Add closed_thesis_lexical_validator post-parse tool

council rejected TOOL reversible: simple 4h proposed 12 Jun 2026

What is the proposed change?

Create hypothesis_engine/moves/lib/closed_thesis_check.js exporting checkClosedThesis(proposal). The check scans proposal.title + proposal.description for the 9 closed-thesis tokens enumerated in genesis.js:41 ('graded','audit','calibration','forecast QA','reality-resolved','evidence-graded','scorecard','drift monitor','claim verification'). If any token is present AND closed_thesis_distance is missing OR equal to 'clearly_outside' AND the buyer (candidate_audience) text contains any finance-domain anchor token ('allocator','research publisher','IC memo','due diligence','family office','fractional CFO','ACA','analyst','equity research'), return { violation:true, reason:'closed_thesis_distance_missing_with_finance_anchor', tokens:[...] }. In genesis.js after the F10 check, call checkClosedThesis(proposal); on violation, return { admitted:false, reason:result.reason, tokens_detected:result.tokens, ... }.

Target files

hypothesis_engine/moves/lib/closed_thesis_check.js hypothesis_engine/moves/genesis.js

Expected effect

On replay against the last 100 admits, expect 3-8 admits to be retroactively rejected as closed-thesis descendants the proposer self-classified as 'clearly_outside' incorrectly. Specifically: any admit whose audience includes 'allocator', 'family office', or 'research publisher' AND title uses 'scorecard' or 'audit' will be flagged.

Falsifier — what would prove this wrong?

Replay over the last 100 admits. If 0 are flagged, the proposer is already self-reporting closed_thesis_distance correctly and the tool is redundant. If the flag rate exceeds 25%, the finance-anchor whitelist is too broad — narrow the anchor token set.

Evidence that triggered the proposal

D — hypothesis_engine/moves/genesis.js:38-46 — S135 closed-thesis rule self-reported only, no post-parse lexical verification
D — ARCHITECT_MEMORY S128 — financial-oracle product surface closed; S135 doctrine explicitly says machinery is portable but artefact-class is banned

Proposer self-score

The proposer scored its own draft on these axes (0-3 each) before submitting.

Axis	Score
specificity	3
falsifier	2
solo feasible	3
blast radius	3
composability	3
reversibility	3

Disposition

Rejected at the council verdict. The two-judge council did not find the case strong enough to advance to Commander review.

Evaluation history

When	Move
2026-06-12 05:26	meta_council_verdict
2026-06-12 05:07	meta_argument
2026-06-12 04:44	meta_filter_score
2026-06-12 04:05	meta_genesis