_size: 1_000_000
   num_jets_estimate: 25_000_000
   base_dir: /unix/atlas2/weilai/datasets/atlas/upp_outs/opendata_rc3
diff --git a/upp/configs/plit_electron.yaml b/upp/configs/plit_electron.yaml
index 828ebf8..4fe1c27 100644
--- a/upp/configs/plit_electron.yaml
+++ b/upp/configs/plit_electron.yaml
@@ -50,7 +50,7 @@ resampling:
 
 # note: sensible defaults are defined in the PreprocessingConfig constructor
 global:
-  jets_name: electrons
+  global_name: electrons
   batch_size: 1_000_000
   num_jets_estimate: 5_000
   base_dir: /nfs/dust/atlas/user/pgadow/plit/data/preprocessed/electrons_38M
diff --git a/upp/configs/plit_muon.yaml b/upp/configs/plit_muon.yaml
index 5427c22..807307f 100644
--- a/upp/configs/plit_muon.yaml
+++ b/upp/configs/plit_muon.yaml
@@ -50,7 +50,7 @@ resampling:
 
 # note: sensible defaults are defined in the PreprocessingConfig constructor
 global:
-  jets_name: muons
+  global_name: muons
   batch_size: 1_000_000
   num_jets_estimate: 5_000_000
   base_dir: /nfs/dust/atlas/user/pgadow/plit/data/preprocessed/muons_40M
diff --git a/upp/configs/single-b-upgrade.yaml b/upp/configs/single-b-upgrade.yaml
index 4864890..3780500 100644
--- a/upp/configs/single-b-upgrade.yaml
+++ b/upp/configs/single-b-upgrade.yaml
@@ -88,7 +88,7 @@ resampling:
 
 # note: sensible defaults are defined in the PreprocessingConfig constructor
 global:
-  jets_name: jets
+  global_name: jets
   batch_size: 1_000_000
   num_jets_estimate: 25_000_000
   base_dir: /atlas_cloud/triglion/preprocessing
diff --git a/upp/configs/single-b.yaml b/upp/configs/single-b.yaml
index fa216f7..0800425 100644
--- a/upp/configs/single-b.yaml
+++ b/upp/configs/single-b.yaml
@@ -88,7 +88,7 @@ resampling:
 
 # note: sensible defaults are defined in the PreprocessingConfig constructor
 global:
-  jets_name: jets
+  global_name: jets
   batch_size: 1_000_000
   num_jets_estimate: 25_000_000
   base_dir: /home/xzcappon/phd/datasets/combined_run2_run3/p5922/high_stats/fold0
diff --git a/upp/configs/xbb-rw.yaml b/upp/configs/xbb-rw.yaml
index 8faa56f..c6d6e62 100644
--- a/upp/configs/xbb-rw.yaml
+++ b/upp/configs/xbb-rw.yaml
@@ -113,7 +113,7 @@ components:
 
 
 global:
-  jets_name: jets
+  global_name: jets
   batch_size: 1_000_000
   num_jets_estimate: 10_000_000
   num_jets_per_output_file: 25_000_000
diff --git a/upp/grid/download_and_prepare.py b/upp/grid/download_and_prepare.py
index fe74a5d..f8f7c34 100644
--- a/upp/grid/download_and_prepare.py
+++ b/upp/grid/download_and_prepare.py
@@ -134,7 +134,7 @@ def create_meta_data(
         split: {
             flavour: H5Reader(
                 files_by_component[split][flavour],
-                jets_name=pp_config.jets_name,
+                jets_name=pp_config.global_name,
             ).num_jets
             for flavour in files_by_component[split]
         }
diff --git a/upp/stages/hist.py b/upp/stages/hist.py
index 6b37c02..7fcbfc4 100644
--- a/upp/stages/hist.py
+++ b/upp/stages/hist.py
@@ -165,7 +165,7 @@ def create_histograms(
             continue
 
         log.info(f"Estimating {component} PDF using {config.num_jets_estimate_hist:,} samples...")
-        component.setup_reader(batch_size=config.batch_size, jets_name=config.jets_name)
+        component.setup_reader(batch_size=config.batch_size, global_name=config.global_name)
         cuts_no_split = component.cuts.ignore(["eventNumber"])
 
         ###
diff --git a/upp/stages/merging.py b/upp/stages/merging.py
index a87a794..1ddcf60 100644
--- a/upp/stages/merging.py
+++ b/upp/stages/merging.py
@@ -26,7 +26,7 @@ def __init__(self, config: PreprocessingConfig):
         self.components = config.components
         self.variables = config.variables
         self.batch_size = config.batch_size
-        self.jets_name = config.jets_name
+        self.global_name = config.global_name
         self.rng = np.random.default_rng(42)
         self.flavours = self.components.flavours
         self.num_jets_per_output_file = config.num_jets_per_output_file
@@ -167,14 +167,14 @@ def _is_part_valid(self, sample: str | None, part_idx: int) -> bool:
                 expected_names = list(self.base_shapes.keys())
 
                 # Tolerate missing optional groups, but require the jet dataset at least
-                if self.jets_name not in f:
-                    log.warning(f"Missing dataset '{self.jets_name}' in {fname}")
+                if self.global_name not in f:
+                    log.warning(f"Missing dataset '{self.global_name}' in {fname}")
                     return False
 
-                # Determine observed length from anchor (jets_name) or first dataset
-                anchor = self.jets_name if self.jets_name in f else expected_names[0]
+                # Determine observed length from anchor (global_name) or first dataset
+                anchor = self.global_name if self.global_name in f else expected_names[0]
                 if anchor not in f:
-                    # if jets_name wasn't found, try any expected dataset that exists
+                    # if global_name wasn't found, try any expected dataset that exists
                     for nm in expected_names:
                         if nm in f:
                             anchor = nm
@@ -332,8 +332,8 @@ def _open_writer(
             fname,
             self.dtypes,
             shapes,
-            add_flavour_label=self.jets_name,
-            jets_name=self.jets_name,
+            add_flavour_label=self.global_name,
+            jets_name=self.global_name,
             num_jets=jets_in_file,
         )
 
@@ -341,7 +341,7 @@ def _open_writer(
         self.writer.add_attr(
             "flavour_label",
             [f.name for f in self.flavours],
-            self.jets_name,
+            self.global_name,
         )
         self.writer.add_attr("unique_jets", components.unique_jets)
         self.writer.add_attr("jet_counts", json.dumps(components.jet_counts))
@@ -385,8 +385,8 @@ def write_chunk(self, components: Components) -> int:
                 try:
                     # shallow copy because we will add a field
                     batch = copy(next(component.stream))
-                    batch[self.jets_name] = self.add_jet_flavour_label(
-                        jets=batch[self.jets_name], component=component
+                    batch[self.global_name] = self.add_jet_flavour_label(
+                        jets=batch[self.global_name], component=component
                     )
                 except StopIteration:
                     component.complete = True
@@ -407,14 +407,14 @@ def write_chunk(self, components: Components) -> int:
 
         # Apply track selections
         for name in self.variables.variables:
-            if name == self.jets_name:
+            if name == self.global_name:
                 continue
             if selector := self.variables.selectors.get(name):
                 merged[name] = selector(merged[name])
 
         # Get the total length of jets from the batch and how much
         # capacity is left in the file
-        merged_len = len(merged[self.jets_name])
+        merged_len = len(merged[self.global_name])
         capacity_left = self.writer.num_jets - self.writer.num_written
 
         if self._fast_forwarding:
@@ -508,7 +508,7 @@ def write_components(self, sample: str | None, components: Components) -> None:
         for component in components:
             if component.num_jets < 0:
                 component.setup_reader(
-                    self.batch_size, fname=component.out_path, jets_name=self.jets_name
+                    self.batch_size, fname=component.out_path, global_name=self.global_name
                 )
                 component.num_jets = component.reader.num_jets
 
@@ -518,7 +518,7 @@ def write_components(self, sample: str | None, components: Components) -> None:
             component.setup_reader(
                 batch_size,
                 fname=component.out_path,
-                jets_name=self.jets_name,
+                global_name=self.global_name,
             )
             component.stream = component.reader.stream(
                 self.variables.combined(),
diff --git a/upp/stages/normalisation.py b/upp/stages/normalisation.py
index 6ef5446..db75683 100644
--- a/upp/stages/normalisation.py
+++ b/upp/stages/normalisation.py
@@ -21,7 +21,7 @@ def __init__(self, config: PreprocessingConfig):
         self.config = config
         self.components = config.components
         self.variables = config.variables
-        self.jets_name = self.config.jets_name
+        self.global_name = self.config.global_name
         self.num_jets = config.num_jets_estimate_norm
         self.norm_fname = config.out_dir / config.config.get("norm_fname", "norm_dict.yaml")
         self.class_fname = config.out_dir / config.config.get("class_fname", "class_dict.yaml")
@@ -78,7 +78,7 @@ def get_norm_dict(self, batch: dict) -> tuple[dict, int]:
         """
         norm_dict: dict[str, dict] = {k: {} for k in self.variables}
         for name, array in batch.items():
-            if name != self.variables.jets_name:
+            if name != self.variables.global_name:
                 array = array[array["valid"]]
             for var in self.variables[name]["inputs"]:
                 if var in ["valid"]:
@@ -86,7 +86,7 @@ def get_norm_dict(self, batch: dict) -> tuple[dict, int]:
                 mean = float(np.nanmean(array[var]))
                 std = float(np.nanstd(array[var]))
                 norm_dict[name][var] = {"mean": mean, "std": std}
-        return norm_dict, len(batch[self.variables.jets_name])
+        return norm_dict, len(batch[self.variables.global_name])
 
     def combine_norm_dict(self, norm_A: dict, norm_B: dict, num_A: int, num_B: int) -> dict:
         """Combine two normalisation dicts into one.
@@ -148,10 +148,10 @@ def get_class_dict(self, batch: dict) -> dict:
         ]
         class_dict: dict[str, dict] = {k: {} for k in self.variables}
         for name, array in batch.items():
-            if name != self.variables.jets_name:
+            if name != self.variables.global_name:
                 array = array[array["valid"]]
             # separate case for flavour_label
-            if name == self.variables.jets_name and "flavour_label" in array.dtype.names:
+            if name == self.variables.global_name and "flavour_label" in array.dtype.names:
                 counts = np.unique(array["flavour_label"], return_counts=True)
                 class_dict[name]["flavour_label"] = counts
             for var in self.variables[name].get("labels", []):
@@ -252,7 +252,7 @@ def run(self):
             fname,
             self.config.batch_size,
             precision="full",
-            jets_name=self.jets_name,
+            jets_name=self.global_name,
         )
         log.debug(f"Setup reader at: {fname}")
 
@@ -261,8 +261,8 @@ def run(self):
         total = None
         vars = self.variables.combined()
         with h5py.File(reader.files[0]) as f:
-            if "flavour_label" in f[self.jets_name].dtype.names:
-                vars[self.jets_name].append("flavour_label")
+            if "flavour_label" in f[self.global_name].dtype.names:
+                vars[self.global_name].append("flavour_label")
         stream = reader.stream(vars, self.num_jets)
 
         with ProgressBar() as progress:
@@ -283,7 +283,7 @@ def run(self):
                     norm_dict = self.combine_norm_dict(norm_dict, this_norm_dict, total, num)
                     total += num
 
-                progress.update(task, advance=len(batch[self.variables.jets_name]))
+                progress.update(task, advance=len(batch[self.variables.global_name]))
 
         log.info(f"[bold green]Finished computing normalisation params on {self.num_jets:,} jets!")
         self.write_norm_dict(norm_dict)
diff --git a/upp/stages/plot.py b/upp/stages/plot.py
index ee0c1a1..918880b 100644
--- a/upp/stages/plot.py
+++ b/upp/stages/plot.py
@@ -438,14 +438,14 @@ def _load_jets(config: PreprocessingConfig, in_paths: Any, vars_to_load: list[st
     return H5Reader(
         fname=in_paths,
         batch_size=config.batch_size,
-        jets_name=config.jets_name,
+        jets_name=config.global_name,
         shuffle=False,
         equal_jets=True,
         vds_dir=config.vds_dir,
     ).load(
-        {config.jets_name: list(dict.fromkeys(vars_to_load))},
+        {config.global_name: list(dict.fromkeys(vars_to_load))},
         num_jets=config.plotting.num_jets_plotting,
-    )[config.jets_name]
+    )[config.global_name]
 
 
 def make_hist(
@@ -454,7 +454,7 @@ def make_hist(
     flavours: list,
     variable: str,
     out_dir: Path,
-    jets_name: str = "jets",
+    global_name: str = "jets",
     bins_range: tuple | None = None,
     suffix: str = "",
     out_format_list: tuple[str, ...] | list[str] | None = None,
@@ -484,7 +484,7 @@ def make_hist(
         Variable that is to be histogrammed and plotted.
     out_dir : Path
         Output directory to which the plots are written.
-    jets_name: str, optional
+    global_name: str, optional
         Name of the jet dataset / the global objects
         by default "jets"
     bins_range : tuple | None, optional
@@ -510,7 +510,7 @@ def make_hist(
 
     # Setup the histogram
     plot = HistogramPlot(
-        ylabel=plotting.ylabel.replace("{jets_name}", jets_name),
+        ylabel=plotting.ylabel.replace("{global_name}", global_name),
         xlabel=plotting.variable_label(variable),
         y_scale=plotting.y_scale,
         figsize=plotting.figsize,
@@ -615,7 +615,7 @@ def _plot_initial(config: PreprocessingConfig) -> None:
                 make_hist(
                     stage="initial",
                     values_dict=values_dict,
-                    jets_name=config.jets_name,
+                    global_name=config.global_name,
                     flavours=region_components.flavours,
                     variable=variable,
                     bins_range=bins_range,
@@ -709,7 +709,7 @@ def _plot_post_resampling(config: PreprocessingConfig, stage: str) -> None:
             make_hist(
                 stage=stage,
                 values_dict=values_dict,
-                jets_name=config.jets_name,
+                global_name=config.global_name,
                 flavours=config.components.flavours,
                 variable=variable,
                 bins_range=bins_range,
@@ -726,7 +726,7 @@ def _plot_post_resampling(config: PreprocessingConfig, stage: str) -> None:
                 make_hist(
                     stage=stage,
                     values_dict=values_dict,
-                    jets_name=config.jets_name,
+                    global_name=config.global_name,
                     flavours=config.components.flavours,
                     variable=variable,
                     bins_range=_display_range(variable, stitching_region.pt_range),
diff --git a/upp/stages/resampling.py b/upp/stages/resampling.py
index dc9888b..f64168b 100644
--- a/upp/stages/resampling.py
+++ b/upp/stages/resampling.py
@@ -52,7 +52,7 @@ def __init__(self, config: PreprocessingConfig):
         self.components = config.components
         self.variables = config.variables
         self.batch_size = config.batch_size
-        self.jets_name = config.jets_name
+        self.global_name = config.global_name
         self.transform = config.transform
         self.rng = np.random.default_rng(42)
 
@@ -241,7 +241,7 @@ def sample(
                     continue
 
                 # Apply selections
-                comp_idx, _ = component.flavour.cuts(batch[self.variables.jets_name])
+                comp_idx, _ = component.flavour.cuts(batch[self.variables.global_name])
                 if len(comp_idx) == 0:
                     continue
 
@@ -249,14 +249,14 @@ def sample(
                 batch_out = select_batch(batch, comp_idx)
 
                 # Apply sampling
-                idx = np.arange(len(batch_out[self.variables.jets_name]))
+                idx = np.arange(len(batch_out[self.variables.global_name]))
 
                 # Check that the component is not the target and a resampling
                 # function is set.
                 if component != self.target and self.select_func:
                     # Apply the resampling
                     idx = self.select_func(
-                        jets=batch_out[self.variables.jets_name],
+                        jets=batch_out[self.variables.global_name],
                         component=component,
                     )
                     if len(idx) == 0:
@@ -350,7 +350,7 @@ def run_on_region(
             reader = H5Reader(
                 sample.path,
                 self.batch_size,
-                jets_name=self.jets_name,
+                jets_name=self.global_name,
                 equal_jets=equal_jets_flag,
                 transform=self.transform,
                 vds_dir=sample.vds_dir,
@@ -513,7 +513,7 @@ def run(self, region: str | None = None, component: str | None = None):
 
             # Setup the reader for the components
             iter_component.setup_reader(
-                self.batch_size, jets_name=self.jets_name, transform=self.transform
+                self.batch_size, global_name=self.global_name, transform=self.transform
             )
 
             # If only one component is run, stop here for the target that needs to be
@@ -522,7 +522,7 @@ def run(self, region: str | None = None, component: str | None = None):
                 continue
 
             # Setup the writer for the component
-            iter_component.setup_writer(self.variables, jets_name=self.jets_name)
+            iter_component.setup_writer(self.variables, global_name=self.global_name)
 
             # Set sampling fraction
             self.set_component_sampling_fractions(component=iter_component)
diff --git a/upp/stages/reweight.py b/upp/stages/reweight.py
index 03019fe..899c467 100644
--- a/upp/stages/reweight.py
+++ b/upp/stages/reweight.py
@@ -48,7 +48,7 @@ def get_input_readers(self):
             f: H5Reader(
                 files_by_flavour[f],
                 batch_size=self.config.batch_size,
-                jets_name=self.config.jets_name,
+                jets_name=self.config.global_name,
             )
             for f in files_by_flavour
         }
@@ -117,8 +117,8 @@ def calculate_weights(
             all_vars[rw_group].extend(rw.reweight_vars)
             if "valid" in existing_vars[rw_group]:
                 all_vars[rw_group] += ["valid"]
-        if self.config.jets_name not in all_vars:
-            all_vars[self.config.jets_name] = ["pt"]
+        if self.config.global_name not in all_vars:
+            all_vars[self.config.global_name] = ["pt"]
         all_vars = {k: list(set(v)) for k, v in all_vars.items()}
         num_in_hists = {}
         all_histograms = {}
diff --git a/upp/stages/rw_merge.py b/upp/stages/rw_merge.py
index 6965858..66e478a 100644
--- a/upp/stages/rw_merge.py
+++ b/upp/stages/rw_merge.py
@@ -39,7 +39,7 @@ def __init__(self, config, outfile_idx_range=None):
 
         num_jets = sum(organised_components["num_jets"][self.config.split].values())
         self.attr_to_write = {
-            self.config.jets_name: {
+            self.config.global_name: {
                 "flavour_label": [f.name for f in self.config.components.flavours],
             },
             None: {
@@ -70,7 +70,7 @@ def run(self):
             "fname": all_files,
             "batch_size": batch_size,
             "shuffle": False,
-            "jets_name": self.config.jets_name,
+            "jets_name": self.config.global_name,
         }
         output_dir = self.config.out_dir / self.config.split
         output_dir.mkdir(parents=True, exist_ok=True)
@@ -83,7 +83,7 @@ def run(self):
 
         variables = self.config.variables.combined() if self.config.split != "test" else None
         if variables and "flavour_label" not in variables:
-            variables[self.config.jets_name] += ["flavour_label"]
+            variables[self.config.global_name] += ["flavour_label"]
         args_list = []
         for i, bi in enumerate(range(0, num_batches, batches_per_file)):
             args_list.append(
@@ -99,7 +99,7 @@ def run(self):
                     if (bi + batches_per_file) < num_batches
                     else (num_batches - bi),
                     self.attr_to_write,
-                    self.config.jets_name,
+                    self.config.global_name,
                 )
             )
         print("Running with ", self.rw_config.merge_num_proc, "processes")
@@ -208,7 +208,7 @@ def do_merge_with_weights(
         writer_id=0,
         limit_batches=False,
         attrs=None,
-        jets_name="jets",
+        global_name="jets",
     ):
         """Take a series of input files and merge them into a single final output file.
 
@@ -255,7 +255,7 @@ def do_merge_with_weights(
 
         for i, batch in enumerate(reader.stream(variables, skip_batches=skip_batches)):
             print(
-                f"Writer {writer_id} Combined batch {i} has {len(batch[jets_name])} jets",
+                f"Writer {writer_id} Combined batch {i} has {len(batch[global_name])} jets",
                 flush=True,
             )
             all_sample_weights = RWMerge.get_sample_weights(batch, weights)
@@ -273,7 +273,7 @@ def do_merge_with_weights(
                     shapes,
                     shuffle=True,
                     compression="gzip",
-                    jets_name=jets_name,
+                    jets_name=global_name,
                 )
                 for group, g_attrs in attrs.items():
                     for attr, value in g_attrs.items():
diff --git a/upp/stages/split_containers.py b/upp/stages/split_containers.py
index c04f0f6..70aa625 100644
--- a/upp/stages/split_containers.py
+++ b/upp/stages/split_containers.py
@@ -130,7 +130,7 @@ def split_file(
     ):
         if isinstance(input_file, str):
             input_file = Path(input_file)
-        jets_name = self.config.jets_name
+        global_name = self.config.global_name
         add_flavour_label = flavour_label_list is not None
         # All variables for test file
         all_variables = get_all_datasets(input_file)
@@ -142,7 +142,7 @@ def split_file(
         print("parsed variables: ", parsed_variables, flush=True)
         start = time.time()
         reader = H5Reader(
-            input_file, batch_size=batch_size, shuffle=False, jets_name=self.config.jets_name
+            input_file, batch_size=batch_size, shuffle=False, jets_name=self.config.global_name
         )
         if output_name is None:
             output_name = input_file.name
@@ -176,7 +176,7 @@ def split_file(
                 variables=all_variables if "test" in split else parsed_variables,
                 compression="gzip",
                 add_flavour_label=add_flavour_label,
-                jets_name=jets_name,
+                jets_name=global_name,
             )
             cuts_by_sample_components[split] = component_cuts
             print(f"Creating writer for {split} saved to {output_file}", flush=True)
@@ -202,28 +202,29 @@ def split_file(
             for sample_component in sample_components:
                 writer = writers_by_sample_components[sample_component]
                 cuts = cuts_by_sample_components[sample_component]
-                sel_idx = cuts(batch[jets_name]).idx
+                sel_idx = cuts(batch[global_name]).idx
                 sel_batch = {k: v[sel_idx] for k, v in batch.items()}
                 if add_flavour_label:
                     this_flavour_label = flavour_label_by_component[sample_component]
                     tfl_arr = (
-                        np.ones(sel_batch[jets_name].shape[0], dtype=np.int32) * this_flavour_label
+                        np.ones(sel_batch[global_name].shape[0], dtype=np.int32)
+                        * this_flavour_label
                     )
 
                     # I think this is only going to happen during tests, as the mock file has
                     # flavour_label in, but we wont
-                    if "flavour_label" in sel_batch[jets_name].dtype.names:
+                    if "flavour_label" in sel_batch[global_name].dtype.names:
                         if i == 0:
                             print(
                                 f"Warning: {sample_component} already has a flavour label. "
                                 "We will overwrite it now.",
                                 flush=True,
                             )
-                        sel_batch[jets_name]["flavour_label"] = tfl_arr
+                        sel_batch[global_name]["flavour_label"] = tfl_arr
                     else:
                         # Get the
-                        sel_batch[jets_name] = rfn.append_fields(
-                            sel_batch[jets_name],
+                        sel_batch[global_name] = rfn.append_fields(
+                            sel_batch[global_name],
                             "flavour_label",
                             tfl_arr,
                             usemask=False,
@@ -283,7 +284,7 @@ def _make_tmp_vds(self, files: list[str] | str | Path) -> Generator[Path, None,
             create_virtual_file(str(tmp_dir / "*.h5"), tmp_out_path, overwrite=True)
             h5vds = H5Reader(
                 tmp_out_path,
-                jets_name=self.config.jets_name,
+                jets_name=self.config.global_name,
             )
             print(
                 f"Created combined virtual dataset with {h5vds.num_jets} jets at {tmp_out_path}",
@@ -374,7 +375,7 @@ def create_meta_data(self):
 
         num_jets = {
             split: {
-                flavour: H5Reader(files[split][flavour], jets_name=self.config.jets_name).num_jets
+                flavour: H5Reader(files[split][flavour], jets_name=self.config.global_name).num_jets
                 for flavour in files[split]
             }
             for split in files
diff --git a/upp/utils/check_input_samples.py b/upp/utils/check_input_samples.py
index ba6230a..fd60d3a 100644
--- a/upp/utils/check_input_samples.py
+++ b/upp/utils/check_input_samples.py
@@ -210,7 +210,7 @@ def run_input_sample_check(
             sample_list[entry_name] = H5Reader(
                 fname=config.ntuple_dir / sample,
                 batch_size=config.batch_size,
-                jets_name=config.jets_name,
+                jets_name=config.global_name,
                 vds_dir=config.vds_dir,
             ).num_jets
 

From 4040d0190e5cad172e6ca2375e6871e975921e2c Mon Sep 17 00:00:00 2001
From: Alexander Froch <Alexander.Froch@cern.ch>
Date: Mon, 22 Jun 2026 22:42:21 +0200
Subject: [PATCH 04/13] Update changelog.md

---
 changelog.md | 3 +--
 1 file changed, 1 insertion(+), 2 deletions(-)

diff --git a/changelog.md b/changelog.md
index 2e49846..fc2a791 100644
--- a/changelog.md
+++ b/changelog.md
@@ -2,8 +2,7 @@
 
 ### [Latest]
 
-- Honour the configured global object name in the split, reweighting and merge stages so preprocessing works with object groups not named "jets" [#156](https://github.com/umami-hep/umami-preprocessing/pull/156)
-- Rename the `jets_name` config option to `global_name` to generalise the framework beyond jets (breaking: update existing configs) [#156](https://github.com/umami-hep/umami-preprocessing/pull/156)
+- Generalise framework: honour & rename the global object name (jets_name -> global_name) [#156](https://github.com/umami-hep/umami-preprocessing/pull/156)
 
 ### [v0.3.1](https://github.com/umami-hep/umami-preprocessing/releases/tag/v0.3.1) (19.06.2026)
 

From 98d956a60237b434911f967ad3852444f400e6dd Mon Sep 17 00:00:00 2001
From: Alexander Froch <Alexander.Froch@cern.ch>
Date: Tue, 23 Jun 2026 11:36:23 +0200
Subject: [PATCH 05/13] Generalise all jet-named identifiers to global_object
 names

Rename every jet-named config option and code identifier in UPP to
object-agnostic global_object names (e.g. num_jets -> num_global_objects,
equal_jets -> equal_global_objects, .jets -> .global_objects,
add_jet_vars -> add_global_vars, add_jet_flavour_label ->
add_global_object_label, unique_jets -> unique_global_objects,
jet_counts -> global_object_counts), addressing the PR #156 review.

Old configs keep working: PreprocessingConfig.from_file recursively
remaps deprecated keys to their new names on load and warns.

The atlas-ftag-tools boundary is left untouched: ftag H5Reader/H5Writer
keyword args (jets_name=, equal_jets=, num_jets=), reader/writer
attributes (reader.num_jets, estimate_available_jets,
get_attr("unique_jets")), the h5 data-format attribute strings, and
physics flavour names (bjets/cjets/taujets/ghost*).

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
---
 changelog.md                                  |   2 +-
 docs/configuration.md                         |  18 +-
 docs/reweighting.md                           |   8 +-
 docs/run.md                                   |  10 +-
 docs/sampling.md                              |   6 +-
 .../fixtures/test_config_countup.yaml         |  20 +--
 .../test_config_countup_upscaled.yaml         |  18 +-
 .../fixtures/test_config_method_none.yaml     |  12 +-
 .../fixtures/test_config_no_resample.yaml     |  12 +-
 .../fixtures/test_config_pdf_auto.yaml        |  18 +-
 .../fixtures/test_config_pdf_upscaled.yaml    |  14 +-
 .../integration/fixtures/test_config_rw.yaml  |  12 +-
 .../fixtures/test_config_rw_custom_name.yaml  |  12 +-
 .../fixtures/test_config_track_selection.yaml |  18 +-
 tests/unit/classes/test_components.py         |   6 +-
 tests/unit/classes/test_plotting_config.py    |   6 +-
 .../unit/classes/test_preprocessing_config.py |  31 +++-
 .../fixtures/test_config_pdf_auto_umami.yaml  |  14 +-
 .../test_config_pdf_auto_umami_required.yaml  |  14 +-
 tests/unit/fixtures/test_config_rw.yaml       |  12 +-
 tests/unit/stages/test_merging.py             | 110 ++++++------
 tests/unit/stages/test_plotting.py            |  22 +--
 tests/unit/stages/test_reweight.py            |  16 +-
 upp/classes/components.py                     | 166 ++++++++++--------
 upp/classes/plotting_config.py                |  26 +--
 upp/classes/preprocessing_config.py           | 120 +++++++++----
 upp/classes/reweight_config.py                |   8 +-
 upp/classes/variable_config.py                |   6 +-
 upp/configs/GN3EPCMV01/GN3EPCMV01.yaml        |  82 ++++-----
 upp/configs/GN3V00/dr.yaml                    |  22 +--
 upp/configs/GN3V00/ghost-highstat.yaml        |  54 +++---
 upp/configs/GN3V00/ghost.yaml                 |  22 +--
 upp/configs/GN3V01/GN3V01-RW.yaml             |  14 +-
 upp/configs/GN3V01/GN3V01.yaml                |  54 +++---
 upp/configs/extended_labels.yaml              |  14 +-
 upp/configs/open-dataset.yaml                 |  10 +-
 upp/configs/plit_electron.yaml                |   8 +-
 upp/configs/plit_muon.yaml                    |   8 +-
 upp/configs/single-b-upgrade.yaml             |  18 +-
 upp/configs/single-b.yaml                     |  18 +-
 upp/configs/test.yaml                         |   6 +-
 upp/configs/xbb-gn3x.yaml                     |  26 +--
 upp/configs/xbb-rw.yaml                       |  30 ++--
 upp/configs/xbb.yaml                          |  14 +-
 upp/configs/xtautau.yaml                      |  14 +-
 upp/grid/download_and_prepare.py              |   6 +-
 upp/main.py                                   |   9 +-
 upp/stages/__init__.py                        |   4 +-
 upp/stages/hist.py                            |  41 +++--
 upp/stages/merging.py                         | 153 ++++++++--------
 upp/stages/normalisation.py                   |  33 ++--
 upp/stages/plot.py                            |  86 ++++-----
 upp/stages/resampling.py                      | 143 +++++++--------
 upp/stages/reweight.py                        |  34 ++--
 upp/stages/rw_merge.py                        |  41 +++--
 upp/stages/split_containers.py                |  24 +--
 upp/utils/check_input_samples.py              |  18 +-
 57 files changed, 939 insertions(+), 804 deletions(-)

diff --git a/changelog.md b/changelog.md
index fc2a791..27e09e8 100644
--- a/changelog.md
+++ b/changelog.md
@@ -2,7 +2,7 @@
 
 ### [Latest]
 
-- Generalise framework: honour & rename the global object name (jets_name -> global_name) [#156](https://github.com/umami-hep/umami-preprocessing/pull/156)
+- Generalise the framework beyond jets: honour the configured global object name in all stages, and rename every jet-named config option and code identifier to object-agnostic `global_object` names (e.g. `jets_name`→`global_name`, `num_jets`→`num_global_objects`, `equal_jets`→`equal_global_objects`). Old configs keep working — deprecated keys are remapped automatically on load with a warning [#156](https://github.com/umami-hep/umami-preprocessing/pull/156)
 
 ### [v0.3.1](https://github.com/umami-hep/umami-preprocessing/releases/tag/v0.3.1) (19.06.2026)
 
diff --git a/docs/configuration.md b/docs/configuration.md
index 99f4ad6..aa9f0ad 100644
--- a/docs/configuration.md
+++ b/docs/configuration.md
@@ -10,7 +10,7 @@ Each aspect of the configuration is described in detail below.
 
 Here we define the input h5 samples which are to be preprocessed.
 Each sample is defined using one or more DSIDs, which generally come from the [training-dataset-dumper](https://gitlab.cern.ch/atlas-flavor-tagging-tools/training-dataset-dumper).
-If a list of DSIDs is provided, jets from each DSID will be merged according to the `equal_jets` flag (see below).
+If a list of DSIDs is provided, jets from each DSID will be merged according to the `equal_global_objects` flag (see below).
 The samples are used to define components later on in configs and so one should define them with [anchors](https://support.atlassian.com/bitbucket-cloud/docs/yaml-anchors/).
 
 Below is an example and a table explaining each setting.
@@ -28,7 +28,7 @@ Below is an example and a table explaining each setting.
     ```yaml
     ttbar: &ttbar
       name: ttbar
-      equal_jets: False
+      equal_global_objects: False
       pattern:
         - name1.*.410470.*/*.h5
         - name2.*.410470.*/*.h5
@@ -38,7 +38,7 @@ Below is an example and a table explaining each setting.
 | ------- | ---- | ----------- | ------- |
 |`name`   |`str`| The name of the sample, used in output filenames.| *Required* |
 |`pattern`|`str` or `list[str]`| A single pattern or a list of pattern that match h5 files in a downloaded dataset. H5 files matching each pattern will be transparently merged using virtual datasets. | *Required* |
-|`equal_jets`|`bool`| Only relevant when providing a list of patterns. If `True`, the same number of jets from each DSID are selected. This is required for e.g. in Xbb QCD where each DSID belongs to a different slice, and the resampling would break if you tried to resample with one or more slices missing. If `False` this is not enforced, allowing for larger numbers of available jets. | `True` |
+|`equal_global_objects`|`bool`| Only relevant when providing a list of patterns. If `True`, the same number of jets from each DSID are selected. This is required for e.g. in Xbb QCD where each DSID belongs to a different slice, and the resampling would break if you tried to resample with one or more slices missing. If `False` this is not enforced, allowing for larger numbers of available jets. | `True` |
 
 The virtual dataset files created from wildcard patterns are by default stored alongside the input ntuples.
 If you have no write access to the input ntuples directory and would like to collect all VDS files in an accessible directory instead, set `vds_dir` in the global config (see [Global Config](#global-config)).
@@ -124,14 +124,14 @@ components:
     sample:
     <<: *ttbar
     flavours: [bjets, cjets, ujets]
-    num_jets: 10_000_000
+    num_global_objects: 10_000_000
 
 - region:
     <<: *highpt
     sample:
     <<: *zprime
     flavours: [bjets, cjets, ujets]
-    num_jets: 5_000_000
+    num_global_objects: 5_000_000
 ```
 
 Notice that we use `<<*` insertion tool to insert already defined regions and samples.
@@ -141,9 +141,9 @@ Notice that we use `<<*` insertion tool to insert already defined regions and sa
 | `region`| anchor | The pre-defined kinematic region anchor, e.g. `lowpt` or `highpt`, or `inclusive` if not splitting in $p_T$ |
 | `sample`| anchor | The pre-defined sample anchor, e.g. $t\bar{t}$ or $Z'$ |
 | `flavours` | `list[str]` | One or more jet flavours, e.g. `[bjets]` or `[ujets]`. The list syntax is pure syntactic sugar. If more then one is provided, separate components are created for each flavour.|
-|`num_jets`|`int`| The number of jets to be sampled from this component in the training split. When resampling is skipped, `-1` writes all jets of this component passing the cuts.|
-|`num_jets_val`|`int`| **Optional** (default: `num_jets//10`) number of jets of this component in validation set.|
-|`num_jets_test`|`int`| **Optional** (default: `num_jets//10`) number of jets of this component in a test set.|
+|`num_global_objects`|`int`| The number of jets to be sampled from this component in the training split. When resampling is skipped, `-1` writes all jets of this component passing the cuts.|
+|`num_global_objects_val`|`int`| **Optional** (default: `num_global_objects//10`) number of jets of this component in validation set.|
+|`num_global_objects_test`|`int`| **Optional** (default: `num_global_objects//10`) number of jets of this component in a test set.|
 
 
 
@@ -251,7 +251,7 @@ Plot labels and styles can be configured under the optional `plotting:` key. Any
 
 ```yaml
 plotting:
-  num_jets_plotting: 10_000_000
+  num_global_objects_plotting: 10_000_000
   variable_labels:
     pt: "Jet $p_\\mathrm{T}$ [GeV]"
     eta: "Jet $|\\eta|$"
diff --git a/docs/reweighting.md b/docs/reweighting.md
index 21f384b..ce9b82c 100644
--- a/docs/reweighting.md
+++ b/docs/reweighting.md
@@ -69,7 +69,7 @@ Once all the samples are prepared, we can calculate the weights. An example conf
 ```yaml
 
 reweighting:
-  num_jets_estimate: 1_500_000
+  num_global_objects_estimate: 1_500_000
   merge_num_proc: 20
   reweights:
     - group: jets
@@ -87,7 +87,7 @@ reweighting:
 
