intervention_comparison_matrix
Compare robustness interventions across clean and shifted metrics using direction-aware evidence signs.
- License 许可
- Apache-2.0
- 最近更新
- 2026-09-03
- Stars
- ★ 351
- Forks
- 27
01 前言 Front Matter
- name
- intervention_comparison_matrix
- description
- Compare robustness interventions across clean and shifted metrics using direction-aware evidence signs.
02 资源文件 2
- 脚本scripts/matrix.py834 B
- 脚本tests/test_matrix.py376 B
03 SKILL.md 正文
Intervention Comparison Matrix
Use this skill to summarize robustness interventions in the style of the paper's tables: each method is compared against a baseline on clean and shifted metrics, and improvements are interpreted according to whether the metric is error or accuracy.
Inputs
- A list of metric rows with an
interventionname and dataset metric values. - The baseline intervention name.
- Metric direction: lower-is-better for error, higher-is-better for accuracy.
Outputs
- Direction-aware deltas for each intervention and dataset.
- Evidence signs showing improvement, regression, or tie.
- The best shifted intervention when the target dataset is supplied.
Workflow
- Locate the baseline row.
- For every intervention, compute signed improvements for available datasets.
- Mark missing values as unavailable rather than zero.
- Report the strongest intervention for the chosen shifted metric and whether the clean/shift gap narrows.
Validation
Run python tests/test_matrix.py or the Distiller tree validator.
Limitations
This skill analyzes metric tables; it does not judge whether the datasets themselves are representative.
04 同仓库更多 Skills
passnet-triton-opt
Make a single PassNet Triton kernel fast AND numerically faithful: performance model (when a replacement can win at all), block/grid/warp tuning, autotune policy, launch overhead, and per-op numeric recipes to pass the dtype baseline tolerances. Use when a pass matches and is correct but speedup below expected, or when correctness fails by small numeric margins.
passnet-solve
END-TO-END playbook for solving one PassNet sample: analyze the computation graphs, decide the optimization strategy (what to fuse, what to replace, what to leave alone), drive the iteration loop, and maximize the sample score. This is the ENTRY skill — invoke it first for any PassNet optimization task; it tells you when to use passnet-pattern-fusion, passnet-triton-opt and passnet-feedback.
passnet-skill
PassNet GPU kernel optimization via compiler passes. Design and implement Triton-based optimization passes, create pass files under ./pass_dir/, self-evaluate with pass_evaluator, and iterate to maximize GPU speedup.
passnet-pattern-fusion
Author PassNet pass files: write patterns that actually MATCH the FX graph, pick fusion regions (which ops to absorb into one Triton kernel), and structure multi-pass submissions with the mandatory shared-dispatch architecture. Use when creating or fixing pattern()/replacement_args()/replacement_func() files, when a pass "failed to match", or when deciding how to fuse multiple kernels/ops.
passnet-orchestrate
Round/batch planning and decision support for PassNet graph optimization. Use for multi-sample triage, worker allocation, eval-budget policy, and post-eval keep/revert decisions. For solving one concrete sample end to end, use passnet-solve as the entry skill; consult this skill only when you need broader planning or a specific decision gate.
passnet-feedback
Fast, deterministic feedback for PassNet work: pre-flight pattern/match verification WITHOUT burning a GPU evaluation, per-node bottleneck analysis of a sample's graphs, and eval-log parsing into per-variant status + estimated score + failure classification. Use BEFORE every GPU evaluation (check_pattern), at the START of a sample (analyze_graph), and AFTER every evaluation (parse_eval_log).