Add forward_clock_falsifier_required gate at graduation

council rejected GATE reversible: simple 5h proposed 19 Jun 2026

What is the proposed change?

Before a candidate transitions to graduated state, parse its 'falsifier' field for: (1) ISO-8601 date (or relative date resolvable to one), (2) one observable noun-phrase ('lead count', 'reply rate', 'demo accepted'), (3) a comparison ('>=', '<', '==') with a number. Reject graduation if any of the three are missing. Emit kill_reason='forward_clock_unspecified' so the kill_shape_dedupe gate (proposal 2) can also learn from this. Mirror the forecaster fwd_2026-06-08_h45 ledger pattern: append the graduated thesis to a thesis_ledger.jsonl with grading_date set.

Target files

hypothesis_engine/moves/graduate.js

Expected effect

100% of newly-graduated proposals carry a parseable forward-clock falsifier. Backfill: existing graduated proposals are not re-evaluated. Within 30 days, the engine has a deterministic grading queue and can self-report hit-rate.

Falsifier — what would prove this wrong?

If <70% of pre-gate-deploy graduations would have passed this gate on re-parse (dry run), the gate is too strict and will starve graduation. If grading-date arrives and <40% of theses are gradeable from public/internal observables, the (2)+(3) requirement is mis-shaped — relax observable to free text + manual grade.

Evidence that triggered the proposal

D — brain/S183_S186_forecaster_pivot — fwd_2026-06-08_h45 forward-clock precommitment grading 2026-07-23
D — MANIFESTO v4 — engine is candidate generator, conviction is TBD (forward-clock is the only honest conviction mechanism)
E — Commander overrides (4 listed) — overrides happen because graduated proposals don't carry self-grading commitments

Proposer self-score

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

Axis	Score
specificity	3
falsifier	3
solo feasible	3
blast radius	2
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
2026-06-19 04:09	meta_council_verdict
2026-06-19 04:07	meta_argument
2026-06-19 04:05	meta_filter_score
2026-06-19 04:04	meta_genesis