docs: add proposed ADR-073 on scoring/reward language scope#681
Open
Brad-Edwards wants to merge 1 commit into
Open
docs: add proposed ADR-073 on scoring/reward language scope#681Brad-Edwards wants to merge 1 commit into
Brad-Edwards wants to merge 1 commit into
Conversation
Examine whether the OCR-inherited SDL scoring pipeline (metrics/evaluations/tlos/goals) and the CybORG agents.reward_calculator label belong in ACES, against the experiment-vs-data-use boundary already drawn by ADR-055/064/069. Recommend (proposed) treating these surfaces as vestigial in the SDL, keeping objectives+conditions, narrowing objective success to observable state, and routing graded scoring to the experiment/evaluator plane. Add scoring-scope research notes (docs/research/scoring-scope/) and a SEM-206 assessment-semantics compatibility guardrail. Decision deferred to review. Refs #671. ADR-073. SEM-206.
|
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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 proposed ADR-073 examining whether the OCR-inherited SDL scoring pipeline (metrics/evaluations/tlos/goals) and the CybORG agents.reward_calculator label belong in ACES, plus scoring-scope research notes and a SEM-206 assessment-semantics compatibility guardrail. Doc-only; the decision is deferred to review (status proposed). Recommends treating these surfaces as vestigial against the experiment-vs-data-use boundary already drawn by ADR-055/064/069 and routing graded scoring to the experiment/evaluator plane, keeping objectives+conditions and narrowing objective success to observable state. Closes #671.
Requirement UIDs
SEM-206Related Issues
Closes #671
ADR Impact
Changes
Test Plan
nox -s verifypasses locally (Sphinx docs build, ADR acceptance-content pin, schema publication manifest + generated-schema drift, ruff, full pytest + integration suite).Ground Control Checks
nox -s verifygreen.Traceability
Checklist
proposedstatus).