Unit 9 (customization-trilemma): split criterion 2 (completes MEDIUM batch)#168
Merged
Conversation
… batch Per docs/RUBRIC_AUDIT.md (MEDIUM): old c2 bundled 'names a concrete failure mode' with 'names the mechanism.' Splits into name-the-failure-mode c2 and a new c3 (mechanism); renumbers regime distinction to position 4. Rubric grows 3 -> 4. Preserve-by-default: faithful decomposition of locked Opus values (old-c2=T -> c2=T,c3=T). All five old-c2=F pairs (p007/p008/p009/ p011/p021) describe correct mappings without naming a MIS-MATCH failure mode at all -> c2=F,c3=F. No c2=T/c3=F differential pairs (Unit 9's c2 mechanism is tightly fused to the failure statement, per the audit). No realignments. c4 (regime) carries old-c3 unchanged. p014 flagged-expected preserved. Updated p007/p008/p011/ p021 labels for the 4-criterion shape. Gate-exempt (faithful split, zero realignments per docs/REGRESSION_GATE.md). Completes the MEDIUM-severity c2-split batch (Units 2-9). Local lint, schema check, ingest-check, pytest all pass.
Same Codex-flagged stale-label pattern as Unit 8: p006 'c1+c2 met, c3 missing' -> 'c1+c2+c3 met, c4 missing' (T,T,T,F); p010 'c2 only' -> 'c2+c3 met, c1/c4 missing' (F,T,T,F); 'All three met' -> 'All four met'. Expected values unchanged; labels caught before #168 merges.
LuminLynx
pushed a commit
that referenced
this pull request
May 21, 2026
The first draft claimed units 8 and 9 still carried a bundled c2. That was read off a stale working tree from before a git pull — PRs #167 and #168 had already split both (rubric + regression sets to 4 criteria) and merged. Remove the false "incomplete sweep" section, fix the numbering note (only tokenization and the reverted multimodal remain 3-criterion), and correct the regime-criterion index for units 8/9 from c3 to c4. The c1 and regime-criterion analysis for 8/9 is unchanged — the split left their c1 text alone and only renumbered the regime criterion. https://claude.ai/code/session_019xEvNkByf5ic4kbMZFdKDR
2 tasks
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
Unit 9 (
customization-trilemma), last of the MEDIUM batch. Faithful preserve-by-default split, gate-exempt.Rubric (3 → 4): c1 unchanged · c2 = name the failure mode · c3 (NEW) = name/explain the mechanism · c4 = regime distinction (was c3).
Decomposition
Post-split distribution (21 pairs)
6 × 4-of-4 · 1 × 3-of-4 (p006) · 5 × 2-of-4 (p007/p008/p010/p011/p021) · 1 × 1-of-4 (p009) · 7 all-missed · 1 flagged-expected (p014).
Local validation
lint_unit_markdown/ingest_units --check— cleanrun_regression_set --check— 21 pairs valid (p014 flagged=true preserved)pytest— 20/20Milestone
This completes the entire c2-split rollout:
Remaining future work: the deferred c1/c3/c4 follow-up audit (the grader-lenient-on-unsplit-AND-clauses pattern, now well-evidenced across units).
Ready to merge (gate-exempt).
Generated by Claude Code