NoCap-Test evidence · think2earn hedge explainer · claim boundary
Source code ↗

Claim boundary · three clauses

Not claimed

Why each clause exists · under-baseline evidence vs our seal only

The intro hedge is a claim boundary, not hedging language for weak results. We publish sealed under-baseline evidence. We do not invent a matched-pair speedup the data cannot support.

01 Under sealed F1 02 vs F1_seal only 03 matched ΔT% N/A
Paste-ready · public hedge intro · report · README
Not claimed. Under our sealed F1 baseline. Public % vs F1_seal only. Matched cand-vs-stock ΔT% = N/A. Joint-QKV stock never crossed on 1337/2029; seed 4242 stock not run.

Source copy lives on intro.html#hedge. Numbers: NUMBERS_CANON · clock: FAIR_CLOCK.

Three terms · brief

First-cross / first-passage
First logged step where val_disjoint ≤ 3.3821. Speed uses wall-clock T at that row — not terminal CE alone.
ΔT%
100 × (T_denom − T_cand) / T_denom. Public published % uses denom F1_seal = 3.866 h. Matched % vs joint stock needs both arms to first-cross — otherwise N/A.
Joint-QKV stock
Matched claim-stack control: same Muon B32 recipe, fused (joint) QKV — not AdamW F1. Differs from candidate only on QKV treatment.
Visual · three hedge clauses Play / Step · claim boundary

Clause 01

Under sealed F1

Under-baseline evidence against our sealed AdamW F1.

Clause 02

vs F1_seal only

Public % denom = AdamW 3.866 h on Clock-W.

Clause 03

Matched ΔT% N/A

No honest pair speedup without a stock first-cross T.

Beat 01 · Under our sealed F1 baseline — campaign evidence vs our own AdamW denom.

Three clauses, one hedge. Digits unchanged — see NUMBERS_CANON / paste block above.

Clause 01 · scope our sealed F1

Under our sealed F1 baseline

We publish under-baseline evidence against our own sealed AdamW F1 — a fair-clock comparison strangers can recompute from public CSVs. That is campaign evidence under a fixed denom, not a substitution for other baselines.

Local seals freeze SUMMARY + CSV against that denom. They do not redefine historical notebook F1 or invent a matched-pair endpoint the data cannot support.

Clause 02 · denominator F1_seal · 3.866 h

Public % vs F1_seal only

Public ΔT% uses one denom: AdamW F1_seal on Clock-W (first-cross T = 3.866 h). Not historical notebook F1 (~229.1 min, provisional). Not a percentage against joint-QKV Muon stock.

Under-baseline vs F1_seal is the sealed claim language. See FAIR_CLOCK for the clock and NUMBERS_CANON for the table.

Clause 03 · matched endpoint PREREG → observed N/A

Matched cand-vs-stock ΔT% = N/A

Predict · Stock never crossed — can we still publish a matched speedup?

No. Matched ΔT% needs both arms to first-cross. Without a stock T, the honest endpoint is N/A — not an inferred percentage, not silent omission.

PREREG wanted matched first-cross % vs joint-QKV Muon stock (same seed, pin, recipe; only QKV treatment differs). Observed: stock never first-crossed on seeds 1337 / 2029; seed 4242 had no stock arm. Without a stock first-cross T, an honest matched speedup cannot be computed.

Published

vs F1_seal

Candidate first-cross T vs AdamW denom 3.866 h → mean ≈ +8.3%.

Not published

matched ΔT% N/A

Joint Muon stock never crossed where measured — no honest pair speedup.

Sealed digits: NUMBERS_CANON · F1_seal · QKV primer · timing-cheap split.

Public % is therefore vs F1_seal only. The joint miss is still useful: a quality ablation (control fails the bar where measured) — not a silent matched speedup. Ledger: FAILURE_LEDGER.