diff --git a/docs/notebook_source/01_your_first_anonymization.py b/docs/notebook_source/01_your_first_anonymization.py index 65f96b6d..878a9faf 100644 --- a/docs/notebook_source/01_your_first_anonymization.py +++ b/docs/notebook_source/01_your_first_anonymization.py @@ -1,3 +1,6 @@ +# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved. +# SPDX-License-Identifier: Apache-2.0 + # --- # jupyter: # jupytext: diff --git a/docs/notebook_source/02_inspecting_detected_entities.py b/docs/notebook_source/02_inspecting_detected_entities.py index 110bf75c..393a8d00 100644 --- a/docs/notebook_source/02_inspecting_detected_entities.py +++ b/docs/notebook_source/02_inspecting_detected_entities.py @@ -1,3 +1,6 @@ +# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved. +# SPDX-License-Identifier: Apache-2.0 + # --- # jupyter: # jupytext: diff --git a/docs/notebook_source/03_choosing_a_replacement_strategy.py b/docs/notebook_source/03_choosing_a_replacement_strategy.py index 9095fccc..ebe75c57 100644 --- a/docs/notebook_source/03_choosing_a_replacement_strategy.py +++ b/docs/notebook_source/03_choosing_a_replacement_strategy.py @@ -1,3 +1,6 @@ +# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved. +# SPDX-License-Identifier: Apache-2.0 + # --- # jupyter: # jupytext: diff --git a/docs/notebook_source/04_rewriting_biographies.py b/docs/notebook_source/04_rewriting_biographies.py index 2199678d..b7955e68 100644 --- a/docs/notebook_source/04_rewriting_biographies.py +++ b/docs/notebook_source/04_rewriting_biographies.py @@ -1,3 +1,6 @@ +# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved. +# SPDX-License-Identifier: Apache-2.0 + # --- # jupyter: # jupytext: @@ -18,8 +21,8 @@ # --> # # 🕵️ Rewriting Biographies # -# Instead of replacing entities with tokens, rewrite mode generates a -# privacy-safe transformation of the entire text. The `run()` / `preview()` pipeline: +# Instead of replacing individual entities, rewrite mode transforms the entire +# text and measures any sensitive information that remains. The `run()` / `preview()` pipeline: # # 1. Detects entities (same as replace mode, plus latent entity detection) # 2. Classifies the domain and assigns sensitivity dispositions @@ -154,7 +157,7 @@ # %% [markdown] # ## 🚩 Filter by review flag # -# - Records where automated metrics exceed thresholds are flagged for manual review. +# - Records that cross the configured leakage or utility thresholds are flagged for manual review. # - `needs_human_review` is threshold-based, so a record can have small nonzero # leakage without being flagged. # - Use this to prioritize human attention on the records that need it most. @@ -173,7 +176,7 @@ # Call `evaluate()` to run LLM-as-judge scoring on the rewrite result — detection validity and three quality rubrics (privacy, quality, style). # Evaluation makes additional LLM calls per record. For larger datasets, evaluate # a preview first; this tutorial evaluates all 25 rows to demonstrate the complete workflow. -# This holistic judge is independent of pipeline leakage scoring, so their assessments may differ. +# The holistic privacy rubric and pipeline leakage metric are independent, so they may disagree. # See [Evaluation](../../concepts/evaluation/#rewrite-evaluation) for details. # %% diff --git a/docs/notebook_source/05_rewriting_legal_documents.py b/docs/notebook_source/05_rewriting_legal_documents.py index a2354af8..e9d305d2 100644 --- a/docs/notebook_source/05_rewriting_legal_documents.py +++ b/docs/notebook_source/05_rewriting_legal_documents.py @@ -1,3 +1,6 @@ +# SPDX-FileCopyrightText: Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved. +# SPDX-License-Identifier: Apache-2.0 + # --- # jupyter: # jupytext: @@ -178,9 +181,10 @@ # %% [markdown] # ## 🚩 Filter by review flag # -# - Records where automated metrics exceed thresholds are flagged for manual review. -# - The repair loop stops after `max_repair_iterations`; records that still need -# repair remain flagged for human review but are not pipeline failures. +# - Records that cross the configured leakage or utility thresholds are flagged for manual review. +# - The repair loop stops after `max_repair_iterations`. Afterward, +# `needs_human_review` is computed separately from the final leakage, utility, +# and high-sensitivity-leak metrics. # - Use this to prioritize human attention on the records that need it most. # - See [Working with flagged