feat(evals): add near-field template experiment#62
Conversation
Add an analytic folded fan near-field experiment for issue 61. The prototype derives and documents the mapped point-target and bilinear self-interaction forms, frames the reusable correction hypothesis as a functional expansion in the smooth metric field M(z), and adds a script wrapper for running the baseline check. Tests cover fan-map invariants, log-kernel scale behavior, point-target convergence, and the diagonal metric singular split.\n\nValidation: uv run --extra dev python -m pytest tests/evals/test_nearfield_templates.py tests/test_script_wrappers.py; uv run --extra dev python scripts/run_nearfield_template_experiment.py --order 6; make dev Entire-Checkpoint: 3d4ca5797c60
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: e1e907dff4
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
Document how smooth metric fields in folded chart singular integrals can be expanded around a reference metric to recover fixed template tables times per-chart runtime coefficients. The derivation ties the precomputed-table technique to the fan-map metric M(r,t), Jacobian factors, and smooth-remainder payloads.\n\nValidation: uv run python scripts/check_docs_freshness.py Entire-Checkpoint: 7ffd824cac89
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: e987ed6079
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
Convert the near-field template derivation from text code fences to display math so GitHub renders the formulas properly. The content is unchanged aside from LaTeX notation cleanup.\n\nValidation: uv run python scripts/check_docs_freshness.py Entire-Checkpoint: c15094b32a03
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 2653068aff
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
Address Codex review feedback on the near-field template prototype. Reject direct self-interaction quadrature choices with overlapping source/target nodes, report a clear error when point-target quadrature hits a coincident source node, and generalize the log-kernel scale law to density-weighted source and target masses. Also weaken the local metric split documentation so it describes a leading singular model plus bounded/higher-order corrections rather than an unqualified smooth remainder.\n\nValidation: make dev Entire-Checkpoint: 95096c66f419
Update the near-field template derivation to start from a CAD-realistic Bezier trim fan chart instead of a straight-edge specialization. Straight fan pieces are now described as smoke-test fixtures, while the metric-field expansion is framed in terms of Bezier control points and seed locations.\n\nValidation: uv run python scripts/check_docs_freshness.py Entire-Checkpoint: c9e0b70886a7
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: 38560bbfc3
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| order=order, | ||
| source_order=source_order, | ||
| ) | ||
| near_point_target = (0.47, 0.42) |
There was a problem hiding this comment.
For the current fan, (0.47, 0.42) is inside the source triangle (approximately (r,t)=(0.773,0.603)), so the baseline computes its point_target_reference with ordinary Gauss quadrature over an on-surface logarithmic singularity. Since point_target_laplace_potential only rejects exact quadrature-node coincidences, this reported low-order-vs-reference error can be dominated by singular quadrature artifacts rather than a reliable near-disjoint reference; fresh evidence beyond the earlier coincident-node comment is that the committed baseline target itself lies on the source piece.
Useful? React with 👍 / 👎.
Remove the folded-target and bilinear self-interaction framing from the near-field template experiment. The docs now describe source folded pieces evaluated at physical target nodes in containing and neighboring boxes, and the experiment API now reports point-target scale-law quantities only.\n\nValidation: make dev; uv run --extra dev python -m pytest tests/evals/test_nearfield_templates.py tests/test_script_wrappers.py; uv run python scripts/check_docs_freshness.py Entire-Checkpoint: 6cb8d3064a3b
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: db19ee4e0d
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
| point_reference = point_target_laplace_potential( | ||
| fan, | ||
| near_point_target, | ||
| order=max(order + 8, 16), |
There was a problem hiding this comment.
When order <= 0 is passed through the public experiment helper or CLI (for example --order 0), this max(order + 8, 16) silently promotes the reference rule to 16 while the low-order path is promoted to 2, so the run succeeds and reports an invalid result.order instead of rejecting the input. This can let automated sweeps record misleading rows, unlike the underlying quadrature helpers that require positive orders; validate order at the experiment entry point before deriving these rule sizes.
Useful? React with 👍 / 👎.
| jacobian = fan.signed_jacobian(r) | ||
| for t, wt in zip(nodes, weights, strict=True): | ||
| source = fan.point(r, t) | ||
| if hypot(target[0] - source[0], target[1] - source[1]) <= _COINCIDENT_TOL: |
There was a problem hiding this comment.
When a valid disjoint near-field case is expressed in a small coordinate scale, this absolute 1e-14 cutoff rejects finite integrals as coincident; for example a fan with vertices on the order of 1e-15 and an off-surface target at (2e-15, 2e-15) raises this error even though no source node equals the target. Since the experiment includes scale-law checks and box-local near-field geometry, use an exact or scale-relative coincidence test so small boxes are not misclassified.
Useful? React with 👍 / 👎.
Revise the point-target singular split to use a high-order Taylor-jet distance model instead of a leading metric-only model. Also adjust display equations to use aligned environments and scalable matrix delimiters so GitHub Markdown renders the formulas correctly.\n\nValidation: uv run python scripts/check_docs_freshness.py Entire-Checkpoint: d6bbf8d080ee
Clarify that P_K is the high-order local model of the physical displacement x - T(xi), obtained by substituting the chart Taylor jet into the point-target kernel distance. This makes the critical table object explicit before defining it.\n\nValidation: uv run python scripts/check_docs_freshness.py Entire-Checkpoint: b61a31d972cf
Rewrite the metric-field expansion tables section around the full high-order displacement polynomial P_K for both on-surface and off-surface point targets. The metric-only model is now explicitly a K=1, d=0 sanity case rather than the intended table construction.\n\nValidation: uv run python scripts/check_docs_freshness.py Entire-Checkpoint: 26fe5c4309e9
Revise the feasibility assessment to reflect the full point-target displacement-jet analysis. The reusable object is now framed as reference-jet tables plus compact interpolation or low-rank coefficients, with metric-only organization called out as a possible subcase rather than the main hypothesis.\n\nValidation: uv run python scripts/check_docs_freshness.py Entire-Checkpoint: 9b045011c52a
Document the Gaussian-window kernel split proposed for controlling point-target near-field tables. The singular table is now restricted to targets inside or very close to each fan piece, while the smooth remainder is handled by ordinary folded-decomposition quadrature.\n\nValidation: uv run python scripts/check_docs_freshness.py Entire-Checkpoint: 3c186d8f69f9
Document the simplification for interior point targets: choose the folded-decomposition anchor at the target and refold the source panel so the logarithmic singularity sits at the Duffy apex. This reduces the table problem to near-boundary/outside targets after Gaussian windowing.\n\nValidation: uv run python scripts/check_docs_freshness.py Entire-Checkpoint: bd206c686530
Update the Gaussian-window split to reflect the DMK-style approach: evaluate the compact local singular part with analytic or semi-analytic asymptotic expansion, while using ordinary folded quadrature for the smooth remainder. The local table target is now asymptotic moments/coefficient maps rather than a generic near-field table.\n\nValidation: uv run python scripts/check_docs_freshness.py Entire-Checkpoint: 4d7a58573bba
1 participant
Summary
Closes #61.
Adds the first CUTKIT-side near-field template experiment for folded-decomposition box-code handoff work.
What Changed
docs/nearfield-template-experiments.mdwith the point-target and bilinear target-piece derivation.M(z) = DT(z)^T DT(z).cutkit.evals.nearfield_templateswith an analytic straight fan map, point-target Laplace potential, bilinear self-interaction reference, scale-law check, and diagonal metric-remainder samples.scripts/run_nearfield_template_experiment.pyfor the baseline experiment.Validation
uv run --extra dev python -m pytest tests/evals/test_nearfield_templates.py tests/test_script_wrappers.pyuv run --extra dev python scripts/run_nearfield_template_experiment.py --order 6make dev