Skip to content

feat(evaluation): add FMEA scorer - #543

Merged
DhavalRepo18 merged 2 commits into
mainfrom
fmea_evaluator
Sep 15, 2026
Merged

DhavalRepo18 merged 2 commits into
mainfrom
fmea_evaluator

Conversation

@ChathurangiShyalika

Copy link
Copy Markdown
Collaborator

Summary

This PR adds a deterministic evaluator for the structured FMEA scenario family.

  • Uses semantic F1 to award partial credit for correct failure modes and catalogue facts.
  • Defines scenario success as semantic F1 strictly greater than 0.70.
  • Loads scenario_meta.json, rubric.json, and reference_answer.json for custom evaluation.
  • Retains rubric-weighted scoring, strict JSON compliance, and catalogue-tool usage as diagnostic measures.
  • Adds the fmea_all scenario selector covering all 17 FMEA scenarios.
  • Adds evaluator documentation and regression tests.

Chathurangi Shyalika added 2 commits September 14, 2026 22:05
Signed-off-by: Chathurangi Shyalika <chathurangishyalika@Chathurangis-MacBook-Pro.local>
Signed-off-by: Chathurangi Shyalika <chathurangishyalika@Chathurangis-MacBook-Pro.local>
@DhavalRepo18
DhavalRepo18 merged commit bcf21c0 into main Sep 15, 2026
5 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants