Add claim outcome prediction as a tracked accuracy metric - #14
Open
Exios66 wants to merge 1 commit into
Open
Conversation
Introduce expected_outcome on synthetic skeletons and a predict_outcome pipeline stage (pay_full/pay_partial/deny/investigate/close_without_payment). Gold labels are deterministic from claim features so outcome accuracy complements classification and extraction reports. Includes eval CLI, batch summary metrics, Discord formatting, and sample eval reports. Co-authored-by: Jack J Burleson // LJM <Exios66@users.noreply.github.com>
Exios66
marked this pull request as ready for review
July 19, 2026 05:09
|
Bugbot is not enabled for your account, so this pull request was not reviewed. Enable Bugbot in the Cursor dashboard to get automatic reviews on future PRs. |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Adds claim outcome prediction as a tracked accuracy metric alongside classification and extraction.
expected_outcome(pay_full/pay_partial/deny/investigate/close_without_payment), derived deterministically from complexity + financials + injuriespredict_outcomein the chain:to_markdown → classify → extract → vision_llm → predict_outcome → summarizepython -m src.pipeline.eval_outcome --in …→evaluation/reports/outcome_prediction_report.*outcome_metrics.accuracywhen gold labels are presentBecause gold labels use the same feature rules as the predictor, outcome accuracy measures how well upstream extraction recovers the features needed for disposition — complementary to doc-type accuracy and field F1.
Test plan
pytest tests/test_outcome_prediction.py tests/test_pipeline.py tests/test_generation.py tests/test_discord_bot.pyevaluation/reports/outcome_prediction_report.*eval_outcomeon a full synthetic document JSONL when available