 ```
 
-`num_jets_estimate` represents the number of each jet flavour used to generate the reweighting histograms. The `merge_num_proc` variable will be relevant in the next section of these docs.
+`num_global_objects_estimate` represents the number of each jet flavour used to generate the reweighting histograms. The `merge_num_proc` variable will be relevant in the next section of these docs.
 Then, you have the `reweights` section, which includes a list of reweight configurations. In this example, we have the first reweight calculated over the jets group. It reweights based on the flavour-label, over the pt and eta distributions. The bins follow the same logic as in resampling.
 The class target can then either be chosen as a single label (e.g, if 0 then the reweighting would target the distribution for `flavour_label==0`), or one of `mean, min, max` which will instead target either the mean distribution, or always take the maximum/minimum bin counts as the target.
 The reweighting can also be performed over track variables, for example
@@ -122,7 +122,7 @@ Finally, we can merge all the relevant jets with their weights. This is done by
 preprocess --config {config} --rwm --split {train/test/val}
 ```
 
-This can either work in series to create 1 single large file, or we can produce multiple files with multi-processing. To do this, ensure the `global` section of the pre-processing config includes `num_jets_per_output_file` and the `reweighting` section has `merge_num_proc>1`.
-This will then launch `merge_num_proc` processes, with approximately `num_jets_per_output_file` per file*.
+This can either work in series to create 1 single large file, or we can produce multiple files with multi-processing. To do this, ensure the `global` section of the pre-processing config includes `num_global_objects_per_output_file` and the `reweighting` section has `merge_num_proc>1`.
+This will then launch `merge_num_proc` processes, with approximately `num_global_objects_per_output_file` per file*.
 
 * Due to the nature of the H5Reader, the actual number of jets per file will be slightly smaller than what is requested, on the order of 0.1%.
diff --git a/docs/run.md b/docs/run.md
index b78d987..f0ab974 100644
--- a/docs/run.md
+++ b/docs/run.md
@@ -51,7 +51,7 @@ The stages are described below.
 #### 1. Prepare
 The prepare stage (`--prep`) checks first the number of initial jets that are available per group/sample. For each of the entries in the `pattern` of the group, it checks how many jets are in total available. If this differs too much between the entries in `pattern`, an error is thrown because it indicates that you will might introduce biases in the training. For example, usually entries in `pattern` are different MC campaigns and by using drastically different numbers of initial jets, a campaign dependency can be introduced. If you manually checked it and you expect large differences, you can skip this by adding the command line argument `--skip-sample-check`. If you run the script the first time and you want to run the prepare stage in parallel, please let this script run first! It creates virtual datasets for each entry in `pattern` which could become corrupted if you do run this script in parallel multiple times! Instructions on how to run this check stand-alone can be found in [here](#additional-scripts-initial-sample-check).
 
-Afterwards, the prepare stage reads a specified number of jets (`num_jets_estimate_hist`) for each flavor and constructs histograms of the resampling variables. These histograms are stored in `<base_dir>/hists`.
+Afterwards, the prepare stage reads a specified number of jets (`num_global_objects_estimate_hist`) for each flavor and constructs histograms of the resampling variables. These histograms are stored in `<base_dir>/hists`.
 
 ???info "Paralellisation"
     This step can be parallelized to speed up the histogram creation. To do so, you need to provide the additional `--component` flag. The argument for the flag is the name of the component, which is to be processed. The argument can be constructed when looking closer at the different blocks in the `components` part of the config file. As an example, we take the `ghost-highstat.yaml` config file from the `gn3` folder in `configs/`:
@@ -62,8 +62,8 @@ Afterwards, the prepare stage reads a specified number of jets (`num_jets_estima
         sample:
         <<: *ttbar
         flavours: [ghostsplitbjets]
-        num_jets: 22_000_000
-        num_jets_test: 2_000_000
+        num_global_objects: 22_000_000
+        num_global_objects_test: 2_000_000
     ```
 
     The argument for the component flag can be constructed by taking the name of the region (this is defined in the definition of `lowpt`)
@@ -81,7 +81,7 @@ Afterwards, the prepare stage reads a specified number of jets (`num_jets_estima
     ```yaml
     ttbar: &ttbar
     name: ttbar
-    equal_jets: False
+    equal_global_objects: False
     pattern:
         - "user.svanstro.601589.e8547_s3797_r13144_p6368.tdd.GN3_dev.25_2_27.24-09-17_v00_output.h5/*.h5" # mc20d
         - "user.svanstro.601589.e8549_s4159_r14799_p6368.tdd.GN3_dev.25_2_27.24-09-17_v00_output.h5/*.h5" # mc23a
@@ -127,7 +127,7 @@ The merge stage (`--merge`) combines the resampled samples into a single file na
 It also handles shuffling.
 
 #### 4. Normalise 
-The normalize stage (`--norm`) calculates scaling and shifting values for all variables intended for training based on (`num_jets_estimate_norm`). The results are stored in` <tbase_dir>/<out_dir>/norm_dict.yaml`.
+The normalize stage (`--norm`) calculates scaling and shifting values for all variables intended for training based on (`num_global_objects_estimate_norm`). The results are stored in` <tbase_dir>/<out_dir>/norm_dict.yaml`.
 
 #### 5. Plotting 
 
diff --git a/docs/sampling.md b/docs/sampling.md
index 031e249..24eea17 100644
--- a/docs/sampling.md
+++ b/docs/sampling.md
@@ -5,7 +5,7 @@ For resampling, UPP has two different methods implemented. The desired method (`
 
 ### Skipping resampling
 
-Resampling can be disabled entirely by either omitting the `resampling` block from the config or setting `method: none`. In this case no `target`, resampling `variables`, or histogram (`--prep`) step are required. The jets passing the cuts are written directly, capped at each component's `num_jets`. Setting `num_jets: -1` (also valid for `num_jets_val` / `num_jets_test`) writes **all** jets of that component passing the cuts.
+Resampling can be disabled entirely by either omitting the `resampling` block from the config or setting `method: none`. In this case no `target`, resampling `variables`, or histogram (`--prep`) step are required. The jets passing the cuts are written directly, capped at each component's `num_global_objects`. Setting `num_global_objects: -1` (also valid for `num_global_objects_val` / `num_global_objects_test`) writes **all** jets of that component passing the cuts.
 
 Note that the `--no-resample` command line flag is different: it only skips the resampling *stage* (for example to re-run the merge/norm/plot stages on existing component files) and does not disable resampling.
 
@@ -15,7 +15,7 @@ This is an implementation of an [importance sampling](https://en.wikipedia.org/w
 
 The resampling is done using the following steps:
 
-1. A `num_jets_estimate` number of jets are binned for each flavour using the configurations for resampling variable bins. This histogram, `pdf_resampled_flavour`, is the initial estimate of the pdf of jets of each flavour.
+1. A `num_global_objects_estimate` number of jets are binned for each flavour using the configurations for resampling variable bins. This histogram, `pdf_resampled_flavour`, is the initial estimate of the pdf of jets of each flavour.
 2. The importance function is estimated by using the ratio of the histograms for each flavor to that of the target flavour, `pdf_target_flavour/pdf_resampled_flavour`. Safe division is used, which ensures that if for a bin in `pdf_resampled_flavour` is 0, we skip that bin. This ensures that we do not divide by 0. If a bin in `pdf_target_flavour` is 0, we also skip the bin. 
 3. Optionally, the importance function is upscaled. This means that it is interpolated using cubic spline interpolation to a finer grid of bins. The centres of bins are used as nodes for the splines. The new bins are created by splitting the old bins into `upscale_pdf` number of bins of equal width. The function is evaluated in the centers of the new bins. This way, the edge bins of each binning region are actually extrapolated rather than interpolated.
 4. The new batch of jets is being read and after the cuts are applied `n_batch` jets remain. The jets are binned with the the binning from step 1 (if upscaling is not used) or upscaled binning defined by 3 (if upscaling is used) and the reference number of the bin for each jet is saved.
@@ -28,7 +28,7 @@ This algorithm is used for all the flavours except the target flavour for which
 
 Countup resampling tries to select as many unique jets from each bin as possible before selecting the duplicates.
 
-1. `num_jets_estimate` jets are binned for each flavour using the configurations for resampling variable bins. This histogram is the initial estimate of the pdf of jets of each flavour.
+1. `num_global_objects_estimate` jets are binned for each flavour using the configurations for resampling variable bins. This histogram is the initial estimate of the pdf of jets of each flavour.
 2. The new batch of jets is being read and after the cuts are applied `n_batch` jets remain. The jets are binned with the the binning from step 1 (if upscaling is not used) or upscaled binning defined by 3 (if upscaling is used) and the reference number of the bin for each jet is saved.
 3. The number of **requested** jets in each bin are calculated as `floor(n_batch*pdf_target_flavour+uniform([0, 1]))` so that if `n_batch*flavour.sampling_fraction*pdf_target_flavour=1.2` it has a 80% chance to be rounded up to 1 and 20% chance to be rounded up to 2 so that for each bin we get an integer number that on average corresponds to the expected value. 
 4. From each bin we select consecutively (without replacement) the required number of jets. If the bin holds less jets than the **requested** number the rest of jets in this bin is chosen at random from this bin with replacement. This way only few jets in each bin are repeated for `flavour.sampling_fraction=1` and rarely any are repeated for smaller sampling fractions
diff --git a/tests/integration/fixtures/test_config_countup.yaml b/tests/integration/fixtures/test_config_countup.yaml
index 9fb46ef..90fcf62 100644
--- a/tests/integration/fixtures/test_config_countup.yaml
+++ b/tests/integration/fixtures/test_config_countup.yaml
@@ -33,42 +33,42 @@ components:
     sample:
       <<: *ttbar
     flavours: [bjets]
-    num_jets: 7_000
+    num_global_objects: 7_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
     flavours: [cjets]
-    num_jets: 7_000
+    num_global_objects: 7_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
     flavours: [ujets]
-    num_jets: 7_000
+    num_global_objects: 7_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [bjets]
-    num_jets: 3_000
+    num_global_objects: 3_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [cjets]
-    num_jets: 3_000
+    num_global_objects: 3_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [ujets]
-    num_jets: 3_000
+    num_global_objects: 3_000
 
 resampling:
   target: bjets
@@ -82,10 +82,10 @@ resampling:
 
 global:
   batch_size: 10_000
-  num_jets_estimate: 5_000
-  num_jets_estimate_norm: 100
-  num_jets_estimate_available: -1
-  num_jets_per_output_file: 15_000
+  num_global_objects_estimate: 5_000
+  num_global_objects_estimate_norm: 100
+  num_global_objects_estimate_available: -1
+  num_global_objects_per_output_file: 15_000
   base_dir: tmp/upp-tests/integration/temp_workspace/
   out_dir: test_out
   ntuple_dir: ntuples
diff --git a/tests/integration/fixtures/test_config_countup_upscaled.yaml b/tests/integration/fixtures/test_config_countup_upscaled.yaml
index 1fa14f9..c2e5c67 100644
--- a/tests/integration/fixtures/test_config_countup_upscaled.yaml
+++ b/tests/integration/fixtures/test_config_countup_upscaled.yaml
@@ -33,42 +33,42 @@ components:
     sample:
       <<: *ttbar
     flavours: [bjets]
-    num_jets: 70_000
+    num_global_objects: 70_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
     flavours: [cjets]
-    num_jets: 70_000
+    num_global_objects: 70_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
     flavours: [ujets]
-    num_jets: 70_000
+    num_global_objects: 70_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [bjets]
-    num_jets: 30_000
+    num_global_objects: 30_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [cjets]
-    num_jets: 30_000
+    num_global_objects: 30_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [ujets]
-    num_jets: 30_000
+    num_global_objects: 30_000
 
 resampling:
   target: cjets
@@ -82,9 +82,9 @@ resampling:
 
 global:
   batch_size: 10_000
-  num_jets_estimate: 5000
-  num_jets_estimate_norm: 100
-  num_jets_estimate_available: -1
+  num_global_objects_estimate: 5000
+  num_global_objects_estimate_norm: 100
+  num_global_objects_estimate_available: -1
   base_dir: tmp/upp-tests/integration/temp_workspace/
   out_dir: test_out
   ntuple_dir: ntuples
diff --git a/tests/integration/fixtures/test_config_method_none.yaml b/tests/integration/fixtures/test_config_method_none.yaml
index f94f71d..e5015e5 100644
--- a/tests/integration/fixtures/test_config_method_none.yaml
+++ b/tests/integration/fixtures/test_config_method_none.yaml
@@ -28,21 +28,21 @@ components:
     sample:
       <<: *ttbar
     flavours: [bjets]
-    num_jets: 1_000
+    num_global_objects: 1_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
     flavours: [cjets]
-    num_jets: 2_000
+    num_global_objects: 2_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
     flavours: [ujets]
-    num_jets: 3_000
+    num_global_objects: 3_000
 
 # Resampling explicitly disabled - no target or variables required.
 resampling:
@@ -50,9 +50,9 @@ resampling:
 
 global:
   batch_size: 10_000
-  num_jets_estimate: 5_000
-  num_jets_estimate_norm: 100
-  num_jets_estimate_available: -1
+  num_global_objects_estimate: 5_000
+  num_global_objects_estimate_norm: 100
+  num_global_objects_estimate_available: -1
   base_dir: tmp/upp-tests/integration/temp_workspace/
   out_dir: test_out
   ntuple_dir: ntuples
diff --git a/tests/integration/fixtures/test_config_no_resample.yaml b/tests/integration/fixtures/test_config_no_resample.yaml
index 331dd2b..9cd3146 100644
--- a/tests/integration/fixtures/test_config_no_resample.yaml
+++ b/tests/integration/fixtures/test_config_no_resample.yaml
@@ -30,27 +30,27 @@ components:
     sample:
       <<: *ttbar
     flavours: [bjets]
-    num_jets: 1_000
+    num_global_objects: 1_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
     flavours: [cjets]
-    num_jets: 1_000
+    num_global_objects: 1_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
     flavours: [ujets]
-    num_jets: -1
+    num_global_objects: -1
 
 global:
   batch_size: 10_000
-  num_jets_estimate: 5_000
-  num_jets_estimate_norm: 100
-  num_jets_estimate_available: -1
+  num_global_objects_estimate: 5_000
+  num_global_objects_estimate_norm: 100
+  num_global_objects_estimate_available: -1
   base_dir: tmp/upp-tests/integration/temp_workspace/
   out_dir: test_out
   ntuple_dir: ntuples
diff --git a/tests/integration/fixtures/test_config_pdf_auto.yaml b/tests/integration/fixtures/test_config_pdf_auto.yaml
index 234590c..51f01b8 100644
--- a/tests/integration/fixtures/test_config_pdf_auto.yaml
+++ b/tests/integration/fixtures/test_config_pdf_auto.yaml
@@ -32,42 +32,42 @@ components:
     sample:
       <<: *ttbar
     flavours: [bjets]
-    num_jets: 12_000
+    num_global_objects: 12_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
     flavours: [cjets]
-    num_jets: 12_000
+    num_global_objects: 12_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
     flavours: [ujets]
-    num_jets: 12_000
+    num_global_objects: 12_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [bjets]
-    num_jets: 6_000
+    num_global_objects: 6_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [cjets]
-    num_jets: 6_000
+    num_global_objects: 6_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [ujets]
-    num_jets: 6_000
+    num_global_objects: 6_000
 
 resampling:
   target: cjets
@@ -81,14 +81,14 @@ resampling:
 
 global:
   batch_size: 10_000
-  num_jets_estimate: 5000
-  num_jets_estimate_available: -1
+  num_global_objects_estimate: 5000
+  num_global_objects_estimate_available: -1
   base_dir: tmp/upp-tests/integration/temp_workspace/
   out_dir: test_out
   ntuple_dir: ntuples
 
 plotting:
-  num_jets_plotting: 100
+  num_global_objects_plotting: 100
   variable_labels:
     pt: "$p_\\mathrm{T}$ [GeV]"
   sample_labels:
diff --git a/tests/integration/fixtures/test_config_pdf_upscaled.yaml b/tests/integration/fixtures/test_config_pdf_upscaled.yaml
index d90f296..85dd350 100644
--- a/tests/integration/fixtures/test_config_pdf_upscaled.yaml
+++ b/tests/integration/fixtures/test_config_pdf_upscaled.yaml
@@ -33,42 +33,42 @@ components:
     sample:
       <<: *ttbar
     flavours: [bjets]
-    num_jets: 7_000
+    num_global_objects: 7_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
     flavours: [cjets]
-    num_jets: 7_000
+    num_global_objects: 7_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
     flavours: [ ujets]
-    num_jets: 7_000
+    num_global_objects: 7_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [bjets]
-    num_jets: 3_000
+    num_global_objects: 3_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [cjets]
-    num_jets: 3_000
+    num_global_objects: 3_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [ujets]
-    num_jets: 3_000
+    num_global_objects: 3_000
 
 resampling:
   target: bjets
@@ -83,7 +83,7 @@ resampling:
 
 global:
   batch_size: 10_000
-  num_jets_estimate: 5000
+  num_global_objects_estimate: 5000
   base_dir: tmp/upp-tests/integration/temp_workspace/
   out_dir: test_out
   ntuple_dir: ntuples
diff --git a/tests/integration/fixtures/test_config_rw.yaml b/tests/integration/fixtures/test_config_rw.yaml
index ee1a86e..4eaf59e 100644
--- a/tests/integration/fixtures/test_config_rw.yaml
+++ b/tests/integration/fixtures/test_config_rw.yaml
@@ -19,14 +19,14 @@ global_cuts: !include GN3V01/simple-split.yaml
 
 ttbar: &ttbar
   name: ttbar
-  equal_jets: False
+  equal_global_objects: False
   pattern:
     - "data1.h5"
     - "data2.h5"
 
 zprime: &zprime
   name: zprime
-  equal_jets: False
+  equal_global_objects: False
   pattern:
     - "data3.h5"
 
@@ -52,17 +52,17 @@ components:
     sample:
       <<: *ttbar
     flavours: [bjets, cjets, ujets, taujets]
-    num_jets: -1
+    num_global_objects: -1
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [bjets, cjets, ujets, taujets]
-    num_jets: -1
+    num_global_objects: -1
 
 reweighting:
-  num_jets_estimate: 200
+  num_global_objects_estimate: 200
   merge_num_proc: 1
   reweights:
     - group: jets
@@ -148,7 +148,7 @@ reweighting:
 global:
   global_name: jets
   batch_size: 1_000_000
-  num_jets_estimate: 25_000_000
+  num_global_objects_estimate: 25_000_000
   base_dir: tmp/upp-tests/integration/temp_workspace/
   out_dir: test_out
   ntuple_dir: ntuples
diff --git a/tests/integration/fixtures/test_config_rw_custom_name.yaml b/tests/integration/fixtures/test_config_rw_custom_name.yaml
index 0187f5e..21019b8 100644
--- a/tests/integration/fixtures/test_config_rw_custom_name.yaml
+++ b/tests/integration/fixtures/test_config_rw_custom_name.yaml
@@ -19,14 +19,14 @@ global_cuts: !include GN3V01/simple-split.yaml
 
 ttbar: &ttbar
   name: ttbar
-  equal_jets: False
+  equal_global_objects: False
   pattern:
     - "data1.h5"
     - "data2.h5"
 
 zprime: &zprime
   name: zprime
-  equal_jets: False
+  equal_global_objects: False
   pattern:
     - "data3.h5"
 
@@ -52,17 +52,17 @@ components:
     sample:
       <<: *ttbar
     flavours: [bjets, cjets, ujets, taujets]
-    num_jets: -1
+    num_global_objects: -1
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [bjets, cjets, ujets, taujets]
-    num_jets: -1
+    num_global_objects: -1
 
 reweighting:
-  num_jets_estimate: 200
+  num_global_objects_estimate: 200
   merge_num_proc: 1
   reweights:
     - group: objects
@@ -88,7 +88,7 @@ reweighting:
 global:
   global_name: objects
   batch_size: 1_000_000
-  num_jets_estimate: 25_000_000
+  num_global_objects_estimate: 25_000_000
   base_dir: tmp/upp-tests/integration/temp_workspace/
   out_dir: test_out
   ntuple_dir: ntuples
diff --git a/tests/integration/fixtures/test_config_track_selection.yaml b/tests/integration/fixtures/test_config_track_selection.yaml
index 3aca725..b7e4fdd 100644
--- a/tests/integration/fixtures/test_config_track_selection.yaml
+++ b/tests/integration/fixtures/test_config_track_selection.yaml
@@ -33,42 +33,42 @@ components:
     sample:
       <<: *ttbar
     flavours: [bjets]
-    num_jets: 7_000
+    num_global_objects: 7_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
     flavours: [cjets]
-    num_jets: 7_000
+    num_global_objects: 7_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
     flavours: [ ujets]
-    num_jets: 7_000
+    num_global_objects: 7_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [bjets]
-    num_jets: 3_000
+    num_global_objects: 3_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [cjets]
-    num_jets: 3_000
+    num_global_objects: 3_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [ujets]
-    num_jets: 3_000
+    num_global_objects: 3_000
 
 resampling:
   target: bjets
@@ -82,9 +82,9 @@ resampling:
 
 global:
   batch_size: 10_000
-  num_jets_estimate: 5000
-  num_jets_estimate_norm: 100
-  num_jets_estimate_available: -1
+  num_global_objects_estimate: 5000
+  num_global_objects_estimate_norm: 100
+  num_global_objects_estimate_available: -1
   base_dir: tmp/upp-tests/integration/temp_workspace/
   out_dir: test_out
   ntuple_dir: ntuples
diff --git a/tests/unit/classes/test_components.py b/tests/unit/classes/test_components.py
index cd885f2..693e276 100644
--- a/tests/unit/classes/test_components.py
+++ b/tests/unit/classes/test_components.py
@@ -20,9 +20,9 @@ def make_component(tmp_path: Path, vds_dir: Path | None) -> Component:
         flavour=Flavours.bjets,
         global_cuts=Cuts.empty(),
         dirname=tmp_path / "components" / "sub",
-        num_jets=100,
-        num_jets_estimate_available=0,
-        equal_jets=True,
+        num_global_objects=100,
+        num_global_objects_estimate_available=0,
+        equal_global_objects=True,
     )
 
 
diff --git a/tests/unit/classes/test_plotting_config.py b/tests/unit/classes/test_plotting_config.py
index 6c263e4..464bf96 100644
--- a/tests/unit/classes/test_plotting_config.py
+++ b/tests/unit/classes/test_plotting_config.py
@@ -18,17 +18,17 @@ def test_plotting_config_labels():
 
 
 def test_plotting_config_default_pt_label():
-    assert PlottingConfig().variable_label("pt_btagJes") == "Jet $p_\\mathrm{T}$ [GeV]"
+    assert PlottingConfig().variable_label("pt_btagJes") == "Object $p_\\mathrm{T}$ [GeV]"
 
 
 def test_plotting_config_default_mass_label():
-    assert PlottingConfig().variable_label("mass") == "Jet Mass [GeV]"
+    assert PlottingConfig().variable_label("mass") == "Object Mass [GeV]"
 
 
 @pytest.mark.parametrize(
     ("kwargs", "message"),
     [
-        ({"num_jets_plotting": 0}, "plotting.num_jets_plotting"),
+        ({"num_global_objects_plotting": 0}, "plotting.num_global_objects_plotting"),
         ({"output_formats": []}, "plotting.output_formats"),
         ({"linestyles": []}, "plotting.linestyles"),
     ],
diff --git a/tests/unit/classes/test_preprocessing_config.py b/tests/unit/classes/test_preprocessing_config.py
index 0ab771f..b1ae143 100644
--- a/tests/unit/classes/test_preprocessing_config.py
+++ b/tests/unit/classes/test_preprocessing_config.py
@@ -11,10 +11,31 @@
 from ftag import Extended_Flavours, Flavours, LabelContainer, get_mock_file
 
 from upp import __version__
-from upp.classes.preprocessing_config import PreprocessingConfig
+from upp.classes.preprocessing_config import (
+    PreprocessingConfig,
+    _rename_legacy_keys,
+)
 from upp.classes.resampling_config import ResamplingConfig
 
 
+def test_rename_legacy_keys_remaps_nested_and_records():
+    """Deprecated jet-named keys are remapped everywhere, others untouched."""
+    raw = {
+        "global": {"jets_name": "muons", "num_jets_estimate": 5},
+        "components": [{"num_jets": 10, "sample": {"equal_jets": True}, "flavours": ["bjets"]}],
+        "plotting": {"show_num_jets": False, "kept": 1},
+    }
+    found: set[str] = set()
+    out = _rename_legacy_keys(raw, found)
+
+    assert out["global"] == {"global_name": "muons", "num_global_objects_estimate": 5}
+    assert out["components"][0]["num_global_objects"] == 10
+    assert out["components"][0]["sample"]["equal_global_objects"] is True
+    assert out["components"][0]["flavours"] == ["bjets"]  # flavour names untouched
+    assert out["plotting"] == {"show_num_global_objects": False, "kept": 1}
+    assert found == {"jets_name", "num_jets_estimate", "num_jets", "equal_jets", "show_num_jets"}
+
+
 class TestPreprocessingConfig(unittest.TestCase):
     """unittest-based rewrite of the original pytest suite."""
 
@@ -57,7 +78,9 @@ def test_legacy_plotting_jet_count(self) -> None:
             skip_config_copy=True,
         )
 
-        self.assertEqual(config.plotting.num_jets_plotting, config.num_jets_estimate_plotting)
+        self.assertEqual(
+            config.plotting.num_global_objects_plotting, config.num_global_objects_estimate_plotting
+        )
 
     def test_plotting_config(self) -> None:
         config = PreprocessingConfig.from_file(
@@ -67,9 +90,9 @@ def test_plotting_config(self) -> None:
             skip_config_copy=True,
         )
 
-        self.assertEqual(config.plotting.num_jets_plotting, 100)
+        self.assertEqual(config.plotting.num_global_objects_plotting, 100)
         self.assertEqual(config.plotting.variable_label("pt"), "$p_\\mathrm{T}$ [GeV]")
-        self.assertEqual(config.plotting.variable_label("mass"), "Jet Mass [GeV]")
+        self.assertEqual(config.plotting.variable_label("mass"), "Object Mass [GeV]")
         self.assertEqual(config.plotting.sample_label("ttbar"), "$t\\bar{t}$")
         self.assertEqual(config.plotting.output_formats, ["png"])
 
diff --git a/tests/unit/fixtures/test_config_pdf_auto_umami.yaml b/tests/unit/fixtures/test_config_pdf_auto_umami.yaml
index 1b3c549..ba6415e 100644
--- a/tests/unit/fixtures/test_config_pdf_auto_umami.yaml
+++ b/tests/unit/fixtures/test_config_pdf_auto_umami.yaml
@@ -33,42 +33,42 @@ components:
     sample:
       <<: *ttbar
     flavours: [bjets]
-    num_jets: 7_000
+    num_global_objects: 7_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
     flavours: [cjets]
-    num_jets: 7_000
+    num_global_objects: 7_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
     flavours: [ ujets]
-    num_jets: 7_000
+    num_global_objects: 7_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [bjets]
-    num_jets: 3_000
+    num_global_objects: 3_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [cjets]
-    num_jets: 3_000
+    num_global_objects: 3_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [ujets]
-    num_jets: 3_000
+    num_global_objects: 3_000
 
 resampling:
   target: bjets
@@ -82,7 +82,7 @@ resampling:
 
 global:
   batch_size: 10_000
-  num_jets_estimate: 5000
+  num_global_objects_estimate: 5000
   base_dir: /tmp/upp-tests/integration/temp_workspace/
   out_dir: test_out
   flavour_category: standard
diff --git a/tests/unit/fixtures/test_config_pdf_auto_umami_required.yaml b/tests/unit/fixtures/test_config_pdf_auto_umami_required.yaml
index 805ba8b..72a0610 100644
--- a/tests/unit/fixtures/test_config_pdf_auto_umami_required.yaml
+++ b/tests/unit/fixtures/test_config_pdf_auto_umami_required.yaml
@@ -33,42 +33,42 @@ components:
     sample:
       <<: *ttbar
     flavours: [singlebjets]
-    num_jets: 7_000
+    num_global_objects: 7_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
     flavours: [singlecjets]
-    num_jets: 7_000
+    num_global_objects: 7_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
     flavours: [ujets]
-    num_jets: 7_000
+    num_global_objects: 7_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [singlebjets]
-    num_jets: 3_000
+    num_global_objects: 3_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [singlecjets]
-    num_jets: 3_000
+    num_global_objects: 3_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [ujets]
-    num_jets: 3_000
+    num_global_objects: 3_000
 
 resampling:
   target: singlebjets
@@ -82,7 +82,7 @@ resampling:
 
 global:
   batch_size: 10_000
-  num_jets_estimate: 5000
+  num_global_objects_estimate: 5000
   base_dir: /tmp/upp-tests/integration/temp_workspace/
   out_dir: test_out
   flavour_category: extended
diff --git a/tests/unit/fixtures/test_config_rw.yaml b/tests/unit/fixtures/test_config_rw.yaml
index e204297..897d527 100644
--- a/tests/unit/fixtures/test_config_rw.yaml
+++ b/tests/unit/fixtures/test_config_rw.yaml
@@ -3,14 +3,14 @@ global_cuts: !include GN3V01/simple-split.yaml
 
 ttbar: &ttbar
   name: ttbar
-  equal_jets: False
+  equal_global_objects: False
   pattern:
     - "data1.h5"
     - "data3.h5"
 
 zprime: &zprime
   name: zprime
-  equal_jets: False
+  equal_global_objects: False
   pattern:
     - "data2.h5"
 
@@ -31,14 +31,14 @@ components:
     sample:
       <<: *ttbar
     flavours: [bjets, cjets, ujets, taujets]
-    num_jets: -1
+    num_global_objects: -1
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [bjets, cjets, ujets, taujets]
-    num_jets: -1
+    num_global_objects: -1
 
 resampling:
   target: ghostcjets
@@ -56,7 +56,7 @@ resampling:
       bins: [[0, 2.5, 10]]
 
 reweighting:
-  num_jets_estimate: 100
+  num_global_objects_estimate: 100
   merge_num_proc: 1
   reweights:
     - group: jets
@@ -71,6 +71,6 @@ reweighting:
 global:
   global_name: jets
   batch_size: 1_000_000
-  num_jets_estimate: 25_000_000
+  num_global_objects_estimate: 25_000_000
   base_dir: /tmp/upp-tests/integration/temp_workspace/
   out_dir: test_out
diff --git a/tests/unit/stages/test_merging.py b/tests/unit/stages/test_merging.py
index 371a27b..843e745 100644
--- a/tests/unit/stages/test_merging.py
+++ b/tests/unit/stages/test_merging.py
@@ -59,7 +59,7 @@ class DummyComponent(SimpleNamespace):
     Simulates the subset of the real Component interface that Merging uses:
     - flavour
     - stream  (generator of batches)
-    - num_jets
+    - num_global_objects
     - complete flag
     """
 
@@ -67,7 +67,7 @@ def __init__(self, flavour, jet_batches):
         super().__init__()
         self.flavour = Flavours[flavour]
         self._batches = list(jet_batches)
-        self.num_jets = sum(len(b["jets"]) for b in self._batches)
+        self.num_global_objects = sum(len(b["jets"]) for b in self._batches)
         self.complete = False
         self.out_path = Path("/dev/null")
 
@@ -105,7 +105,7 @@ def _minimal_merging(monkeypatch, jets_per_file=10) -> merging_mod.Merging:
         variables=variables,
         batch_size=100,
         global_name="jets",
-        num_jets_per_output_file=jets_per_file,
+        num_global_objects_per_output_file=jets_per_file,
         file_tag="split",
         out_fname=Path("/tmp/merged.h5"),
         split="train",
@@ -126,13 +126,13 @@ def test_add_jet_flavour_label(monkeypatch):
 
     jets = _jets_struct(5)
     comp = SimpleNamespace(flavour=Flavours["bjets"])
-    tagged = merge.add_jet_flavour_label(jets, comp)
+    tagged = merge.add_global_object_label(jets, comp)
 
     assert "flavour_label" in tagged.dtype.names
     assert np.all(tagged["flavour_label"] == 0)
 
     # Calling again must not duplicate the column
-    same = merge.add_jet_flavour_label(tagged, comp)
+    same = merge.add_global_object_label(tagged, comp)
     assert same.dtype == tagged.dtype
 
 
@@ -146,9 +146,9 @@ def test_open_writer_names_and_shapes(monkeypatch):
 
     merge._open_writer(
         sample=None,
-        jets_in_file=7,
+        global_objects_in_file=7,
         file_idx=0,
-        components=SimpleNamespace(unique_jets=True, jet_counts={}, dsids=[]),
+        components=SimpleNamespace(unique_global_objects=True, global_object_counts={}, dsids=[]),
     )
 
     writer = merge.writer
@@ -162,7 +162,7 @@ def test_open_writer_names_and_shapes(monkeypatch):
 def test_write_chunk_splits(monkeypatch):
     """Test split writing of write_chunk.
 
-    With num_jets_per_output_file=5 and a batch of 8 jets, write_chunk must
+    With num_global_objects_per_output_file=5 and a batch of 8 jets, write_chunk must
     create two MemWriter instances and write all jets.
     """
     merge = _minimal_merging(monkeypatch, jets_per_file=5)
@@ -175,10 +175,12 @@ def test_write_chunk_splits(monkeypatch):
     # Fake dtypes / shapes and open first writer
     merge.dtypes = {"jets": jets1["jets"].dtype}
     merge.base_shapes = {"jets": (8,)}
-    merge.total_jets = 8
+    merge.total_global_objects = 8
     merge._file_idx = 0
-    merge.jets_written = 0
-    merge.current_components = SimpleNamespace(unique_jets=True, jet_counts={}, dsids=[])
+    merge.global_objects_written = 0
+    merge.current_components = SimpleNamespace(
+        unique_global_objects=True, global_object_counts={}, dsids=[]
+    )
     merge._sample = None
 
     merge._open_writer(None, 5, 0, merge.current_components)
@@ -203,7 +205,7 @@ def test_write_chunk_rollover(monkeypatch):
     1. close that writer,
     2. open a fresh one (file_idx increments),
     3. write the incoming batch into the new file,
-    4. update jets_written.
+    4. update global_objects_written.
     """
     # Create a merger with 5 jets / file
     merge = _minimal_merging(monkeypatch, jets_per_file=5)
@@ -216,11 +218,13 @@ def test_write_chunk_rollover(monkeypatch):
     # Fake the bookkeeping exactly as write_components() would
     merge.dtypes = {"jets": batch["jets"].dtype}
     merge.base_shapes = {"jets": (8,)}
-    merge.total_jets = 8
-    merge.jets_written = 5
+    merge.total_global_objects = 8
+    merge.global_objects_written = 5
     merge._file_idx = 0
     merge._sample = None
-    merge.current_components = SimpleNamespace(unique_jets=True, jet_counts={}, dsids=[])
+    merge.current_components = SimpleNamespace(
+        unique_global_objects=True, global_object_counts={}, dsids=[]
+    )
 
     # Open the first writer with capacity 5 and mark it as "full"
     merge._open_writer(None, 5, 0, merge.current_components)
@@ -232,7 +236,7 @@ def test_write_chunk_rollover(monkeypatch):
     assert n == 3
     assert merge._file_idx == 1
     assert merge.writer.num_written == 3
-    assert merge.jets_written == 8
+    assert merge.global_objects_written == 8
 
 
 def test_write_chunk_returns_zero_when_no_space_left(monkeypatch):
@@ -245,10 +249,12 @@ def test_write_chunk_returns_zero_when_no_space_left(monkeypatch):
     comps = [comp]
 
     # Mimic state after everything has already been written
-    merge.total_jets = 4
-    merge.jets_written = 4
+    merge.total_global_objects = 4
+    merge.global_objects_written = 4
     merge._file_idx = 0
-    merge.current_components = SimpleNamespace(unique_jets=True, jet_counts={}, dsids=[])
+    merge.current_components = SimpleNamespace(
+        unique_global_objects=True, global_object_counts={}, dsids=[]
+    )
     merge._sample = None
 
     # We still need valid dtypes / shapes for _open_writer
@@ -280,9 +286,9 @@ def dtypes(self, _vars):
         # Assume at least one batch exists
         return {"jets": self._batches[0]["jets"].dtype}
 
-    def shapes(self, total_jets: int, _keys):
+    def shapes(self, total_global_objects: int, _keys):
         # Base-shapes are used only for dataset names and leading dim
-        return {"jets": (total_jets,)}
+        return {"jets": (total_global_objects,)}
 
     def stream(self, _vars, _num_jets):
         def _gen():
@@ -297,7 +303,7 @@ class ComponentStub:
     def __init__(self, flavour: str, batches: list[dict[str, np.ndarray]]):
         self.flavour = Flavours[flavour]
         self._batches = batches
-        self.num_jets = sum(len(b["jets"]) for b in batches)
+        self.num_global_objects = sum(len(b["jets"]) for b in batches)
         self.complete = False
         self.out_path = Path("/dev/null")
         self.reader = None
@@ -311,9 +317,9 @@ class ComponentsStub:
 
     def __init__(self, comps: list[ComponentStub]):
         self._comps = comps
-        self.num_jets = sum(c.num_jets for c in comps)
-        self.unique_jets = True
-        self.jet_counts: dict[str, int] = {}
+        self.num_global_objects = sum(c.num_global_objects for c in comps)
+        self.unique_global_objects = True
+        self.global_object_counts: dict[str, int] = {}
         self.dsids: list[int] = []
 
     def __iter__(self):
@@ -339,7 +345,7 @@ def _mk_merge_for_path(monkeypatch, out_path: Path, jets_per_file=5):
         variables=variables,
         batch_size=100,
         global_name="jets",
-        num_jets_per_output_file=jets_per_file,
+        num_global_objects_per_output_file=jets_per_file,
         file_tag="split",
         out_fname=out_path,
         split="train",
@@ -390,7 +396,7 @@ def test_part_fname_formatting(monkeypatch, tmp_path):
 
 def test_detect_and_clean_completed_parts_empty_dir(monkeypatch, tmp_path):
     merge = _mk_merge_for_path(monkeypatch, tmp_path / "merged.h5", jets_per_file=5)
-    merge.total_jets = 10
+    merge.total_global_objects = 10
     merge.base_shapes = {"jets": (10,)}
     # no files exist
     idx = merge._detect_and_clean_completed_parts(None)
@@ -399,7 +405,7 @@ def test_detect_and_clean_completed_parts_empty_dir(monkeypatch, tmp_path):
 
 def test_expected_rows_for_part_middle_and_tail(monkeypatch, tmp_path):
     merge = _mk_merge_for_path(monkeypatch, tmp_path / "merged.h5", jets_per_file=5)
-    merge.total_jets = 12  # 5 + 5 + 2
+    merge.total_global_objects = 12  # 5 + 5 + 2
     assert merge._expected_rows_for_part(0) == 5
     assert merge._expected_rows_for_part(1) == 5
     assert merge._expected_rows_for_part(2) == 2
@@ -408,7 +414,7 @@ def test_expected_rows_for_part_middle_and_tail(monkeypatch, tmp_path):
 
 def test_is_part_valid_happy_path(monkeypatch, tmp_path):
     merge = _mk_merge_for_path(monkeypatch, tmp_path / "merged.h5", jets_per_file=5)
-    merge.total_jets = 12
+    merge.total_global_objects = 12
     merge.base_shapes = {"jets": (12,)}  # dataset names only; length unused here
 
     f0 = merge._part_fname(None, 0)
@@ -419,7 +425,7 @@ def test_is_part_valid_happy_path(monkeypatch, tmp_path):
 
 def test_is_part_valid_multiple_datasets(monkeypatch, tmp_path):
     merge = _mk_merge_for_path(monkeypatch, tmp_path / "merged.h5", jets_per_file=5)
-    merge.total_jets = 5
+    merge.total_global_objects = 5
     merge.base_shapes = {"jets": (5,), "tracks": (5,)}
 
     f0 = merge._part_fname(None, 0)
@@ -432,7 +438,7 @@ def test_is_part_valid_multiple_datasets(monkeypatch, tmp_path):
 
 def test_is_part_valid_wrong_length(monkeypatch, tmp_path):
     merge = _mk_merge_for_path(monkeypatch, tmp_path / "merged.h5", jets_per_file=5)
-    merge.total_jets = 12
+    merge.total_global_objects = 12
     merge.base_shapes = {"jets": (12,)}
 
     f1 = merge._part_fname(None, 1)
@@ -442,7 +448,7 @@ def test_is_part_valid_wrong_length(monkeypatch, tmp_path):
 
 def test_is_part_valid_missing_jets_dataset(monkeypatch, tmp_path):
     merge = _mk_merge_for_path(monkeypatch, tmp_path / "merged.h5", jets_per_file=5)
-    merge.total_jets = 5
+    merge.total_global_objects = 5
     merge.base_shapes = {"jets": (5,)}
 
     f0 = merge._part_fname(None, 0)
@@ -454,7 +460,7 @@ def test_is_part_valid_missing_jets_dataset(monkeypatch, tmp_path):
 
 def test_is_part_valid_mismatched_lengths(monkeypatch, tmp_path):
     merge = _mk_merge_for_path(monkeypatch, tmp_path / "merged.h5", jets_per_file=5)
-    merge.total_jets = 5
+    merge.total_global_objects = 5
     # Declare two expected datasets; only those present are compared
     merge.base_shapes = {"jets": (5,), "tracks": (5,)}
 
@@ -468,7 +474,7 @@ def test_is_part_valid_mismatched_lengths(monkeypatch, tmp_path):
 
 def test_is_part_valid_corrupt_file(monkeypatch, tmp_path):
     merge = _mk_merge_for_path(monkeypatch, tmp_path / "merged.h5", jets_per_file=5)
-    merge.total_jets = 5
+    merge.total_global_objects = 5
     merge.base_shapes = {"jets": (5,)}
 
     f0 = merge._part_fname(None, 0)
@@ -478,7 +484,7 @@ def test_is_part_valid_corrupt_file(monkeypatch, tmp_path):
 
 def test_detect_and_clean_completed_parts_counts_and_deletes(monkeypatch, tmp_path):
     merge = _mk_merge_for_path(monkeypatch, tmp_path / "merged.h5", jets_per_file=5)
-    merge.total_jets = 13  # parts: [5, 5, 3]
+    merge.total_global_objects = 13  # parts: [5, 5, 3]
     merge.base_shapes = {"jets": (13,)}
 
     # Create two valid parts 0 and 1
@@ -503,7 +509,7 @@ def test_detect_and_clean_completed_parts_counts_and_deletes(monkeypatch, tmp_pa
 
 def test_detect_and_clean_completed_parts_no_delete_when_disabled(monkeypatch, tmp_path):
     merge = _mk_merge_for_path(monkeypatch, tmp_path / "merged.h5", jets_per_file=5)
-    merge.total_jets = 10
+    merge.total_global_objects = 10
     merge.base_shapes = {"jets": (10,)}
 
     _write_valid_part(merge._part_fname(None, 0), rows=5)
@@ -519,7 +525,7 @@ def test_detect_and_clean_completed_parts_no_delete_when_disabled(monkeypatch, t
 def test_detect_and_clean_handles_unlink_error(monkeypatch, tmp_path):
     """Simulate OSError during unlink to cover error logging branch."""
     merge = _mk_merge_for_path(monkeypatch, tmp_path / "merged.h5", jets_per_file=5)
-    merge.total_jets = 10
+    merge.total_global_objects = 10
     merge.base_shapes = {"jets": (10,)}
 
     # Valid part 0
@@ -564,11 +570,11 @@ def test_resume_skips_completed_parts_and_opens_next(monkeypatch, tmp_path):
     open_calls = []
     _orig_open = merging_mod.Merging._open_writer
 
-    def _wrapped_open(self, sample, jets_in_file, file_idx, components):
+    def _wrapped_open(self, sample, global_objects_in_file, file_idx, components):
         # Fast-forward must be finished when we open a real writer
         assert self._fast_forwarding is False
-        open_calls.append((sample, jets_in_file, file_idx))
-        return _orig_open(self, sample, jets_in_file, file_idx, components)
+        open_calls.append((sample, global_objects_in_file, file_idx))
+        return _orig_open(self, sample, global_objects_in_file, file_idx, components)
 
     monkeypatch.setattr(merging_mod.Merging, "_open_writer", _wrapped_open)
 
@@ -577,9 +583,9 @@ def _wrapped_open(self, sample, jets_in_file, file_idx, components):
 
     # We expect the first (and only) open to be for part index 2 with capacity 3
     assert len(open_calls) >= 1
-    _, jets_in_file, file_idx = open_calls[0]
+    _, global_objects_in_file, file_idx = open_calls[0]
     assert file_idx == 2
-    assert jets_in_file == 3
+    assert global_objects_in_file == 3
 
     # The MemWriter should have written exactly 3 jets in that last file
     assert isinstance(merge.writer, MemWriter)
@@ -606,11 +612,11 @@ def test_fast_forward_does_not_open_real_writer(monkeypatch, tmp_path):
     call_times = {"count": 0}
     _orig_open = merging_mod.Merging._open_writer
 
-    def _wrapped_open(self, sample, jets_in_file, file_idx, components):
+    def _wrapped_open(self, sample, global_objects_in_file, file_idx, components):
         # Must never be invoked while fast-forwarding
         assert self._fast_forwarding is False
         call_times["count"] += 1
-        return _orig_open(self, sample, jets_in_file, file_idx, components)
+        return _orig_open(self, sample, global_objects_in_file, file_idx, components)
 
     monkeypatch.setattr(merging_mod.Merging, "_open_writer", _wrapped_open)
 
@@ -648,10 +654,12 @@ def test_write_chunk_all_components_complete_early_return(monkeypatch):
     jets0 = _jets_struct(0)
     merge.dtypes = {"jets": jets0.dtype}
     merge.base_shapes = {"jets": (0,)}
-    merge.total_jets = 0
+    merge.total_global_objects = 0
     merge._file_idx = 0
-    merge.jets_written = 0
-    merge.current_components = SimpleNamespace(unique_jets=True, jet_counts={}, dsids=[])
+    merge.global_objects_written = 0
+    merge.current_components = SimpleNamespace(
+        unique_global_objects=True, global_object_counts={}, dsids=[]
+    )
     merge._sample = None
     merge._open_writer(None, 0, 0, merge.current_components)
 
@@ -660,10 +668,10 @@ def test_write_chunk_all_components_complete_early_return(monkeypatch):
 
 
 def test_write_components_single_file_mode(monkeypatch, tmp_path):
-    """When num_jets_per_output_file is None, no split suffix is added."""
+    """When num_global_objects_per_output_file is None, no split suffix is added."""
     out = tmp_path / "merged.h5"
     merge = _mk_merge_for_path(monkeypatch, out, jets_per_file=None)
-    merge.num_jets_per_output_file = None  # ensure single-file mode
+    merge.num_global_objects_per_output_file = None  # ensure single-file mode
 
     jets = {"jets": _jets_struct(7)}
     comp = ComponentStub("bjets", [jets])
@@ -705,7 +713,7 @@ def groupby_sample(self):
         variables=variables,
         batch_size=100,
         global_name="jets",
-        num_jets_per_output_file=10,
+        num_global_objects_per_output_file=10,
         file_tag="split",
         out_fname=tmp_path / "merged.h5",
         split="train",
@@ -720,7 +728,7 @@ def groupby_sample(self):
     called = []
 
     def _wc(self, sample, components):  # noqa: ARG001
-        called.append((sample, components.num_jets))
+        called.append((sample, components.num_global_objects))
 
     monkeypatch.setattr(merging_mod.Merging, "write_components", _wc)
 
diff --git a/tests/unit/stages/test_plotting.py b/tests/unit/stages/test_plotting.py
index 024c23e..6261d66 100644
--- a/tests/unit/stages/test_plotting.py
+++ b/tests/unit/stages/test_plotting.py
@@ -85,19 +85,19 @@ def test_make_hist_initial_no_pt(self):
 
 def test_plot_helpers_format_labels_and_ranges():
     """Check compact labels and GeV unit conversion helpers."""
-    assert plot_mod._format_num_jets(999) == "999"
-    assert plot_mod._format_num_jets(100_000) == "100k"
-    assert plot_mod._format_num_jets(10_000_000) == "10M"
+    assert plot_mod._format_num_global_objects(999) == "999"
+    assert plot_mod._format_num_global_objects(100_000) == "100k"
+    assert plot_mod._format_num_global_objects(10_000_000) == "10M"
     assert (
         plot_mod._atlas_second_tag(
             "ttbar",
             "zprime",
             plotting=PlottingConfig(),
-            num_jets=100_000,
+            num_global_objects=100_000,
             resampling_status="Pre Resampling",
         )
-        == "$\\sqrt{s} = 13/13.6\\,\\mathrm{TeV}$, $t\\bar{t}$ + $Z'$ jets"
-        "\nPre Resampling\n100k jets"
+        == "$\\sqrt{s} = 13/13.6\\,\\mathrm{TeV}$, $t\\bar{t}$ + $Z'$ objects"
+        "\nPre Resampling\n100k objects"
     )
     assert plot_mod._display_range("pt_btagJes", (20_000, 250_000)) == (20, 250)
     assert plot_mod._display_range("JetFitterSecondaryVertex_mass", (0, 25_000)) == (0, 25)
@@ -198,7 +198,7 @@ def test_post_resampling_paths_split_mode(tmp_path):
         out_fname=tmp_path / "pp_output_test.h5",
         split="test",
         merge_test_samples=False,
-        num_jets_per_output_file=10,
+        num_global_objects_per_output_file=10,
         components=components,
     )
 
@@ -229,13 +229,13 @@ def groupby_region(self):
             )
             region_components = SimpleNamespace(
                 flavours=[Flavours["bjets"]],
-                num_jets=100_000,
+                num_global_objects=100_000,
             )
             return [(region, region_components)]
 
     config = SimpleNamespace(
         split="val",
-        plotting=PlottingConfig(num_jets_plotting=10_000),
+        plotting=PlottingConfig(num_global_objects_plotting=10_000),
         sampl_cfg=SimpleNamespace(
             vars=["pt"],
             bins={"pt": [[20_000, 250_000, 5]]},
@@ -254,7 +254,7 @@ def fake_load_jets(_config, _in_paths, _vars_to_load):
     def fake_make_hist(**kwargs):
         calls.append(kwargs)
 
-    monkeypatch.setattr(plot_mod, "_load_jets", fake_load_jets)
+    monkeypatch.setattr(plot_mod, "_load_global_objects", fake_load_jets)
     monkeypatch.setattr(plot_mod, "make_hist", fake_make_hist)
 
     plot_mod._plot_initial(config)
@@ -263,5 +263,5 @@ def fake_make_hist(**kwargs):
     assert calls[0]["suffix"] == "_val_ttbar_lowpt"
     assert calls[0]["bins_range"] == (20, 250)
     assert calls[0]["atlas_second_tag"] == (
-        "$\\sqrt{s} = 13/13.6\\,\\mathrm{TeV}$, $t\\bar{t}$ jets\nPre Resampling\n10k jets"
+        "$\\sqrt{s} = 13/13.6\\,\\mathrm{TeV}$, $t\\bar{t}$ objects\nPre Resampling\n10k objects"
     )
diff --git a/tests/unit/stages/test_reweight.py b/tests/unit/stages/test_reweight.py
index 6b2982a..8d1b9f3 100644
--- a/tests/unit/stages/test_reweight.py
+++ b/tests/unit/stages/test_reweight.py
@@ -32,7 +32,7 @@ def _make_organised_components(tmpdir, jets_per_flavour):
     return config_path
 
 
-def _make_reweight_obj(tmpdir, jets_per_flavour, num_jets_estimate, batch_size=1000):
+def _make_reweight_obj(tmpdir, jets_per_flavour, num_global_objects_estimate, batch_size=1000):
     """Create a Reweight instance with mocked config."""
     config_path = _make_organised_components(tmpdir, jets_per_flavour)
 
@@ -41,7 +41,9 @@ def _make_reweight_obj(tmpdir, jets_per_flavour, num_jets_estimate, batch_size=1
     config.base_dir = str(tmpdir)
     config.global_name = "jets"
 
-    rw_config = SimpleNamespace(num_jets_estimate=num_jets_estimate, reweights=[])
+    rw_config = SimpleNamespace(
+        num_global_objects_estimate=num_global_objects_estimate, reweights=[]
+    )
 
     rw = object.__new__(Reweight)
     rw.config = config
@@ -53,11 +55,11 @@ def _make_reweight_obj(tmpdir, jets_per_flavour, num_jets_estimate, batch_size=1
 
 class TestGetInputReaders:
     def test_caps_at_available_jets(self, tmp_path):
-        """When a reader has fewer jets than num_jets_estimate, cap to available."""
+        """When a reader has fewer jets than num_global_objects_estimate, cap to available."""
         rw = _make_reweight_obj(
             tmp_path,
             jets_per_flavour={"bjets": 50, "cjets": 200},
-            num_jets_estimate=100,
+            num_global_objects_estimate=100,
         )
         readers, per_reader_num_jets = rw.get_input_readers()
         assert len(readers) == 2
@@ -68,11 +70,11 @@ def test_caps_at_available_jets(self, tmp_path):
         assert per_reader_num_jets[1] == 100
 
     def test_all_above_estimate(self, tmp_path):
-        """When all readers have enough jets, use num_jets_estimate for all."""
+        """When all readers have enough jets, use num_global_objects_estimate for all."""
         rw = _make_reweight_obj(
             tmp_path,
             jets_per_flavour={"bjets": 500, "cjets": 300},
-            num_jets_estimate=100,
+            num_global_objects_estimate=100,
         )
         _, per_reader_num_jets = rw.get_input_readers()
         assert per_reader_num_jets == [100, 100]
@@ -86,7 +88,7 @@ def test_unequal_reader_lengths(self, tmp_path):
         rw = _make_reweight_obj(
             tmp_path,
             jets_per_flavour={"bjets": 50, "cjets": 200},
-            num_jets_estimate=200,
+            num_global_objects_estimate=200,
             batch_size=100,
         )
 
diff --git a/upp/classes/components.py b/upp/classes/components.py
index a9d94bd..c11830e 100644
--- a/upp/classes/components.py
+++ b/upp/classes/components.py
@@ -37,12 +37,12 @@ class Component:
         Global cuts that should be applied for this component
     dirname : Path
         Directory of where this component is/will be stored
-    num_jets : int
-        Number of jets that are to be used from this component
-    num_jets_estimate_available : int
-        Estimated available jets for this component
-    equal_jets : bool
-        If the same number of jets should be used from the different samples
+    num_global_objects : int
+        Number of objects that are to be used from this component
+    num_global_objects_estimate_available : int
+        Estimated available objects for this component
+    equal_global_objects : bool
+        If the same number of objects should be used from the different samples
     """
 
     region: Region
@@ -50,14 +50,14 @@ class Component:
     flavour: Label
     global_cuts: Cuts
     dirname: Path
-    num_jets: int
-    num_jets_estimate_available: int
-    equal_jets: bool
+    num_global_objects: int
+    num_global_objects_estimate_available: int
+    equal_global_objects: bool
 
     def __post_init__(self):
         """Post init setup of internal variables."""
         self.hist = Hist(self.dirname.parent.parent / "hists" / f"hist_{self.name}.h5")
-        self._unique_jets = -1
+        self._unique_global_objects = -1
         self._complete = None
         self._ups_ratio = None
         self._ups_max = None
@@ -70,16 +70,16 @@ def setup_reader(
         fname: Path | str | list[Path | str] | None = None,
         **kwargs,
     ) -> None:
-        """Set up the reader of the jets to load them from file.
+        """Set up the reader of the objects to load them from file.
 
         Parameters
         ----------
         batch_size : int
             Batch size that is used for loading from file
         global_name : str, optional
-            Name of the group in which the jets are stored, by default "jets"
+            Name of the group in which the objects are stored, by default "jets"
         fname : Path | str | list[Path | str] | None, optional
-            Filename of the file(s) from which the jets are loaded, by default None
+            Filename of the file(s) from which the objects are loaded, by default None
         **kwargs
             Additional kwargs passed to the H5Reader
         """
@@ -93,24 +93,24 @@ def setup_reader(
             fname=fname,
             batch_size=batch_size,
             jets_name=global_name,
-            equal_jets=self.equal_jets,
+            equal_jets=self.equal_global_objects,
             **kwargs,
         )
         log.debug(f"Setup component reader at: {fname}")
 
     def setup_writer(self, variables: VariableConfig, global_name: str = "jets") -> None:
-        """Set up the writer of the jets to file.
+        """Set up the writer of the objects to file.
 
         Parameters
         ----------
         variables : VariableConfig
             Instance of VariableConfig in which the variables are stored.
         global_name : str, optional
-            Name of the group in which the jets are stored, by default "jets"
+            Name of the group in which the objects are stored, by default "jets"
         """
         dtypes = self.reader.dtypes(variables.combined())
-        # num_jets == -1 ("write all") -> 0 leading dim so the writer grows dynamically
-        shapes = self.reader.shapes(max(self.num_jets, 0), variables.keys())
+        # num_global_objects == -1 ("write all") -> 0 leading dim so the writer grows dynamically
+        shapes = self.reader.shapes(max(self.num_global_objects, 0), variables.keys())
         self.writer = H5Writer(self.out_path, dtypes, shapes, jets_name=global_name)
         log.debug(f"Setup component writer at: {self.out_path}")
 
@@ -162,27 +162,29 @@ def is_target(self, target_str: str) -> bool:
         """
         return self.flavour.name == target_str
 
-    def get_jets(self, variables: list, num_jets: int, cuts: Cuts | None = None) -> dict:
-        """Load jets from file.
+    def get_global_objects(
+        self, variables: list, num_global_objects: int, cuts: Cuts | None = None
+    ) -> dict:
+        """Load objects from file.
 
         Parameters
         ----------
         variables : list
             Variables that are to be loaded
-        num_jets : int
-            Number of jets that are to be loaded
+        num_global_objects : int
+            Number of objects that are to be loaded
         cuts : Cuts | None, optional
-            Cuts instance of the cuts that should be applied on the jets, by default None
+            Cuts instance of the cuts that should be applied on the objects, by default None
 
         Returns
         -------
         dict
-            Dict with the loaded jets
+            Dict with the loaded objects
         """
         jn = self.reader.jets_name
-        return self.reader.load({jn: variables}, num_jets, cuts)[jn]
+        return self.reader.load({jn: variables}, num_global_objects, cuts)[jn]
 
-    def check_num_jets(
+    def check_num_global_objects(
         self,
         num_req: int,
         sampling_fraction: float | None = None,
@@ -190,36 +192,38 @@ def check_num_jets(
         silent: bool = False,
         raise_error: bool = True,
     ) -> None:
-        """Check the number of available jets.
+        """Check the number of available objects.
 
-        If more jets are requested than available, throw an Error.
+        If more objects are requested than available, throw an Error.
 
         Parameters
         ----------
         num_req : int
-            Number of requested jets
+            Number of requested objects
         sampling_fraction : float | None, optional
             Sampling , by default None
         cuts : Cuts | None, optional
-            Cuts instance of the cuts that are to be applied on the jets, by default None
+            Cuts instance of the cuts that are to be applied on the objects, by default None
         silent : bool, optional
             Decide, if the debug and info log statements are printed, by default False
         raise_error : bool, optional
-            Decide if the error should be raised if not enough jets are available,
+            Decide if the error should be raised if not enough objects are available,
             by default True
 
         Raises
         ------
         ValueError
-            If more jets are requsted than available
+            If more objects are requsted than available
         """
-        # num_req < 0 means "use all available jets" - nothing to check
+        # num_req < 0 means "use all available objects" - nothing to check
         if num_req < 0:
             return
 
-        # Check if num_jets jets are aviailable after the cuts and sampling fraction
+        # Check if num_global_objects objects are aviailable after the cuts and sampling fraction
         num_est = (
-            None if self.num_jets_estimate_available <= 0 else self.num_jets_estimate_available
+            None
+            if self.num_global_objects_estimate_available <= 0
+            else self.num_global_objects_estimate_available
         )
         total = self.reader.estimate_available_jets(cuts, num_est)
         available = total
@@ -229,22 +233,22 @@ def check_num_jets(
         # check with tolerance to avoid failure midway through preprocessing
         if available < num_req and raise_error:
             raise ValueError(
-                f"{num_req:,} jets requested, but only {total:,} are estimated to be"
+                f"{num_req:,} objects requested, but only {total:,} are estimated to be"
                 f" in {self}. With a sampling fraction of {sampling_fraction}, at most"
                 f" {available:,} of these are available. You can either reduce the"
-                " number of requested jets or increase the sampling fraction."
+                " number of requested objects or increase the sampling fraction."
             )
 
         if not silent:
             log.debug(f"Sampling fraction {sampling_fraction}")
             log.info(
-                f"Estimated {available:,} {self} jets available - {num_req:,} requested"
+                f"Estimated {available:,} {self} objects available - {num_req:,} requested"
                 f"({self.reader.num_jets:,} in {self.sample})"
             )
 
     def get_auto_sampling_fraction(
         self,
-        num_jets: int,
+        num_global_objects: int,
         cuts: Cuts | None = None,
         silent: bool = False,
     ) -> float:
@@ -252,10 +256,10 @@ def get_auto_sampling_fraction(
 
         Parameters
         ----------
-        num_jets : int
-            Number of jets available
+        num_global_objects : int
+            Number of objects available
         cuts : Cuts | None, optional
-            Cuts instance of the cuts that should be applied on the jets, by default None
+            Cuts instance of the cuts that should be applied on the objects, by default None
         silent : bool, optional
             Decide, if the debug and info log statements are printed, by default False
 
@@ -265,10 +269,12 @@ def get_auto_sampling_fraction(
             Automatically estimated sampling fraction
         """
         num_est = (
-            None if self.num_jets_estimate_available <= 0 else self.num_jets_estimate_available
+            None
+            if self.num_global_objects_estimate_available <= 0
+            else self.num_global_objects_estimate_available
         )
         total = self.reader.estimate_available_jets(cuts, num_est)
-        auto_sampling_frac = round(1.1 * num_jets / total, 3)  # 1.1 is a tolerance factor
+        auto_sampling_frac = round(1.1 * num_global_objects / total, 3)  # 1.1 is a tolerance factor
         if not silent:
             log.debug(f"optimal sampling fraction {auto_sampling_frac:.3f}")
         return auto_sampling_frac
@@ -284,18 +290,20 @@ def __str__(self) -> str:
         return self.name
 
     @property
-    def unique_jets(self) -> int:
-        """Return the number of unique jets for this component.
+    def unique_global_objects(self) -> int:
+        """Return the number of unique objects for this component.
 
         Returns
         -------
         int
-            Number of unique jets for this component
+            Number of unique objects for this component
         """
-        if self._unique_jets == -1:
-            self._unique_jets = sum([r.get_attr("unique_jets") for r in self.reader.readers])
+        if self._unique_global_objects == -1:
+            self._unique_global_objects = sum(
+                [r.get_attr("unique_jets") for r in self.reader.readers]
+            )
 
-        return self._unique_jets
+        return self._unique_global_objects
 
 
 class Components:
@@ -320,9 +328,9 @@ def from_config(cls, config: PreprocessingConfig) -> Components:
         """
         component_list = []
         for component in config.config["components"]:
-            # Ensure equal_jets flag is correctly set
-            assert "equal_jets" not in component, (
-                "equal_jets flag should be set in the sample config"
+            # Ensure equal_global_objects flag is correctly set
+            assert "equal_global_objects" not in component, (
+                "equal_global_objects flag should be set in the sample config"
             )
 
             # Get the region cuts
@@ -333,9 +341,9 @@ def from_config(cls, config: PreprocessingConfig) -> Components:
             # Get the region and apply the region cuts
             region = Region(component["region"]["name"], region_cuts + config.global_cuts)
 
-            # Load the pattern and the equal_jets settings
+            # Load the pattern and the equal_global_objects settings
             pattern = component["sample"]["pattern"]
-            equal_jets = component["sample"].get("equal_jets", True)
+            equal_global_objects = component["sample"].get("equal_global_objects", True)
             if isinstance(pattern, list):
                 pattern = tuple(pattern)
 
@@ -350,11 +358,15 @@ def from_config(cls, config: PreprocessingConfig) -> Components:
 
             # Create the Component instances for the different flavours
             for name in component["flavours"]:
-                num_jets = component["num_jets"]
+                num_global_objects = component["num_global_objects"]
                 if config.split == "val":
-                    num_jets = component.get("num_jets_val", num_jets // 10)
+                    num_global_objects = component.get(
+                        "num_global_objects_val", num_global_objects // 10
+                    )
                 elif config.split == "test":
-                    num_jets = component.get("num_jets_test", num_jets // 10)
+                    num_global_objects = component.get(
+                        "num_global_objects_test", num_global_objects // 10
+                    )
                 component_list.append(
                     Component(
                         region=region,
@@ -362,9 +374,9 @@ def from_config(cls, config: PreprocessingConfig) -> Components:
                         flavour=config.flavour_cont[name],
                         global_cuts=config.global_cuts,
                         dirname=config.components_dir,
-                        num_jets=num_jets,
-                        num_jets_estimate_available=config.num_jets_estimate_available,  # type: ignore
-                        equal_jets=equal_jets,
+                        num_global_objects=num_global_objects,
+                        num_global_objects_estimate_available=config.num_global_objects_estimate_available,  # type: ignore
+                        equal_global_objects=equal_global_objects,
                     )
                 )
         components = cls(component_list)
@@ -388,7 +400,9 @@ def check_flavour_ratios(self) -> None:
         for region, components in self.groupby_region():
             this_ratios = {}
             for f in flavours:
-                this_ratios[f.name] = components[f].num_jets / components.num_jets
+                this_ratios[f.name] = (
+                    components[f].num_global_objects / components.num_global_objects
+                )
             ratios[region] = this_ratios
 
         ref = next(iter(ratios.values()))
@@ -445,26 +459,26 @@ def cuts(self) -> Cuts:
         return sum((c.cuts for c in self), Cuts.from_list([]))
 
     @property
-    def num_jets(self) -> int:
-        """Return the number of jets available.
+    def num_global_objects(self) -> int:
+        """Return the number of objects available.
 
         Returns
         -------
         int
-            Number of available jets
+            Number of available objects
         """
-        return sum(c.num_jets for c in self)
+        return sum(c.num_global_objects for c in self)
 
     @property
-    def unique_jets(self) -> int:
-        """Return the number of unique jets available.
+    def unique_global_objects(self) -> int:
+        """Return the number of unique objects available.
 
         Returns
         -------
         int
-            Number of available unique jets
+            Number of available unique objects
         """
-        return sum(c.unique_jets for c in self)
+        return sum(c.unique_global_objects for c in self)
 
     @property
     def out_dir(self):
@@ -473,13 +487,17 @@ def out_dir(self):
         return next(iter(out_dir))
 
     @property
-    def jet_counts(self):
+    def global_object_counts(self):
         num_dict = {
-            c.name: {"num_jets": int(c.num_jets), "unique_jets": int(c.unique_jets)} for c in self
+            c.name: {
+                "num_jets": int(c.num_global_objects),
+                "unique_jets": int(c.unique_global_objects),
+            }
+            for c in self
         }
         num_dict["total"] = {
-            "num_jets": int(self.num_jets),
-            "unique_jets": int(self.unique_jets),
+            "num_jets": int(self.num_global_objects),
+            "unique_jets": int(self.unique_global_objects),
         }
         return num_dict
 
diff --git a/upp/classes/plotting_config.py b/upp/classes/plotting_config.py
index 7dff1da..e1f61fb 100644
--- a/upp/classes/plotting_config.py
+++ b/upp/classes/plotting_config.py
@@ -5,9 +5,9 @@
 
 def _default_variable_labels() -> dict[str, str]:
     return {
-        "pt": "Jet $p_\\mathrm{T}$ [GeV]",
-        "eta": "Jet $|\\eta|$",
-        "mass": "Jet Mass [GeV]",
+        "pt": "Object $p_\\mathrm{T}$ [GeV]",
+        "eta": "Object $|\\eta|$",
+        "mass": "Object Mass [GeV]",
     }
 
 
@@ -28,9 +28,9 @@ class PlottingConfig:
 
     Attributes
     ----------
-    num_jets_plotting : int | None, optional
-        Number of jets loaded for plotting. If not set, use the global
-        `num_jets_estimate_plotting` value. By default None.
+    num_global_objects_plotting : int | None, optional
+        Number of objects loaded for plotting. If not set, use the global
+        `num_global_objects_estimate_plotting` value. By default None.
     variable_labels : dict[str, str], optional
         Display labels for plotted variables. Keys are matched case-insensitively
         against variable names, with the longest matching key taking precedence.
@@ -45,8 +45,8 @@ class PlottingConfig:
         First ATLAS plot label. By default "Simulation Internal".
     atlas_second_tag : str, optional
         Second ATLAS plot label. By default "$\\sqrt{s} = 13/13.6\\,\\mathrm{TeV}$".
-    show_num_jets : bool, optional
-        Decide, if the number of jets is shown in the ATLAS second tag
+    show_num_global_objects : bool, optional
+        Decide, if the number of objects is shown in the ATLAS second tag
     output_formats : list[str], optional
         File formats in which each plot is saved. By default `["pdf", "png"]`.
     linestyles : list[str], optional
@@ -76,13 +76,13 @@ class PlottingConfig:
         By default "plots".
     """
 
-    num_jets_plotting: int | None = None
+    num_global_objects_plotting: int | None = None
     variable_labels: dict[str, str] = field(default_factory=_default_variable_labels)
     sample_labels: dict[str, str] = field(default_factory=_default_sample_labels)
     ylabel: str = "Normalised Number of {global_name}"
     atlas_first_tag: str = "Simulation Internal"
     atlas_second_tag: str = "$\\sqrt{s} = 13/13.6\\,\\mathrm{TeV}$"
-    show_num_jets: bool = True
+    show_num_global_objects: bool = True
     output_formats: list[str] = field(default_factory=lambda: ["pdf", "png"])
     linestyles: list[str] = field(default_factory=lambda: ["-", "--", "-.", ":"])
     bins: int = 50
@@ -99,8 +99,10 @@ class PlottingConfig:
     def __post_init__(self) -> None:
         self.variable_labels = {**_default_variable_labels(), **self.variable_labels}
         self.sample_labels = {**_default_sample_labels(), **self.sample_labels}
-        if self.num_jets_plotting is not None and self.num_jets_plotting <= 0:
-            raise ValueError("plotting.num_jets_plotting must be a positive integer or None")
+        if self.num_global_objects_plotting is not None and self.num_global_objects_plotting <= 0:
+            raise ValueError(
+                "plotting.num_global_objects_plotting must be a positive integer or None"
+            )
         if not self.output_formats:
             raise ValueError("plotting.output_formats must contain at least one format")
         if not self.linestyles:
diff --git a/upp/classes/preprocessing_config.py b/upp/classes/preprocessing_config.py
index 550d30f..d42b15b 100644
--- a/upp/classes/preprocessing_config.py
+++ b/upp/classes/preprocessing_config.py
@@ -34,6 +34,39 @@
 
 Split = Literal["train", "val", "test"]
 
+# Deprecated config keys mapped to their generalised (object-agnostic) names.
+# Old configs keep working: the keys are remapped on load (see from_file).
+LEGACY_KEY_MAP = {
+    "jets_name": "global_name",
+    "num_jets": "num_global_objects",
+    "num_jets_val": "num_global_objects_val",
+    "num_jets_test": "num_global_objects_test",
+    "num_jets_estimate": "num_global_objects_estimate",
+    "num_jets_estimate_available": "num_global_objects_estimate_available",
+    "num_jets_estimate_hist": "num_global_objects_estimate_hist",
+    "num_jets_estimate_norm": "num_global_objects_estimate_norm",
+    "num_jets_estimate_plotting": "num_global_objects_estimate_plotting",
+    "num_jets_per_output_file": "num_global_objects_per_output_file",
+    "num_jets_plotting": "num_global_objects_plotting",
+    "show_num_jets": "show_num_global_objects",
+    "equal_jets": "equal_global_objects",
+}
+
+
+def _rename_legacy_keys(obj, found: set[str]):
+    """Recursively rename deprecated object-named config keys to their new names."""
+    if isinstance(obj, dict):
+        out = {}
+        for key, value in obj.items():
+            if key in LEGACY_KEY_MAP:
+                found.add(key)
+                key = LEGACY_KEY_MAP[key]
+            out[key] = _rename_legacy_keys(value, found)
+        return out
+    if isinstance(obj, list):
+        return [_rename_legacy_keys(value, found) for value in obj]
+    return obj
+
 
 @dataclass
 class PreprocessingConfig:
@@ -47,9 +80,9 @@ class PreprocessingConfig:
     For example:
     ```yaml
     global:
-        global_name: jets
+        global_name: objects
         batch_size: 1_000_000
-        num_jets_estimate: 5_000_000
+        num_global_objects_estimate: 5_000_000
         base_dir: /my/stuff/
         ntuple_dir: h5-inputs # resolved path: /my/stuff/h5-inputs/
     ```
@@ -82,30 +115,31 @@ class PreprocessingConfig:
         `sampling_fraction*batch_size_after_cuts`. It is recommended to choose high batch sizes
         especially to the `countup` method to achive best agreement of target and resampled
         distributions. By default 100_000
-    num_jets_estimate : int, optional
+    num_global_objects_estimate : int, optional
         Any of the further three arguments that are not specified will default to this value
         Is equal to 1_000_000 by default.
-    num_jets_estimate_available : int | None, optional
-        A sabsample taken from the whole sample to estimate the number of jets after the cuts.
+    num_global_objects_estimate_available : int | None, optional
+        A sabsample taken from the whole sample to estimate the number of objects after the cuts.
         Please keep this number high in order to not get poisson error of more then 5%.
-        If time allows you can use -1 to get a precise number of jets and not just an estimate
-        although it will be slow for large datasets. Is equal to num_jets_estimate by default.
-    num_jets_estimate_hist : int | None, optional
-        Number of jets of each flavour that are used to construct histograms for probability
+        If time allows you can use -1 to get a precise number of objects and not just an estimate
+        although it will be slow for large datasets.
+        Is equal to num_global_objects_estimate by default.
+    num_global_objects_estimate_hist : int | None, optional
+        Number of objects of each flavour that are used to construct histograms for probability
         density function estimation. Larger numbers give a better quality estmate of the pdfs.
-        Is equal to num_jets_estimate by default.
-    num_jets_estimate_norm : int | None, optional
-        Number of jets of each flavour that are used to estimate shifting and scaling during
+        Is equal to num_global_objects_estimate by default.
+    num_global_objects_estimate_norm : int | None, optional
+        Number of objects of each flavour that are used to estimate shifting and scaling during
         normalisation step. Larger numbers give a better quality estmates.
-        Is equal to num_jets_estimate by default.
-    num_jets_estimate_plotting : int | None, optional
-        Number of jets of each flavour used for plotting the initial and the final resampling
+        Is equal to num_global_objects_estimate by default.
+    num_global_objects_estimate_plotting : int | None, optional
+        Number of objects of each flavour used for plotting the initial and the final resampling
         variable distributions. Larger numbers give a better estimate of the full distributions.
-        Is equal to num_jets_estimate by default.
+        Is equal to num_global_objects_estimate by default.
     merge_test_samples : bool, optional
         Merge the test samples of the different processes into one file. By default False.
     global_name : str, optional
-        Name of the global (per-object) dataset in the input file, e.g. the jets.
+        Name of the global (per-object) dataset in the input file, e.g. the objects.
         By default "jets".
     flavour_config : Path | None, optional
         Flavour config yaml file which is to be used. By default None
@@ -113,10 +147,10 @@ class PreprocessingConfig:
         Flavour categories that are to be used. By default, the "standard" (non-extended)
         labels are loaded. The extended labels can be used by setting this value to "extended".
         By default "standard". To use this option, flavour_config must be None.
-    num_jets_per_output_file : int | None, optional
-        Number of jets per final output file. If the number of total jets is larger
+    num_global_objects_per_output_file : int | None, optional
+        Number of objects per final output file. If the number of total objects is larger
         than this number, the final h5 output files are splitted in multiple smaller
-        files with this number of jets per file. By default None which produces one
+        files with this number of objects per file. By default None which produces one
         huge output file.
     skip_checks : bool, optional
         Skip checks for the input files. This is used for grid submission
@@ -136,31 +170,33 @@ class PreprocessingConfig:
     out_dir: Path = Path("output")
     out_fname: Path = Path("pp_output.h5")
     batch_size: int = 100_000
-    num_jets_estimate: int = 1_000_000
-    num_jets_estimate_available: int | None = None
-    num_jets_estimate_hist: int | None = None
-    num_jets_estimate_norm: int | None = None
-    num_jets_estimate_plotting: int | None = None
+    num_global_objects_estimate: int = 1_000_000
+    num_global_objects_estimate_available: int | None = None
+    num_global_objects_estimate_hist: int | None = None
+    num_global_objects_estimate_norm: int | None = None
+    num_global_objects_estimate_plotting: int | None = None
     merge_test_samples: bool = False
     global_name: str = "jets"
     flavour_config: Path | None = None
     flavour_category: str = "standard"
-    num_jets_per_output_file: int | None = None
+    num_global_objects_per_output_file: int | None = None
     skip_checks: bool = False
     skip_config_copy: bool = False
     vds_dir: Path | None = None
 
     def __post_init__(self):
         # postprocess paths
-        if self.num_jets_estimate:
-            if self.num_jets_estimate_available is None:
-                self.num_jets_estimate_available = max(self.num_jets_estimate, int(1e6))
-            if self.num_jets_estimate_hist is None:
-                self.num_jets_estimate_hist = self.num_jets_estimate
-            if self.num_jets_estimate_norm is None:
-                self.num_jets_estimate_norm = self.num_jets_estimate
-            if self.num_jets_estimate_plotting is None:
-                self.num_jets_estimate_plotting = self.num_jets_estimate
+        if self.num_global_objects_estimate:
+            if self.num_global_objects_estimate_available is None:
+                self.num_global_objects_estimate_available = max(
+                    self.num_global_objects_estimate, int(1e6)
+                )
+            if self.num_global_objects_estimate_hist is None:
+                self.num_global_objects_estimate_hist = self.num_global_objects_estimate
+            if self.num_global_objects_estimate_norm is None:
+                self.num_global_objects_estimate_norm = self.num_global_objects_estimate
+            if self.num_global_objects_estimate_plotting is None:
+                self.num_global_objects_estimate_plotting = self.num_global_objects_estimate
 
         for field in dataclasses.fields(self):
             if field.type == "Path" and field.name != "out_fname" and field.name != "base_dir":
@@ -213,7 +249,7 @@ def __post_init__(self):
             self.config["variables"], self.global_name, self.is_test, selectors
         )
         if self.sampl_cfg is not None and self.sampl_cfg.variables:
-            self.variables = self.variables.add_jet_vars(
+            self.variables = self.variables.add_global_vars(
                 list(self.config["resampling"]["variables"].keys()), "labels"
             )
         self.transform = (
@@ -228,8 +264,8 @@ def __post_init__(self):
             else None
         )
         self.plotting = PlottingConfig(**self.config.get("plotting", {}))
-        if self.plotting.num_jets_plotting is None:
-            self.plotting.num_jets_plotting = self.num_jets_estimate_plotting
+        if self.plotting.num_global_objects_plotting is None:
+            self.plotting.num_global_objects_plotting = self.num_global_objects_estimate_plotting
 
         # reproducibility
         try:
@@ -260,6 +296,14 @@ def from_file(
             raise FileNotFoundError(f"{config_path} does not exist - check your --config arg")
         with open(config_path) as file:
             config = yaml.safe_load(file)
+            legacy: set[str] = set()
+            config = _rename_legacy_keys(config, legacy)
+            if legacy:
+                log.warning(
+                    "Deprecated object-named config keys %s were remapped to their "
+                    "global-object names; please update your config.",
+                    sorted(legacy),
+                )
             return cls(
                 config_path=config_path,
                 split=split,
diff --git a/upp/classes/reweight_config.py b/upp/classes/reweight_config.py
index a488621..8049bd7 100644
--- a/upp/classes/reweight_config.py
+++ b/upp/classes/reweight_config.py
@@ -8,14 +8,14 @@
 
 @dataclass
 class ReweightConfig:
-    # Number of jets to estimate, if None, use the global num jets estimate
-    num_jets_estimate: None | int = None
+    # Number of objects to estimate, if None, use the global num objects estimate
+    num_global_objects_estimate: None | int = None
     merge_num_proc: int = 1  # Number of processes to use for merging
     reweights: list[SingleReweightConfig] = field(default_factory=list)
 
     def __post_init__(self):
-        if self.num_jets_estimate is not None and self.num_jets_estimate <= 0:
-            raise ValueError("num_jets_estimate must be a positive integer or None")
+        if self.num_global_objects_estimate is not None and self.num_global_objects_estimate <= 0:
+            raise ValueError("num_global_objects_estimate must be a positive integer or None")
 
         parsed_reweights = []
         for rw in self.reweights:
diff --git a/upp/classes/variable_config.py b/upp/classes/variable_config.py
index f76d37d..1dad96b 100644
--- a/upp/classes/variable_config.py
+++ b/upp/classes/variable_config.py
@@ -27,19 +27,19 @@ def combined(self):
         return combined
 
     @property
-    def jets(self):
+    def global_objects(self):
         return self[self.global_name]
 
     @property
     def tracks(self):
         return {name: var for name, var in self.variables.items() if name != self.global_name}
 
-    def add_jet_vars(self, variables: list[str], kind: str = "inputs") -> VariableConfig:
+    def add_global_vars(self, variables: list[str], kind: str = "inputs") -> VariableConfig:
         """Return a new VariableConfig instance."""
         vc = VariableConfig(
             deepcopy(self.variables), self.global_name, self.keep_all, self.selectors
         )
-        vc.jets[kind] = list(dict.fromkeys(vc.jets[kind] + variables))
+        vc.global_objects[kind] = list(dict.fromkeys(vc.global_objects[kind] + variables))
         return vc
 
     def items(self):
diff --git a/upp/configs/GN3EPCMV01/GN3EPCMV01.yaml b/upp/configs/GN3EPCMV01/GN3EPCMV01.yaml
index 4b52d22..d24e0ab 100644
--- a/upp/configs/GN3EPCMV01/GN3EPCMV01.yaml
+++ b/upp/configs/GN3EPCMV01/GN3EPCMV01.yaml
@@ -3,7 +3,7 @@ global_cuts: !include /home/users/r/reisch/production/slurm-scripts/umami-prepro
 
 ttbar: &ttbar
   name: ttbar
-  equal_jets: False
+  equal_global_objects: False
   pattern:
     - "user.treisch.601589.e8547_s3797_r13144_p7085.tdd.GN3_dev.25_2_76.26-01-07_CentralDump_p7085_output.h5/*.h5" # MC20d
     - "user.treisch.601589.e8549_s4159_r15530_p7085.tdd.GN3_dev.25_2_76.26-01-07_CentralDump_p7085_output.h5/*.h5" # MC23d
@@ -13,7 +13,7 @@ ttbar: &ttbar
 
 zprime: &zprime
   name: zprime
-  equal_jets: False
+  equal_global_objects: False
   pattern:
     - "user.treisch.802818.e8599_s3797_r13144_p7085.tdd.GN3_dev.25_2_76.26-01-07_CentralDump_p7085_output.h5/*.h5" # MC20d
     - "user.treisch.802818.e8599_s4159_r15530_p7085.tdd.GN3_dev.25_2_76.26-01-07_CentralDump_p7085_output.h5/*.h5" # MC23d
@@ -38,108 +38,108 @@ components:
     sample:
       <<: *ttbar
     flavours: [ghostbjets]
-    num_jets: 168_968_784
-    num_jets_test: 2_000_000
-    num_jets_val: 2_000_000
+    num_global_objects: 168_968_784
+    num_global_objects_test: 2_000_000
+    num_global_objects_val: 2_000_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
     flavours: [ghostcjets]
-    num_jets: 38_872_067
-    num_jets_test: 2_000_000
-    num_jets_val: 2_000_000
+    num_global_objects: 38_872_067
+    num_global_objects_test: 2_000_000
+    num_global_objects_val: 2_000_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
     flavours: [ghostsjets]
-    num_jets: 30_714_894
-    num_jets_test: 1_706_567
-    num_jets_val: 1_706_567
+    num_global_objects: 30_714_894
+    num_global_objects_test: 1_706_567
+    num_global_objects_val: 1_706_567
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
     flavours: [ghostudjets]
-    num_jets: 78_352_864
-    num_jets_test: 2_000_000
-    num_jets_val: 2_000_000
+    num_global_objects: 78_352_864
+    num_global_objects_test: 2_000_000
+    num_global_objects_val: 2_000_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
     flavours: [ghostgjets]
-    num_jets: 92_319_320
-    num_jets_test: 2_000_000
-    num_jets_val: 2_000_000
+    num_global_objects: 92_319_320
+    num_global_objects_test: 2_000_000
+    num_global_objects_val: 2_000_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
     flavours: [ghosttaujets]
-    num_jets: 16_261_627
-    num_jets_test: 896_611
-    num_jets_val: 896_611
+    num_global_objects: 16_261_627
+    num_global_objects_test: 896_611
+    num_global_objects_val: 896_611
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [ghostbjets]
-    num_jets: 40_230_662 #40_696_238
-    num_jets_test: 476_190
-    num_jets_val: 476_190
+    num_global_objects: 40_230_662 #40_696_238
+    num_global_objects_test: 476_190
+    num_global_objects_val: 476_190
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [ghostcjets]
-    num_jets: 9_255_254 #39_928_286
-    num_jets_test: 476_190
-    num_jets_val: 476_190
+    num_global_objects: 9_255_254 #39_928_286
+    num_global_objects_test: 476_190
+    num_global_objects_val: 476_190
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [ghostsjets]
-    num_jets: 7_313_070 #25_814_913
-    num_jets_test: 406_325
-    num_jets_val: 406_325
+    num_global_objects: 7_313_070 #25_814_913
+    num_global_objects_test: 406_325
+    num_global_objects_val: 406_325
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [ghostudjets]
-    num_jets: 18_655_443 #28_206_672
-    num_jets_test: 476_190
-    num_jets_val: 476_190
+    num_global_objects: 18_655_443 #28_206_672
+    num_global_objects_test: 476_190
+    num_global_objects_val: 476_190
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [ghostgjets]
-    num_jets: 21_980_790 #55_036_052
-    num_jets_test: 476_190
-    num_jets_val: 476_190
+    num_global_objects: 21_980_790 #55_036_052
+    num_global_objects_test: 476_190
+    num_global_objects_val: 476_190
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [ghosttaujets]
-    num_jets: 3_871_815 #25_623_679
-    num_jets_test: 213_478
-    num_jets_val: 213_478
+    num_global_objects: 3_871_815 #25_623_679
+    num_global_objects_test: 213_478
+    num_global_objects_val: 213_478
 
 resampling:
   target: ghostcjets
@@ -155,9 +155,9 @@ resampling:
 global:
   global_name: jets
   batch_size: 1_000_000
-  num_jets_estimate: 50_000_000
-  num_jets_estimate_plotting: 10_000_000
-  num_jets_per_output_file: 5_000_000
+  num_global_objects_estimate: 50_000_000
+  num_global_objects_estimate_plotting: 10_000_000
+  num_global_objects_per_output_file: 5_000_000
   base_dir: /srv/beegfs/scratch/groups/rodem/DAOD_FTAG/
   out_dir: p7085/upp/
   ntuple_dir: p7085/
diff --git a/upp/configs/GN3V00/dr.yaml b/upp/configs/GN3V00/dr.yaml
index 36fc70f..1dbfb51 100644
--- a/upp/configs/GN3V00/dr.yaml
+++ b/upp/configs/GN3V00/dr.yaml
@@ -3,14 +3,14 @@ global_cuts: !include splits/simple-split.yaml
 
 ttbar: &ttbar
   name: ttbar
-  equal_jets: False
+  equal_global_objects: False
   pattern:
     - "user.svanstro.601589.e8547_s3797_r13144_p6368.tdd.GN3_dev.25_2_27.24-09-17_v00_output.h5/*.h5" # mc20d
     - "user.svanstro.601589.e8549_s4159_r14799_p6368.tdd.GN3_dev.25_2_27.24-09-17_v00_output.h5/*.h5" # mc23a
 
 zprime: &zprime
   name: zprime
-  equal_jets: False
+  equal_global_objects: False
   pattern:
     - "user.svanstro.800030.e7954_s3681_r13144_p6368.tdd.GN3_dev.25_2_27.24-09-17_v00_output.h5/*.h5" # mc20d
     - "user.svanstro.800030.e7954_s3797_r13144_p6368.tdd.GN3_dev.25_2_27.24-09-17_v00_output.h5/*.h5" # mc20d
@@ -33,32 +33,32 @@ components:
     sample:
       <<: *ttbar
     flavours: [bjets, cjets, ujets]
-    num_jets: 6_000_000
-    num_jets_test: 2_000_000
+    num_global_objects: 6_000_000
+    num_global_objects_test: 2_000_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
     flavours: [taujets]
-    num_jets: 2_000_000
-    num_jets_test: 500_000
+    num_global_objects: 2_000_000
+    num_global_objects_test: 500_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [bjets, cjets, ujets]
-    num_jets: 3_000_000
-    num_jets_test: 500_000
+    num_global_objects: 3_000_000
+    num_global_objects_test: 500_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [taujets]
-    num_jets: 1_000_000
-    num_jets_test: 200_000
+    num_global_objects: 1_000_000
+    num_global_objects_test: 200_000
 
 resampling:
   target: cjets
@@ -74,6 +74,6 @@ resampling:
 global:
   global_name: jets
   batch_size: 1_000_000
-  num_jets_estimate: 2_000_000
+  num_global_objects_estimate: 2_000_000
   base_dir: /unix/atlastracking/samples/gn3v00/dr/
   ntuple_dir: /unix/atlastracking/samples/gn3v00/ntuples/
diff --git a/upp/configs/GN3V00/ghost-highstat.yaml b/upp/configs/GN3V00/ghost-highstat.yaml
index 5148203..3b96c72 100644
--- a/upp/configs/GN3V00/ghost-highstat.yaml
+++ b/upp/configs/GN3V00/ghost-highstat.yaml
@@ -3,7 +3,7 @@ global_cuts: !include splits/simple-split.yaml
 
 ttbar: &ttbar
   name: ttbar
-  equal_jets: False
+  equal_global_objects: False
   pattern:
     - "user.wlai.601589.e8547_s3797_r13144_p6368.tdd.GN3_dev.25_2_27.24-11-10_GN3v00_output.h5/*.h5" # mc20d
     - "user.wlai.601589.e8549_s4159_r14799_p6368.tdd.GN3_dev.25_2_27.24-11-10_GN3v00_output.h5/*.h5" # mc23a
@@ -11,7 +11,7 @@ ttbar: &ttbar
 
 zprime: &zprime
   name: zprime
-  equal_jets: False
+  equal_global_objects: False
   pattern:
     - "user.wlai.800030.e7954_s3681_r13144_p6368.tdd.GN3_dev.25_2_27.24-11-10_GN3v00_output.h5/*.h5" # mc20d
     - "user.wlai.800030.e7954_s3797_r13144_p6368.tdd.GN3_dev.25_2_27.24-11-10_GN3v00_output.h5/*.h5" # mc20d
@@ -34,96 +34,96 @@ components:
     sample:
       <<: *ttbar
     flavours: [ghostsplitbjets]
-    num_jets: 79_000_000
-    num_jets_test: 2_000_000
+    num_global_objects: 79_000_000
+    num_global_objects_test: 2_000_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
     flavours: [ghostsplitcjets]
-    num_jets: 26_500_000
-    num_jets_test: 2_000_000
+    num_global_objects: 26_500_000
+    num_global_objects_test: 2_000_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
     flavours: [ghostsplitsjets]
-    num_jets: 21_000_000
-    num_jets_test: 1_000_000
+    num_global_objects: 21_000_000
+    num_global_objects_test: 1_000_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
     flavours: [ghostsplitudjets]
-    num_jets: 54_000_000
-    num_jets_test: 1_000_000
+    num_global_objects: 54_000_000
+    num_global_objects_test: 1_000_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
     flavours: [ghostsplitgjets]
-    num_jets: 46_000_000
-    num_jets_test: 1_000_000
+    num_global_objects: 46_000_000
+    num_global_objects_test: 1_000_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
     flavours: [ghostsplittaujets]
-    num_jets: 9_000_000
-    num_jets_test: 500_000
+    num_global_objects: 9_000_000
+    num_global_objects_test: 500_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [ghostsplitbjets]
-    num_jets: 39_500_000
-    num_jets_test: 2_000_000
+    num_global_objects: 39_500_000
+    num_global_objects_test: 2_000_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [ghostsplitcjets]
-    num_jets: 13_250_000
-    num_jets_test: 2_000_000
+    num_global_objects: 13_250_000
+    num_global_objects_test: 2_000_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [ghostsplitsjets]
-    num_jets: 10_500_000
-    num_jets_test: 1_000_000
+    num_global_objects: 10_500_000
+    num_global_objects_test: 1_000_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [ghostsplitudjets]
-    num_jets: 27_000_000
-    num_jets_test: 1_000_000
+    num_global_objects: 27_000_000
+    num_global_objects_test: 1_000_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [ghostsplitgjets]
-    num_jets: 23_000_000
-    num_jets_test: 1_000_000
+    num_global_objects: 23_000_000
+    num_global_objects_test: 1_000_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [ghostsplittaujets]
-    num_jets: 4_500_000
-    num_jets_test: 200_000
+    num_global_objects: 4_500_000
+    num_global_objects_test: 200_000
 
 resampling:
   target: ghostsplitcjets
@@ -139,6 +139,6 @@ resampling:
 global:
   global_name: jets
   batch_size: 1_000_000
-  num_jets_estimate: 25_000_000
+  num_global_objects_estimate: 25_000_000
   base_dir: /unix/atlas2/weilai/datasets/atlas/upp_outs/ghost_high_stat_full
   ntuple_dir: /unix/atlas2/weilai/datasets/atlas/ntuples/gn3v00
diff --git a/upp/configs/GN3V00/ghost.yaml b/upp/configs/GN3V00/ghost.yaml
index 9c2ece6..203c8ad 100644
--- a/upp/configs/GN3V00/ghost.yaml
+++ b/upp/configs/GN3V00/ghost.yaml
@@ -3,7 +3,7 @@ global_cuts: !include splits/simple-split.yaml
 
 ttbar: &ttbar
   name: ttbar
-  equal_jets: False
+  equal_global_objects: False
   pattern:
     - "user.wlai.601589.e8547_s3797_r13144_p6368.tdd.GN3_dev.25_2_27.24-11-10_GN3v00_output.h5/*.h5" # mc20d
     - "user.wlai.601589.e8549_s4159_r14799_p6368.tdd.GN3_dev.25_2_27.24-11-10_GN3v00_output.h5/*.h5" # mc23a
@@ -11,7 +11,7 @@ ttbar: &ttbar
 
 zprime: &zprime
   name: zprime
-  equal_jets: False
+  equal_global_objects: False
   pattern:
     - "user.wlai.800030.e7954_s3681_r13144_p6368.tdd.GN3_dev.25_2_27.24-11-10_GN3v00_output.h5/*.h5" # mc20d
     - "user.wlai.800030.e7954_s3797_r13144_p6368.tdd.GN3_dev.25_2_27.24-11-10_GN3v00_output.h5/*.h5" # mc20d
@@ -34,32 +34,32 @@ components:
     sample:
       <<: *ttbar
     flavours: [ghostbjets, ghostcjets, ghostujets]
-    num_jets: 6_000_000
-    num_jets_test: 2_000_000
+    num_global_objects: 6_000_000
+    num_global_objects_test: 2_000_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
     flavours: [ghosttaujets]
-    num_jets: 2_000_000
-    num_jets_test: 500_000
+    num_global_objects: 2_000_000
+    num_global_objects_test: 500_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [ghostbjets, ghostcjets, ghostujets]
-    num_jets: 3_000_000
-    num_jets_test: 2_000_000
+    num_global_objects: 3_000_000
+    num_global_objects_test: 2_000_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [ghosttaujets]
-    num_jets: 1_000_000
-    num_jets_test: 200_000
+    num_global_objects: 1_000_000
+    num_global_objects_test: 200_000
 
 resampling:
   target: ghostcjets
@@ -75,6 +75,6 @@ resampling:
 global:
   global_name: jets
   batch_size: 1_000_000
-  num_jets_estimate: 2_000_000
+  num_global_objects_estimate: 2_000_000
   base_dir: /unix/atlas2/weilai/datasets/atlas/upp_outs/ghost_correct
   ntuple_dir: /unix/atlas2/weilai/datasets/atlas/ntuples/gn3v00
diff --git a/upp/configs/GN3V01/GN3V01-RW.yaml b/upp/configs/GN3V01/GN3V01-RW.yaml
index a4bbf6b..ff74ac5 100644
--- a/upp/configs/GN3V01/GN3V01-RW.yaml
+++ b/upp/configs/GN3V01/GN3V01-RW.yaml
@@ -3,7 +3,7 @@ global_cuts: !include GN3V01/simple-split.yaml
 
 ttbar: &ttbar
   name: ttbar
-  equal_jets: False
+  equal_global_objects: False
   pattern:
     - "user.alfroch.601589.e8547_s3797_r13144_p6859.tdd.GN3_dev.25_2_56.250729_Central_Dump_output.h5"
     - "user.alfroch.601589.e8549_s4162_r14622_p6859.tdd.GN3_dev.25_2_56.250729_Central_Dump_output.h5"
@@ -12,7 +12,7 @@ ttbar: &ttbar
 
 zprime: &zprime
   name: zprime
-  equal_jets: False
+  equal_global_objects: False
   pattern:
     - "user.alfroch.800030.e7954_s3797_r13144_p6859.tdd.GN3_dev.25_2_56.250729_Central_Dump_output.h5"
     - "user.alfroch.800030.e8514_s4162_r14622_p6859.tdd.GN3_dev.25_2_56.250729_Central_Dump_output.h5"
@@ -46,7 +46,7 @@ components:
         ghostgjets,
         ghosttaujets,
       ]
-    num_jets: -1
+    num_global_objects: -1
 
   - region:
       <<: *highpt
@@ -61,19 +61,19 @@ components:
         ghostgjets,
         ghosttaujets,
       ]
-    num_jets: -1
+    num_global_objects: -1
 
 # note: sensible defaults are defined in the PreprocessingConfig constructor
 global:
   global_name: jets
   batch_size: 1_000_000
-  num_jets_estimate: 25_000_000
-  num_jets_per_output_file: 25_000_000
+  num_global_objects_estimate: 25_000_000
+  num_global_objects_per_output_file: 25_000_000
   base_dir: /home/xzcappon/phd/datasets/flavour_tagging/gn3/high-stats/
   ntuple_dir: /home/xzcappon/phd/datasets/flavour_tagging/gn3/high-stats/ntuples
 
 reweighting:
-  num_jets_estimate: 5_000_000
+  num_global_objects_estimate: 5_000_000
   merge_num_proc: 20
   reweights:
     - group: jets
diff --git a/upp/configs/GN3V01/GN3V01.yaml b/upp/configs/GN3V01/GN3V01.yaml
index 8289060..c1a44e3 100644
--- a/upp/configs/GN3V01/GN3V01.yaml
+++ b/upp/configs/GN3V01/GN3V01.yaml
@@ -3,7 +3,7 @@ global_cuts: !include GN3V01/simple-split.yaml
 
 ttbar: &ttbar
   name: ttbar
-  equal_jets: False
+  equal_global_objects: False
   pattern:
     - "user.alfroch.601589.e8547_s3797_r13144_p6698.tdd.GN3_dev.25_2_48.GN3V01-Training_output.h5/*.h5" # MC20d
     - "user.alfroch.601589.e8549_s4162_r14622_p6698.tdd.GN3_dev.25_2_48.GN3V01-Training_output.h5/*.h5" # MC23a
@@ -11,7 +11,7 @@ ttbar: &ttbar
 
 zprime: &zprime
   name: zprime
-  equal_jets: False
+  equal_global_objects: False
   pattern:
     - "user.alfroch.800030.e7954_s3797_r13144_p6698.tdd.GN3_dev.25_2_48.GN3V01-Training_output.h5/*.h5" # MC20d
     - "user.alfroch.800030.e8514_s4162_r14622_p6698.tdd.GN3_dev.25_2_48.GN3V01-Training_output.h5/*.h5" # MC23a
@@ -34,96 +34,96 @@ components:
     sample:
       <<: *ttbar
     flavours: [ghostbjets]
-    num_jets: 100_000_000
-    num_jets_test: 2_000_000
+    num_global_objects: 100_000_000
+    num_global_objects_test: 2_000_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
     flavours: [ghostcjets]
-    num_jets: 27_500_000
-    num_jets_test: 2_000_000
+    num_global_objects: 27_500_000
+    num_global_objects_test: 2_000_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
     flavours: [ghostsjets]
-    num_jets: 20_000_000
-    num_jets_test: 1_000_000
+    num_global_objects: 20_000_000
+    num_global_objects_test: 1_000_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
     flavours: [ghostudjets]
-    num_jets: 55_000_000
-    num_jets_test: 1_000_000
+    num_global_objects: 55_000_000
+    num_global_objects_test: 1_000_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
     flavours: [ghostgjets]
-    num_jets: 65_000_000
-    num_jets_test: 1_000_000
+    num_global_objects: 65_000_000
+    num_global_objects_test: 1_000_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
     flavours: [ghosttaujets]
-    num_jets: 11_000_000
-    num_jets_test: 500_000
+    num_global_objects: 11_000_000
+    num_global_objects_test: 500_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [ghostbjets]
-    num_jets: 50_000_000
-    num_jets_test: 2_000_000
+    num_global_objects: 50_000_000
+    num_global_objects_test: 2_000_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [ghostcjets]
-    num_jets: 13_750_000
-    num_jets_test: 2_000_000
+    num_global_objects: 13_750_000
+    num_global_objects_test: 2_000_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [ghostsjets]
-    num_jets: 10_000_000
-    num_jets_test: 1_000_000
+    num_global_objects: 10_000_000
+    num_global_objects_test: 1_000_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [ghostudjets]
-    num_jets: 27_500_000
-    num_jets_test: 1_000_000
+    num_global_objects: 27_500_000
+    num_global_objects_test: 1_000_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [ghostgjets]
-    num_jets: 32_500_000
-    num_jets_test: 1_000_000
+    num_global_objects: 32_500_000
+    num_global_objects_test: 1_000_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [ghosttaujets]
-    num_jets: 5_500_000
-    num_jets_test: 200_000
+    num_global_objects: 5_500_000
+    num_global_objects_test: 200_000
 
 resampling:
   target: ghostcjets
@@ -139,6 +139,6 @@ resampling:
 global:
   global_name: jets
   batch_size: 1_000_000
-  num_jets_estimate: 25_000_000
+  num_global_objects_estimate: 25_000_000
   base_dir: GN3V01_Training_preprocessed/
   ntuple_dir: GN3V01_Training_h5/
diff --git a/upp/configs/extended_labels.yaml b/upp/configs/extended_labels.yaml
index 8de3c94..a84b9b2 100644
--- a/upp/configs/extended_labels.yaml
+++ b/upp/configs/extended_labels.yaml
@@ -6,7 +6,7 @@ global_cuts: !include splits/simple-split.yaml
 
 ttbar: &ttbar
   name: ttbar
-  equal_jets: False
+  equal_global_objects: False
   pattern:
     - "user.svanstro.410470.e6337_s3681_r13144_p5922.tdd.EMPFlow_kfold.24_2_27.23-11-10_kfoldtrain_output.h5/*.h5"
 
@@ -22,35 +22,35 @@ components:
     sample:
       <<: *ttbar
     flavours: [bjets]
-    num_jets: 25_000_000
+    num_global_objects: 25_000_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
     flavours: [D0meson]
-    num_jets: 12_500_000
+    num_global_objects: 12_500_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
     flavours: [nonD0meson]
-    num_jets: 12_500_000
+    num_global_objects: 12_500_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
     flavours: [ujets]
-    num_jets: 50_000_000
+    num_global_objects: 50_000_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
     flavours: [taujets]
-    num_jets: 4_000_000
+    num_global_objects: 4_000_000
 
 resampling:
   target: bjets
@@ -66,6 +66,6 @@ resampling:
 global:
   global_name: nominal_Loose
   batch_size: 1_000_000
-  num_jets_estimate: 5_000_000
+  num_global_objects_estimate: 5_000_000
   base_dir: /nfs/dust/atlas/user/nkumari/UPP_latest/umami-preprocessing/upp/configs/prep
   ntuple_dir: /nfs/dust/atlas/user/nkumari/FTAG_tdd
diff --git a/upp/configs/open-dataset.yaml b/upp/configs/open-dataset.yaml
index 41f1a87..8a385cc 100644
--- a/upp/configs/open-dataset.yaml
+++ b/upp/configs/open-dataset.yaml
@@ -47,7 +47,7 @@ global_cuts:
 
 ttbar: &ttbar
   name: ttbar
-  equal_jets: False
+  equal_global_objects: False
   pattern:
     - "user.wlai.601589.e8549_s4159_r15530_p6698.tdd.OpenDataset.25_2_46.25-04-08_open-rc3_output.h5/*.h5"
     - "user.wlai.601589.e8549_s4162_r14622_p6698.tdd.OpenDataset.25_2_46.25-04-08_open-rc3_output.h5/*.h5"
@@ -64,21 +64,21 @@ components:
     sample:
       <<: *ttbar
     flavours: [bjets, cjets]
-    num_jets: 13_000_000
+    num_global_objects: 13_000_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
     flavours: [ujets]
-    num_jets: 26_000_000
+    num_global_objects: 26_000_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
     flavours: [taujets]
-    num_jets: 1_500_000
+    num_global_objects: 1_500_000
 
 resampling:
   target: cjets
@@ -94,6 +94,6 @@ resampling:
 global:
   global_name: jets
   batch_size: 1_000_000
-  num_jets_estimate: 25_000_000
+  num_global_objects_estimate: 25_000_000
   base_dir: /unix/atlas2/weilai/datasets/atlas/upp_outs/opendata_rc3
   ntuple_dir: /unix/atlas2/weilai/datasets/atlas/ntuples/opendata/rc3
diff --git a/upp/configs/plit_electron.yaml b/upp/configs/plit_electron.yaml
index 4fe1c27..47eb1e2 100644
--- a/upp/configs/plit_electron.yaml
+++ b/upp/configs/plit_electron.yaml
@@ -3,7 +3,7 @@ variables: !include plit_electron_variables.yaml
 
 ttbar: &ttbar
   name: ttbar
-  equal_jets: False
+  equal_global_objects: False
   pattern:
     - "user.pgadow.LD_2023_11_28.601589.PhPy8EG_A14_ttbar_hdamp258p75_nonallhadron.e8547_s3797_r13144_p5934_TREE/*.h5"
     - "user.pgadow.LD_2023_11_28.601589.PhPy8EG_A14_ttbar_hdamp258p75_nonallhadron.e8549_s4159_r14799_p5934_TREE/*.h5"
@@ -28,14 +28,14 @@ components:
     sample:
       <<: *ttbar
     flavours: [elxprompt]
-    num_jets: 25_000_000
+    num_global_objects: 25_000_000
 
   - region:
       <<: *electron
     sample:
       <<: *ttbar
     flavours: [npxall]
-    num_jets: 13_000_000
+    num_global_objects: 13_000_000
 
 
 resampling:
@@ -52,7 +52,7 @@ resampling:
 global:
   global_name: electrons
   batch_size: 1_000_000
-  num_jets_estimate: 5_000
+  num_global_objects_estimate: 5_000
   base_dir: /nfs/dust/atlas/user/pgadow/plit/data/preprocessed/electrons_38M
   ntuple_dir: /nfs/dust/atlas/user/pgadow/plit/data/ntuples
   out_dir: /nfs/dust/atlas/user/pgadow/plit/data/preprocessed/electrons_38M
diff --git a/upp/configs/plit_muon.yaml b/upp/configs/plit_muon.yaml
index 807307f..a4092c3 100644
--- a/upp/configs/plit_muon.yaml
+++ b/upp/configs/plit_muon.yaml
@@ -3,7 +3,7 @@ variables: !include plit_muon_variables.yaml
 
 ttbar: &ttbar
   name: ttbar
-  equal_jets: False
+  equal_global_objects: False
   pattern:
     - "user.pgadow.LD_2023_11_28.601589.PhPy8EG_A14_ttbar_hdamp258p75_nonallhadron.e8547_s3797_r13144_p5934_TREE/*.h5"
     - "user.pgadow.LD_2023_11_28.601589.PhPy8EG_A14_ttbar_hdamp258p75_nonallhadron.e8549_s4159_r14799_p5934_TREE/*.h5"
@@ -28,14 +28,14 @@ components:
     sample:
       <<: *ttbar
     flavours: [muxprompt]
-    num_jets: 30_000_000
+    num_global_objects: 30_000_000
 
   - region:
       <<: *muon
     sample:
       <<: *ttbar
     flavours: [npxall]
-    num_jets: 10_000_000
+    num_global_objects: 10_000_000
 
 
 resampling:
@@ -52,7 +52,7 @@ resampling:
 global:
   global_name: muons
   batch_size: 1_000_000
-  num_jets_estimate: 5_000_000
+  num_global_objects_estimate: 5_000_000
   base_dir: /nfs/dust/atlas/user/pgadow/plit/data/preprocessed/muons_40M
   ntuple_dir: /nfs/dust/atlas/user/pgadow/plit/data/ntuples
   out_dir: /nfs/dust/atlas/user/pgadow/plit/data/preprocessed/muons_40M
diff --git a/upp/configs/single-b-upgrade.yaml b/upp/configs/single-b-upgrade.yaml
index 3780500..f3f0278 100644
--- a/upp/configs/single-b-upgrade.yaml
+++ b/upp/configs/single-b-upgrade.yaml
@@ -6,7 +6,7 @@ global_cuts: !include splits/simple-split.yaml
 
 ttbar: &ttbar
   name: ttbar
-  equal_jets: False
+  equal_global_objects: False
   pattern:
     - "/atlas_cloud/triglion/data/TDD_ttbar_DiLep/user.tstreble.601230.e8481_s4446_r16176_p6677.tdd.upgrade.25_0_29.25-05-06_Run4_May6_output.h5/user.tstreble.44562989._*.output.h5"
     - "/atlas_cloud/triglion/data/TDD_ttbar_SingleLep/user.tstreble.601229.e8481_s4446_r16176_p6677.tdd.upgrade.25_0_29.25-05-06_Run4_May6_output.h5/user.tstreble.44562988._*.output.h5"
@@ -14,7 +14,7 @@ ttbar: &ttbar
 
 zprime: &zprime
   name: zprime
-  equal_jets: False
+  equal_global_objects: False
   pattern:
     - "/atlas_cloud/triglion/data/TDD_Zprime/user.tstreble.800030.e8481_s4446_r16176_p6677.tdd.upgrade.25_0_29.25-05-06_Run4_May6_output.h5/user.tstreble.44562987._*.output.h5"
 
@@ -37,42 +37,42 @@ components:
     sample:
       <<: *ttbar
     flavours: [bjets, cjets]
-    num_jets: 14_500_000
+    num_global_objects: 14_500_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
     flavours: [ujets]
-    num_jets: 29_000_000
+    num_global_objects: 29_000_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
     flavours: [taujets]
-    num_jets: 2_013_889
+    num_global_objects: 2_013_889
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [bjets, cjets]
-    num_jets: 5_800_000
+    num_global_objects: 5_800_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [ujets]
-    num_jets: 11_600_000
+    num_global_objects: 11_600_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [taujets]
-    num_jets: 805_555
+    num_global_objects: 805_555
 
 
 
@@ -90,6 +90,6 @@ resampling:
 global:
   global_name: jets
   batch_size: 1_000_000
-  num_jets_estimate: 25_000_000
+  num_global_objects_estimate: 25_000_000
   base_dir: /atlas_cloud/triglion/preprocessing
   ntuple_dir: /atlas_cloud/triglion/preprocessing
diff --git a/upp/configs/single-b.yaml b/upp/configs/single-b.yaml
index 0800425..fa32887 100644
--- a/upp/configs/single-b.yaml
+++ b/upp/configs/single-b.yaml
@@ -6,7 +6,7 @@ global_cuts: !include splits/simple-split.yaml
 
 ttbar: &ttbar
   name: ttbar
-  equal_jets: False
+  equal_global_objects: False
   pattern:
     - "user.svanstro.410470.e6337_s3681_r13144_p5922.tdd.EMPFlow_kfold.24_2_27.23-11-10_kfoldtrain_output.h5/*.h5"
     - "user.svanstro.601229.e8514_s4162_r14622_p5922.tdd.EMPFlow_kfold.24_2_27.23-11-10_kfoldtrain_output.h5/*.h5"
@@ -14,7 +14,7 @@ ttbar: &ttbar
 
 zprime: &zprime
   name: zprime
-  equal_jets: False
+  equal_global_objects: False
   pattern:
     - "user.svanstro.800030.e7954_s3681_r13144_p5922.tdd.EMPFlow_kfold.24_2_27.23-11-10_kfoldtrain_output.h5/*.h5"
     - "user.svanstro.800030.e7954_s3797_r13144_p5922.tdd.EMPFlow_kfold.24_2_27.23-11-19_kfoldtrain_output.h5/*.h5"
@@ -38,42 +38,42 @@ components:
     sample:
       <<: *ttbar
     flavours: [bjets, cjets]
-    num_jets: 45_000_000
+    num_global_objects: 45_000_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
     flavours: [ujets]
-    num_jets: 90_000_000
+    num_global_objects: 90_000_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
     flavours: [taujets]
-    num_jets: 6_250_000
+    num_global_objects: 6_250_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [bjets, cjets]
-    num_jets: 18_000_000
+    num_global_objects: 18_000_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [ujets]
-    num_jets: 36_000_000
+    num_global_objects: 36_000_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [taujets]
-    num_jets: 2_500_000
+    num_global_objects: 2_500_000
 
 
 resampling:
@@ -90,6 +90,6 @@ resampling:
 global:
   global_name: jets
   batch_size: 1_000_000
-  num_jets_estimate: 25_000_000
+  num_global_objects_estimate: 25_000_000
   base_dir: /home/xzcappon/phd/datasets/combined_run2_run3/p5922/high_stats/fold0
   ntuple_dir: /home/xucapsva/data/ftag/h5/gn2_v01/ntuples
diff --git a/upp/configs/test.yaml b/upp/configs/test.yaml
index bf72dfc..f439947 100644
--- a/upp/configs/test.yaml
+++ b/upp/configs/test.yaml
@@ -30,14 +30,14 @@ components:
     sample:
       <<: *ttbar
     flavours: [bjets, cjets, ujets]
-    num_jets: 10_000
+    num_global_objects: 10_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
     flavours: [bjets, cjets, ujets]
-    num_jets: 10_000
+    num_global_objects: 10_000
 
 resampling:
   target: cjets
@@ -51,7 +51,7 @@ resampling:
 
 global:
   batch_size: 10_000
-  num_jets_estimate: 10_000
+  num_global_objects_estimate: 10_000
   base_dir: /unix/atlastracking/samples/gnn_training/martino/v1/
   out_dir: test_out
   ntuple_dir: source_data
diff --git a/upp/configs/xbb-gn3x.yaml b/upp/configs/xbb-gn3x.yaml
index 50fd9ff..956db93 100644
--- a/upp/configs/xbb-gn3x.yaml
+++ b/upp/configs/xbb-gn3x.yaml
@@ -3,35 +3,35 @@ global_cuts: !include splits/simple-split.yaml
 
 htautauhad: &htautauhad
   name: htautauhad
-  equal_jets: False
+  equal_global_objects: False
   pattern:
     - user.edcritel.802168.e8558_s3797_r13144_p6453.tdd.*/*.h5
     - user.edcritel.802168.e8558_s4159_r15530_p6453.tdd.*/*.h5
 
 hbb: &hbb
   name: hbb
-  equal_jets: False
+  equal_global_objects: False
   pattern:
     - group.perf-flavtag.801471.e8441_s3681_r13144_p6453.tdd.*/*.h5
     - group.perf-flavtag.801972.e8514_s4159_r15224_p6453.tdd.*/*.h5
 
 hcc: &hcc
   name: hcc
-  equal_jets: False
+  equal_global_objects: False
   pattern:
     - group.perf-flavtag.801472.e8441_s3681_r13144_p6453.tdd.*/*.h5
     - group.perf-flavtag.801973.e8514_s4159_r15224_p6453.tdd.*/*.h5
 
 top: &Zprime
   name: Zprime
-  equal_jets: False
+  equal_global_objects: False
   pattern:
     - group.perf-flavtag.426345.e6880_s3681_r13144_p6453.tdd.*/*.h5
     - group.perf-flavtag.802423.e8514_s4159_r15530_p6453.tdd.*/*.h5
 
 qcd: &qcd
   name: qcd
-  equal_jets: False
+  equal_global_objects: False
   pattern:
     - group.perf-flavtag.364703.e7142_s3681_r13144_p6453.tdd.*/*.h5
     - group.perf-flavtag.364704.e7142_s3681_r13144_p6453.tdd.*/*.h5
@@ -46,7 +46,7 @@ qcd: &qcd
 
 Wqq: &Wqq
   name: Wqq
-  equal_jets: False
+  equal_global_objects: False
   pattern:
     - group.perf-flavtag.802017.e8482_s3797_r13144_p6453.tdd.*/*.h5
     - group.perf-flavtag.802017.e8557_s4159_r15224_p6453.tdd.*/*.h5
@@ -62,42 +62,42 @@ components:
     sample:
       <<: *htautauhad
     flavours: [htautauhad]
-    num_jets: 10_000_000
+    num_global_objects: 10_000_000
 
   - region:
       <<: *inclusive
     sample:
       <<: *hbb
     flavours: [hbb]
-    num_jets: 40_000_000
+    num_global_objects: 40_000_000
 
   - region:
       <<: *inclusive
     sample:
       <<: *hcc
     flavours: [hcc]
-    num_jets: 40_000_000
+    num_global_objects: 40_000_000
 
   - region:
       <<: *inclusive
     sample:
       <<: *Zprime
     flavours: [top]
-    num_jets: 35_000_000
+    num_global_objects: 35_000_000
 
   - region:
       <<: *inclusive
     sample:
       <<: *qcd
     flavours: [qcd]
-    num_jets: 80_000_000
+    num_global_objects: 80_000_000
 
   - region:
       <<: *inclusive
     sample:
       <<: *Wqq
     flavours: [Wqq]
-    num_jets: 5_000_000
+    num_global_objects: 5_000_000
 
 
 resampling:
@@ -117,7 +117,7 @@ resampling:
 # note: sensible defaults are defined in the PreprocessingConfig constructor
 global:
   batch_size: 4_000_000
-  num_jets_estimate: 10_000_000
+  num_global_objects_estimate: 10_000_000
   base_dir: /share/lustre/ecritelli/xbb_upp_Zprimeonly_withRegr/base_dir
   ntuple_dir: /share/lustre/ecritelli/ntuples/gn3xv00
   out_dir: /share/lustre/ecritelli/xbb_upp_Zprimeonly_withRegr/output
diff --git a/upp/configs/xbb-rw.yaml b/upp/configs/xbb-rw.yaml
index c6d6e62..9c06172 100644
--- a/upp/configs/xbb-rw.yaml
+++ b/upp/configs/xbb-rw.yaml
@@ -4,7 +4,7 @@ global_cuts: !include splits/simple-split.yaml
 
 hbb: &hbb
   name: hbb
-  equal_jets: False
+  equal_global_objects: False
   pattern:
     # mc20
     - "user.jabarr.801471.e8441_s3681_r13144_p6453.tdd.FatJets.25_2_76.26-01-05_cb_output.h5"
@@ -13,7 +13,7 @@ hbb: &hbb
 
 hcc: &hcc
   name: hcc
-  equal_jets: False
+  equal_global_objects: False
   pattern:
     # mc20
     - "user.jabarr.801472.e8441_s3681_r13144_p6453.tdd.FatJets.25_2_76.26-01-05_cb_output.h5"
@@ -22,7 +22,7 @@ hcc: &hcc
 
 htautauhad: &htautauhad
   name: htautauhad
-  equal_jets: False
+  equal_global_objects: False
   pattern:
     # mc20
     - "user.jabarr.802168.e8558_s3797_r13144_p6453.tdd.FatJets.25_2_76.26-01-05_cb_output.h5"
@@ -31,7 +31,7 @@ htautauhad: &htautauhad
 
 zprime: &zprime
   name: zprime
-  equal_jets: False
+  equal_global_objects: False
   pattern:
     # mc20
     - "user.jabarr.426345.e6880_s3681_r13144_p6453.tdd.FatJets.25_2_76.26-01-05_cb_output.h5"
@@ -40,7 +40,7 @@ zprime: &zprime
 
 qcd: &qcd
   name: qcd
-  equal_jets: False
+  equal_global_objects: False
   pattern:
     # mc20 dijet
     - "user.jabarr.364703.e7142_s3681_r13144_p6453.tdd.FatJets.25_2_76.26-01-05_cb_output.h5"
@@ -57,7 +57,7 @@ qcd: &qcd
 
 wqq: &wqq
   name: wqq
-  equal_jets: False
+  equal_global_objects: False
   pattern:
     # mc20
     - "user.jabarr.802017.e8482_s3797_r13144_p6453.tdd.FatJets.25_2_76.26-01-05_cb_output.h5"
@@ -74,55 +74,55 @@ components:
     sample:
       <<: *hbb
     flavours: [hbb]
-    num_jets: -1
+    num_global_objects: -1
 
   - region:
       <<: *inclusive
     sample:
       <<: *hcc
     flavours: [hcc]
-    num_jets: -1
+    num_global_objects: -1
 
   - region:
       <<: *inclusive
     sample:
       <<: *htautauhad
     flavours: [htautauhad]
-    num_jets: -1
+    num_global_objects: -1
 
   - region:
       <<: *inclusive
     sample:
       <<: *zprime
     flavours: [top]
-    num_jets: -1
+    num_global_objects: -1
 
   - region:
       <<: *inclusive
     sample:
       <<: *qcd
     flavours: [qcd]
-    num_jets: -1
+    num_global_objects: -1
 
   - region:
       <<: *inclusive
     sample:
       <<: *wqq
     flavours: [Wqq]
-    num_jets: -1
+    num_global_objects: -1
 
 
 global:
   global_name: jets
   batch_size: 1_000_000
-  num_jets_estimate: 10_000_000
-  num_jets_per_output_file: 25_000_000
+  num_global_objects_estimate: 10_000_000
+  num_global_objects_per_output_file: 25_000_000
   base_dir: /share/lustre/jbarr/training-files/2026-01-01-cb/
   merge_test_samples: False
 
 
 reweighting:
-  num_jets_estimate: 5_000_000
+  num_global_objects_estimate: 5_000_000
   merge_num_proc: 10
   reweights:
     # 4D reweighting over pt, eta, mass, and mcCampaignYear
diff --git a/upp/configs/xbb.yaml b/upp/configs/xbb.yaml
index 866e41d..0f558f4 100644
--- a/upp/configs/xbb.yaml
+++ b/upp/configs/xbb.yaml
@@ -9,13 +9,13 @@ hcc: &hcc
   pattern: user.svanstro.801472.e8441_e7400_s3681_r13144_r13146_p5488.tdd.*/*.h5
 top: &top
   name: top
-  equal_jets: true
+  equal_global_objects: true
   pattern:
     - user.svanstro.426345.e6880_s3681_r13144_p5488.tdd.*/*.h5
     - user.svanstro.426345.e6880_s3681_r13145_p5488.tdd.*/*.h5
 qcd: &qcd
   name: qcd
-  equal_jets: true
+  equal_global_objects: true
   pattern:
     - user.svanstro.364703.e7142_s3681_r13144_p5488.tdd.*/*.h5
     - user.svanstro.364704.e7142_s3681_r13144_p5488.tdd.*/*.h5
@@ -31,28 +31,28 @@ components:
     sample:
       <<: *hbb
     flavours: [hbb]
-    num_jets: 30_000_000
+    num_global_objects: 30_000_000
 
   - region:
       <<: *inclusive
     sample:
       <<: *hcc
     flavours: [hcc]
-    num_jets: 30_000_000
+    num_global_objects: 30_000_000
 
   - region:
       <<: *inclusive
     sample:
       <<: *top
     flavours: [top]
-    num_jets: 30_000_000
+    num_global_objects: 30_000_000
 
   - region:
       <<: *inclusive
     sample:
       <<: *qcd
     flavours: [qcd]
-    num_jets: 50_000_000
+    num_global_objects: 50_000_000
 
 resampling:
   target: hbb
@@ -71,6 +71,6 @@ resampling:
 # note: sensible defaults are defined in the PreprocessingConfig constructor
 global:
   batch_size: 4_000_000
-  num_jets_estimate: 10_000_000
+  num_global_objects_estimate: 10_000_000
   base_dir: /unix/atlastracking/samples/xbb/dumps/p5488_ext/
   merge_test_samples: True