records](../../concepts/rewrite/#working-with-flagged-records) # for guidance on diagnosing and resolving flagged records. @@ -197,7 +201,7 @@ # Call `evaluate()` to run LLM-as-judge scoring on the rewrite result — detection validity and three quality rubrics (privacy, quality, style). # Evaluation makes additional LLM calls per record. For larger datasets, evaluate # a preview first; this tutorial evaluates all 25 rows to demonstrate the complete workflow. -# This holistic judge is independent of pipeline leakage scoring, so their assessments may differ. +# The holistic privacy rubric and pipeline leakage metric are independent, so they may disagree. # See [Evaluation](../../concepts/evaluation/#rewrite-evaluation) for details. # %% diff --git a/docs/notebooks/04_rewriting_biographies.ipynb b/docs/notebooks/04_rewriting_biographies.ipynb index aad8be15..5a8796c4 100644 --- a/docs/notebooks/04_rewriting_biographies.ipynb +++ b/docs/notebooks/04_rewriting_biographies.ipynb @@ -11,8 +11,8 @@ "-->\n", "# 🕵️ Rewriting Biographies\n", "\n", - "Instead of replacing entities with tokens, rewrite mode generates a\n", - "privacy-safe transformation of the entire text. The `run()` / `preview()` pipeline:\n", + "Instead of replacing individual entities, rewrite mode transforms the entire\n", + "text and measures any sensitive information that remains. The `run()` / `preview()` pipeline:\n", "\n", "1. Detects entities (same as replace mode, plus latent entity detection)\n", "2. Classifies the domain and assigns sensitivity dispositions\n", @@ -800,7 +800,7 @@ "source": [ "## 🚩 Filter by review flag\n", "\n", - "- Records where automated metrics exceed thresholds are flagged for manual review.\n", + "- Records that cross the configured leakage or utility thresholds are flagged for manual review.\n", "- `needs_human_review` is threshold-based, so a record can have small nonzero\n", " leakage without being flagged.\n", "- Use this to prioritize human attention on the records that need it most.\n", @@ -891,7 +891,7 @@ "Call `evaluate()` to run LLM-as-judge scoring on the rewrite result — detection validity and three quality rubrics (privacy, quality, style).\n", "Evaluation makes additional LLM calls per record. For larger datasets, evaluate\n", "a preview first; this tutorial evaluates all 25 rows to demonstrate the complete workflow.\n", - "This holistic judge is independent of pipeline leakage scoring, so their assessments may differ.\n", + "The holistic privacy rubric and pipeline leakage metric are independent, so they may disagree.\n", "See [Evaluation](../../concepts/evaluation/#rewrite-evaluation) for details." ] }, diff --git a/docs/notebooks/05_rewriting_legal_documents.ipynb b/docs/notebooks/05_rewriting_legal_documents.ipynb index ad423f63..26cd69e3 100644 --- a/docs/notebooks/05_rewriting_legal_documents.ipynb +++ b/docs/notebooks/05_rewriting_legal_documents.ipynb @@ -960,9 +960,10 @@ "source": [ "## 🚩 Filter by review flag\n", "\n", - "- Records where automated metrics exceed thresholds are flagged for manual review.\n", - "- The repair loop stops after `max_repair_iterations`; records that still need\n", - " repair remain flagged for human review but are not pipeline failures.\n", + "- Records that cross the configured leakage or utility thresholds are flagged for manual review.\n", + "- The repair loop stops after `max_repair_iterations`. Afterward,\n", + " `needs_human_review` is computed separately from the final leakage, utility,\n", + " and high-sensitivity-leak metrics.\n", "- Use this to prioritize human attention on the records that need it most.\n", "- See [Working with flagged records](../../concepts/rewrite/#working-with-flagged-records)\n", " for guidance on diagnosing and resolving flagged records." @@ -1136,7 +1137,7 @@ "Call `evaluate()` to run LLM-as-judge scoring on the rewrite result — detection validity and three quality rubrics (privacy, quality, style).\n", "Evaluation makes additional LLM calls per record. For larger datasets, evaluate\n", "a preview first; this tutorial evaluates all 25 rows to demonstrate the complete workflow.\n", - "This holistic judge is independent of pipeline leakage scoring, so their assessments may differ.\n", + "The holistic privacy rubric and pipeline leakage metric are independent, so they may disagree.\n", "See [Evaluation](../../concepts/evaluation/#rewrite-evaluation) for details." ] },