Repository navigation
Conversation
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Record partial parity reached on the tested GLM subsets for harbor-framework/adapters#9. This PR targets its
discoverphysics-adapterbranch; merging here updates harbor-framework#9.Harbor's run-score range-overlap criterion is met for both configurations, each with three repetitions per side:
Scores are fractions. Both discovery and judging used
zai-org/GLM-5.3-Flash; the two runtime strata stay separate. Changes are limited toparity_experiment.json, the README parity summary, andadapter_metadata.json.HF parity PR #270 contains the raw evidence and provenance and is stacked on the author's oracle PR #271. The bundle retains the unique evidence; 29 byte-identical log copies were removed.
The result applies to these historical subsets; full-adapter acceptance and migrated-head equivalence are not established. The reviewer-runtime patch/fork is deferred, leaving
original_parity_repoexplicitly empty. Existing security/fidelity findings and the standard CLI-agent check remain outstanding.Validation: 31 structural checks pass with zero errors or warnings. Raw run arrays and sample SEMs agree with the uploaded result collections; counts, sampling rates, range overlap, and parity-summary parsing were checked.
git diff --checkpasses. No runtime or grading changes and no new model runs.Prepared with Codex assistance.