diff --git a/upp/configs/xtautau.yaml b/upp/configs/xtautau.yaml
index 46afab2..e0fcf81 100644
--- a/upp/configs/xtautau.yaml
+++ b/upp/configs/xtautau.yaml
@@ -15,7 +15,7 @@ top: &top
   pattern: /atlas_cloud/fujimoto/umamiMCd/user.mfujimot.802423.e8514_s4159_r15530_p6453.tdd.FatJets.25_2_34.prod_131224_output.h5/*.h5
 qcd: &qcd
   name: qcd
-  equal_jets: true
+  equal_global_objects: true
   pattern:
     - /atlas_cloud/fujimoto/umamiMCd/user.mfujimot.801168.e8514_s4159_r15224_p6453.tdd.FatJets.25_2_34.prod_131224_output.h5/*.h5
     - /atlas_cloud/fujimoto/umamiMCd/user.mfujimot.801169.e8514_s4159_r15224_p6453.tdd.FatJets.25_2_34.prod_131224_output.h5/*.h5
@@ -31,35 +31,35 @@ components:
     sample:
       <<: *htauhad
     flavours: [htauhad]
-    num_jets: 5_000_000
+    num_global_objects: 5_000_000
 
   - region:
       <<: *inclusive
     sample:
       <<: *hbb
     flavours: [hbb]
-    num_jets: 14_500_000
+    num_global_objects: 14_500_000
 
   - region:
       <<: *inclusive
     sample:
       <<: *hcc
     flavours: [hcc]
-    num_jets: 14_500_000
+    num_global_objects: 14_500_000
 
   - region:
       <<: *inclusive
     sample:
       <<: *top
     flavours: [top]
-    num_jets: 8_000_000
+    num_global_objects: 8_000_000
 
   - region:
       <<: *inclusive
     sample:
       <<: *qcd
     flavours: [qcd]
-    num_jets: 22_000_000
+    num_global_objects: 22_000_000
 
 resampling:
   target: hbb
@@ -76,6 +76,6 @@ resampling:
 # note: sensible defaults are defined in the PreprocessingConfig constructor
 global:
   batch_size: 4_000_000
-  num_jets_estimate: 5_000_000
+  num_global_objects_estimate: 5_000_000
   base_dir: /atlas_cloud/fujimoto/samplesMC23d/
   merge_test_samples: True
diff --git a/upp/grid/download_and_prepare.py b/upp/grid/download_and_prepare.py
index f8f7c34..79a7bff 100644
--- a/upp/grid/download_and_prepare.py
+++ b/upp/grid/download_and_prepare.py
@@ -129,8 +129,8 @@ def create_meta_data(
 
     output_file = output_dir / "organised-components.yaml"
 
-    # Create a reader for each components to get num jets
-    num_jets = {
+    # Create a reader for each components to get num objects
+    num_global_objects = {
         split: {
             flavour: H5Reader(
                 files_by_component[split][flavour],
@@ -145,7 +145,7 @@ def create_meta_data(
         yaml.dump(
             {
                 "files": files_by_component,
-                "num_jets": num_jets,
+                "num_jets": num_global_objects,
             },
             f,
             default_flow_style=False,
diff --git a/upp/main.py b/upp/main.py
index 1dd23b9..98f45f5 100644
--- a/upp/main.py
+++ b/upp/main.py
@@ -1,13 +1,14 @@
 """
-Preprocessing pipeline for jet tagging.
+Preprocessing pipeline for object tagging.
 
 By default all stages for the training split are run.
 To run with only specific stages enabled, include the flag for the required stages.
 To run without certain stages, include the corresponding negative flag.
 
-To disable resampling, omit the `resampling` block or set `method: none`. The jets passing
-the cuts are then written directly, capped at each component's `num_jets` (use `num_jets: -1`
-to keep all of them). The `--no-resample` flag only skips the resampling *stage* (e.g. to
+To disable resampling, omit the `resampling` block or set `method: none`. The objects passing
+the cuts are then written directly, capped at each component's `num_global_objects`
+(use `num_global_objects: -1` to keep all of them). The `--no-resample` flag only skips
+the resampling *stage* (e.g. to
 re-run later stages); it does not disable resampling.
 """
 
diff --git a/upp/stages/__init__.py b/upp/stages/__init__.py
index 84a7619..dcf1fa6 100644
--- a/upp/stages/__init__.py
+++ b/upp/stages/__init__.py
@@ -2,7 +2,7 @@
 
 from __future__ import annotations
 
-from upp.stages.hist import Hist, bin_jets, create_histograms
+from upp.stages.hist import Hist, bin_global_objects, create_histograms
 from upp.stages.interpolation import subdivide_bins, upscale_array, upscale_array_regionally
 from upp.stages.merging import Merging
 from upp.stages.normalisation import Normalisation
@@ -14,7 +14,7 @@
     "Merging",
     "Normalisation",
     "Resampling",
-    "bin_jets",
+    "bin_global_objects",
     "create_histograms",
     "make_hist",
     "plot_resampling_dists",
diff --git a/upp/stages/hist.py b/upp/stages/hist.py
index 7fcbfc4..f49a440 100644
--- a/upp/stages/hist.py
+++ b/upp/stages/hist.py
@@ -18,13 +18,13 @@
     from upp.classes.preprocessing_config import PreprocessingConfig
 
 
-def bin_jets(array: dict, bins: list) -> tuple[np.ndarray, np.ndarray]:
+def bin_global_objects(array: dict, bins: list) -> tuple[np.ndarray, np.ndarray]:
     """Create the histogram and bins for the given resampling variables.
 
     Parameters
     ----------
     array : dict
-        Dict with the loaded jets and the resampling
+        Dict with the loaded objects and the resampling
         variables.
     bins : list
         Flat list with the bins which are to be used.
@@ -61,7 +61,7 @@ class Hist:
 
     def write_hist(
         self,
-        jets: dict,
+        global_objects: dict,
         resampling_vars: list,
         bins: list,
     ) -> None:
@@ -70,8 +70,8 @@ def write_hist(
 
         Parameters
         ----------
-        jets : dict
-            Dict with the loaded jets.
+        global_objects : dict
+            Dict with the loaded objects.
         resampling_vars : list
             List of the resampling variables.
         bins : list
@@ -85,16 +85,16 @@ def write_hist(
         # make parent dir
         self.path.parent.mkdir(parents=True, exist_ok=True)
 
-        # bin jets
-        hist = bin_jets(jets[resampling_vars], bins)[0]
-        pbin = hist / len(jets)  # probability (rate) of each bin
+        # bin objects
+        hist = bin_global_objects(global_objects[resampling_vars], bins)[0]
+        pbin = hist / len(global_objects)  # probability (rate) of each bin
         if not math.isclose(pbin.sum(), 1, rel_tol=1e-4, abs_tol=1e-4):
             raise ValueError(f"{pbin.sum()} != 1, check cuts and binning")
 
         with h5py.File(self.path, "w") as f:
             f.create_dataset("pbin", data=pbin)
             f.create_dataset("hist", data=hist)
-            f.attrs.create("num_jets", len(jets))
+            f.attrs.create("num_jets", len(global_objects))
             f.attrs.create("resampling_vars", resampling_vars)
             for i, v in enumerate(resampling_vars):
                 f.attrs.create(f"bins_{v}", bins[i])
@@ -153,7 +153,9 @@ def create_histograms(
 
     title = " Writing PDFs "
     log.info(f"[bold green]{title:-^100}")
-    log.info(f"[bold green]Estimating PDFs using {config.num_jets_estimate_hist:,} jets...")
+    log.info(
+        f"[bold green]Estimating PDFs using {config.num_global_objects_estimate_hist:,} objects..."
+    )
 
     # Create check variable to ensure at least one component was processed
     component_processed = not component_to_run
@@ -164,30 +166,33 @@ def create_histograms(
         if isinstance(component_to_run, str) and component_to_run != component.name:
             continue
 
-        log.info(f"Estimating {component} PDF using {config.num_jets_estimate_hist:,} samples...")
+        log.info(
+            f"Estimating {component} PDF using "
+            f"{config.num_global_objects_estimate_hist:,} samples..."
+        )
         component.setup_reader(batch_size=config.batch_size, global_name=config.global_name)
         cuts_no_split = component.cuts.ignore(["eventNumber"])
 
         ###
-        # TODO: return the number of jets here and pass to the next function to get started
+        # TODO: return the number of objects here and pass to the next function to get started
         ###
-        component.check_num_jets(
-            config.num_jets_estimate_hist,
+        component.check_num_global_objects(
+            config.num_global_objects_estimate_hist,
             cuts=cuts_no_split,
             silent=False,
             raise_error=False,
         )
 
-        # Load the jets from file used for resampling
-        jets = component.get_jets(
+        # Load the objects from file used for resampling
+        global_objects = component.get_global_objects(
             variables=sampl_vars,
-            num_jets=config.num_jets_estimate_hist,
+            num_global_objects=config.num_global_objects_estimate_hist,
             cuts=cuts_no_split,
         )
 
         # Write out the hist used for resampling
         component.hist.write_hist(
-            jets=jets,
+            global_objects=global_objects,
             resampling_vars=sampl_vars,
             bins=config.sampl_cfg.flat_bins,
         )
diff --git a/upp/stages/merging.py b/upp/stages/merging.py
index 1ddcf60..8ccf44c 100644
--- a/upp/stages/merging.py
+++ b/upp/stages/merging.py
@@ -29,7 +29,7 @@ def __init__(self, config: PreprocessingConfig):
         self.global_name = config.global_name
         self.rng = np.random.default_rng(42)
         self.flavours = self.components.flavours
-        self.num_jets_per_output_file = config.num_jets_per_output_file
+        self.num_global_objects_per_output_file = config.num_global_objects_per_output_file
         self.file_tag = "split"
 
         # Auto-resume toggle (make configurable if you prefer opt-in)
@@ -48,10 +48,10 @@ def __init__(self, config: PreprocessingConfig):
         self.dtypes: dict[str, np.dtype] = {}
         self.base_shapes: dict[str, tuple[int, ...]] = {}
 
-        # Setup all the jet counters
+        # Setup all the object counters
         self._file_idx: int = 0
-        self.total_jets: int = 0
-        self.jets_written: int = 0
+        self.total_global_objects: int = 0
+        self.global_objects_written: int = 0
 
         # Setup the sample string
         self._sample: str | None = None
@@ -60,30 +60,32 @@ def __init__(self, config: PreprocessingConfig):
         self.current_components = cast("Components", None)
         self.writer = cast(H5Writer, None)
 
-    def add_jet_flavour_label(self, jets: np.ndarray, component: Component) -> np.ndarray:
-        """Add the jet flavour label to the jets.
+    def add_global_object_label(
+        self, global_objects: np.ndarray, component: Component
+    ) -> np.ndarray:
+        """Add the object flavour label to the objects.
 
-        If already present, jets will be returned without any changes.
+        If already present, objects will be returned without any changes.
 
         Parameters
         ----------
-        jets : np.ndarray
-            Structured array of with the jets and their variables
+        global_objects : np.ndarray
+            Structured array of with the objects and their variables
         component : Component
             Component instance of the
 
         Returns
         -------
         np.ndarray
-            Structured array of the jets and their variables with the
+            Structured array of the objects and their variables with the
             "flavour_label" added.
         """
-        if "flavour_label" in jets.dtype.names:
-            return jets
+        if "flavour_label" in global_objects.dtype.names:
+            return global_objects
         int_label = self.flavours.index(component.flavour)
-        label_array = np.full(len(jets), int_label, dtype=[("flavour_label", "i4")])
+        label_array = np.full(len(global_objects), int_label, dtype=[("flavour_label", "i4")])
 
-        return join_structured_arrays([jets, label_array])
+        return join_structured_arrays([global_objects, label_array])
 
     def _part_fname(self, sample: str | None, file_idx: int) -> Path:
         """Construct the exact output filename for a given part index.
@@ -115,7 +117,9 @@ def _part_fname(self, sample: str | None, file_idx: int) -> Path:
         return fname.parent / self.config.split / fname.name
 
     def _expected_rows_for_part(self, part_idx: int) -> int:
-        """Return the expected number of rows for part `part_idx` given total_jets and split size.
+        """Return the expected number of rows for part `part_idx`.
+
+        Uses ``total_global_objects`` and the configured split size.
 
         Parameters
         ----------
@@ -128,13 +132,13 @@ def _expected_rows_for_part(self, part_idx: int) -> int:
             Expected number of rows for the given partial file
         """
         # Assert that the final output file will be splitted
-        assert self.num_jets_per_output_file is not None
+        assert self.num_global_objects_per_output_file is not None
 
-        # Remaining jets starting at this part
-        start = part_idx * int(self.num_jets_per_output_file)
-        remaining = max(0, self.total_jets - start)
+        # Remaining objects starting at this part
+        start = part_idx * int(self.num_global_objects_per_output_file)
+        remaining = max(0, self.total_global_objects - start)
 
-        return min(int(self.num_jets_per_output_file), remaining)
+        return min(int(self.num_global_objects_per_output_file), remaining)
 
     def _is_part_valid(self, sample: str | None, part_idx: int) -> bool:
         """Heuristically validate that a part file is complete and consistent.
@@ -166,7 +170,7 @@ def _is_part_valid(self, sample: str | None, part_idx: int) -> bool:
                 # Collect expected dataset names from base_shapes (already computed)
                 expected_names = list(self.base_shapes.keys())
 
-                # Tolerate missing optional groups, but require the jet dataset at least
+                # Tolerate missing optional groups, but require the object dataset at least
                 if self.global_name not in f:
                     log.warning(f"Missing dataset '{self.global_name}' in {fname}")
                     return False
@@ -193,7 +197,7 @@ def _is_part_valid(self, sample: str | None, part_idx: int) -> bool:
                         return False
 
                 # Compare with expected rows for this part (if split mode)
-                if self.num_jets_per_output_file is not None:
+                if self.num_global_objects_per_output_file is not None:
                     exp_len = self._expected_rows_for_part(part_idx)
                     if obs_len != exp_len:
                         log.warning(
@@ -227,7 +231,7 @@ def _detect_and_clean_completed_parts(self, sample: str | None) -> int:
             The index of the first missing/invalid part.
         """
         # Check that multiple output files should be created
-        if self.num_jets_per_output_file is None:
+        if self.num_global_objects_per_output_file is None:
             return 0
 
         # Define a counter
@@ -267,11 +271,12 @@ class _NullWriter:
         """A minimal writer that discards data while tracking how much would be written."""
 
         def __init__(self, capacity: int):
+            # Mirrors the ftag H5Writer API (assigned to self.writer)
             self.num_jets = capacity
             self.num_written = 0
 
         def write(self, batch: dict[str, np.ndarray]) -> None:
-            """Count the number of jets that would be written.
+            """Count the number of objects that would be written.
 
             Parameters
             ----------
@@ -296,7 +301,7 @@ def close(self):
     def _open_writer(
         self,
         sample: str | None,
-        jets_in_file: int,
+        global_objects_in_file: int,
         file_idx: int,
         components: Components,
     ) -> None:
@@ -306,15 +311,15 @@ def _open_writer(
         ----------
         sample : str | None
             Sample name (``None`` for the "train/val test" merge).
-        jets_in_file : int
+        global_objects_in_file : int
             Capacity of the new file (= leading dimension of every dataset).
         file_idx : int
             Running part index (0, 1, 2, …); used only for the filename suffix.
         components : Components
-            The `Components` object we are currently merging needed for `jet_counts`, etc.
+            The `Components` object we are currently merging needed for `global_object_counts`, etc.
         """
         # Construct the filename
-        if self.num_jets_per_output_file is not None:
+        if self.num_global_objects_per_output_file is not None:
             fname = self._part_fname(sample, file_idx)
         else:
             fname = Path(self.config.out_fname)
@@ -322,7 +327,9 @@ def _open_writer(
                 fname = path_append(fname, sample)
 
         # Adjust shapes to the capacity of this file
-        shapes = {name: (jets_in_file,) + shape[1:] for name, shape in self.base_shapes.items()}
+        shapes = {
+            name: (global_objects_in_file,) + shape[1:] for name, shape in self.base_shapes.items()
+        }
 
         # Ensure the output directory exists before opening the writer
         fname.parent.mkdir(parents=True, exist_ok=True)
@@ -334,7 +341,7 @@ def _open_writer(
             shapes,
             add_flavour_label=self.global_name,
             jets_name=self.global_name,
-            num_jets=jets_in_file,
+            num_jets=global_objects_in_file,
         )
 
         # Copy the metadata attributes
@@ -343,8 +350,8 @@ def _open_writer(
             [f.name for f in self.flavours],
             self.global_name,
         )
-        self.writer.add_attr("unique_jets", components.unique_jets)
-        self.writer.add_attr("jet_counts", json.dumps(components.jet_counts))
+        self.writer.add_attr("unique_jets", components.unique_global_objects)
+        self.writer.add_attr("jet_counts", json.dumps(components.global_object_counts))
         self.writer.add_attr("dsids", str(components.dsids))
         self.writer.add_attr("config", json.dumps(self.config.config))
         self.writer.add_attr("upp_hash", self.config.git_hash)
@@ -368,7 +375,7 @@ def write_chunk(self, components: Components) -> int:
         Returns
         -------
         int
-            The number of jets that were consumed from the components
+            The number of objects that were consumed from the components
             (== written to disk).  When all components are exhausted the
             function returns 0 so that the caller can stop its loop.
         """
@@ -385,8 +392,8 @@ def write_chunk(self, components: Components) -> int:
                 try:
                     # shallow copy because we will add a field
                     batch = copy(next(component.stream))
-                    batch[self.global_name] = self.add_jet_flavour_label(
-                        jets=batch[self.global_name], component=component
+                    batch[self.global_name] = self.add_global_object_label(
+                        global_objects=batch[self.global_name], component=component
                     )
                 except StopIteration:
                     component.complete = True
@@ -412,7 +419,7 @@ def write_chunk(self, components: Components) -> int:
             if selector := self.variables.selectors.get(name):
                 merged[name] = selector(merged[name])
 
-        # Get the total length of jets from the batch and how much
+        # Get the total length of objects from the batch and how much
         # capacity is left in the file
         merged_len = len(merged[self.global_name])
         capacity_left = self.writer.num_jets - self.writer.num_written
@@ -421,14 +428,14 @@ def write_chunk(self, components: Components) -> int:
             # Limit consumption to the remaining discard quota
             if merged_len <= capacity_left:
                 self.writer.write(merged)
-                self.jets_written += merged_len
+                self.global_objects_written += merged_len
                 return merged_len
             else:
                 head = {n: a[:capacity_left] for n, a in merged.items()}
                 tail = {n: a[capacity_left:] for n, a in merged.items()}
                 self.writer.write(head)
                 self._ff_pending = tail  # keep remainder for next iteration
-                self.jets_written += capacity_left
+                self.global_objects_written += capacity_left
                 return capacity_left
 
         # If current file is full (and not fast-forwarding), roll to next file
@@ -438,15 +445,15 @@ def write_chunk(self, components: Components) -> int:
 
             # open the next one
             self._file_idx += 1
-            remaining_total = self.total_jets - self.jets_written
+            remaining_total = self.total_global_objects - self.global_objects_written
 
-            # Quit writing when no jets are left to write
+            # Quit writing when no objects are left to write
             if remaining_total == 0:
                 return 0
 
             next_file_size = (
-                min(self.num_jets_per_output_file, remaining_total)
-                if self.num_jets_per_output_file
+                min(self.num_global_objects_per_output_file, remaining_total)
+                if self.num_global_objects_per_output_file
                 else remaining_total
             )
             self._open_writer(
@@ -470,12 +477,14 @@ def write_chunk(self, components: Components) -> int:
             self.writer.write(head)
             self.writer.close()
 
-            # Open a fresh file sized for the remaining jets
+            # Open a fresh file sized for the remaining objects
             self._file_idx += 1
-            remaining_total = self.total_jets - (self.jets_written + capacity_left)
+            remaining_total = self.total_global_objects - (
+                self.global_objects_written + capacity_left
+            )
             next_file_size = (
-                min(self.num_jets_per_output_file, remaining_total)
-                if self.num_jets_per_output_file
+                min(self.num_global_objects_per_output_file, remaining_total)
+                if self.num_global_objects_per_output_file
                 else remaining_total
             )
             self._open_writer(self._sample, next_file_size, self._file_idx, self.current_components)
@@ -485,15 +494,15 @@ def write_chunk(self, components: Components) -> int:
             self.writer.write(tail)
 
         # Updating the progress-bar
-        self.jets_written += merged_len
+        self.global_objects_written += merged_len
         return merged_len
 
     def write_components(self, sample: str | None, components: Components) -> None:
         """Merge *components* into one or more HDF5 files.
 
-        If ``self.num_jets_per_output_file`` is ``None`` the behaviour is identical to the
+        If ``self.num_global_objects_per_output_file`` is ``None`` the behaviour is identical to the
         original implementation (exactly one output file).  Otherwise the function
-        keeps opening new `H5Writer`s whenever the current file reaches that jet
+        keeps opening new `H5Writer`s whenever the current file reaches that object
         limit.  All heavy work (splitting batches, rolling files) is handled in
         ``self.write_chunk``.
 
@@ -504,17 +513,19 @@ def write_components(self, sample: str | None, components: Components) -> None:
         components : Components
             Components that are to be written
         """
-        # Resolve "write all" (num_jets < 0) to the actual number of jets on disk
+        # Resolve "write all" (num_global_objects < 0) to the actual number of objects on disk
         for component in components:
-            if component.num_jets < 0:
+            if component.num_global_objects < 0:
                 component.setup_reader(
                     self.batch_size, fname=component.out_path, global_name=self.global_name
                 )
-                component.num_jets = component.reader.num_jets
+                component.num_global_objects = component.reader.num_jets
 
         # Prepare every Component's reader
         for component in components:
-            batch_size = self.batch_size * component.num_jets // components.num_jets + 1
+            batch_size = (
+                self.batch_size * component.num_global_objects // components.num_global_objects + 1
+            )
             component.setup_reader(
                 batch_size,
                 fname=component.out_path,
@@ -528,30 +539,32 @@ def write_components(self, sample: str | None, components: Components) -> None:
 
         # Cache dtype / base shapes once (re-used for every new file)
         self.dtypes = components[0].reader.dtypes(self.variables.combined())
-        self.base_shapes = components[0].reader.shapes(components.num_jets, self.variables.keys())
+        self.base_shapes = components[0].reader.shapes(
+            components.num_global_objects, self.variables.keys()
+        )
 
         # Bookkeeping shared with write_chunk
-        self.total_jets = components.num_jets
-        self.jets_written = 0
+        self.total_global_objects = components.num_global_objects
+        self.global_objects_written = 0
         self._file_idx = 0
         self._sample = sample
         self.current_components = components
 
         # Auto-resume: detect contiguous valid parts; delete a corrupt last part if found
         resume_parts = 0
-        if self.resume and isinstance(self.num_jets_per_output_file, int):
+        if self.resume and isinstance(self.num_global_objects_per_output_file, int):
             resume_parts = self._detect_and_clean_completed_parts(sample)
 
-        if resume_parts and isinstance(self.num_jets_per_output_file, int):
-            to_discard = resume_parts * int(self.num_jets_per_output_file)
+        if resume_parts and isinstance(self.num_global_objects_per_output_file, int):
+            to_discard = resume_parts * int(self.num_global_objects_per_output_file)
             log.info(
                 f"[bold yellow]Resuming merge: found {resume_parts} completed part(s); "
-                f"skipping first {to_discard:,} jets."
+                f"skipping first {to_discard:,} objects."
             )
             # Use a NullWriter to pre-consume data via the exact same logic
             self._fast_forwarding = True
             self.writer = self._NullWriter(to_discard)
-            while self.jets_written < to_discard:
+            while self.global_objects_written < to_discard:
                 consumed = self.write_chunk(components)
                 if consumed == 0:
                     break
@@ -560,13 +573,13 @@ def write_components(self, sample: str | None, components: Components) -> None:
 
             # Align counters with the next missing part
             self._file_idx = resume_parts
-            self.jets_written = to_discard
+            self.global_objects_written = to_discard
 
         # Decide capacity of the first real file
-        remaining_total = self.total_jets - self.jets_written
+        remaining_total = self.total_global_objects - self.global_objects_written
         first_file_size = (
-            min(self.num_jets_per_output_file, remaining_total)
-            if self.num_jets_per_output_file
+            min(self.num_global_objects_per_output_file, remaining_total)
+            if self.num_global_objects_per_output_file
             else remaining_total
         )
 
@@ -576,11 +589,11 @@ def write_components(self, sample: str | None, components: Components) -> None:
         # Main merge loop with progress
         with ProgressBar() as progress:
             task = progress.add_task(
-                f"[green]Merging {components.num_jets:,} jets...",
-                total=components.num_jets,
+                f"[green]Merging {components.num_global_objects:,} objects...",
+                total=components.num_global_objects,
             )
-            if self.jets_written:
-                progress.update(task, advance=self.jets_written)
+            if self.global_objects_written:
+                progress.update(task, advance=self.global_objects_written)
 
             while True:
                 n = self.write_chunk(components)
@@ -591,7 +604,7 @@ def write_components(self, sample: str | None, components: Components) -> None:
         # Close Writer
         self.writer.close()
         label = "merged" if sample is None else sample
-        log.info(f"[bold green]Finished merging {components.num_jets:,} {label} jets!")
+        log.info(f"[bold green]Finished merging {components.num_global_objects:,} {label} objects!")
 
     def run(self):
         """Run merging of the components."""
diff --git a/upp/stages/normalisation.py b/upp/stages/normalisation.py
index db75683..0e7812b 100644
--- a/upp/stages/normalisation.py
+++ b/upp/stages/normalisation.py
@@ -22,7 +22,7 @@ def __init__(self, config: PreprocessingConfig):
         self.components = config.components
         self.variables = config.variables
         self.global_name = self.config.global_name
-        self.num_jets = config.num_jets_estimate_norm
+        self.num_global_objects = config.num_global_objects_estimate_norm
         self.norm_fname = config.out_dir / config.config.get("norm_fname", "norm_dict.yaml")
         self.class_fname = config.out_dir / config.config.get("class_fname", "class_dict.yaml")
 
@@ -48,9 +48,9 @@ def combine_mean_std(
         std_B : float
             Standard deviation of the variable B
         num_A : int
-            Number of jets for variable A
+            Number of objects for variable A
         num_B : int
-            Number of jets for variable B
+            Number of objects for variable B
 
         Returns
         -------
@@ -64,17 +64,17 @@ def combine_mean_std(
         return float(combined_mean), float(combined_std)
 
     def get_norm_dict(self, batch: dict) -> tuple[dict, int]:
-        """Get the normalisation dict with the mean and standard deviation for the given jets.
+        """Get the normalisation dict with the mean and standard deviation for the given objects.
 
         Parameters
         ----------
         batch : dict
-            Dict with the jets and all variables
+            Dict with the objects and all variables
 
         Returns
         -------
         tuple[dict, int]
-            Normalisation dict and the number of jets used to calculate it
+            Normalisation dict and the number of objects used to calculate it
         """
         norm_dict: dict[str, dict] = {k: {} for k in self.variables}
         for name, array in batch.items():
@@ -98,9 +98,9 @@ def combine_norm_dict(self, norm_A: dict, norm_B: dict, num_A: int, num_B: int)
         norm_B : dict
             Normalisation dict B
         num_A : int
-            Number of jets used to calculate normalisation dict A
+            Number of objects used to calculate normalisation dict A
         num_B : int
-            Number of jets used to calculate normalisation dict B
+            Number of objects used to calculate normalisation dict B
 
         Returns
         -------
@@ -127,12 +127,12 @@ def combine_norm_dict(self, norm_A: dict, norm_B: dict, num_A: int, num_B: int)
         return combined
 
     def get_class_dict(self, batch: dict) -> dict:
-        """Get the class dict for the given jets.
+        """Get the class dict for the given objects.
 
         Parameters
         ----------
         batch : dict
-            Dict with the jets and their variables
+            Dict with the objects and their variables
 
         Returns
         -------
@@ -237,7 +237,7 @@ def run(self):
             fname = str(self.config.out_fname).replace(".h5", "_vds.h5")
 
         # Get the correct output names if multiple output files were written
-        elif self.config.num_jets_per_output_file is not None:
+        elif self.config.num_global_objects_per_output_file is not None:
             fname = (
                 self.config.out_fname.parent
                 / self.config.split
@@ -263,12 +263,12 @@ def run(self):
         with h5py.File(reader.files[0]) as f:
             if "flavour_label" in f[self.global_name].dtype.names:
                 vars[self.global_name].append("flavour_label")
-        stream = reader.stream(vars, self.num_jets)
+        stream = reader.stream(vars, self.num_global_objects)
 
         with ProgressBar() as progress:
             task = progress.add_task(
-                f"[green]Computing normalisations using {self.num_jets:,} jets...",
-                total=self.num_jets,
+                f"[green]Computing normalisations using {self.num_global_objects:,} objects...",
+                total=self.num_global_objects,
             )
 
             for i, batch in enumerate(stream):
@@ -285,7 +285,10 @@ def run(self):
 
                 progress.update(task, advance=len(batch[self.variables.global_name]))
 
-        log.info(f"[bold green]Finished computing normalisation params on {self.num_jets:,} jets!")
+        log.info(
+            f"[bold green]Finished computing normalisation params on "
+            f"{self.num_global_objects:,} objects!"
+        )
         self.write_norm_dict(norm_dict)
         self.write_class_dict(class_dict)
         log.info(f"[bold green]Saved norm dict to {self.norm_fname}")
diff --git a/upp/stages/plot.py b/upp/stages/plot.py
index 918880b..ed6a45a 100644
--- a/upp/stages/plot.py
+++ b/upp/stages/plot.py
@@ -27,7 +27,7 @@ class PlotRegion:
     name : str
         Name used in output file suffixes and log messages.
     cuts : Cuts
-        Jet-level selection defining the region.
+        Object-level selection defining the region.
     pt_range : tuple[float, float] | None
         Raw pT range defining the region. Values follow the input ntuple units,
         usually MeV. If ``None``, the region has no explicit pT range.
@@ -157,35 +157,35 @@ def _sample_label(sample_name: str, plotting: PlottingConfig) -> str:
     return plotting.sample_label(sample_name)
 
 
-def _format_num_jets(num_jets: int) -> str:
-    """Format a jet count with compact suffixes.
+def _format_num_global_objects(num_global_objects: int) -> str:
+    """Format a object count with compact suffixes.
 
     Parameters
     ----------
-    num_jets : int
-        Number of jets to format.
+    num_global_objects : int
+        Number of objects to format.
 
     Returns
     -------
     str
         Compact count using ``k`` for thousands and ``M`` for millions.
     """
-    if num_jets >= 1_000_000:
-        value = num_jets / 1_000_000
+    if num_global_objects >= 1_000_000:
+        value = num_global_objects / 1_000_000
         return f"{value:g}M"
-    if num_jets >= 1_000:
-        value = num_jets / 1_000
+    if num_global_objects >= 1_000:
+        value = num_global_objects / 1_000
         return f"{value:g}k"
-    return str(num_jets)
+    return str(num_global_objects)
 
 
 def _atlas_second_tag(
     *sample_names: str,
     plotting: PlottingConfig,
-    num_jets: int | None = None,
+    num_global_objects: int | None = None,
     resampling_status: str | None = None,
 ) -> str:
-    """Build the second ATLAS tag with energy, sample labels, status, and jet count.
+    """Build the second ATLAS tag with energy, sample labels, status, and object count.
 
     Parameters
     ----------
@@ -193,8 +193,8 @@ def _atlas_second_tag(
         Sample names to include after the centre-of-mass energy.
     plotting : PlottingConfig
         Active plotting configuration.
-    num_jets : int | None, optional
-        Number of jets requested for plotting. If provided, it is added as an
+    num_global_objects : int | None, optional
+        Number of objects requested for plotting. If provided, it is added as an
         extra line using compact formatting.
     resampling_status : str | None, optional
         Resampling status added as an extra line.
@@ -204,37 +204,37 @@ def _atlas_second_tag(
     str
         Multiline ATLAS second tag. Sample labels share the first line with the
         centre-of-mass energy, followed by the optional resampling status and
-        jet count.
+        object count.
     """
     labels = [_sample_label(name, plotting) for name in dict.fromkeys(sample_names) if name]
     first_line = plotting.atlas_second_tag
     if labels:
-        first_line = f"{first_line}, {' + '.join(labels)} jets"
+        first_line = f"{first_line}, {' + '.join(labels)} objects"
     lines = [first_line]
     if resampling_status is not None:
         lines.append(resampling_status)
-    if num_jets is not None:
-        lines.append(f"{_format_num_jets(num_jets)} jets")
+    if num_global_objects is not None:
+        lines.append(f"{_format_num_global_objects(num_global_objects)} objects")
     return "\n".join(lines)
 
 
-def _plotting_num_jets(config: PreprocessingConfig, available_jets: int) -> int:
-    """Return the number of jets requested for plotting.
+def _plotting_num_global_objects(config: PreprocessingConfig, available_global_objects: int) -> int:
+    """Return the number of objects requested for plotting.
 
     Parameters
     ----------
     config : PreprocessingConfig
         Active preprocessing configuration.
-    available_jets : int
-        Number of jets available for the plotted selection.
+    available_global_objects : int
+        Number of objects available for the plotted selection.
 
     Returns
     -------
     int
-        Minimum of the available jets and ``plotting.num_jets_plotting``.
+        Minimum of the available objects and ``plotting.num_global_objects_plotting``.
     """
-    assert config.plotting.num_jets_plotting is not None
-    return min(available_jets, config.plotting.num_jets_plotting)
+    assert config.plotting.num_global_objects_plotting is not None
+    return min(available_global_objects, config.plotting.num_global_objects_plotting)
 
 
 def _pt_bounds_from_cuts(cuts: Cuts, pt_variable: str) -> tuple[float, float] | None:
@@ -243,7 +243,7 @@ def _pt_bounds_from_cuts(cuts: Cuts, pt_variable: str) -> tuple[float, float] |
     Parameters
     ----------
     cuts : Cuts
-        Jet-level cuts associated with a component region.
+        Object-level cuts associated with a component region.
     pt_variable : str
         Name of the pT variable used for resampling.
 
@@ -418,8 +418,10 @@ def _stitching_regions(regions: list[PlotRegion], pt_variable: str | None) -> li
     return stitching_regions
 
 
-def _load_jets(config: PreprocessingConfig, in_paths: Any, vars_to_load: list[str]) -> Any:
-    """Load jet variables for plotting.
+def _load_global_objects(
+    config: PreprocessingConfig, in_paths: Any, vars_to_load: list[str]
+) -> Any:
+    """Load object variables for plotting.
 
     Parameters
     ----------
@@ -428,12 +430,12 @@ def _load_jets(config: PreprocessingConfig, in_paths: Any, vars_to_load: list[st
     in_paths : Any
         Input HDF5 file path, glob, or list of paths passed to ``H5Reader``.
     vars_to_load : list[str]
-        Jet variables needed for plotting and selections.
+        Object variables needed for plotting and selections.
 
     Returns
     -------
     Any
-        Structured jet array loaded from the input files.
+        Structured object array loaded from the input files.
     """
     return H5Reader(
         fname=in_paths,
@@ -444,7 +446,7 @@ def _load_jets(config: PreprocessingConfig, in_paths: Any, vars_to_load: list[st
         vds_dir=config.vds_dir,
     ).load(
         {config.global_name: list(dict.fromkeys(vars_to_load))},
-        num_jets=config.plotting.num_jets_plotting,
+        num_jets=config.plotting.num_global_objects_plotting,
     )[config.global_name]
 
 
@@ -485,7 +487,7 @@ def make_hist(
     out_dir : Path
         Output directory to which the plots are written.
     global_name: str, optional
-        Name of the jet dataset / the global objects
+        Name of the object dataset / the global objects
         by default "jets"
     bins_range : tuple | None, optional
         bins_range argument from from puma.HistogramPlot,
@@ -601,7 +603,7 @@ def _plot_initial(config: PreprocessingConfig) -> None:
                 vars_to_load += flavour.cuts.variables
 
             values_dict = {
-                sample.name: _load_jets(config, list(sample.path), vars_to_load),
+                sample.name: _load_global_objects(config, list(sample.path), vars_to_load),
             }
             pt_range = _pt_bounds_from_cuts(selection_cuts, pt_var) if pt_var else None
 
@@ -624,8 +626,10 @@ def _plot_initial(config: PreprocessingConfig) -> None:
                     atlas_second_tag=_atlas_second_tag(
                         sample.name,
                         plotting=config.plotting,
-                        num_jets=_plotting_num_jets(config, region_components.num_jets)
-                        if config.plotting.show_num_jets
+                        num_global_objects=_plotting_num_global_objects(
+                            config, region_components.num_global_objects
+                        )
+                        if config.plotting.show_num_global_objects
                         else None,
                         resampling_status="Pre Resampling",
                     ),
@@ -653,13 +657,13 @@ def _post_resampling_paths(config: PreprocessingConfig, stage: str) -> list[Path
         return [
             (
                 config.out_fname.parent / config.split / f"{config.out_fname.stem}*.h5"
-                if config.num_jets_per_output_file is not None
+                if config.num_global_objects_per_output_file is not None
                 else config.out_fname
             )
         ]
 
     paths = [path_append(config.out_fname, sample.name) for sample in config.components.samples]
-    if config.num_jets_per_output_file is not None:
+    if config.num_global_objects_per_output_file is not None:
         return [path.parent / config.split / f"{path.stem}*.h5" for path in paths]
     return paths
 
@@ -684,8 +688,10 @@ def _plot_post_resampling(config: PreprocessingConfig, stage: str) -> None:
     atlas_second_tag = _atlas_second_tag(
         *sample_names,
         plotting=config.plotting,
-        num_jets=_plotting_num_jets(config, config.components.num_jets)
-        if config.plotting.show_num_jets
+        num_global_objects=_plotting_num_global_objects(
+            config, config.components.num_global_objects
+        )
+        if config.plotting.show_num_global_objects
         else None,
         resampling_status="Post Resampling",
     )
@@ -695,7 +701,7 @@ def _plot_post_resampling(config: PreprocessingConfig, stage: str) -> None:
         vars_to_load += region.cuts.variables
 
     values_dict = {
-        "": _load_jets(config, _post_resampling_paths(config, stage), vars_to_load),
+        "": _load_global_objects(config, _post_resampling_paths(config, stage), vars_to_load),
     }
 
     for variable in config.sampl_cfg.vars:
diff --git a/upp/stages/resampling.py b/upp/stages/resampling.py
index f64168b..389ee03 100644
--- a/upp/stages/resampling.py
+++ b/upp/stages/resampling.py
@@ -10,7 +10,7 @@
 from ftag.hdf5 import H5Reader
 from yamlinclude import YamlIncludeConstructor
 
-from upp.stages.hist import bin_jets
+from upp.stages.hist import bin_global_objects
 from upp.stages.interpolation import subdivide_bins, upscale_array_regionally
 from upp.utils.logger import ProgressBar
 
@@ -59,7 +59,7 @@ def __init__(self, config: PreprocessingConfig):
         # Define what type self.target will be
         self.target = cast("Component", None)
 
-        # In skip mode no selection is applied; jets are written as-is (see sample())
+        # In skip mode no selection is applied; objects are written as-is (see sample())
         if self.skip:
             self.method = None
             self.upscale_pdf = 1
@@ -81,20 +81,20 @@ def __init__(self, config: PreprocessingConfig):
             )
         self.select_func = self.methods_map[self.method]
 
-    def countup_select_func(self, jets: dict, component: Component) -> np.ndarray:
+    def countup_select_func(self, global_objects: dict, component: Component) -> np.ndarray:
         """Countup resampling function.
 
         Parameters
         ----------
-        jets : dict
-            Dict with the jets which are to be resampled.
+        global_objects : dict
+            Dict with the objects which are to be resampled.
         component : Component
             Component instance for a given flavour/class.
 
         Returns
         -------
         np.ndarray
-            Numpy array with the index numbers of the jets that are to be used.
+            Numpy array with the index numbers of the objects that are to be used.
 
         Raises
         ------
@@ -106,22 +106,22 @@ def countup_select_func(self, jets: dict, component: Component) -> np.ndarray:
         if self.upscale_pdf != 1:
             raise ValueError("Upscaling of histograms is not supported for countup method")
 
-        # Get the target number of jets and target PDF values
-        num_jets = int(len(jets) * component.sampling_fraction)
+        # Get the target number of objects and target PDF values
+        num_global_objects = int(len(global_objects) * component.sampling_fraction)
         target_pdf = self.target.hist.pbin
 
         # Get the target histograms
-        target_hist = target_pdf * num_jets
+        target_hist = target_pdf * num_global_objects
         target_hist = (np.floor(target_hist + self.rng.random(target_pdf.shape))).astype(int)
 
         # Create histogram and bins for the given resampling variables
-        _hist, binnumbers = bin_jets(
-            array=jets[self.config.vars],
+        _hist, binnumbers = bin_global_objects(
+            array=global_objects[self.config.vars],
             bins=self.config.flat_bins,
         )
         assert target_pdf.shape == _hist.shape
 
-        # Loop over bins and select relevant jets (indicies)
+        # Loop over bins and select relevant objects (indicies)
         all_idx = []
         for bin_id in np.ndindex(*target_hist.shape):
             idx = np.where((bin_id == binnumbers.T).all(axis=-1))[0][: target_hist[bin_id]]
@@ -130,25 +130,25 @@ def countup_select_func(self, jets: dict, component: Component) -> np.ndarray:
             all_idx.append(idx)
         idx = np.concatenate(all_idx).astype(int)
 
-        # If not enough jets are found, re-use randomly some of them
-        if len(idx) < num_jets:
-            idx = np.concatenate([idx, self.rng.choice(idx, num_jets - len(idx))])
+        # If not enough objects are found, re-use randomly some of them
+        if len(idx) < num_global_objects:
+            idx = np.concatenate([idx, self.rng.choice(idx, num_global_objects - len(idx))])
 
-        # Shuffle the jet indicies
+        # Shuffle the object indicies
         self.rng.shuffle(idx)
 
         return idx
 
-    def pdf_select_func(self, jets: dict, component: Component) -> np.ndarray:
-        # bin jets
+    def pdf_select_func(self, global_objects: dict, component: Component) -> np.ndarray:
+        # bin objects
         if self.upscale_pdf > 1:
             bins = [subdivide_bins(bins, self.upscale_pdf) for bins in self.config.flat_bins]
         else:
             bins = self.config.flat_bins
 
         # Create histogram and bins for the given resampling variables
-        _hist, binnumbers = bin_jets(
-            array=jets[self.config.vars],
+        _hist, binnumbers = bin_global_objects(
+            array=global_objects[self.config.vars],
             bins=bins,
         )
 
@@ -157,7 +157,7 @@ def pdf_select_func(self, jets: dict, component: Component) -> np.ndarray:
             binnumbers = tuple(binnumbers[i] for i in range(len(binnumbers)))
 
         # importance sample with replacement
-        num_samples = int(len(jets) * component.sampling_fraction)
+        num_samples = int(len(global_objects) * component.sampling_fraction)
 
         # Calculate the ratios between the target and the to-be-resampled distribution
         ratios = safe_divide(a=self.target.hist.pbin, b=component.hist.pbin)
@@ -173,13 +173,13 @@ def pdf_select_func(self, jets: dict, component: Component) -> np.ndarray:
         # Get the probabilities for the resampling from the ratios
         probs = ratios[binnumbers]
 
-        # Select the jets (indicies) for the resampled final output
-        idx = random.choices(np.arange(len(jets)), weights=probs, k=num_samples)
+        # Select the objects (indicies) for the resampled final output
+        idx = random.choices(np.arange(len(global_objects)), weights=probs, k=num_samples)
 
         return idx
 
     def track_upsampling_stats(self, idx: np.ndarray, component: Component) -> None:
-        """Tracking the upsampling ratio and update the number of unique jets.
+        """Tracking the upsampling ratio and update the number of unique objects.
 
         Parameters
         ----------
@@ -189,16 +189,16 @@ def track_upsampling_stats(self, idx: np.ndarray, component: Component) -> None:
             Component instance for a given flavour/class.
         """
         unique, ups_counts = np.unique(idx, return_counts=True)
-        component._unique_jets += len(unique)
+        component._unique_global_objects += len(unique)
         max_ups = ups_counts.max()
         component._ups_max = max_ups if max_ups > component._ups_max else component._ups_max
 
     def _finalise_component(self, component: Component) -> None:
         """Write metadata attrs and close the writer for a completed component."""
-        unique = component._unique_jets
+        unique = component._unique_global_objects
         component._ups_ratio = component.writer.num_written / unique if unique else 0.0
         component.writer.add_attr("upsampling_ratio", component._ups_ratio)
-        component.writer.add_attr("unique_jets", component._unique_jets)
+        component.writer.add_attr("unique_jets", component._unique_global_objects)
         component.writer.add_attr("dsid", str(component.sample.dsid))
         component.writer.close()
 
@@ -209,14 +209,14 @@ def sample(
         progress: Progress,
         selected_component: str | None = None,
     ) -> None:
-        """Sample the jets by the given selected indicies from the resampling function.
+        """Sample the objects by the given selected indicies from the resampling function.
 
         Parameters
         ----------
         components : Components
             Components instance of the components which are to be resampled.
         stream : Generator[Any, None, None]
-            Generator of the jets which are to be resampled.
+            Generator of the objects which are to be resampled.
         progress : Progress
             Progress bar instance for updating the shown progress bar.
         selected_component : str | None, optional
@@ -226,7 +226,7 @@ def sample(
         Raises
         ------
         ValueError
-            If not enough jets for a given component are present.
+            If not enough objects for a given component are present.
         """
         # Loop through input file
         for batch in stream:
@@ -245,7 +245,7 @@ def sample(
                 if len(comp_idx) == 0:
                     continue
 
-                # Get the batch of jets as a separate dict
+                # Get the batch of objects as a separate dict
                 batch_out = select_batch(batch, comp_idx)
 
                 # Apply sampling
@@ -256,19 +256,19 @@ def sample(
                 if component != self.target and self.select_func:
                     # Apply the resampling
                     idx = self.select_func(
-                        jets=batch_out[self.variables.global_name],
+                        global_objects=batch_out[self.variables.global_name],
                         component=component,
                     )
                     if len(idx) == 0:
                         continue
 
-                    # Get the resampled jets in the dict
+                    # Get the resampled objects in the dict
                     batch_out = select_batch(batch_out, idx)
 
-                # Check for completion (only when a finite num_jets is requested;
-                # num_jets < 0 means write all jets passing the cuts)
-                if 0 <= component.num_jets <= component.writer.num_written + len(idx):
-                    keep = component.num_jets - component.writer.num_written
+                # Check for completion (only when a finite num_global_objects is requested;
+                # num_global_objects < 0 means write all objects passing the cuts)
+                if 0 <= component.num_global_objects <= component.writer.num_written + len(idx):
+                    keep = component.num_global_objects - component.writer.num_written
                     idx = idx[:keep]
                     for name, array in batch_out.items():
                         batch_out[name] = array[:keep]
@@ -277,7 +277,7 @@ def sample(
                 # Track upsampling stats
                 self.track_upsampling_stats(idx=idx, component=component)
 
-                # Write the resampled jets to file
+                # Write the resampled objects to file
                 component.writer.write(batch_out)
 
                 # Update the progress bar
@@ -291,17 +291,17 @@ def sample(
             if all(component._complete for component in components):
                 break
 
-        # Finalise components: unbounded ones (num_jets < 0) are done once the input is
-        # exhausted; bounded ones that didn't reach their target ran out of jets.
+        # Finalise components: unbounded ones (num_global_objects < 0) are done once the input is
+        # exhausted; bounded ones that didn't reach their target ran out of objects.
         for component in components:
             if component._complete:
                 continue
-            if component.num_jets < 0:
+            if component.num_global_objects < 0:
                 component._complete = True
                 self._finalise_component(component)
             else:
                 raise ValueError(
-                    f"Ran out of {component} jets after writing {component.writer.num_written:,}"
+                    f"Ran out of {component} objects after writing {component.writer.num_written:,}"
                 )
 
     def run_on_region(
@@ -325,7 +325,7 @@ def run_on_region(
         Raises
         ------
         ValueError
-            If the equal_jets flag is not the same for all components.
+            If the equal_global_objects flag is not the same for all components.
         """
         # Get the target component (not needed when resampling is skipped)
         if not self.skip:
@@ -337,26 +337,30 @@ def run_on_region(
         grouped_samples = components.groupby_sample()
 
         for sample, components in grouped_samples:
-            # Ensure all components have the same equal_jets flag
-            equal_jets_flags = [component.equal_jets for component in components]
-            if len(set(equal_jets_flags)) != 1:
-                raise ValueError("equal_jets must be the same for all components in a sample")
-            equal_jets_flag = equal_jets_flags[0]
+            # Ensure all components have the same equal_global_objects flag
+            equal_global_objects_flags = [
+                component.equal_global_objects for component in components
+            ]
+            if len(set(equal_global_objects_flags)) != 1:
+                raise ValueError(
+                    "equal_global_objects must be the same for all components in a sample"
+                )
+            equal_global_objects_flag = equal_global_objects_flags[0]
 
             # Get the variables which are to be used
-            variables = self.variables.add_jet_vars(components.cuts.variables)
+            variables = self.variables.add_global_vars(components.cuts.variables)
 
-            # Setup the Reader for reading the jets
+            # Setup the Reader for reading the objects
             reader = H5Reader(
                 sample.path,
                 self.batch_size,
                 jets_name=self.global_name,
-                equal_jets=equal_jets_flag,
+                equal_jets=equal_global_objects_flag,
                 transform=self.transform,
                 vds_dir=sample.vds_dir,
             )
 
-            # Define a stream of jets with the cuts for the region and the variables used
+            # Define a stream of objects with the cuts for the region and the variables used
             stream = reader.stream(variables.combined(), reader.num_jets, region.cuts)
 
             # Run with progress bar
@@ -368,12 +372,12 @@ def run_on_region(
                     if selected_component and selected_component != component.name:
                         component._complete = True
                         component._ups_max = 0.0
-                        component._unique_jets = 0
+                        component._unique_global_objects = 0
 
                     else:
                         component._complete = False
                         component._ups_max = 1.0
-                        component._unique_jets = 0
+                        component._unique_global_objects = 0
 
                 # Add each component to the progress bar
                 for component in components:
@@ -381,11 +385,11 @@ def run_on_region(
                     if selected_component and selected_component != component.name:
                         continue
 
-                    unbounded = component.num_jets < 0
-                    label = "all" if unbounded else f"{component.num_jets:,}"
+                    unbounded = component.num_global_objects < 0
+                    label = "all" if unbounded else f"{component.num_global_objects:,}"
                     component.pbar = progress.add_task(
-                        f"[green]Sampling {label} jets from {component}...",
-                        total=None if unbounded else component.num_jets,
+                        f"[green]Sampling {label} objects from {component}...",
+                        total=None if unbounded else component.num_global_objects,
                     )
 
                 # Run the actual resampling sampling
@@ -406,8 +410,8 @@ def run_on_region(
                 log.info(
                     f"{component} usampling ratio is {np.mean(component._ups_ratio):.3f}, with"
                     f" {written / np.mean(component._ups_ratio):,.0f}/"
-                    f"{written:,} written jets."
-                    f" Jets are upsampled at most {np.max(component._ups_max):.0f} times"
+                    f"{written:,} written objects."
+                    f" Objects are upsampled at most {np.max(component._ups_max):.0f} times"
                 )
 
     def set_component_sampling_fractions(self, component: Component) -> None:
@@ -441,7 +445,7 @@ def set_component_sampling_fractions(self, component: Component) -> None:
 
             else:
                 sam_frac = component.get_auto_sampling_fraction(
-                    num_jets=component.num_jets,
+                    num_global_objects=component.num_global_objects,
                     cuts=component.cuts,
                 )
 
@@ -527,15 +531,15 @@ def run(self, region: str | None = None, component: str | None = None):
             # Set sampling fraction
             self.set_component_sampling_fractions(component=iter_component)
 
-            # Check that enough jets are available
+            # Check that enough objects are available
             sampling_fraction = 1 if self.skip else self.config.sampling_fraction
             log.info(
-                "[bold green]Checking requested num_jets based on a sampling fraction of"
+                "[bold green]Checking requested num_global_objects based on a sampling fraction of"
                 f" {sampling_fraction}..."
             )
             frac = iter_component.sampling_fraction if self.select_func else 1
-            iter_component.check_num_jets(
-                iter_component.num_jets,
