Add three-way critic closing line (keep finding labels) - #1
Open
shagghiesuperstar wants to merge 1 commit into
Open
Add three-way critic closing line (keep finding labels)#1shagghiesuperstar wants to merge 1 commit into
shagghiesuperstar wants to merge 1 commit into
Conversation
The critic still classifies each dispute with confirmed / refuted-with-evidence / unresolved / duplicate / out-of-scope. The report must then end with exactly one of AGREE, DISAGREE_EVIDENCE, or DISAGREE_CONCERN so a citation-free rubber-stamp cannot pass as a complete critic pass. Source: arXiv:2608.18167 section 4.4.
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
What this changes
Adds a required three-way closing line on the critic report (
AGREE|DISAGREE_EVIDENCE|DISAGREE_CONCERN) without replacing the existing per-dispute finding labels (confirmed,refuted-with-evidence,unresolved,duplicate,out-of-scope).Why
A critic that only triages findings can still rubber-stamp a thin review or cave to a citation-free rebuttal (false consensus). The three-way close is the review-audit contract from arXiv:2608.18167 section 4.4. Finding labels stay for each dispute.
Checks
python3 -B -m scripts.check_packagepassespython3 -B -m unittest discover -s testspasses (122 tests)review/inventory.jsonunchangedNotes for the reviewer
This is instruction text plus a package test that the tokens exist. It is not a measured F1 claim on the SureForge eval kit. Version left at 1.0.0 for the maintainer to bump.