+            iter_component.check_num_global_objects(
+                iter_component.num_global_objects,
                 sampling_fraction=frac,
                 cuts=iter_component.cuts,
             )
@@ -576,9 +580,9 @@ def run(self, region: str | None = None, component: str | None = None):
                     unique += iter_component.writer.get_attr("unique_jets")
             log.info(
                 f"[bold green]Finished resampling of region {region}. "
-                f"A total of {self.components.num_jets:,} jets!"
+                f"A total of {self.components.num_global_objects:,} objects!"
             )
-            log.info(f"[bold green]Estimated unique jets: {unique:,.0f}")
+            log.info(f"[bold green]Estimated unique objects: {unique:,.0f}")
             log.info(f"[bold green]Saved to {self.components.out_dir}/")
 
         else:
@@ -586,9 +590,10 @@ def run(self, region: str | None = None, component: str | None = None):
                 iter_component.writer.get_attr("unique_jets") for iter_component in self.components
             )
             log.info(
-                f"[bold green]Finished resampling a total of {self.components.num_jets:,} jets!"
+                f"[bold green]Finished resampling a total of "
+                f"{self.components.num_global_objects:,} objects!"
             )
-            log.info(f"[bold green]Estimated unique jets: {unique:,.0f}")
+            log.info(f"[bold green]Estimated unique objects: {unique:,.0f}")
             log.info(f"[bold green]Saved to {self.components.out_dir}/")
 
     def get_num_bins_from_config(self) -> list[list[int]]:
diff --git a/upp/stages/reweight.py b/upp/stages/reweight.py
index 899c467..ee1817f 100644
--- a/upp/stages/reweight.py
+++ b/upp/stages/reweight.py
@@ -12,7 +12,7 @@
 from puma import Histogram, HistogramPlot
 
 from upp.classes.preprocessing_config import PreprocessingConfig
-from upp.stages.hist import bin_jets
+from upp.stages.hist import bin_global_objects
 
 
 class Reweight:
@@ -35,8 +35,8 @@ def hists_path(self):
         return self.config.out_dir / "histograms.h5"
 
     @property
-    def num_jets_estimate(self):
-        return self.rw_config.num_jets_estimate or self.config.num_jets_estimate
+    def num_global_objects_estimate(self):
+        return self.rw_config.num_global_objects_estimate or self.config.num_global_objects_estimate
 
     def get_input_readers(self):
         components_config = self.organised_components_config
@@ -52,20 +52,20 @@ def get_input_readers(self):
             )
             for f in files_by_flavour
         }
-        per_reader_num_jets = []
+        per_reader_num_global_objects = []
         for f, r in input_readers.items():
-            n = min(self.num_jets_estimate, r.num_jets)
-            if r.num_jets < self.num_jets_estimate:
+            n = min(self.num_global_objects_estimate, r.num_jets)
+            if r.num_jets < self.num_global_objects_estimate:
                 print(
-                    f"WARNING: Requested {self.num_jets_estimate} jets for {f}, "
+                    f"WARNING: Requested {self.num_global_objects_estimate} objects for {f}, "
                     f"but only {r.num_jets} available. Using {r.num_jets}."
                 )
             print(
-                f"Flavour {f} has {r.num_jets} jets, using {n}, "
+                f"Flavour {f} has {r.num_jets} objects, using {n}, "
                 f"reading in batches of {self.config.batch_size}"
             )
-            per_reader_num_jets.append(n)
-        return list(input_readers.values()), per_reader_num_jets
+            per_reader_num_global_objects.append(n)
+        return list(input_readers.values()), per_reader_num_global_objects
 
     def calculate_weights(
         self,
@@ -89,7 +89,7 @@ def calculate_weights(
         """
         reweights = self.rw_config.reweights
         print(f"Calculating weights for {len(reweights)} reweights")
-        readers, per_reader_num_jets = self.get_input_readers()
+        readers, per_reader_num_global_objects = self.get_input_readers()
         for reader in readers:
             assert reader.batch_size == readers[0].batch_size, (
                 "All readers must have the same batch size"
@@ -105,7 +105,7 @@ def calculate_weights(
         rw_groups = list(set([rw.group for rw in reweights]))
         print("Found rw groups : ", rw_groups)
         print("Batch size : ", batch_size_per_file)
-        print("N per file : ", self.num_jets_estimate)
+        print("N per file : ", self.num_global_objects_estimate)
 
         # Get the variables we need to reweight
         for rw in reweights:
@@ -125,11 +125,11 @@ def calculate_weights(
         print("Setting up streams with vars: ", all_vars, flush=True)
         reader_streams = [
             r.stream(all_vars, num_jets=n)
-            for r, n in zip(readers, per_reader_num_jets, strict=False)
+            for r, n in zip(readers, per_reader_num_global_objects, strict=False)
         ]
-        max_num_jets = max(per_reader_num_jets)
-        num_batches = max_num_jets // batch_size_per_file + (
-            1 if max_num_jets % batch_size_per_file != 0 else 0
+        max_num_global_objects = max(per_reader_num_global_objects)
+        num_batches = max_num_global_objects // batch_size_per_file + (
+            1 if max_num_global_objects % batch_size_per_file != 0 else 0
         )
         start_time = time.time()
         for i in range(num_batches):
@@ -175,7 +175,7 @@ def calculate_weights(
 
                 for cls in classes:
                     mask = data[rw.class_var] == cls
-                    hist, _outbins = bin_jets(data[mask][rw.reweight_vars], rw.flat_bins)
+                    hist, _outbins = bin_global_objects(data[mask][rw.reweight_vars], rw.flat_bins)
                     if rw.class_var is not None:
                         cls = str(cls)
                     if rw_group not in all_histograms:
diff --git a/upp/stages/rw_merge.py b/upp/stages/rw_merge.py
index 66e478a..a0e15fe 100644
--- a/upp/stages/rw_merge.py
+++ b/upp/stages/rw_merge.py
@@ -10,7 +10,7 @@
 from ftag.hdf5 import H5Reader, H5Writer, join_structured_arrays
 from ftag.vds import create_virtual_file
 
-from upp.stages.hist import bin_jets
+from upp.stages.hist import bin_global_objects
 
 # from ftag_rw.weights.rw_utils import get_sample_weights
 from upp.stages.reweight import Reweight
@@ -37,14 +37,14 @@ def __init__(self, config, outfile_idx_range=None):
         with open(self.organised_components_config) as f:
             organised_components = yaml.safe_load(f)
 
-        num_jets = sum(organised_components["num_jets"][self.config.split].values())
+        num_global_objects = sum(organised_components["num_jets"][self.config.split].values())
         self.attr_to_write = {
             self.config.global_name: {
                 "flavour_label": [f.name for f in self.config.components.flavours],
             },
             None: {
-                "unique_jets": num_jets,
-                "jet_counts": num_jets,
+                "unique_jets": num_global_objects,
+                "jet_counts": num_global_objects,
                 "dsids": str(self.config.components.dsids),
                 "config": json.dumps(self.config.config),
                 "upp_hash": self.config.git_hash,
@@ -57,13 +57,13 @@ def run(self):
 
         with open(self.organised_components_config) as f:
             organised_components = yaml.safe_load(f)
-        # Get the number of jets per flavour
+        # Get the number of objects per flavour
         files_by_flavour = organised_components["files"][self.config.split]
-        num_jets_per_flavours = organised_components["num_jets"][self.config.split]
+        num_global_objects_per_flavours = organised_components["num_jets"][self.config.split]
         all_files = []
         for f in files_by_flavour:
             all_files.extend(files_by_flavour[f])
-        total_jets = sum(num_jets_per_flavours.values())
+        total_global_objects = sum(num_global_objects_per_flavours.values())
 
         batch_size = 250_000
         reader_kwargs = {
@@ -74,11 +74,14 @@ def run(self):
         }
         output_dir = self.config.out_dir / self.config.split
         output_dir.mkdir(parents=True, exist_ok=True)
-        num_jets_per_file = self.config.num_jets_per_output_file or total_jets
+        num_global_objects_per_file = (
+            self.config.num_global_objects_per_output_file or total_global_objects
+        )
 
-        batches_per_file = num_jets_per_file // batch_size or 1
+        batches_per_file = num_global_objects_per_file // batch_size or 1
         num_batches = (
-            total_jets // batch_size + (1 if total_jets % num_jets_per_file != 0 else 0)
+            total_global_objects // batch_size
+            + (1 if total_global_objects % num_global_objects_per_file != 0 else 0)
         ) or 1
 
         variables = self.config.variables.combined() if self.config.split != "test" else None
@@ -91,7 +94,7 @@ def run(self):
                     reader_kwargs,
                     output_dir / f"pp_output_{self.config.split}-full_{i}.h5",
                     weights,
-                    num_jets_per_flavours,
+                    num_global_objects_per_flavours,
                     variables,
                     bi,
                     i,
@@ -166,7 +169,7 @@ def get_sample_weights(
                 rw_vars = rw["rw_vars"]
                 class_var = rw["class_var"]
 
-                _, bins = bin_jets(to_dump[rw_vars], rw["bins"])
+                _, bins = bin_global_objects(to_dump[rw_vars], rw["bins"])
                 # Enforce that bins are of shape (nvars, num_objects)
                 if len(rw["bins"]) == 1:
                     bins = np.expand_dims(bins, axis=0)
@@ -202,7 +205,7 @@ def do_merge_with_weights(
         reader_kwargs: dict[str, dict],
         output_file: str,
         weights: dict,
-        num_jets_per_flavour: dict,
+        num_global_objects_per_flavour: dict,
         variables: dict[str, list[str]] | None = None,
         skip_batches: int = 0,
         writer_id=0,
@@ -224,7 +227,7 @@ def do_merge_with_weights(
         )
         batch_size = reader.batch_size
         # reader = H5Reader(input_file)
-        # num_jets = reader.num_jets if N == -1 else N
+        # num_global_objects = reader.num_jets if N == -1 else N
         writer: H5Writer = None
         additional_vars = {}
 
@@ -241,12 +244,12 @@ def do_merge_with_weights(
         for group in dtypes:
             dtypes[group] = np.dtype(dtypes[group])
 
-        num_jets_total = sum(num_jets_per_flavour.values())
+        num_global_objects_total = sum(num_global_objects_per_flavour.values())
         if limit_batches:
             num_batches = limit_batches
         else:
-            num_batches = num_jets_total // batch_size + (
-                1 if num_jets_total % batch_size != 0 else 0
+            num_batches = num_global_objects_total // batch_size + (
+                1 if num_global_objects_total % batch_size != 0 else 0
             )
 
         print(f"Writer {writer_id} has batches: {num_batches} ", flush=True)
@@ -255,7 +258,7 @@ def do_merge_with_weights(
 
         for i, batch in enumerate(reader.stream(variables, skip_batches=skip_batches)):
             print(
-                f"Writer {writer_id} Combined batch {i} has {len(batch[global_name])} jets",
+                f"Writer {writer_id} Combined batch {i} has {len(batch[global_name])} objects",
                 flush=True,
             )
             all_sample_weights = RWMerge.get_sample_weights(batch, weights)
@@ -297,7 +300,7 @@ def do_merge_with_weights(
         print(f"Writer {writer_id} batches complete - closing writer", flush=True)
         writer.close()
         message = (
-            f"Writer {writer_id} finished writing {writer.num_written} jets in "
+            f"Writer {writer_id} finished writing {writer.num_written} objects in "
             f"{time.time() - start_time:.2f}s"
         )
         print(message, flush=True)
diff --git a/upp/stages/split_containers.py b/upp/stages/split_containers.py
index 70aa625..82ca320 100644
--- a/upp/stages/split_containers.py
+++ b/upp/stages/split_containers.py
@@ -146,15 +146,17 @@ def split_file(
         )
         if output_name is None:
             output_name = input_file.name
-        num_jets = reader.num_jets
-        num_batches = num_jets // batch_size + (1 if num_jets % batch_size != 0 else 0)
-        if num_jets == 0:
-            print(f"File {input_file} has no jets. Skipping it", flush=True)
+        num_global_objects = reader.num_jets
+        num_batches = num_global_objects // batch_size + (
+            1 if num_global_objects % batch_size != 0 else 0
+        )
+        if num_global_objects == 0:
+            print(f"File {input_file} has no objects. Skipping it", flush=True)
             return
         sample_components = []
         writers_by_sample_components = {}
         cuts_by_sample_components = {}
-        print(f"Input file: {input_file} has {num_jets} jets", flush=True)
+        print(f"Input file: {input_file} has {num_global_objects} objects", flush=True)
         print(f"Running {num_batches} batches of size {batch_size}", flush=True)
         print(f"Output directory: {output_dir}", flush=True)
 
@@ -252,7 +254,7 @@ def split_file(
         message += "\n"
         for sample_component, writer in writers_by_sample_components.items():
             perc = 100 * (num_written_by_sample_components[sample_component] / sum_written)
-            message += f"{sample_component}: {writer.num_written} jets ({perc:.2f}%)\n"
+            message += f"{sample_component}: {writer.num_written} objects ({perc:.2f}%)\n"
 
             writer.close()
 
@@ -260,9 +262,9 @@ def split_file(
         message += "-" * 20 + "\n"
         message += "Summary\n"
         message += "-" * 20 + "\n"
-        message += f"Total number of jets: {num_jets}\n"
+        message += f"Total number of objects: {num_global_objects}\n"
         message += f"Total number of batches: {num_batches}\n"
-        message += f"Total number of written jets: {sum_written}\n"
+        message += f"Total number of written objects: {sum_written}\n"
         message += f"Total time taken: {time_taken:.2f} seconds\n"
         message += "-" * 20
         print(message, flush=True)
@@ -287,7 +289,7 @@ def _make_tmp_vds(self, files: list[str] | str | Path) -> Generator[Path, None,
                 jets_name=self.config.global_name,
             )
             print(
-                f"Created combined virtual dataset with {h5vds.num_jets} jets at {tmp_out_path}",
+                f"Created combined virtual dataset with {h5vds.num_jets} objects at {tmp_out_path}",
                 flush=True,
             )
             yield tmp_out_path
@@ -373,7 +375,7 @@ def create_meta_data(self):
 
                     files[split][flavour].append(str(file[0]))
 
-        num_jets = {
+        num_global_objects = {
             split: {
                 flavour: H5Reader(files[split][flavour], jets_name=self.config.global_name).num_jets
                 for flavour in files[split]
@@ -382,7 +384,7 @@ def create_meta_data(self):
         }
         metadata = {
             "files": files,
-            "num_jets": num_jets,
+            "num_jets": num_global_objects,
         }
 
         output_file = output_dir / "organised-components.yaml"
diff --git a/upp/utils/check_input_samples.py b/upp/utils/check_input_samples.py
index fd60d3a..a80242c 100644
--- a/upp/utils/check_input_samples.py
+++ b/upp/utils/check_input_samples.py
@@ -69,7 +69,7 @@ def check_within_factor(
     Raises
     ------
     ValueError
-        If n_jets is zero for a sample
+        If n_global_objects is zero for a sample
         If the spread factor is too high
         If the geometric mean deviation is too high
     """
@@ -80,7 +80,7 @@ def check_within_factor(
         # Check that each sample is not zero
         for inner_key, inner_value in inner.items():
             if inner_value == 0:
-                raise ValueError(f"Found zero jets in group {name} / sample {inner_key}!")
+                raise ValueError(f"Found zero objects in group {name} / sample {inner_key}!")
 
         inner_values = {k: v for k, v in inner.items() if v > 0}
 
@@ -112,7 +112,7 @@ def run_input_sample_check(
     deviation_factor: float,
     verbose: bool = True,
 ) -> None:
-    """Run the input sample checks on the number of the jets.
+    """Run the input sample checks on the number of the objects.
 
     Parameters
     ----------
@@ -158,7 +158,7 @@ def run_input_sample_check(
             sample_type_dict[config_blocks] = {}
             sample_type_dict[config_blocks]["pattern"] = config.config[config_blocks]["pattern"]
 
-    # Setup H5Reader for the different samples to read the total number of jets
+    # Setup H5Reader for the different samples to read the total number of objects
     for sample_type, sample_list in sample_type_dict.items():
         # Log the status
         if verbose:
@@ -206,7 +206,7 @@ def run_input_sample_check(
             else:
                 entry_name = sample
 
-            # Create the H5 reader for each sample and read the number of jets from it
+            # Create the H5 reader for each sample and read the number of objects from it
             sample_list[entry_name] = H5Reader(
                 fname=config.ntuple_dir / sample,
                 batch_size=config.batch_size,
@@ -220,15 +220,15 @@ def run_input_sample_check(
     # Check that all the samples per group are not too different
     check_within_factor(groups=sample_type_dict, factor=deviation_factor)
 
-    # Printing the dict with all the number of jets to the terminal, if wanted
+    # Printing the dict with all the number of objects to the terminal, if wanted
     if verbose:
-        log.info("Available jets in given groups:\n")
+        log.info("Available objects in given groups:\n")
 
         for sample_type, sample_dict in sample_type_dict.items():
             log.info(f"Group: {sample_type}")
 
-            for entry_name, n_jets in sample_dict.items():
-                log.info(f"  - Sample: {entry_name}, N_Jets: {n_jets:,}")
+            for entry_name, n_global_objects in sample_dict.items():
+                log.info(f"  - Sample: {entry_name}, N_Jets: {n_global_objects:,}")
 
 
 def main(args: Any | None = None) -> None:

From 4c2675c4abd124636e831aa8ac3a22d042691252 Mon Sep 17 00:00:00 2001
From: Alexander Froch <Alexander.Froch@cern.ch>
Date: Tue, 30 Jun 2026 22:45:59 +0200
Subject: [PATCH 06/13] Update atlas-ftag-tools and puma

---
 pyproject.toml | 4 ++--
 1 file changed, 2 insertions(+), 2 deletions(-)

diff --git a/pyproject.toml b/pyproject.toml
index 7c65c07..93d975e 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -19,10 +19,10 @@ classifiers = [
 ]
 
 dependencies = [
-  "atlas-ftag-tools==0.3.3",
+  "atlas-ftag-tools==0.3.5",
   "dotmap>=1.3.30",
   "numpy>=2.2.6",
-  "puma-hep==0.5.3",
+  "puma-hep==0.5.4",
   "pyyaml-include==1.3",
   "PyYAML>=6.0.2",
   "rich>=14.1.0",

From dd6177e4f4eba5cae70c4e3aadc312ff365ee37a Mon Sep 17 00:00:00 2001
From: Alexander Froch <Alexander.Froch@cern.ch>
Date: Tue, 30 Jun 2026 23:10:09 +0200
Subject: [PATCH 07/13] Remove remaining jet-named identifiers via
 atlas-ftag-tools 0.3.5

Align with the object-agnostic ftag H5Reader/H5Writer API and rename the
remaining jet-named touchpoints: ftag kwargs/attributes (jets_name,
num_jets, equal_jets, estimate_available_jets) and the output h5 metadata
attribute strings (num_jets, unique_jets, jet_counts) to their
global_object equivalents.
---
 changelog.md                                 |  2 +-
 tests/integration/test_run.py                | 12 ++++-----
 tests/integration/test_run_rw.py             |  8 +++---
 tests/unit/stages/test_merging.py            | 26 ++++++++++----------
 tests/unit/stages/test_plotting.py           | 10 +++++---
 tests/unit/stages/test_reweight.py           | 16 ++++++------
 tests/unit/utils/test_check_input_samples.py |  8 +++---
 upp/classes/components.py                    | 24 +++++++++---------
 upp/grid/download_and_prepare.py             |  6 ++---
 upp/stages/hist.py                           |  2 +-
 upp/stages/merging.py                        | 20 +++++++--------
 upp/stages/normalisation.py                  |  2 +-
 upp/stages/plot.py                           |  6 ++---
 upp/stages/resampling.py                     | 13 +++++-----
 upp/stages/reweight.py                       | 12 ++++-----
 upp/stages/rw_merge.py                       | 18 ++++++++------
 upp/stages/split_containers.py               | 22 +++++++++++------
 upp/utils/check_input_samples.py             |  4 +--
 18 files changed, 113 insertions(+), 98 deletions(-)

diff --git a/changelog.md b/changelog.md
index 27e09e8..0eceae3 100644
--- a/changelog.md
+++ b/changelog.md
@@ -2,7 +2,7 @@
 
 ### [Latest]
 
-- Generalise the framework beyond jets: honour the configured global object name in all stages, and rename every jet-named config option and code identifier to object-agnostic `global_object` names (e.g. `jets_name`→`global_name`, `num_jets`→`num_global_objects`, `equal_jets`→`equal_global_objects`). Old configs keep working — deprecated keys are remapped automatically on load with a warning [#156](https://github.com/umami-hep/umami-preprocessing/pull/156)
+- Generalise the framework beyond jets to arbitrary global objects [#156](https://github.com/umami-hep/umami-preprocessing/pull/156)
 
 ### [v0.3.1](https://github.com/umami-hep/umami-preprocessing/releases/tag/v0.3.1) (19.06.2026)
 
diff --git a/tests/integration/test_run.py b/tests/integration/test_run.py
index d86a1d6..b40e458 100644
--- a/tests/integration/test_run.py
+++ b/tests/integration/test_run.py
@@ -119,14 +119,14 @@ def test_run_no_resample(self):
         assert os.path.exists(fname)
         with h5py.File(fname, "r") as f:
             jets = f["jets"][:]
-            jet_counts = json.loads(f.attrs["jet_counts"])
+            global_object_counts = json.loads(f.attrs["global_object_counts"])
             assert f.attrs["resampling_method"] == "none"
 
-        # capped components write exactly num_jets; the -1 component writes all its jets
-        assert jet_counts["lowpt_ttbar_bjets"]["num_jets"] == 1_000
-        assert jet_counts["lowpt_ttbar_cjets"]["num_jets"] == 1_000
-        assert jet_counts["lowpt_ttbar_ujets"]["num_jets"] > 1_000
-        assert jet_counts["total"]["num_jets"] == len(jets)
+        # capped components write exactly num_global_objects; -1 writes all its objects
+        assert global_object_counts["lowpt_ttbar_bjets"]["num_global_objects"] == 1_000
+        assert global_object_counts["lowpt_ttbar_cjets"]["num_global_objects"] == 1_000
+        assert global_object_counts["lowpt_ttbar_ujets"]["num_global_objects"] > 1_000
+        assert global_object_counts["total"]["num_global_objects"] == len(jets)
 
     def test_run_method_none(self):
         args = [
diff --git a/tests/integration/test_run_rw.py b/tests/integration/test_run_rw.py
index 44ff733..5981dfb 100644
--- a/tests/integration/test_run_rw.py
+++ b/tests/integration/test_run_rw.py
@@ -168,15 +168,15 @@ def test_rw_custom_object_name(self):
                 assert "flavour_label" in f["objects"].attrs
                 assert "flavour_label" in f["objects"].dtype.names
 
-    def test_rw_unequal_jets(self):
-        """Test reweighting when a file has fewer jets than num_jets_estimate.
+    def test_rw_unequal_objects(self):
+        """Test reweighting when a file has fewer objects than num_global_objects_estimate.
 
         Previously this would crash with an assertion error. After the fix,
-        get_input_readers() caps per-reader jet counts at available jets and
+        get_input_readers() caps per-reader object counts at available objects and
         the batch loop handles StopIteration from shorter readers.
         """
         # Overwrite data1.h5 with a smaller mock — after per-flavour splitting
-        # some flavour files will have fewer jets than num_jets_estimate
+        # some flavour files will have fewer objects than num_global_objects_estimate
         self.generate_mock("tmp/upp-tests/integration/temp_workspace/ntuples/data1.h5", N=500)
         self._run_split()
         self._calculate_weights()
diff --git a/tests/unit/stages/test_merging.py b/tests/unit/stages/test_merging.py
index 843e745..4ec6864 100644
--- a/tests/unit/stages/test_merging.py
+++ b/tests/unit/stages/test_merging.py
@@ -22,21 +22,21 @@
 
 # Stub H5Writer that just records calls, does NO real IO
 class MemWriter:
-    def __init__(self, dst, dtypes, shapes, jets_name, **_):
+    def __init__(self, dst, dtypes, shapes, global_objects_name, **_):
         self.dst = Path(dst)
         self.dtypes = dtypes
         self.shapes = shapes
-        self.num_jets = next(iter(shapes.values()))[0]
-        self.jets_name = jets_name
+        self.num_global_objects = next(iter(shapes.values()))[0]
+        self.global_objects_name = global_objects_name
         self.num_written = 0
         self.attrs = {}
 
     # API that Merging calls
     def write(self, data: dict):
-        self.num_written += len(data[self.jets_name])
+        self.num_written += len(data[self.global_objects_name])
 
     def close(self):
-        assert self.num_written == self.num_jets
+        assert self.num_written == self.num_global_objects
 
     def add_attr(self, name, value, *_):
         self.attrs[name] = value
@@ -153,7 +153,7 @@ def test_open_writer_names_and_shapes(monkeypatch):
 
     writer = merge.writer
     assert isinstance(writer, MemWriter)
-    assert writer.num_jets == 7
+    assert writer.num_global_objects == 7
     assert writer.dst.name.startswith("merged_split_000")
     assert writer.dst.parent.name == "train"
     assert "flavour_label" in writer.attrs
@@ -261,9 +261,9 @@ def test_write_chunk_returns_zero_when_no_space_left(monkeypatch):
     merge.dtypes = {"jets": jets_batch["jets"].dtype}
     merge.base_shapes = {"jets": (4,)}
 
-    # Open a writer that is already full (num_written == num_jets)
+    # Open a writer that is already full (num_written == num_global_objects)
     merge._open_writer(None, 4, 0, merge.current_components)
-    merge.writer.num_written = merge.writer.num_jets
+    merge.writer.num_written = merge.writer.num_global_objects
 
     n_written = merge.write_chunk(comps)
 
@@ -272,7 +272,7 @@ def test_write_chunk_returns_zero_when_no_space_left(monkeypatch):
 
     # _file_idx is incremented once, but _open_writer was not called again
     assert merge._file_idx == 1
-    assert merge.writer.num_written == merge.writer.num_jets
+    assert merge.writer.num_written == merge.writer.num_global_objects
 
 
 class ReaderStub:
@@ -280,7 +280,7 @@ class ReaderStub:
 
     def __init__(self, batches: list[dict[str, np.ndarray]]):
         self._batches = batches
-        self.num_jets = sum(len(b["jets"]) for b in batches)
+        self.num_global_objects = sum(len(b["jets"]) for b in batches)
 
     def dtypes(self, _vars):
         # Assume at least one batch exists
@@ -290,7 +290,7 @@ def shapes(self, total_global_objects: int, _keys):
         # Base-shapes are used only for dataset names and leading dim
         return {"jets": (total_global_objects,)}
 
-    def stream(self, _vars, _num_jets):
+    def stream(self, _vars, _num_global_objects):
         def _gen():
             yield from self._batches
 
@@ -589,7 +589,7 @@ def _wrapped_open(self, sample, global_objects_in_file, file_idx, components):
 
     # The MemWriter should have written exactly 3 jets in that last file
     assert isinstance(merge.writer, MemWriter)
-    assert merge.writer.num_jets == 3
+    assert merge.writer.num_global_objects == 3
     assert merge.writer.num_written == 3
 
 
@@ -680,7 +680,7 @@ def test_write_components_single_file_mode(monkeypatch, tmp_path):
     merge.write_components(sample=None, components=comps)
 
     assert isinstance(merge.writer, MemWriter)
-    assert merge.writer.num_jets == 7
+    assert merge.writer.num_global_objects == 7
     assert merge.writer.num_written == 7
     assert merge.writer.dst.name == "merged.h5"
 
diff --git a/tests/unit/stages/test_plotting.py b/tests/unit/stages/test_plotting.py
index 6261d66..37f83e4 100644
--- a/tests/unit/stages/test_plotting.py
+++ b/tests/unit/stages/test_plotting.py
@@ -38,9 +38,9 @@ def setup_method(self, method):
             "test": H5Reader(
                 fname=self.fname1,
                 batch_size=self.config.batch_size,
-                jets_name=self.config.global_name,
+                global_objects_name=self.config.global_name,
                 shuffle=False,
-                equal_jets=True,
+                equal_global_objects=True,
             ).load(
                 {
                     self.config.global_name: [
@@ -169,7 +169,11 @@ def test_make_hist_adds_sample_linestyle_legend(monkeypatch, tmp_path):
     fname, file = get_mock_file(num_jets=100, fname=tmp_path / "sample.h5")
     file.close()
     values = H5Reader(
-        fname=fname, batch_size=100, jets_name="jets", shuffle=False, equal_jets=True
+        fname=fname,
+        batch_size=100,
+        global_objects_name="jets",
+        shuffle=False,
+        equal_global_objects=True,
     ).load({"jets": ["pt", "HadronConeExclTruthLabelID"]})["jets"]
     calls = []
     monkeypatch.setattr(
diff --git a/tests/unit/stages/test_reweight.py b/tests/unit/stages/test_reweight.py
index 8d1b9f3..3762248 100644
--- a/tests/unit/stages/test_reweight.py
+++ b/tests/unit/stages/test_reweight.py
@@ -25,7 +25,7 @@ def _make_organised_components(tmpdir, jets_per_flavour):
             f.create_dataset("jets", data=data)
         files[flav] = [str(fpath)]
 
-    config = {"files": {"train": files}, "num_jets": {"train": jets_per_flavour}}
+    config = {"files": {"train": files}, "num_global_objects": {"train": jets_per_flavour}}
     config_path = tmpdir / "organised-components.yaml"
     with open(config_path, "w") as f:
         yaml.dump(config, f)
@@ -61,13 +61,13 @@ def test_caps_at_available_jets(self, tmp_path):
             jets_per_flavour={"bjets": 50, "cjets": 200},
             num_global_objects_estimate=100,
         )
-        readers, per_reader_num_jets = rw.get_input_readers()
+        readers, per_reader_num_global_objects = rw.get_input_readers()
         assert len(readers) == 2
-        assert len(per_reader_num_jets) == 2
+        assert len(per_reader_num_global_objects) == 2
         # bjets has 50 < 100, should be capped at 50
-        assert per_reader_num_jets[0] == 50
+        assert per_reader_num_global_objects[0] == 50
         # cjets has 200 >= 100, should use estimate
-        assert per_reader_num_jets[1] == 100
+        assert per_reader_num_global_objects[1] == 100
 
     def test_all_above_estimate(self, tmp_path):
         """When all readers have enough jets, use num_global_objects_estimate for all."""
@@ -76,15 +76,15 @@ def test_all_above_estimate(self, tmp_path):
             jets_per_flavour={"bjets": 500, "cjets": 300},
             num_global_objects_estimate=100,
         )
-        _, per_reader_num_jets = rw.get_input_readers()
-        assert per_reader_num_jets == [100, 100]
+        _, per_reader_num_global_objects = rw.get_input_readers()
+        assert per_reader_num_global_objects == [100, 100]
 
 
 class TestCalculateWeightsStopIteration:
     """Test that the batch loop handles StopIteration from shorter readers."""
 
     def test_unequal_reader_lengths(self, tmp_path):
-        """Readers with different num_jets don't crash the batch loop."""
+        """Readers with different num_global_objects don't crash the batch loop."""
         rw = _make_reweight_obj(
             tmp_path,
             jets_per_flavour={"bjets": 50, "cjets": 200},
diff --git a/tests/unit/utils/test_check_input_samples.py b/tests/unit/utils/test_check_input_samples.py
index 9d858eb..ebc6b9c 100644
--- a/tests/unit/utils/test_check_input_samples.py
+++ b/tests/unit/utils/test_check_input_samples.py
@@ -35,7 +35,7 @@ def error(self, *_a, **_k):
     # H5Reader stub: we don't care about values here, just that it's called
     class _H5:
         def __init__(self, **_kwargs):
-            self.num_jets = 123
+            self.num_global_objects = 123
 
     monkeypatch.setattr(cis, "H5Reader", _H5)
 
@@ -160,7 +160,7 @@ def error(self, *_a, **_k):
     # H5Reader stub
     class _H5:
         def __init__(self, **_kwargs):
-            self.num_jets = 10
+            self.num_global_objects = 10
 
     monkeypatch.setattr(cis, "H5Reader", _H5)
 
@@ -205,7 +205,7 @@ def error(self, *_a, **_k):
 
     class _H5:
         def __init__(self, **_kwargs):
-            self.num_jets = 10
+            self.num_global_objects = 10
 
     monkeypatch.setattr(cis, "H5Reader", _H5)
 
@@ -247,7 +247,7 @@ def test_script_entry_point_executes_main(tmp_path):
 
     class _H5:
         def __init__(self, **_kwargs):
-            self.num_jets = 1
+            self.num_global_objects = 1
 
     fake_hdf5.H5Reader = _H5
 
diff --git a/upp/classes/components.py b/upp/classes/components.py
index c11830e..69e5ef3 100644
--- a/upp/classes/components.py
+++ b/upp/classes/components.py
@@ -92,8 +92,8 @@ def setup_reader(
         self.reader = H5Reader(
             fname=fname,
             batch_size=batch_size,
-            jets_name=global_name,
-            equal_jets=self.equal_global_objects,
+            global_objects_name=global_name,
+            equal_global_objects=self.equal_global_objects,
             **kwargs,
         )
         log.debug(f"Setup component reader at: {fname}")
@@ -111,7 +111,7 @@ def setup_writer(self, variables: VariableConfig, global_name: str = "jets") ->
         dtypes = self.reader.dtypes(variables.combined())
         # num_global_objects == -1 ("write all") -> 0 leading dim so the writer grows dynamically
         shapes = self.reader.shapes(max(self.num_global_objects, 0), variables.keys())
-        self.writer = H5Writer(self.out_path, dtypes, shapes, jets_name=global_name)
+        self.writer = H5Writer(self.out_path, dtypes, shapes, global_objects_name=global_name)
         log.debug(f"Setup component writer at: {self.out_path}")
 
     @property
@@ -181,7 +181,7 @@ def get_global_objects(
         dict
             Dict with the loaded objects
         """
-        jn = self.reader.jets_name
+        jn = self.reader.global_objects_name
         return self.reader.load({jn: variables}, num_global_objects, cuts)[jn]
 
     def check_num_global_objects(
@@ -225,7 +225,7 @@ def check_num_global_objects(
             if self.num_global_objects_estimate_available <= 0
             else self.num_global_objects_estimate_available
         )
-        total = self.reader.estimate_available_jets(cuts, num_est)
+        total = self.reader.estimate_available_global_objects(cuts, num_est)
         available = total
         if sampling_fraction:
             available = int(total * sampling_fraction)
@@ -243,7 +243,7 @@ def check_num_global_objects(
             log.debug(f"Sampling fraction {sampling_fraction}")
             log.info(
                 f"Estimated {available:,} {self} objects available - {num_req:,} requested"
-                f"({self.reader.num_jets:,} in {self.sample})"
+                f"({self.reader.num_global_objects:,} in {self.sample})"
             )
 
     def get_auto_sampling_fraction(
@@ -273,7 +273,7 @@ def get_auto_sampling_fraction(
             if self.num_global_objects_estimate_available <= 0
             else self.num_global_objects_estimate_available
         )
-        total = self.reader.estimate_available_jets(cuts, num_est)
+        total = self.reader.estimate_available_global_objects(cuts, num_est)
         auto_sampling_frac = round(1.1 * num_global_objects / total, 3)  # 1.1 is a tolerance factor
         if not silent:
             log.debug(f"optimal sampling fraction {auto_sampling_frac:.3f}")
@@ -300,7 +300,7 @@ def unique_global_objects(self) -> int:
         """
         if self._unique_global_objects == -1:
             self._unique_global_objects = sum(
-                [r.get_attr("unique_jets") for r in self.reader.readers]
+                [r.get_attr("unique_global_objects") for r in self.reader.readers]
             )
 
         return self._unique_global_objects
@@ -490,14 +490,14 @@ def out_dir(self):
     def global_object_counts(self):
         num_dict = {
             c.name: {
-                "num_jets": int(c.num_global_objects),
-                "unique_jets": int(c.unique_global_objects),
+                "num_global_objects": int(c.num_global_objects),
+                "unique_global_objects": int(c.unique_global_objects),
             }
             for c in self
         }
         num_dict["total"] = {
-            "num_jets": int(self.num_global_objects),
-            "unique_jets": int(self.unique_global_objects),
+            "num_global_objects": int(self.num_global_objects),
+            "unique_global_objects": int(self.unique_global_objects),
         }
         return num_dict
 
diff --git a/upp/grid/download_and_prepare.py b/upp/grid/download_and_prepare.py
index 79a7bff..9b116e5 100644
--- a/upp/grid/download_and_prepare.py
+++ b/upp/grid/download_and_prepare.py
@@ -134,8 +134,8 @@ def create_meta_data(
         split: {
             flavour: H5Reader(
                 files_by_component[split][flavour],
-                jets_name=pp_config.global_name,
-            ).num_jets
+                global_objects_name=pp_config.global_name,
+            ).num_global_objects
             for flavour in files_by_component[split]
         }
         for split in files_by_component
@@ -145,7 +145,7 @@ def create_meta_data(
         yaml.dump(
             {
                 "files": files_by_component,
-                "num_jets": num_global_objects,
+                "num_global_objects": num_global_objects,
             },
             f,
             default_flow_style=False,
diff --git a/upp/stages/hist.py b/upp/stages/hist.py
index f49a440..765cd88 100644
--- a/upp/stages/hist.py
+++ b/upp/stages/hist.py
@@ -94,7 +94,7 @@ def write_hist(
         with h5py.File(self.path, "w") as f:
             f.create_dataset("pbin", data=pbin)
             f.create_dataset("hist", data=hist)
-            f.attrs.create("num_jets", len(global_objects))
+            f.attrs.create("num_global_objects", len(global_objects))
             f.attrs.create("resampling_vars", resampling_vars)
             for i, v in enumerate(resampling_vars):
                 f.attrs.create(f"bins_{v}", bins[i])
diff --git a/upp/stages/merging.py b/upp/stages/merging.py
index 8ccf44c..9244d91 100644
--- a/upp/stages/merging.py
+++ b/upp/stages/merging.py
@@ -272,7 +272,7 @@ class _NullWriter:
 
         def __init__(self, capacity: int):
             # Mirrors the ftag H5Writer API (assigned to self.writer)
-            self.num_jets = capacity
+            self.num_global_objects = capacity
             self.num_written = 0
 
         def write(self, batch: dict[str, np.ndarray]) -> None:
@@ -288,7 +288,7 @@ def write(self, batch: dict[str, np.ndarray]) -> None:
                 return
             any_arr = next(iter(batch.values()))
             k = len(any_arr)
-            self.num_written = min(self.num_written + k, self.num_jets)
+            self.num_written = min(self.num_written + k, self.num_global_objects)
 
         def add_attr(self, *args, **kwargs):
             """Skip the attribute addition."""
@@ -340,8 +340,8 @@ def _open_writer(
             self.dtypes,
             shapes,
             add_flavour_label=self.global_name,
-            jets_name=self.global_name,
-            num_jets=global_objects_in_file,
+            global_objects_name=self.global_name,
+            num_global_objects=global_objects_in_file,
         )
 
         # Copy the metadata attributes
@@ -350,8 +350,8 @@ def _open_writer(
             [f.name for f in self.flavours],
             self.global_name,
         )
-        self.writer.add_attr("unique_jets", components.unique_global_objects)
-        self.writer.add_attr("jet_counts", json.dumps(components.global_object_counts))
+        self.writer.add_attr("unique_global_objects", components.unique_global_objects)
+        self.writer.add_attr("global_object_counts", json.dumps(components.global_object_counts))
         self.writer.add_attr("dsids", str(components.dsids))
         self.writer.add_attr("config", json.dumps(self.config.config))
         self.writer.add_attr("upp_hash", self.config.git_hash)
@@ -422,7 +422,7 @@ def write_chunk(self, components: Components) -> int:
         # Get the total length of objects from the batch and how much
         # capacity is left in the file
         merged_len = len(merged[self.global_name])
-        capacity_left = self.writer.num_jets - self.writer.num_written
+        capacity_left = self.writer.num_global_objects - self.writer.num_written
 
         if self._fast_forwarding:
             # Limit consumption to the remaining discard quota
@@ -464,7 +464,7 @@ def write_chunk(self, components: Components) -> int:
             )
 
             # Recompute free space in the freshly-opened file
-            capacity_left = self.writer.num_jets - self.writer.num_written
+            capacity_left = self.writer.num_global_objects - self.writer.num_written
 
         # Write (or discard) the batch
         if merged_len <= capacity_left or self._fast_forwarding:
@@ -519,7 +519,7 @@ def write_components(self, sample: str | None, components: Components) -> None:
                 component.setup_reader(
                     self.batch_size, fname=component.out_path, global_name=self.global_name
                 )
-                component.num_global_objects = component.reader.num_jets
+                component.num_global_objects = component.reader.num_global_objects
 
         # Prepare every Component's reader
         for component in components:
@@ -533,7 +533,7 @@ def write_components(self, sample: str | None, components: Components) -> None:
             )
             component.stream = component.reader.stream(
                 self.variables.combined(),
-                component.reader.num_jets,
+                component.reader.num_global_objects,
             )
             component.complete = False
 
diff --git a/upp/stages/normalisation.py b/upp/stages/normalisation.py
index 0e7812b..c2bc361 100644
--- a/upp/stages/normalisation.py
+++ b/upp/stages/normalisation.py
@@ -252,7 +252,7 @@ def run(self):
             fname,
             self.config.batch_size,
             precision="full",
-            jets_name=self.global_name,
+            global_objects_name=self.global_name,
         )
         log.debug(f"Setup reader at: {fname}")
 
diff --git a/upp/stages/plot.py b/upp/stages/plot.py
index ed6a45a..2678976 100644
--- a/upp/stages/plot.py
+++ b/upp/stages/plot.py
@@ -440,13 +440,13 @@ def _load_global_objects(
     return H5Reader(
         fname=in_paths,
         batch_size=config.batch_size,
-        jets_name=config.global_name,
+        global_objects_name=config.global_name,
         shuffle=False,
-        equal_jets=True,
+        equal_global_objects=True,
         vds_dir=config.vds_dir,
     ).load(
         {config.global_name: list(dict.fromkeys(vars_to_load))},
-        num_jets=config.plotting.num_global_objects_plotting,
+        num_global_objects=config.plotting.num_global_objects_plotting,
     )[config.global_name]
 
 
diff --git a/upp/stages/resampling.py b/upp/stages/resampling.py
index 389ee03..c118254 100644
--- a/upp/stages/resampling.py
+++ b/upp/stages/resampling.py
@@ -198,7 +198,7 @@ def _finalise_component(self, component: Component) -> None:
         unique = component._unique_global_objects
         component._ups_ratio = component.writer.num_written / unique if unique else 0.0
         component.writer.add_attr("upsampling_ratio", component._ups_ratio)
-        component.writer.add_attr("unique_jets", component._unique_global_objects)
+        component.writer.add_attr("unique_global_objects", component._unique_global_objects)
         component.writer.add_attr("dsid", str(component.sample.dsid))
         component.writer.close()
 
@@ -354,14 +354,14 @@ def run_on_region(
             reader = H5Reader(
                 sample.path,
                 self.batch_size,
-                jets_name=self.global_name,
-                equal_jets=equal_global_objects_flag,
+                global_objects_name=self.global_name,
+                equal_global_objects=equal_global_objects_flag,
                 transform=self.transform,
                 vds_dir=sample.vds_dir,
             )
 
             # Define a stream of objects with the cuts for the region and the variables used
-            stream = reader.stream(variables.combined(), reader.num_jets, region.cuts)
+            stream = reader.stream(variables.combined(), reader.num_global_objects, region.cuts)
 
             # Run with progress bar
             with ProgressBar() as progress:
@@ -577,7 +577,7 @@ def run(self, region: str | None = None, component: str | None = None):
                     # If a component is given, skip all components that are not selected
                     if component and iter_component.name != component:
                         continue
-                    unique += iter_component.writer.get_attr("unique_jets")
+                    unique += iter_component.writer.get_attr("unique_global_objects")
             log.info(
                 f"[bold green]Finished resampling of region {region}. "
                 f"A total of {self.components.num_global_objects:,} objects!"
@@ -587,7 +587,8 @@ def run(self, region: str | None = None, component: str | None = None):
 
         else:
             unique = sum(
-                iter_component.writer.get_attr("unique_jets") for iter_component in self.components
+                iter_component.writer.get_attr("unique_global_objects")
+                for iter_component in self.components
             )
             log.info(
                 f"[bold green]Finished resampling a total of "
diff --git a/upp/stages/reweight.py b/upp/stages/reweight.py
index ee1817f..bd266ff 100644
--- a/upp/stages/reweight.py
+++ b/upp/stages/reweight.py
@@ -48,20 +48,20 @@ def get_input_readers(self):
             f: H5Reader(
                 files_by_flavour[f],
                 batch_size=self.config.batch_size,
-                jets_name=self.config.global_name,
+                global_objects_name=self.config.global_name,
             )
             for f in files_by_flavour
         }
         per_reader_num_global_objects = []
         for f, r in input_readers.items():
-            n = min(self.num_global_objects_estimate, r.num_jets)
-            if r.num_jets < self.num_global_objects_estimate:
+            n = min(self.num_global_objects_estimate, r.num_global_objects)
+            if r.num_global_objects < self.num_global_objects_estimate:
                 print(
                     f"WARNING: Requested {self.num_global_objects_estimate} objects for {f}, "
-                    f"but only {r.num_jets} available. Using {r.num_jets}."
+                    f"but only {r.num_global_objects} available. Using {r.num_global_objects}."
                 )
             print(
-                f"Flavour {f} has {r.num_jets} objects, using {n}, "
+                f"Flavour {f} has {r.num_global_objects} objects, using {n}, "
                 f"reading in batches of {self.config.batch_size}"
             )
             per_reader_num_global_objects.append(n)
@@ -124,7 +124,7 @@ def calculate_weights(
         all_histograms = {}
         print("Setting up streams with vars: ", all_vars, flush=True)
         reader_streams = [
-            r.stream(all_vars, num_jets=n)
+            r.stream(all_vars, num_global_objects=n)
             for r, n in zip(readers, per_reader_num_global_objects, strict=False)
         ]
         max_num_global_objects = max(per_reader_num_global_objects)
diff --git a/upp/stages/rw_merge.py b/upp/stages/rw_merge.py
index a0e15fe..0f54c19 100644
--- a/upp/stages/rw_merge.py
+++ b/upp/stages/rw_merge.py
@@ -37,14 +37,16 @@ def __init__(self, config, outfile_idx_range=None):
         with open(self.organised_components_config) as f:
             organised_components = yaml.safe_load(f)
 
-        num_global_objects = sum(organised_components["num_jets"][self.config.split].values())
+        num_global_objects = sum(
+            organised_components["num_global_objects"][self.config.split].values()
+        )
         self.attr_to_write = {
             self.config.global_name: {
                 "flavour_label": [f.name for f in self.config.components.flavours],
             },
             None: {
-                "unique_jets": num_global_objects,
-                "jet_counts": num_global_objects,
+                "unique_global_objects": num_global_objects,
+                "global_object_counts": num_global_objects,
                 "dsids": str(self.config.components.dsids),
                 "config": json.dumps(self.config.config),
                 "upp_hash": self.config.git_hash,
@@ -59,7 +61,9 @@ def run(self):
             organised_components = yaml.safe_load(f)
         # Get the number of objects per flavour
         files_by_flavour = organised_components["files"][self.config.split]
-        num_global_objects_per_flavours = organised_components["num_jets"][self.config.split]
+        num_global_objects_per_flavours = organised_components["num_global_objects"][
+            self.config.split
+        ]
         all_files = []
         for f in files_by_flavour:
             all_files.extend(files_by_flavour[f])
@@ -70,7 +74,7 @@ def run(self):
             "fname": all_files,
             "batch_size": batch_size,
             "shuffle": False,
-            "jets_name": self.config.global_name,
+            "global_objects_name": self.config.global_name,
         }
         output_dir = self.config.out_dir / self.config.split
         output_dir.mkdir(parents=True, exist_ok=True)
@@ -227,7 +231,7 @@ def do_merge_with_weights(
         )
         batch_size = reader.batch_size
         # reader = H5Reader(input_file)
-        # num_global_objects = reader.num_jets if N == -1 else N
+        # num_global_objects = reader.num_global_objects if N == -1 else N
         writer: H5Writer = None
         additional_vars = {}
 
@@ -276,7 +280,7 @@ def do_merge_with_weights(
                     shapes,
                     shuffle=True,
                     compression="gzip",
-                    jets_name=global_name,
+                    global_objects_name=global_name,
                 )
                 for group, g_attrs in attrs.items():
                     for attr, value in g_attrs.items():
diff --git a/upp/stages/split_containers.py b/upp/stages/split_containers.py
index 82ca320..988c25f 100644
--- a/upp/stages/split_containers.py
+++ b/upp/stages/split_containers.py
@@ -142,11 +142,14 @@ def split_file(
         print("parsed variables: ", parsed_variables, flush=True)
         start = time.time()
         reader = H5Reader(
-            input_file, batch_size=batch_size, shuffle=False, jets_name=self.config.global_name
+            input_file,
+            batch_size=batch_size,
+            shuffle=False,
+            global_objects_name=self.config.global_name,
         )
         if output_name is None:
             output_name = input_file.name
-        num_global_objects = reader.num_jets
+        num_global_objects = reader.num_global_objects
         num_batches = num_global_objects // batch_size + (
             1 if num_global_objects % batch_size != 0 else 0
         )
@@ -170,7 +173,7 @@ def split_file(
 
             writers_by_sample_components[split] = H5Writer.from_file(
                 input_file,
-                num_jets=None,
+                num_global_objects=None,
                 dst=output_file,
                 precision="half",
                 full_precision_vars=fp_vars,
@@ -178,7 +181,7 @@ def split_file(
                 variables=all_variables if "test" in split else parsed_variables,
                 compression="gzip",
                 add_flavour_label=add_flavour_label,
-                jets_name=global_name,
+                global_objects_name=global_name,
             )
             cuts_by_sample_components[split] = component_cuts
             print(f"Creating writer for {split} saved to {output_file}", flush=True)
@@ -286,10 +289,11 @@ def _make_tmp_vds(self, files: list[str] | str | Path) -> Generator[Path, None,
             create_virtual_file(str(tmp_dir / "*.h5"), tmp_out_path, overwrite=True)
             h5vds = H5Reader(
                 tmp_out_path,
-                jets_name=self.config.global_name,
+                global_objects_name=self.config.global_name,
             )
             print(
-                f"Created combined virtual dataset with {h5vds.num_jets} objects at {tmp_out_path}",
+                f"Created combined virtual dataset with {h5vds.num_global_objects} "
+                f"objects at {tmp_out_path}",
                 flush=True,
             )
             yield tmp_out_path
@@ -377,14 +381,16 @@ def create_meta_data(self):
 
         num_global_objects = {
             split: {
-                flavour: H5Reader(files[split][flavour], jets_name=self.config.global_name).num_jets
+                flavour: H5Reader(
+                    files[split][flavour], global_objects_name=self.config.global_name
+                ).num_global_objects
                 for flavour in files[split]
             }
             for split in files
         }
         metadata = {
             "files": files,
-            "num_jets": num_global_objects,
+            "num_global_objects": num_global_objects,
         }
 
         output_file = output_dir / "organised-components.yaml"
diff --git a/upp/utils/check_input_samples.py b/upp/utils/check_input_samples.py
index a80242c..d534df3 100644
--- a/upp/utils/check_input_samples.py
+++ b/upp/utils/check_input_samples.py
@@ -210,9 +210,9 @@ def run_input_sample_check(
             sample_list[entry_name] = H5Reader(
                 fname=config.ntuple_dir / sample,
                 batch_size=config.batch_size,
-                jets_name=config.global_name,
+                global_objects_name=config.global_name,
                 vds_dir=config.vds_dir,
-            ).num_jets
+            ).num_global_objects
 
         # Drop the pattern
         del sample_list["pattern"]

From 9b50c48ff0149ac9603587524650fe8defd9e461 Mon Sep 17 00:00:00 2001
From: Alexander Froch <Alexander.Froch@cern.ch>
Date: Tue, 30 Jun 2026 23:15:05 +0200
Subject: [PATCH 08/13] Keep default Jet plot labels and rename N_Jets log
 label

Restore the jet-flavoured default variable labels in _default_variable_labels
(pt/eta/mass), and rename the remaining N_Jets sample-check log label to
N_Objects.
---
 tests/unit/classes/test_plotting_config.py      | 4 ++--
 tests/unit/classes/test_preprocessing_config.py | 2 +-
 upp/classes/plotting_config.py                  | 6 +++---
 upp/utils/check_input_samples.py                | 2 +-
 4 files changed, 7 insertions(+), 7 deletions(-)

diff --git a/tests/unit/classes/test_plotting_config.py b/tests/unit/classes/test_plotting_config.py
index 464bf96..1e642a0 100644
--- a/tests/unit/classes/test_plotting_config.py
+++ b/tests/unit/classes/test_plotting_config.py
@@ -18,11 +18,11 @@ def test_plotting_config_labels():
 
 
 def test_plotting_config_default_pt_label():
-    assert PlottingConfig().variable_label("pt_btagJes") == "Object $p_\\mathrm{T}$ [GeV]"
+    assert PlottingConfig().variable_label("pt_btagJes") == "Jet $p_\\mathrm{T}$ [GeV]"
 
 
 def test_plotting_config_default_mass_label():
-    assert PlottingConfig().variable_label("mass") == "Object Mass [GeV]"
+    assert PlottingConfig().variable_label("mass") == "Jet Mass [GeV]"
 
 
 @pytest.mark.parametrize(
diff --git a/tests/unit/classes/test_preprocessing_config.py b/tests/unit/classes/test_preprocessing_config.py
index b1ae143..638107c 100644
--- a/tests/unit/classes/test_preprocessing_config.py
+++ b/tests/unit/classes/test_preprocessing_config.py
@@ -92,7 +92,7 @@ def test_plotting_config(self) -> None:
 
         self.assertEqual(config.plotting.num_global_objects_plotting, 100)
         self.assertEqual(config.plotting.variable_label("pt"), "$p_\\mathrm{T}$ [GeV]")
-        self.assertEqual(config.plotting.variable_label("mass"), "Object Mass [GeV]")
+        self.assertEqual(config.plotting.variable_label("mass"), "Jet Mass [GeV]")
         self.assertEqual(config.plotting.sample_label("ttbar"), "$t\\bar{t}$")
         self.assertEqual(config.plotting.output_formats, ["png"])
 
diff --git a/upp/classes/plotting_config.py b/upp/classes/plotting_config.py
index e1f61fb..28022e3 100644
--- a/upp/classes/plotting_config.py
+++ b/upp/classes/plotting_config.py
@@ -5,9 +5,9 @@
 
 def _default_variable_labels() -> dict[str, str]:
     return {
-        "pt": "Object $p_\\mathrm{T}$ [GeV]",
-        "eta": "Object $|\\eta|$",
-        "mass": "Object Mass [GeV]",
+        "pt": "Jet $p_\\mathrm{T}$ [GeV]",
+        "eta": "Jet $|\\eta|$",
+        "mass": "Jet Mass [GeV]",
     }
 
 
diff --git a/upp/utils/check_input_samples.py b/upp/utils/check_input_samples.py
index d534df3..b60fa98 100644
--- a/upp/utils/check_input_samples.py
+++ b/upp/utils/check_input_samples.py
@@ -228,7 +228,7 @@ def run_input_sample_check(
             log.info(f"Group: {sample_type}")
 
             for entry_name, n_global_objects in sample_dict.items():
-                log.info(f"  - Sample: {entry_name}, N_Jets: {n_global_objects:,}")
+                log.info(f"  - Sample: {entry_name}, N_Objects: {n_global_objects:,}")
 
 
 def main(args: Any | None = None) -> None:

From 864d6d0996ab8854bc1fbab33f1fc4ac906254e4 Mon Sep 17 00:00:00 2001
From: Alexander Froch <Alexander.Froch@cern.ch>
Date: Tue, 30 Jun 2026 23:33:31 +0200
Subject: [PATCH 09/13] Name output metadata attributes after the configured
 global object

Derive the output h5 metadata attribute names from global_name instead of
hardcoding them, so a config with global_name=jets again writes unique_jets /
num_jets / jets_counts (restoring backward compatibility for jet datasets),
while a custom name yields unique_<name> / num_<name> / <name>_counts.
---
 tests/integration/test_run.py     | 12 ++++++------
 tests/unit/stages/test_merging.py | 16 ++++++++++------
 upp/classes/components.py         | 28 +++++++++++++++++++---------
 upp/stages/hist.py                |  6 +++++-
 upp/stages/merging.py             |  7 +++++--
 upp/stages/resampling.py          |  6 +++---
 upp/stages/rw_merge.py            |  4 ++--
 7 files changed, 50 insertions(+), 29 deletions(-)

diff --git a/tests/integration/test_run.py b/tests/integration/test_run.py
index b40e458..64e4a16 100644
--- a/tests/integration/test_run.py
+++ b/tests/integration/test_run.py
@@ -119,14 +119,14 @@ def test_run_no_resample(self):
         assert os.path.exists(fname)
         with h5py.File(fname, "r") as f:
             jets = f["jets"][:]
-            global_object_counts = json.loads(f.attrs["global_object_counts"])
+            jets_counts = json.loads(f.attrs["jets_counts"])
             assert f.attrs["resampling_method"] == "none"
 
-        # capped components write exactly num_global_objects; -1 writes all its objects
-        assert global_object_counts["lowpt_ttbar_bjets"]["num_global_objects"] == 1_000
-        assert global_object_counts["lowpt_ttbar_cjets"]["num_global_objects"] == 1_000
-        assert global_object_counts["lowpt_ttbar_ujets"]["num_global_objects"] > 1_000
-        assert global_object_counts["total"]["num_global_objects"] == len(jets)
+        # capped components write exactly num_jets; -1 writes all its objects
+        assert jets_counts["lowpt_ttbar_bjets"]["num_jets"] == 1_000
+        assert jets_counts["lowpt_ttbar_cjets"]["num_jets"] == 1_000
+        assert jets_counts["lowpt_ttbar_ujets"]["num_jets"] > 1_000
+        assert jets_counts["total"]["num_jets"] == len(jets)
 
     def test_run_method_none(self):
         args = [
diff --git a/tests/unit/stages/test_merging.py b/tests/unit/stages/test_merging.py
index 4ec6864..e9c2c05 100644
--- a/tests/unit/stages/test_merging.py
+++ b/tests/unit/stages/test_merging.py
@@ -148,7 +148,9 @@ def test_open_writer_names_and_shapes(monkeypatch):
         sample=None,
         global_objects_in_file=7,
         file_idx=0,
-        components=SimpleNamespace(unique_global_objects=True, global_object_counts={}, dsids=[]),
+        components=SimpleNamespace(
+            unique_global_objects=True, global_object_counts=lambda _gn: {}, dsids=[]
+        ),
     )
 
     writer = merge.writer
@@ -179,7 +181,7 @@ def test_write_chunk_splits(monkeypatch):
     merge._file_idx = 0
     merge.global_objects_written = 0
     merge.current_components = SimpleNamespace(
-        unique_global_objects=True, global_object_counts={}, dsids=[]
+        unique_global_objects=True, global_object_counts=lambda _gn: {}, dsids=[]
     )
     merge._sample = None
 
@@ -223,7 +225,7 @@ def test_write_chunk_rollover(monkeypatch):
     merge._file_idx = 0
     merge._sample = None
     merge.current_components = SimpleNamespace(
-        unique_global_objects=True, global_object_counts={}, dsids=[]
+        unique_global_objects=True, global_object_counts=lambda _gn: {}, dsids=[]
     )
 
     # Open the first writer with capacity 5 and mark it as "full"
@@ -253,7 +255,7 @@ def test_write_chunk_returns_zero_when_no_space_left(monkeypatch):
     merge.global_objects_written = 4
     merge._file_idx = 0
     merge.current_components = SimpleNamespace(
-        unique_global_objects=True, global_object_counts={}, dsids=[]
+        unique_global_objects=True, global_object_counts=lambda _gn: {}, dsids=[]
     )
     merge._sample = None
 
@@ -319,9 +321,11 @@ def __init__(self, comps: list[ComponentStub]):
         self._comps = comps
         self.num_global_objects = sum(c.num_global_objects for c in comps)
         self.unique_global_objects = True
-        self.global_object_counts: dict[str, int] = {}
         self.dsids: list[int] = []
 
+    def global_object_counts(self, _global_name="jets"):
+        return {}
+
     def __iter__(self):
         return iter(self._comps)
 
@@ -658,7 +662,7 @@ def test_write_chunk_all_components_complete_early_return(monkeypatch):
     merge._file_idx = 0
     merge.global_objects_written = 0
     merge.current_components = SimpleNamespace(
-        unique_global_objects=True, global_object_counts={}, dsids=[]
+        unique_global_objects=True, global_object_counts=lambda _gn: {}, dsids=[]
     )
     merge._sample = None
     merge._open_writer(None, 0, 0, merge.current_components)
diff --git a/upp/classes/components.py b/upp/classes/components.py
index 69e5ef3..a5e1578 100644
--- a/upp/classes/components.py
+++ b/upp/classes/components.py
@@ -299,9 +299,8 @@ def unique_global_objects(self) -> int:
             Number of unique objects for this component
         """
         if self._unique_global_objects == -1:
-            self._unique_global_objects = sum(
-                [r.get_attr("unique_global_objects") for r in self.reader.readers]
-            )
+            attr = f"unique_{self.reader.global_objects_name}"
+            self._unique_global_objects = sum([r.get_attr(attr) for r in self.reader.readers])
 
         return self._unique_global_objects
 
@@ -486,18 +485,29 @@ def out_dir(self):
         assert len(out_dir) == 1
         return next(iter(out_dir))
 
-    @property
-    def global_object_counts(self):
+    def global_object_counts(self, global_name: str = "jets") -> dict:
+        """Return per-component and total object counts.
+
+        Parameters
+        ----------
+        global_name : str, optional
+            Name of the global object, used to key the counts, by default "jets".
+
+        Returns
+        -------
+        dict
+            Counts keyed by ``num_{global_name}`` and ``unique_{global_name}``.
+        """
         num_dict = {
             c.name: {
-                "num_global_objects": int(c.num_global_objects),
-                "unique_global_objects": int(c.unique_global_objects),
+                f"num_{global_name}": int(c.num_global_objects),
+                f"unique_{global_name}": int(c.unique_global_objects),
             }
             for c in self
         }
         num_dict["total"] = {
-            "num_global_objects": int(self.num_global_objects),
-            "unique_global_objects": int(self.unique_global_objects),
+            f"num_{global_name}": int(self.num_global_objects),
+            f"unique_{global_name}": int(self.unique_global_objects),
         }
         return num_dict
 
diff --git a/upp/stages/hist.py b/upp/stages/hist.py
index 765cd88..7ce8e9f 100644
--- a/upp/stages/hist.py
+++ b/upp/stages/hist.py
@@ -64,6 +64,7 @@ def write_hist(
         global_objects: dict,
         resampling_vars: list,
         bins: list,
+        global_name: str = "jets",
     ) -> None:
         """
         Write the histogram to file.
@@ -76,6 +77,8 @@ def write_hist(
             List of the resampling variables.
         bins : list
             Flat list with the bins.
+        global_name : str, optional
+            Name of the global object, used for the count attribute, by default "jets".
 
         Raises
         ------
@@ -94,7 +97,7 @@ def write_hist(
         with h5py.File(self.path, "w") as f:
             f.create_dataset("pbin", data=pbin)
             f.create_dataset("hist", data=hist)
-            f.attrs.create("num_global_objects", len(global_objects))
+            f.attrs.create(f"num_{global_name}", len(global_objects))
             f.attrs.create("resampling_vars", resampling_vars)
             for i, v in enumerate(resampling_vars):
                 f.attrs.create(f"bins_{v}", bins[i])
@@ -195,6 +198,7 @@ def create_histograms(
             global_objects=global_objects,
             resampling_vars=sampl_vars,
             bins=config.sampl_cfg.flat_bins,
+            global_name=config.global_name,
         )
 
         # Set the check variable to true
diff --git a/upp/stages/merging.py b/upp/stages/merging.py
index 9244d91..c5ac043 100644
--- a/upp/stages/merging.py
+++ b/upp/stages/merging.py
@@ -350,8 +350,11 @@ def _open_writer(
             [f.name for f in self.flavours],
             self.global_name,
         )
-        self.writer.add_attr("unique_global_objects", components.unique_global_objects)
-        self.writer.add_attr("global_object_counts", json.dumps(components.global_object_counts))
+        self.writer.add_attr(f"unique_{self.global_name}", components.unique_global_objects)
+        self.writer.add_attr(
+            f"{self.global_name}_counts",
+            json.dumps(components.global_object_counts(self.global_name)),
+        )
         self.writer.add_attr("dsids", str(components.dsids))
         self.writer.add_attr("config", json.dumps(self.config.config))
         self.writer.add_attr("upp_hash", self.config.git_hash)
diff --git a/upp/stages/resampling.py b/upp/stages/resampling.py
index c118254..7180d95 100644
--- a/upp/stages/resampling.py
+++ b/upp/stages/resampling.py
@@ -198,7 +198,7 @@ def _finalise_component(self, component: Component) -> None:
         unique = component._unique_global_objects
         component._ups_ratio = component.writer.num_written / unique if unique else 0.0
         component.writer.add_attr("upsampling_ratio", component._ups_ratio)
-        component.writer.add_attr("unique_global_objects", component._unique_global_objects)
+        component.writer.add_attr(f"unique_{self.global_name}", component._unique_global_objects)
         component.writer.add_attr("dsid", str(component.sample.dsid))
         component.writer.close()
 
@@ -577,7 +577,7 @@ def run(self, region: str | None = None, component: str | None = None):
                     # If a component is given, skip all components that are not selected
                     if component and iter_component.name != component:
                         continue
-                    unique += iter_component.writer.get_attr("unique_global_objects")
+                    unique += iter_component.writer.get_attr(f"unique_{self.global_name}")
             log.info(
                 f"[bold green]Finished resampling of region {region}. "
                 f"A total of {self.components.num_global_objects:,} objects!"
@@ -587,7 +587,7 @@ def run(self, region: str | None = None, component: str | None = None):
 
         else:
             unique = sum(
-                iter_component.writer.get_attr("unique_global_objects")
+                iter_component.writer.get_attr(f"unique_{self.global_name}")
                 for iter_component in self.components
             )
             log.info(
diff --git a/upp/stages/rw_merge.py b/upp/stages/rw_merge.py
index 0f54c19..41c88f3 100644
--- a/upp/stages/rw_merge.py
+++ b/upp/stages/rw_merge.py
@@ -45,8 +45,8 @@ def __init__(self, config, outfile_idx_range=None):
                 "flavour_label": [f.name for f in self.config.components.flavours],
             },
             None: {
-                "unique_global_objects": num_global_objects,
-                "global_object_counts": num_global_objects,
+                f"unique_{self.config.global_name}": num_global_objects,
+                f"{self.config.global_name}_counts": num_global_objects,
                 "dsids": str(self.config.components.dsids),
                 "config": json.dumps(self.config.config),
                 "upp_hash": self.config.git_hash,

From 4595d52632059b6c1c669287c120b4ca7cb85fd7 Mon Sep 17 00:00:00 2001
From: Alexander Froch <Alexander.Froch@cern.ch>
Date: Thu, 2 Jul 2026 16:43:35 +0200
Subject: [PATCH 10/13] Label the ATLAS second tag with the configured global
 object name

---
 tests/unit/stages/test_plotting.py | 18 +++++++++++++++---
 upp/stages/plot.py                 | 10 ++++++++--
 2 files changed, 23 insertions(+), 5 deletions(-)

diff --git a/tests/unit/stages/test_plotting.py b/tests/unit/stages/test_plotting.py
index 37f83e4..4584006 100644
--- a/tests/unit/stages/test_plotting.py
+++ b/tests/unit/stages/test_plotting.py
@@ -96,8 +96,20 @@ def test_plot_helpers_format_labels_and_ranges():
             num_global_objects=100_000,
             resampling_status="Pre Resampling",
         )
-        == "$\\sqrt{s} = 13/13.6\\,\\mathrm{TeV}$, $t\\bar{t}$ + $Z'$ objects"
-        "\nPre Resampling\n100k objects"
+        == "$\\sqrt{s} = 13/13.6\\,\\mathrm{TeV}$, $t\\bar{t}$ + $Z'$ jets"
+        "\nPre Resampling\n100k jets"
+    )
+    assert (
+        plot_mod._atlas_second_tag(
+            "ttbar",
+            "zprime",
+            plotting=PlottingConfig(),
+            global_name="tracks",
+            num_global_objects=100_000,
+            resampling_status="Pre Resampling",
+        )
+        == "$\\sqrt{s} = 13/13.6\\,\\mathrm{TeV}$, $t\\bar{t}$ + $Z'$ tracks"
+        "\nPre Resampling\n100k tracks"
     )
     assert plot_mod._display_range("pt_btagJes", (20_000, 250_000)) == (20, 250)
     assert plot_mod._display_range("JetFitterSecondaryVertex_mass", (0, 25_000)) == (0, 25)
@@ -267,5 +279,5 @@ def fake_make_hist(**kwargs):
     assert calls[0]["suffix"] == "_val_ttbar_lowpt"
     assert calls[0]["bins_range"] == (20, 250)
     assert calls[0]["atlas_second_tag"] == (
-        "$\\sqrt{s} = 13/13.6\\,\\mathrm{TeV}$, $t\\bar{t}$ objects\nPre Resampling\n10k objects"
+        "$\\sqrt{s} = 13/13.6\\,\\mathrm{TeV}$, $t\\bar{t}$ jets\nPre Resampling\n10k jets"
     )
diff --git a/upp/stages/plot.py b/upp/stages/plot.py
index 2678976..1c63f6c 100644
--- a/upp/stages/plot.py
+++ b/upp/stages/plot.py
@@ -182,6 +182,7 @@ def _format_num_global_objects(num_global_objects: int) -> str:
 def _atlas_second_tag(
     *sample_names: str,
     plotting: PlottingConfig,
+    global_name: str = "jets",
     num_global_objects: int | None = None,
     resampling_status: str | None = None,
 ) -> str:
@@ -193,6 +194,9 @@ def _atlas_second_tag(
         Sample names to include after the centre-of-mass energy.
     plotting : PlottingConfig
         Active plotting configuration.
+    global_name : str, optional
+        Name of the global object used to label the sample and count lines,
+        by default "jets".
     num_global_objects : int | None, optional
         Number of objects requested for plotting. If provided, it is added as an
         extra line using compact formatting.
@@ -209,12 +213,12 @@ def _atlas_second_tag(
     labels = [_sample_label(name, plotting) for name in dict.fromkeys(sample_names) if name]
     first_line = plotting.atlas_second_tag
     if labels:
-        first_line = f"{first_line}, {' + '.join(labels)} objects"
+        first_line = f"{first_line}, {' + '.join(labels)} {global_name}"
     lines = [first_line]
     if resampling_status is not None:
         lines.append(resampling_status)
     if num_global_objects is not None:
-        lines.append(f"{_format_num_global_objects(num_global_objects)} objects")
+        lines.append(f"{_format_num_global_objects(num_global_objects)} {global_name}")
     return "\n".join(lines)
 
 
@@ -626,6 +630,7 @@ def _plot_initial(config: PreprocessingConfig) -> None:
                     atlas_second_tag=_atlas_second_tag(
                         sample.name,
                         plotting=config.plotting,
+                        global_name=config.global_name,
                         num_global_objects=_plotting_num_global_objects(
                             config, region_components.num_global_objects
                         )
@@ -688,6 +693,7 @@ def _plot_post_resampling(config: PreprocessingConfig, stage: str) -> None:
     atlas_second_tag = _atlas_second_tag(
         *sample_names,
         plotting=config.plotting,
+        global_name=config.global_name,
         num_global_objects=_plotting_num_global_objects(
             config, config.components.num_global_objects
         )

From 3d80f96adf85efd67a860806dadd1c76ad1c9bf1 Mon Sep 17 00:00:00 2001
From: Alexander Froch <Alexander.Froch@cern.ch>
Date: Thu, 2 Jul 2026 17:27:37 +0200
Subject: [PATCH 11/13] Rename flavour config settings to class_* with
 back-compat aliases

Rename the user-facing settings flavour_config -> class_config,
flavour_category -> class_category and the per-component flavours ->
classes across the config schema, in-repo configs and tests. Old keys
are remapped on load via LEGACY_KEY_MAP so existing configs keep working
with a deprecation warning. Internal flavour identifiers and the
flavour_label output attribute are unchanged.
---
 .../fixtures/test_config_countup.yaml         | 12 +++---
 .../test_config_countup_upscaled.yaml         | 12 +++---
 .../fixtures/test_config_method_none.yaml     |  6 +--
 .../fixtures/test_config_no_resample.yaml     |  6 +--
 .../fixtures/test_config_pdf_auto.yaml        | 12 +++---
 .../fixtures/test_config_pdf_upscaled.yaml    | 12 +++---
 .../integration/fixtures/test_config_rw.yaml  |  4 +-
 .../fixtures/test_config_rw_custom_name.yaml  |  4 +-
 .../fixtures/test_config_track_selection.yaml | 12 +++---
 .../unit/classes/test_preprocessing_config.py | 41 ++++++++++++++-----
 .../fixtures/test_config_pdf_auto_umami.yaml  | 14 +++----
 .../test_config_pdf_auto_umami_required.yaml  | 14 +++----
 tests/unit/fixtures/test_config_rw.yaml       |  4 +-
 upp/classes/components.py                     |  2 +-
 upp/classes/preprocessing_config.py           | 40 +++++++++++-------
 upp/configs/GN3EPCMV01/GN3EPCMV01.yaml        | 24 +++++------
 upp/configs/GN3V00/dr.yaml                    |  8 ++--
 upp/configs/GN3V00/ghost-highstat.yaml        | 24 +++++------
 upp/configs/GN3V00/ghost.yaml                 |  8 ++--
 upp/configs/GN3V01/GN3V01-RW.yaml             |  4 +-
 upp/configs/GN3V01/GN3V01.yaml                | 24 +++++------
 upp/configs/extended_labels.yaml              | 10 ++---
 upp/configs/open-dataset.yaml                 |  6 +--
 upp/configs/plit_electron.yaml                |  4 +-
 upp/configs/plit_muon.yaml                    |  4 +-
 upp/configs/single-b-upgrade.yaml             | 12 +++---
 upp/configs/single-b.yaml                     | 12 +++---
 upp/configs/test.yaml                         |  4 +-
 upp/configs/xbb-gn3x.yaml                     | 12 +++---
 upp/configs/xbb-rw.yaml                       | 12 +++---
 upp/configs/xbb.yaml                          |  8 ++--
 upp/configs/xtautau.yaml                      | 10 ++---
 32 files changed, 205 insertions(+), 176 deletions(-)

diff --git a/tests/integration/fixtures/test_config_countup.yaml b/tests/integration/fixtures/test_config_countup.yaml
index 90fcf62..78055a1 100644
--- a/tests/integration/fixtures/test_config_countup.yaml
+++ b/tests/integration/fixtures/test_config_countup.yaml
@@ -32,42 +32,42 @@ components:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [bjets]
+    classes: [bjets]
     num_global_objects: 7_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [cjets]
+    classes: [cjets]
     num_global_objects: 7_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [ujets]
+    classes: [ujets]
     num_global_objects: 7_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [bjets]
+    classes: [bjets]
     num_global_objects: 3_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [cjets]
+    classes: [cjets]
     num_global_objects: 3_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [ujets]
+    classes: [ujets]
     num_global_objects: 3_000
 
 resampling:
diff --git a/tests/integration/fixtures/test_config_countup_upscaled.yaml b/tests/integration/fixtures/test_config_countup_upscaled.yaml
index c2e5c67..dc25c84 100644
--- a/tests/integration/fixtures/test_config_countup_upscaled.yaml
+++ b/tests/integration/fixtures/test_config_countup_upscaled.yaml
@@ -32,42 +32,42 @@ components:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [bjets]
+    classes: [bjets]
     num_global_objects: 70_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [cjets]
+    classes: [cjets]
     num_global_objects: 70_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [ujets]
+    classes: [ujets]
     num_global_objects: 70_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [bjets]
+    classes: [bjets]
     num_global_objects: 30_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [cjets]
+    classes: [cjets]
     num_global_objects: 30_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [ujets]
+    classes: [ujets]
     num_global_objects: 30_000
 
 resampling:
diff --git a/tests/integration/fixtures/test_config_method_none.yaml b/tests/integration/fixtures/test_config_method_none.yaml
index e5015e5..ccc407e 100644
--- a/tests/integration/fixtures/test_config_method_none.yaml
+++ b/tests/integration/fixtures/test_config_method_none.yaml
@@ -27,21 +27,21 @@ components:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [bjets]
+    classes: [bjets]
     num_global_objects: 1_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [cjets]
+    classes: [cjets]
     num_global_objects: 2_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [ujets]
+    classes: [ujets]
     num_global_objects: 3_000
 
 # Resampling explicitly disabled - no target or variables required.
diff --git a/tests/integration/fixtures/test_config_no_resample.yaml b/tests/integration/fixtures/test_config_no_resample.yaml
index 9cd3146..3d7186a 100644
--- a/tests/integration/fixtures/test_config_no_resample.yaml
+++ b/tests/integration/fixtures/test_config_no_resample.yaml
@@ -29,21 +29,21 @@ components:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [bjets]
+    classes: [bjets]
     num_global_objects: 1_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [cjets]
+    classes: [cjets]
     num_global_objects: 1_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [ujets]
+    classes: [ujets]
     num_global_objects: -1
 
 global:
diff --git a/tests/integration/fixtures/test_config_pdf_auto.yaml b/tests/integration/fixtures/test_config_pdf_auto.yaml
index 51f01b8..eaa2520 100644
--- a/tests/integration/fixtures/test_config_pdf_auto.yaml
+++ b/tests/integration/fixtures/test_config_pdf_auto.yaml
@@ -31,42 +31,42 @@ components:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [bjets]
+    classes: [bjets]
     num_global_objects: 12_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [cjets]
+    classes: [cjets]
     num_global_objects: 12_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [ujets]
+    classes: [ujets]
     num_global_objects: 12_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [bjets]
+    classes: [bjets]
     num_global_objects: 6_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [cjets]
+    classes: [cjets]
     num_global_objects: 6_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [ujets]
+    classes: [ujets]
     num_global_objects: 6_000
 
 resampling:
diff --git a/tests/integration/fixtures/test_config_pdf_upscaled.yaml b/tests/integration/fixtures/test_config_pdf_upscaled.yaml
index 85dd350..3bc4428 100644
--- a/tests/integration/fixtures/test_config_pdf_upscaled.yaml
+++ b/tests/integration/fixtures/test_config_pdf_upscaled.yaml
@@ -32,42 +32,42 @@ components:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [bjets]
+    classes: [bjets]
     num_global_objects: 7_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [cjets]
+    classes: [cjets]
     num_global_objects: 7_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [ ujets]
+    classes: [ ujets]
     num_global_objects: 7_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [bjets]
+    classes: [bjets]
     num_global_objects: 3_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [cjets]
+    classes: [cjets]
     num_global_objects: 3_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [ujets]
+    classes: [ujets]
     num_global_objects: 3_000
 
 resampling:
diff --git a/tests/integration/fixtures/test_config_rw.yaml b/tests/integration/fixtures/test_config_rw.yaml
index 4eaf59e..ca7dd71 100644
--- a/tests/integration/fixtures/test_config_rw.yaml
+++ b/tests/integration/fixtures/test_config_rw.yaml
@@ -51,14 +51,14 @@ components:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [bjets, cjets, ujets, taujets]
+    classes: [bjets, cjets, ujets, taujets]
     num_global_objects: -1
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [bjets, cjets, ujets, taujets]
+    classes: [bjets, cjets, ujets, taujets]
     num_global_objects: -1
 
 reweighting:
diff --git a/tests/integration/fixtures/test_config_rw_custom_name.yaml b/tests/integration/fixtures/test_config_rw_custom_name.yaml
index 21019b8..1c22288 100644
--- a/tests/integration/fixtures/test_config_rw_custom_name.yaml
+++ b/tests/integration/fixtures/test_config_rw_custom_name.yaml
@@ -51,14 +51,14 @@ components:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [bjets, cjets, ujets, taujets]
+    classes: [bjets, cjets, ujets, taujets]
     num_global_objects: -1
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [bjets, cjets, ujets, taujets]
+    classes: [bjets, cjets, ujets, taujets]
     num_global_objects: -1
 
 reweighting:
diff --git a/tests/integration/fixtures/test_config_track_selection.yaml b/tests/integration/fixtures/test_config_track_selection.yaml
index b7e4fdd..727a14c 100644
--- a/tests/integration/fixtures/test_config_track_selection.yaml
+++ b/tests/integration/fixtures/test_config_track_selection.yaml
@@ -32,42 +32,42 @@ components:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [bjets]
+    classes: [bjets]
     num_global_objects: 7_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [cjets]
+    classes: [cjets]
     num_global_objects: 7_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [ ujets]
+    classes: [ ujets]
     num_global_objects: 7_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [bjets]
+    classes: [bjets]
     num_global_objects: 3_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [cjets]
+    classes: [cjets]
     num_global_objects: 3_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [ujets]
+    classes: [ujets]
     num_global_objects: 3_000
 
 resampling:
diff --git a/tests/unit/classes/test_preprocessing_config.py b/tests/unit/classes/test_preprocessing_config.py
index 638107c..e7a2f12 100644
--- a/tests/unit/classes/test_preprocessing_config.py
+++ b/tests/unit/classes/test_preprocessing_config.py
@@ -21,19 +21,38 @@
 def test_rename_legacy_keys_remaps_nested_and_records():
     """Deprecated jet-named keys are remapped everywhere, others untouched."""
     raw = {
-        "global": {"jets_name": "muons", "num_jets_estimate": 5},
+        "global": {
+            "jets_name": "muons",
+            "num_jets_estimate": 5,
+            "flavour_config": "my_flavours.yaml",
+            "flavour_category": "extended",
+        },
         "components": [{"num_jets": 10, "sample": {"equal_jets": True}, "flavours": ["bjets"]}],
         "plotting": {"show_num_jets": False, "kept": 1},
     }
     found: set[str] = set()
     out = _rename_legacy_keys(raw, found)
 
-    assert out["global"] == {"global_name": "muons", "num_global_objects_estimate": 5}
+    assert out["global"] == {
+        "global_name": "muons",
+        "num_global_objects_estimate": 5,
+        "class_config": "my_flavours.yaml",
+        "class_category": "extended",
+    }
     assert out["components"][0]["num_global_objects"] == 10
     assert out["components"][0]["sample"]["equal_global_objects"] is True
-    assert out["components"][0]["flavours"] == ["bjets"]  # flavour names untouched
+    assert out["components"][0]["classes"] == ["bjets"]  # class names (values) untouched
     assert out["plotting"] == {"show_num_global_objects": False, "kept": 1}
-    assert found == {"jets_name", "num_jets_estimate", "num_jets", "equal_jets", "show_num_jets"}
+    assert found == {
+        "jets_name",
+        "num_jets_estimate",
+        "num_jets",
+        "equal_jets",
+        "show_num_jets",
+        "flavours",
+        "flavour_config",
+        "flavour_category",
+    }
 
 
 class TestPreprocessingConfig(unittest.TestCase):
@@ -212,7 +231,7 @@ def test_standard_flavour_config(self) -> None:
                 "variables": {"jets": {"labels": ["test"]}},
             },
             base_dir=Path("/tmp/upp-tests/integration/temp_workspace/"),
-            flavour_category="standard",
+            class_category="standard",
         )
         self.assertEqual(config.flavour_cont, Flavours)
 
@@ -226,7 +245,7 @@ def test_extended_flavour_config(self) -> None:
                 "variables": {"jets": {"labels": ["test"]}},
             },
             base_dir=Path("/tmp/upp-tests/integration/temp_workspace/"),
-            flavour_category="extended",
+            class_category="extended",
         )
         self.assertEqual(config.flavour_cont, Extended_Flavours)
 
@@ -270,13 +289,13 @@ def test_unsupported_flavour_config(self) -> None:
                     "variables": {"jets": {"labels": ["test"]}},
                 },
                 base_dir=Path("/tmp/upp-tests/integration/temp_workspace/"),
-                flavour_category="error",
+                class_category="error",
             )
 
         self.assertEqual(
-            "flavour_category error is not supported in the default "
-            + "flavours! If you want to use your own flavour config yaml file, please "
-            + "provide flavour_config!",
+            "class_category error is not supported in the default "
+            + "flavours! If you want to use your own class config yaml file, please "
+            + "provide class_config!",
             str(ctx.exception),
         )
 
@@ -290,7 +309,7 @@ def test_separate_flavour_config(self) -> None:
                 "variables": {"jets": {"labels": ["test"]}},
             },
             base_dir=Path("/tmp/upp-tests/integration/temp_workspace/"),
-            flavour_config=self.CFG_DIR / "test_flavour_config.yaml",
+            class_config=self.CFG_DIR / "test_flavour_config.yaml",
         )
         self.assertEqual(
             config.flavour_cont,
diff --git a/tests/unit/fixtures/test_config_pdf_auto_umami.yaml b/tests/unit/fixtures/test_config_pdf_auto_umami.yaml
index ba6415e..4e11559 100644
--- a/tests/unit/fixtures/test_config_pdf_auto_umami.yaml
+++ b/tests/unit/fixtures/test_config_pdf_auto_umami.yaml
@@ -32,42 +32,42 @@ components:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [bjets]
+    classes: [bjets]
     num_global_objects: 7_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [cjets]
+    classes: [cjets]
     num_global_objects: 7_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [ ujets]
+    classes: [ ujets]
     num_global_objects: 7_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [bjets]
+    classes: [bjets]
     num_global_objects: 3_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [cjets]
+    classes: [cjets]
     num_global_objects: 3_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [ujets]
+    classes: [ujets]
     num_global_objects: 3_000
 
 resampling:
@@ -85,7 +85,7 @@ global:
   num_global_objects_estimate: 5000
   base_dir: /tmp/upp-tests/integration/temp_workspace/
   out_dir: test_out
-  flavour_category: standard
+  class_category: standard
 
 variables:
   jets:
diff --git a/tests/unit/fixtures/test_config_pdf_auto_umami_required.yaml b/tests/unit/fixtures/test_config_pdf_auto_umami_required.yaml
index 72a0610..7b76eec 100644
--- a/tests/unit/fixtures/test_config_pdf_auto_umami_required.yaml
+++ b/tests/unit/fixtures/test_config_pdf_auto_umami_required.yaml
@@ -32,42 +32,42 @@ components:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [singlebjets]
+    classes: [singlebjets]
     num_global_objects: 7_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [singlecjets]
+    classes: [singlecjets]
     num_global_objects: 7_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [ujets]
+    classes: [ujets]
     num_global_objects: 7_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [singlebjets]
+    classes: [singlebjets]
     num_global_objects: 3_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [singlecjets]
+    classes: [singlecjets]
     num_global_objects: 3_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [ujets]
+    classes: [ujets]
     num_global_objects: 3_000
 
 resampling:
@@ -85,7 +85,7 @@ global:
   num_global_objects_estimate: 5000
   base_dir: /tmp/upp-tests/integration/temp_workspace/
   out_dir: test_out
-  flavour_category: extended
+  class_category: extended
 
 variables:
   jets:
diff --git a/tests/unit/fixtures/test_config_rw.yaml b/tests/unit/fixtures/test_config_rw.yaml
index 897d527..7c50754 100644
--- a/tests/unit/fixtures/test_config_rw.yaml
+++ b/tests/unit/fixtures/test_config_rw.yaml
@@ -30,14 +30,14 @@ components:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [bjets, cjets, ujets, taujets]
+    classes: [bjets, cjets, ujets, taujets]
     num_global_objects: -1
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [bjets, cjets, ujets, taujets]
+    classes: [bjets, cjets, ujets, taujets]
     num_global_objects: -1
 
 resampling:
diff --git a/upp/classes/components.py b/upp/classes/components.py
index a5e1578..3bd2af0 100644
--- a/upp/classes/components.py
+++ b/upp/classes/components.py
@@ -356,7 +356,7 @@ def from_config(cls, config: PreprocessingConfig) -> Components:
             )
 
             # Create the Component instances for the different flavours
-            for name in component["flavours"]:
+            for name in component["classes"]:
                 num_global_objects = component["num_global_objects"]
                 if config.split == "val":
                     num_global_objects = component.get(
diff --git a/upp/classes/preprocessing_config.py b/upp/classes/preprocessing_config.py
index d42b15b..c028349 100644
--- a/upp/classes/preprocessing_config.py
+++ b/upp/classes/preprocessing_config.py
@@ -50,6 +50,9 @@
     "num_jets_plotting": "num_global_objects_plotting",
     "show_num_jets": "show_num_global_objects",
     "equal_jets": "equal_global_objects",
+    "flavours": "classes",
+    "flavour_config": "class_config",
+    "flavour_category": "class_category",
 }
 
 
@@ -141,12 +144,19 @@ class PreprocessingConfig:
     global_name : str, optional
         Name of the global (per-object) dataset in the input file, e.g. the objects.
         By default "jets".
-    flavour_config : Path | None, optional
-        Flavour config yaml file which is to be used. By default None
-    flavour_category : str, optional
-        Flavour categories that are to be used. By default, the "standard" (non-extended)
-        labels are loaded. The extended labels can be used by setting this value to "extended".
-        By default "standard". To use this option, flavour_config must be None.
+    class_config : Path | None, optional
+        Path to a custom class-definition yaml, used instead of the flavour labels
+        bundled with atlas-ftag-tools. This lets the framework classify any object type,
+        not just jets. The file is a list of class dicts with keys ``name``, ``label``,
+        ``cuts``, ``colour`` and ``category`` (plus an optional ``_px`` probability name);
+        the ``classes`` listed per component must match the ``name`` entries here. A
+        relative path is resolved against ``base_dir``. Takes precedence over
+        ``class_category``. By default None
+    class_category : str, optional
+        Class categories that are to be used from the atlas-ftag-tools bundled labels.
+        By default, the "standard" (non-extended) labels are loaded. The extended labels
+        can be used by setting this value to "extended". By default "standard". To use
+        this option, class_config must be None.
     num_global_objects_per_output_file : int | None, optional
         Number of objects per final output file. If the number of total objects is larger
         than this number, the final h5 output files are splitted in multiple smaller
@@ -177,8 +187,8 @@ class PreprocessingConfig:
     num_global_objects_estimate_plotting: int | None = None
     merge_test_samples: bool = False
     global_name: str = "jets"
-    flavour_config: Path | None = None
-    flavour_category: str = "standard"
+    class_config: Path | None = None
+    class_category: str = "standard"
     num_global_objects_per_output_file: int | None = None
     skip_checks: bool = False
     skip_config_copy: bool = False
@@ -209,22 +219,22 @@ def __post_init__(self):
         self.components_dir = self.components_dir / self.split
         self.out_fname = self.out_dir / path_append(self.out_fname, self.split)
         # Define the content of the flavour label container
-        if self.flavour_config:
+        if self.class_config:
             self.flavour_cont = LabelContainer.from_yaml(
-                yaml_path=self.flavour_config,
+                yaml_path=self.class_config,
             )
 
-        elif self.flavour_category == "standard":
+        elif self.class_category == "standard":
             self.flavour_cont = Flavours
 
-        elif self.flavour_category == "extended":
+        elif self.class_category == "extended":
             self.flavour_cont = Extended_Flavours
 
         else:
             raise ValueError(
-                f"flavour_category {self.flavour_category} is not supported in the default "
-                "flavours! If you want to use your own flavour config yaml file, please "
-                "provide flavour_config!"
+                f"class_category {self.class_category} is not supported in the default "
+                "flavours! If you want to use your own class config yaml file, please "
+                "provide class_config!"
             )
         # configure classes
         if sampl_cfg := self.config.get("resampling", None):
diff --git a/upp/configs/GN3EPCMV01/GN3EPCMV01.yaml b/upp/configs/GN3EPCMV01/GN3EPCMV01.yaml
index d24e0ab..0b63b56 100644
--- a/upp/configs/GN3EPCMV01/GN3EPCMV01.yaml
+++ b/upp/configs/GN3EPCMV01/GN3EPCMV01.yaml
@@ -37,7 +37,7 @@ components:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [ghostbjets]
+    classes: [ghostbjets]
     num_global_objects: 168_968_784
     num_global_objects_test: 2_000_000
     num_global_objects_val: 2_000_000
@@ -46,7 +46,7 @@ components:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [ghostcjets]
+    classes: [ghostcjets]
     num_global_objects: 38_872_067
     num_global_objects_test: 2_000_000
     num_global_objects_val: 2_000_000
@@ -55,7 +55,7 @@ components:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [ghostsjets]
+    classes: [ghostsjets]
     num_global_objects: 30_714_894
     num_global_objects_test: 1_706_567
     num_global_objects_val: 1_706_567
@@ -64,7 +64,7 @@ components:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [ghostudjets]
+    classes: [ghostudjets]
     num_global_objects: 78_352_864
     num_global_objects_test: 2_000_000
     num_global_objects_val: 2_000_000
@@ -73,7 +73,7 @@ components:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [ghostgjets]
+    classes: [ghostgjets]
     num_global_objects: 92_319_320
     num_global_objects_test: 2_000_000
     num_global_objects_val: 2_000_000
@@ -82,7 +82,7 @@ components:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [ghosttaujets]
+    classes: [ghosttaujets]
     num_global_objects: 16_261_627
     num_global_objects_test: 896_611
     num_global_objects_val: 896_611
@@ -91,7 +91,7 @@ components:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [ghostbjets]
+    classes: [ghostbjets]
     num_global_objects: 40_230_662 #40_696_238
     num_global_objects_test: 476_190
     num_global_objects_val: 476_190
@@ -100,7 +100,7 @@ components:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [ghostcjets]
+    classes: [ghostcjets]
     num_global_objects: 9_255_254 #39_928_286
     num_global_objects_test: 476_190
     num_global_objects_val: 476_190
@@ -109,7 +109,7 @@ components:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [ghostsjets]
+    classes: [ghostsjets]
     num_global_objects: 7_313_070 #25_814_913
     num_global_objects_test: 406_325
     num_global_objects_val: 406_325
@@ -118,7 +118,7 @@ components:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [ghostudjets]
+    classes: [ghostudjets]
     num_global_objects: 18_655_443 #28_206_672
     num_global_objects_test: 476_190
     num_global_objects_val: 476_190
@@ -127,7 +127,7 @@ components:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [ghostgjets]
+    classes: [ghostgjets]
     num_global_objects: 21_980_790 #55_036_052
     num_global_objects_test: 476_190
     num_global_objects_val: 476_190
@@ -136,7 +136,7 @@ components:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [ghosttaujets]
+    classes: [ghosttaujets]
     num_global_objects: 3_871_815 #25_623_679
     num_global_objects_test: 213_478
     num_global_objects_val: 213_478
diff --git a/upp/configs/GN3V00/dr.yaml b/upp/configs/GN3V00/dr.yaml
index 1dbfb51..2ceb1d2 100644
--- a/upp/configs/GN3V00/dr.yaml
+++ b/upp/configs/GN3V00/dr.yaml
@@ -32,7 +32,7 @@ components:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [bjets, cjets, ujets]
+    classes: [bjets, cjets, ujets]
     num_global_objects: 6_000_000
     num_global_objects_test: 2_000_000
 
@@ -40,7 +40,7 @@ components:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [taujets]
+    classes: [taujets]
     num_global_objects: 2_000_000
     num_global_objects_test: 500_000
 
@@ -48,7 +48,7 @@ components:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [bjets, cjets, ujets]
+    classes: [bjets, cjets, ujets]
     num_global_objects: 3_000_000
     num_global_objects_test: 500_000
 
@@ -56,7 +56,7 @@ components:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [taujets]
+    classes: [taujets]
     num_global_objects: 1_000_000
     num_global_objects_test: 200_000
 
diff --git a/upp/configs/GN3V00/ghost-highstat.yaml b/upp/configs/GN3V00/ghost-highstat.yaml
index 3b96c72..d39e0c2 100644
--- a/upp/configs/GN3V00/ghost-highstat.yaml
+++ b/upp/configs/GN3V00/ghost-highstat.yaml
@@ -33,7 +33,7 @@ components:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [ghostsplitbjets]
+    classes: [ghostsplitbjets]
     num_global_objects: 79_000_000
     num_global_objects_test: 2_000_000
 
@@ -41,7 +41,7 @@ components:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [ghostsplitcjets]
+    classes: [ghostsplitcjets]
     num_global_objects: 26_500_000
     num_global_objects_test: 2_000_000
 
@@ -49,7 +49,7 @@ components:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [ghostsplitsjets]
+    classes: [ghostsplitsjets]
     num_global_objects: 21_000_000
     num_global_objects_test: 1_000_000
 
@@ -57,7 +57,7 @@ components:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [ghostsplitudjets]
+    classes: [ghostsplitudjets]
     num_global_objects: 54_000_000
     num_global_objects_test: 1_000_000
 
@@ -65,7 +65,7 @@ components:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [ghostsplitgjets]
+    classes: [ghostsplitgjets]
     num_global_objects: 46_000_000
     num_global_objects_test: 1_000_000
 
@@ -73,7 +73,7 @@ components:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [ghostsplittaujets]
+    classes: [ghostsplittaujets]
     num_global_objects: 9_000_000
     num_global_objects_test: 500_000
 
@@ -81,7 +81,7 @@ components:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [ghostsplitbjets]
+    classes: [ghostsplitbjets]
     num_global_objects: 39_500_000
     num_global_objects_test: 2_000_000
 
@@ -89,7 +89,7 @@ components:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [ghostsplitcjets]
+    classes: [ghostsplitcjets]
     num_global_objects: 13_250_000
     num_global_objects_test: 2_000_000
 
@@ -97,7 +97,7 @@ components:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [ghostsplitsjets]
+    classes: [ghostsplitsjets]
     num_global_objects: 10_500_000
     num_global_objects_test: 1_000_000
 
@@ -105,7 +105,7 @@ components:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [ghostsplitudjets]
+    classes: [ghostsplitudjets]
     num_global_objects: 27_000_000
     num_global_objects_test: 1_000_000
 
@@ -113,7 +113,7 @@ components:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [ghostsplitgjets]
+    classes: [ghostsplitgjets]
     num_global_objects: 23_000_000
     num_global_objects_test: 1_000_000
 
@@ -121,7 +121,7 @@ components:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [ghostsplittaujets]
+    classes: [ghostsplittaujets]
     num_global_objects: 4_500_000
     num_global_objects_test: 200_000
 
diff --git a/upp/configs/GN3V00/ghost.yaml b/upp/configs/GN3V00/ghost.yaml
index 203c8ad..04cd5f3 100644
--- a/upp/configs/GN3V00/ghost.yaml
+++ b/upp/configs/GN3V00/ghost.yaml
@@ -33,7 +33,7 @@ components:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [ghostbjets, ghostcjets, ghostujets]
+    classes: [ghostbjets, ghostcjets, ghostujets]
     num_global_objects: 6_000_000
     num_global_objects_test: 2_000_000
 
@@ -41,7 +41,7 @@ components:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [ghosttaujets]
+    classes: [ghosttaujets]
     num_global_objects: 2_000_000
     num_global_objects_test: 500_000
 
@@ -49,7 +49,7 @@ components:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [ghostbjets, ghostcjets, ghostujets]
+    classes: [ghostbjets, ghostcjets, ghostujets]
     num_global_objects: 3_000_000
     num_global_objects_test: 2_000_000
 
@@ -57,7 +57,7 @@ components:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [ghosttaujets]
+    classes: [ghosttaujets]
     num_global_objects: 1_000_000
     num_global_objects_test: 200_000
 
diff --git a/upp/configs/GN3V01/GN3V01-RW.yaml b/upp/configs/GN3V01/GN3V01-RW.yaml
index ff74ac5..0be49b3 100644
--- a/upp/configs/GN3V01/GN3V01-RW.yaml
+++ b/upp/configs/GN3V01/GN3V01-RW.yaml
@@ -37,7 +37,7 @@ components:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours:
+    classes:
       [
         ghostbjets,
         ghostcjets,
@@ -52,7 +52,7 @@ components:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours:
+    classes:
       [
         ghostbjets,
         ghostcjets,
diff --git a/upp/configs/GN3V01/GN3V01.yaml b/upp/configs/GN3V01/GN3V01.yaml
index c1a44e3..f14dd9d 100644
--- a/upp/configs/GN3V01/GN3V01.yaml
+++ b/upp/configs/GN3V01/GN3V01.yaml
@@ -33,7 +33,7 @@ components:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [ghostbjets]
+    classes: [ghostbjets]
     num_global_objects: 100_000_000
     num_global_objects_test: 2_000_000
 
@@ -41,7 +41,7 @@ components:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [ghostcjets]
+    classes: [ghostcjets]
     num_global_objects: 27_500_000
     num_global_objects_test: 2_000_000
 
@@ -49,7 +49,7 @@ components:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [ghostsjets]
+    classes: [ghostsjets]
     num_global_objects: 20_000_000
     num_global_objects_test: 1_000_000
 
@@ -57,7 +57,7 @@ components:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [ghostudjets]
+    classes: [ghostudjets]
     num_global_objects: 55_000_000
     num_global_objects_test: 1_000_000
 
@@ -65,7 +65,7 @@ components:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [ghostgjets]
+    classes: [ghostgjets]
     num_global_objects: 65_000_000
     num_global_objects_test: 1_000_000
 
@@ -73,7 +73,7 @@ components:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [ghosttaujets]
+    classes: [ghosttaujets]
     num_global_objects: 11_000_000
     num_global_objects_test: 500_000
 
@@ -81,7 +81,7 @@ components:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [ghostbjets]
+    classes: [ghostbjets]
     num_global_objects: 50_000_000
     num_global_objects_test: 2_000_000
 
@@ -89,7 +89,7 @@ components:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [ghostcjets]
+    classes: [ghostcjets]
     num_global_objects: 13_750_000
     num_global_objects_test: 2_000_000
 
@@ -97,7 +97,7 @@ components:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [ghostsjets]
+    classes: [ghostsjets]
     num_global_objects: 10_000_000
     num_global_objects_test: 1_000_000
 
@@ -105,7 +105,7 @@ components:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [ghostudjets]
+    classes: [ghostudjets]
     num_global_objects: 27_500_000
     num_global_objects_test: 1_000_000
 
@@ -113,7 +113,7 @@ components:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [ghostgjets]
+    classes: [ghostgjets]
     num_global_objects: 32_500_000
     num_global_objects_test: 1_000_000
 
@@ -121,7 +121,7 @@ components:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [ghosttaujets]
+    classes: [ghosttaujets]
     num_global_objects: 5_500_000
     num_global_objects_test: 200_000
 
diff --git a/upp/configs/extended_labels.yaml b/upp/configs/extended_labels.yaml
index a84b9b2..0c717b8 100644
--- a/upp/configs/extended_labels.yaml
+++ b/upp/configs/extended_labels.yaml
@@ -21,35 +21,35 @@ components:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [bjets]
+    classes: [bjets]
     num_global_objects: 25_000_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [D0meson]
+    classes: [D0meson]
     num_global_objects: 12_500_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [nonD0meson]
+    classes: [nonD0meson]
     num_global_objects: 12_500_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [ujets]
+    classes: [ujets]
     num_global_objects: 50_000_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [taujets]
+    classes: [taujets]
     num_global_objects: 4_000_000
 
 resampling:
diff --git a/upp/configs/open-dataset.yaml b/upp/configs/open-dataset.yaml
index 8a385cc..830ca36 100644
--- a/upp/configs/open-dataset.yaml
+++ b/upp/configs/open-dataset.yaml
@@ -63,21 +63,21 @@ components:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [bjets, cjets]
+    classes: [bjets, cjets]
     num_global_objects: 13_000_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [ujets]
+    classes: [ujets]
     num_global_objects: 26_000_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [taujets]
+    classes: [taujets]
     num_global_objects: 1_500_000
 
 resampling:
diff --git a/upp/configs/plit_electron.yaml b/upp/configs/plit_electron.yaml
index 47eb1e2..afe8411 100644
--- a/upp/configs/plit_electron.yaml
+++ b/upp/configs/plit_electron.yaml
@@ -27,14 +27,14 @@ components:
       <<: *electron
     sample:
       <<: *ttbar
-    flavours: [elxprompt]
+    classes: [elxprompt]
     num_global_objects: 25_000_000
 
   - region:
       <<: *electron
     sample:
       <<: *ttbar
-    flavours: [npxall]
+    classes: [npxall]
     num_global_objects: 13_000_000
 
 
diff --git a/upp/configs/plit_muon.yaml b/upp/configs/plit_muon.yaml
index a4092c3..663c51f 100644
--- a/upp/configs/plit_muon.yaml
+++ b/upp/configs/plit_muon.yaml
@@ -27,14 +27,14 @@ components:
       <<: *muon
     sample:
       <<: *ttbar
-    flavours: [muxprompt]
+    classes: [muxprompt]
     num_global_objects: 30_000_000
 
   - region:
       <<: *muon
     sample:
       <<: *ttbar
-    flavours: [npxall]
+    classes: [npxall]
     num_global_objects: 10_000_000
 
 
diff --git a/upp/configs/single-b-upgrade.yaml b/upp/configs/single-b-upgrade.yaml
index f3f0278..533a8cf 100644
--- a/upp/configs/single-b-upgrade.yaml
+++ b/upp/configs/single-b-upgrade.yaml
@@ -36,42 +36,42 @@ components:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [bjets, cjets]
+    classes: [bjets, cjets]
     num_global_objects: 14_500_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [ujets]
+    classes: [ujets]
     num_global_objects: 29_000_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [taujets]
+    classes: [taujets]
     num_global_objects: 2_013_889
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [bjets, cjets]
+    classes: [bjets, cjets]
     num_global_objects: 5_800_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [ujets]
+    classes: [ujets]
     num_global_objects: 11_600_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [taujets]
+    classes: [taujets]
     num_global_objects: 805_555
 
 
diff --git a/upp/configs/single-b.yaml b/upp/configs/single-b.yaml
index fa32887..19f715b 100644
--- a/upp/configs/single-b.yaml
+++ b/upp/configs/single-b.yaml
@@ -37,42 +37,42 @@ components:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [bjets, cjets]
+    classes: [bjets, cjets]
     num_global_objects: 45_000_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [ujets]
+    classes: [ujets]
     num_global_objects: 90_000_000
 
   - region:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [taujets]
+    classes: [taujets]
     num_global_objects: 6_250_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [bjets, cjets]
+    classes: [bjets, cjets]
     num_global_objects: 18_000_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [ujets]
+    classes: [ujets]
     num_global_objects: 36_000_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [taujets]
+    classes: [taujets]
     num_global_objects: 2_500_000
 
 
diff --git a/upp/configs/test.yaml b/upp/configs/test.yaml
index f439947..9653ae0 100644
--- a/upp/configs/test.yaml
+++ b/upp/configs/test.yaml
@@ -29,14 +29,14 @@ components:
       <<: *lowpt
     sample:
       <<: *ttbar
-    flavours: [bjets, cjets, ujets]
+    classes: [bjets, cjets, ujets]
     num_global_objects: 10_000
 
   - region:
       <<: *highpt
     sample:
       <<: *zprime
-    flavours: [bjets, cjets, ujets]
+    classes: [bjets, cjets, ujets]
     num_global_objects: 10_000
 
 resampling:
diff --git a/upp/configs/xbb-gn3x.yaml b/upp/configs/xbb-gn3x.yaml
index 956db93..d3a1c54 100644
--- a/upp/configs/xbb-gn3x.yaml
+++ b/upp/configs/xbb-gn3x.yaml
@@ -61,42 +61,42 @@ components:
       <<: *inclusive
     sample:
       <<: *htautauhad
-    flavours: [htautauhad]
+    classes: [htautauhad]
     num_global_objects: 10_000_000
 
   - region:
       <<: *inclusive
     sample:
       <<: *hbb
-    flavours: [hbb]
+    classes: [hbb]
     num_global_objects: 40_000_000
 
   - region:
       <<: *inclusive
     sample:
       <<: *hcc
-    flavours: [hcc]
+    classes: [hcc]
     num_global_objects: 40_000_000
 
   - region:
       <<: *inclusive
     sample:
       <<: *Zprime
-    flavours: [top]
+    classes: [top]
     num_global_objects: 35_000_000
 
   - region:
       <<: *inclusive
     sample:
       <<: *qcd
-    flavours: [qcd]
+    classes: [qcd]
     num_global_objects: 80_000_000
 
   - region:
       <<: *inclusive
     sample:
       <<: *Wqq
-    flavours: [Wqq]
+    classes: [Wqq]
     num_global_objects: 5_000_000
 
 
diff --git a/upp/configs/xbb-rw.yaml b/upp/configs/xbb-rw.yaml
index 9c06172..73843ae 100644
--- a/upp/configs/xbb-rw.yaml
+++ b/upp/configs/xbb-rw.yaml
@@ -73,42 +73,42 @@ components:
       <<: *inclusive
     sample:
       <<: *hbb
-    flavours: [hbb]
+    classes: [hbb]
     num_global_objects: -1
 
   - region:
       <<: *inclusive
     sample:
       <<: *hcc
-    flavours: [hcc]
+    classes: [hcc]
     num_global_objects: -1
 
   - region:
       <<: *inclusive
     sample:
       <<: *htautauhad
-    flavours: [htautauhad]
+    classes: [htautauhad]
     num_global_objects: -1
 
   - region:
       <<: *inclusive
     sample:
       <<: *zprime
-    flavours: [top]
+    classes: [top]
     num_global_objects: -1
 
   - region:
       <<: *inclusive
     sample:
       <<: *qcd
-    flavours: [qcd]
+    classes: [qcd]
     num_global_objects: -1
 
   - region:
       <<: *inclusive
     sample:
       <<: *wqq
-    flavours: [Wqq]
+    classes: [Wqq]
     num_global_objects: -1
 
 
diff --git a/upp/configs/xbb.yaml b/upp/configs/xbb.yaml
index 0f558f4..0555a16 100644
--- a/upp/configs/xbb.yaml
+++ b/upp/configs/xbb.yaml
@@ -30,28 +30,28 @@ components:
       <<: *inclusive
     sample:
       <<: *hbb
-    flavours: [hbb]
+    classes: [hbb]
     num_global_objects: 30_000_000
 
   - region:
       <<: *inclusive
     sample:
       <<: *hcc
-    flavours: [hcc]
+    classes: [hcc]
     num_global_objects: 30_000_000
 
   - region:
       <<: *inclusive
     sample:
       <<: *top
-    flavours: [top]
+    classes: [top]
     num_global_objects: 30_000_000
 
   - region:
       <<: *inclusive
     sample:
       <<: *qcd
-    flavours: [qcd]
+    classes: [qcd]
     num_global_objects: 50_000_000
 
 resampling:
diff --git a/upp/configs/xtautau.yaml b/upp/configs/xtautau.yaml
index e0fcf81..454d3bf 100644
--- a/upp/configs/xtautau.yaml
+++ b/upp/configs/xtautau.yaml
@@ -30,35 +30,35 @@ components:
       <<: *inclusive
     sample:
       <<: *htauhad
-    flavours: [htauhad]
+    classes: [htauhad]
     num_global_objects: 5_000_000
 
   - region:
       <<: *inclusive
     sample:
       <<: *hbb
-    flavours: [hbb]
+    classes: [hbb]
     num_global_objects: 14_500_000
 
   - region:
       <<: *inclusive
     sample:
       <<: *hcc
-    flavours: [hcc]
+    classes: [hcc]
     num_global_objects: 14_500_000
 
   - region:
       <<: *inclusive
     sample:
       <<: *top
-    flavours: [top]
+    classes: [top]
     num_global_objects: 8_000_000
 
   - region:
       <<: *inclusive
     sample:
       <<: *qcd
-    flavours: [qcd]
+    classes: [qcd]
     num_global_objects: 22_000_000
 
 resampling:

From 1bb5517b4a7df813c3af0b357363d654222e992f Mon Sep 17 00:00:00 2001
From: Alexander Froch <Alexander.Froch@cern.ch>
Date: Thu, 2 Jul 2026 17:28:13 +0200
Subject: [PATCH 12/13] Resolve the custom class_config path relative to the
 config directory

class_config is annotated Path | None, so it was skipped by the Path
resolution loop in __post_init__ and, unlike other path fields, resolved
against the CWD instead of base_dir. Resolve it against base_dir like
vds_dir so a relative class_config next to the config is found.
---
 tests/unit/classes/test_preprocessing_config.py | 17 +++++++++++++++++
 upp/classes/preprocessing_config.py             |  3 +++
 2 files changed, 20 insertions(+)

diff --git a/tests/unit/classes/test_preprocessing_config.py b/tests/unit/classes/test_preprocessing_config.py
index e7a2f12..27b6217 100644
--- a/tests/unit/classes/test_preprocessing_config.py
+++ b/tests/unit/classes/test_preprocessing_config.py
@@ -315,3 +315,20 @@ def test_separate_flavour_config(self) -> None:
             config.flavour_cont,
             LabelContainer.from_yaml(yaml_path=self.CFG_DIR / "test_flavour_config.yaml"),
         )
+
+    def test_relative_class_config_resolved_against_base_dir(self) -> None:
+        config = PreprocessingConfig(
+            config_path=self.CFG_DIR / "test.yaml",
+            split="train",
+            config={
+                "resampling": {"variables": {"jets": {"labels": ["test"]}}, "target": "bjets"},
+                "components": [],
+                "variables": {"jets": {"labels": ["test"]}},
+            },
+            base_dir=self.CFG_DIR,
+            class_config=Path("test_flavour_config.yaml"),
+            skip_checks=True,
+        )
+        expected = (self.CFG_DIR / "test_flavour_config.yaml").absolute()
+        self.assertEqual(config.class_config, expected)
+        self.assertEqual(config.flavour_cont, LabelContainer.from_yaml(yaml_path=expected))
diff --git a/upp/classes/preprocessing_config.py b/upp/classes/preprocessing_config.py
index c028349..bc8ccb9 100644
--- a/upp/classes/preprocessing_config.py
+++ b/upp/classes/preprocessing_config.py
@@ -214,6 +214,9 @@ def __post_init__(self):
         # vds_dir is optional (Path | None), so the loop above skips it; resolve it here
         if self.vds_dir is not None:
             self.vds_dir = self.get_path(Path(self.vds_dir))
+        # class_config is optional (Path | None) and also skipped above; resolve it too
+        if self.class_config is not None:
+            self.class_config = self.get_path(Path(self.class_config))
         if not self.ntuple_dir.exists() and not self.skip_checks:
             raise FileNotFoundError(f"Path {self.ntuple_dir} does not exist")
         self.components_dir = self.components_dir / self.split

From d1603f613832f86af12ba173b83938e7c7e55682 Mon Sep 17 00:00:00 2001
From: Alexander Froch <Alexander.Froch@cern.ch>
Date: Thu, 2 Jul 2026 17:28:45 +0200
Subject: [PATCH 13/13] Document custom classes and add a non-jet end-to-end
 example

Add a Custom classes section to the configuration docs describing the
class definition yaml schema and how class_config generalises the
framework beyond jets. Add an end-to-end reweighting test that renames
the mock object group and drives the pipeline with a custom class_config
(relative path) defining non-standard classes, asserting the output
carries the custom class labels.
---
 docs/configuration.md                         | 40 +++++++-
 docs/run.md                                   |  2 +-
 .../integration/fixtures/custom_flavours.yaml | 13 +++
 .../test_config_rw_custom_flavours.yaml       | 96 +++++++++++++++++++
 tests/integration/test_run_rw.py              | 39 ++++++++
 5 files changed, 186 insertions(+), 4 deletions(-)
 create mode 100644 tests/integration/fixtures/custom_flavours.yaml
 create mode 100644 tests/integration/fixtures/test_config_rw_custom_flavours.yaml

diff --git a/docs/configuration.md b/docs/configuration.md
index aa9f0ad..26694e2 100644
--- a/docs/configuration.md
+++ b/docs/configuration.md
@@ -123,14 +123,14 @@ components:
     <<: *lowpt
     sample:
     <<: *ttbar
-    flavours: [bjets, cjets, ujets]
+    classes: [bjets, cjets, ujets]
     num_global_objects: 10_000_000
 
 - region:
     <<: *highpt
     sample:
     <<: *zprime
-    flavours: [bjets, cjets, ujets]
+    classes: [bjets, cjets, ujets]
     num_global_objects: 5_000_000
 ```
 
@@ -140,13 +140,47 @@ Notice that we use `<<*` insertion tool to insert already defined regions and sa
 | ------- | ---- | ----------- |
 | `region`| anchor | The pre-defined kinematic region anchor, e.g. `lowpt` or `highpt`, or `inclusive` if not splitting in $p_T$ |
 | `sample`| anchor | The pre-defined sample anchor, e.g. $t\bar{t}$ or $Z'$ |
-| `flavours` | `list[str]` | One or more jet flavours, e.g. `[bjets]` or `[ujets]`. The list syntax is pure syntactic sugar. If more then one is provided, separate components are created for each flavour.|
+| `classes` | `list[str]` | One or more object classes (flavours), e.g. `[bjets]` or `[ujets]`. Each name must exist in the active class container (the atlas-ftag-tools bundled flavours by default, or your own file via `class_config` — see [Custom classes](#custom-classes)). The list syntax is pure syntactic sugar. If more then one is provided, separate components are created for each class.|
 |`num_global_objects`|`int`| The number of jets to be sampled from this component in the training split. When resampling is skipped, `-1` writes all jets of this component passing the cuts.|
 |`num_global_objects_val`|`int`| **Optional** (default: `num_global_objects//10`) number of jets of this component in validation set.|
 |`num_global_objects_test`|`int`| **Optional** (default: `num_global_objects//10`) number of jets of this component in a test set.|
 
 
 
+### Custom classes
+
+By default the class definitions come from the flavour labels bundled with
+`atlas-ftag-tools`, selected with `class_category` (`standard` or `extended`).
+These are jet flavours, but the framework itself is object-agnostic: to classify
+any other object type, point `class_config` at your own classes yaml. It is a
+list of class definitions, each with a `name`, plotting `label`, selection
+`cuts`, a `colour`, a `category`, and an optional `_px` probability name:
+
+```yaml
+- name: heavy
+  label: Heavy objects
+  cuts: ["HadronConeExclTruthLabelID == 5"]
+  colour: tab:red
+  category: custom
+- name: light
+  label: Light objects
+  cuts: ["HadronConeExclTruthLabelID == 0"]
+  colour: tab:blue
+  category: custom
+```
+
+Reference it from the global config; a relative path is resolved against
+`base_dir`, and `class_config` takes precedence over `class_category`:
+
+```yaml
+global:
+  global_name: objects
+  class_config: custom_flavours.yaml
+```
+
+The `classes` listed for each component then refer to the `name` entries in this
+file (e.g. `classes: [heavy, light]`).
+
 ### Variables
 
 The next thing you need is to provide the variables that are taken from the TDD files and written in the resampled dataset.
diff --git a/docs/run.md b/docs/run.md
index f0ab974..bfb1037 100644
--- a/docs/run.md
+++ b/docs/run.md
@@ -61,7 +61,7 @@ Afterwards, the prepare stage reads a specified number of jets (`num_global_obje
         <<: *lowpt
         sample:
         <<: *ttbar
-        flavours: [ghostsplitbjets]
+        classes: [ghostsplitbjets]
         num_global_objects: 22_000_000
         num_global_objects_test: 2_000_000
     ```
diff --git a/tests/integration/fixtures/custom_flavours.yaml b/tests/integration/fixtures/custom_flavours.yaml
new file mode 100644
index 0000000..27e8f01
--- /dev/null
+++ b/tests/integration/fixtures/custom_flavours.yaml
@@ -0,0 +1,13 @@
+# Custom, non-jet flavour definitions used by test_rw_custom_flavours.
+# Names deliberately differ from the atlas-ftag-tools bundled flavours to prove
+# the container is loaded from this file. Cuts select on the mock truth variable.
+- name: heavy
+  label: Heavy objects
+  cuts: ["HadronConeExclTruthLabelID == 5"]
+  colour: tab:red
+  category: custom
+- name: light
+  label: Light objects
+  cuts: ["HadronConeExclTruthLabelID == 0"]
+  colour: tab:blue
+  category: custom
diff --git a/tests/integration/fixtures/test_config_rw_custom_flavours.yaml b/tests/integration/fixtures/test_config_rw_custom_flavours.yaml
new file mode 100644
index 0000000..a39c9a9
--- /dev/null
+++ b/tests/integration/fixtures/test_config_rw_custom_flavours.yaml
@@ -0,0 +1,96 @@
+variables:
+  objects:
+    inputs:
+      - pt
+      - eta
+    labels:
+      - mass
+      - eventNumber
+
+  tracks:
+    inputs:
+      - dphi
+      - deta
+      - qOverP
+    labels:
+      - qOverP
+      - leptonID
+global_cuts: !include GN3V01/simple-split.yaml
+
+ttbar: &ttbar
+  name: ttbar
+  equal_global_objects: False
+  pattern:
+    - "data1.h5"
+    - "data2.h5"
+
+zprime: &zprime
+  name: zprime
+  equal_global_objects: False
+  pattern:
+    - "data3.h5"
+
+lowpt: &lowpt
+  name: lowpt
+  cuts:
+    - [pt, ">", 20_000]
+    - [pt, "<", 250_000]
+    - [eta, "<", 2.5]
+    - [eta, ">", -2.5]
+
+highpt: &highpt
+  name: highpt
+  cuts:
+    - [pt, ">", 250_000]
+    - [pt, "<", 6_000_000]
+    - [eta, "<", 2.5]
+    - [eta, ">", -2.5]
+
+components:
+  - region:
+      <<: *lowpt
+    sample:
+      <<: *ttbar
+    classes: [heavy, light]
+    num_global_objects: -1
+
+  - region:
+      <<: *highpt
+    sample:
+      <<: *zprime
+    classes: [heavy, light]
+    num_global_objects: -1
+
+reweighting:
+  num_global_objects_estimate: 200
+  merge_num_proc: 1
+  reweights:
+    - group: objects
+      reweight_vars: [pt, eta]
+      bins:
+        pt:
+          [
+            [20_000, 250_000, 50],
+            [250_000, 1_000_000, 50],
+            [1_000_000, 6_000_000, 50],
+          ]
+        eta: [[-2.5, 2.5, 40]]
+      class_var: flavour_label
+      class_target: mean
+    - group: tracks
+      reweight_vars: [deta]
+      bins:
+        deta: [[-1.0, 1.0, 50]]
+      class_var: leptonID
+      class_target: mean
+
+# note: sensible defaults are defined in the PreprocessingConfig constructor
+# class_config is a relative path, resolved against base_dir
+global:
+  global_name: objects
+  class_config: custom_flavours.yaml
+  batch_size: 1_000_000
+  num_global_objects_estimate: 25_000_000
+  base_dir: tmp/upp-tests/integration/temp_workspace/
+  out_dir: test_out
+  ntuple_dir: ntuples
diff --git a/tests/integration/test_run_rw.py b/tests/integration/test_run_rw.py
index 5981dfb..b2f3332 100644
--- a/tests/integration/test_run_rw.py
+++ b/tests/integration/test_run_rw.py
@@ -1,6 +1,7 @@
 from __future__ import annotations
 
 import os
+import shutil
 import subprocess
 from pathlib import Path
 
@@ -168,6 +169,44 @@ def test_rw_custom_object_name(self):
                 assert "flavour_label" in f["objects"].attrs
                 assert "flavour_label" in f["objects"].dtype.names
 
+    def test_rw_custom_flavours(self):
+        """End-to-end reweighting with a user-supplied custom class_config.
+
+        The mock "jets" group is renamed to "objects" and the config points
+        class_config at a custom classes yaml (given as a path relative to
+        base_dir) defining non-standard classes (heavy/light). Proves custom
+        classes work end-to-end for a non-jet object and that a relative
+        class_config path resolves against base_dir.
+        """
+        for container in ["data1.h5", "data2.h5", "data3.h5"]:
+            self._rename_mock_group(f"tmp/upp-tests/integration/temp_workspace/ntuples/{container}")
+
+        # Copy the custom classes file into base_dir so the relative
+        # class_config path in the config resolves against base_dir.
+        base_dir = Path("tmp/upp-tests/integration/temp_workspace")
+        shutil.copy(this_dir / "fixtures/custom_flavours.yaml", base_dir / "custom_flavours.yaml")
+
+        config = str(Path(this_dir / "fixtures/test_config_rw_custom_flavours.yaml"))
+
+        main(["--config", config, "--split", "train", "--split-components", *self.no])
+        main(["--config", config, "--rw", *self.no])
+
+        for split in ["train", "val", "test"]:
+            main(["--config", config, "--rwm", "--split", split, *self.no])
+            outfile = Path(
+                f"tmp/upp-tests/integration/temp_workspace/test_out/pp_output_{split}_vds.h5"
+            )
+            assert outfile.exists()
+            with h5py.File(outfile, "r") as f:
+                assert "objects" in f, "Expected 'objects' group in output file"
+                assert "jets" not in f, "Output must not contain a hardcoded 'jets' group"
+                assert "flavour_label" in f["objects"].dtype.names
+                labels = [
+                    x.decode() if isinstance(x, bytes) else str(x)
+                    for x in f["objects"].attrs["flavour_label"]
+                ]
+                assert labels == ["heavy", "light"], f"Expected custom flavours, found {labels}"
+
     def test_rw_unequal_objects(self):
         """Test reweighting when a file has fewer objects than num_global_objects_estimate.