NoCap-Test evidence · think2earn seeds explainer
Source code ↗

Learn the multi-seed seal · not a new knob

Seeds 1337 · 2029 · 4242

One recipe · three RNG seeds · three independent first-cross clocks

A seed here is an RNG seed for a full-horizon claim-stack run — not a hyperparameter to tune, and not a third optimizer. Same candidate recipe. Three independent draws. Each draw gets its own first-cross T and ΔT% vs sealed F1_seal (3.866 h).

One-line definition

Seed = RNG draw for one independent full run · 3/3 = all three candidate seals pass vs F1_seal

1337 · Claim-W1 2029 · Claim-W2 4242 · Claim-W1 · cand-only mean ΔT% ≈ +8.3%

NUMBERS_CANON RECIPE_CARD GLOSSARY · workspaces GLOSSARY · Seal / 3/3 Intro · Read more Docs

Visual · one recipe × three dice → three clocks Play / Step · sealed digits below

One recipe

Candidate stack

Muon B32
+ timing-cheap split-QKV
· 4768 steps · pin fixed

Three dice

Independent seeds

1337Claim-W1 · matched pair
2029Claim-W2 · matched pair
4242Claim-W1 · cand-only

Three clocks

Own T · own ΔT%

3.553 h+8.1% vs F1_seal
3.567 h+7.7% vs F1_seal
3.511 h+9.2% · no stock arm

Beat 01 · Recipe — One candidate stack. Pin fixed. Seeds do not retune it.

Same recipe, three RNG draws, three first-cross times. Digits from NUMBERS_CANON. Mean cand T ≈ 3.544 h · mean ΔT% ≈ +8.3%. Not an official NoCap win.

Problem 01 · seed RNG · not a knob

What a seed is

In this package, 1337, 2029, and 4242 are RNG seeds for independent full claim-stack runs. They reshuffle stochasticity (init / data order / noise), not the recipe pin.

The shared recipe stays fixed: B32×accum16 · Muon + timing-cheap split-QKV · 4768 updates · A100-SXM4-40GB · torch 2.13 · first-cross at val_disjoint ≤ 3.3821. See RECIPE_CARD.

Not a tune knob. Seeds are independence draws for the seal bar — not a search over lucky RNG.

Problem 02 · multi-seed 3/3 · pass bar

Why multi-seed · 3/3

First-cross time is high variance. One seed is not a confidence interval. The process bar is 3/3: the composed candidate must first-cross on three seeds, each with ΔT% vs F1_seal6% (noise-floor prior).

Predict · Is +7.7% on one seed enough to publish?

Not as a campaign seal. Single-seed |ΔT%| under the ~6% noise floor is not a win; even above it, the seal bar is 3/3 independent first-crosses vs F1_seal. Seed 2029’s +7.7% counts as one of three — not the whole claim.

Sealed outcome: all three pass (+8.1%, +7.7%, +9.2%). Mean ΔT% ≈ +8.3%. That freezes SUMMARY + CSV for claims. It does not mint an organizer win.

Seal / 3/3 sits after kill → bank. Bank ≠ claim until the three-seed seal.

Problem 03 · per-seed clocks vs F1_seal only

Each seed’s own T / ΔT%

Do not collapse the three runs into one invented number on a chart without saying so. Report each seed’s first-cross T, then the mean. Public denominator is always sealed F1_seal = 3.866 h (Clock-W).

Case tabs · per-seed readouts TensorTonic pattern · static · NUMBERS_CANON
Seed 1337
T (first-cross) 3.553 h
ΔT% vs F1_seal +8.1%
Cross @ step 4736 · Claim-W1

Matched pair · stock arm did not cross · summary-only (no public cand CSV).

Seed 2029
T (first-cross) 3.567 h
ΔT% vs F1_seal +7.7%
Cross @ step 4736 · Claim-W2

Matched pair · stock arm did not cross · also +7.5% vs F1_Claim-W2 (not public denom).

Seed 4242
T (first-cross) 3.511 h
ΔT% vs F1_seal +9.2%
Cross @ step 4736 · Claim-W1

Cand-only · no stock arm run · still counts toward 3/3 vs F1_seal.

Seed Workspace Cross T ΔT% vs F1_seal Stock arm
1337 Claim-W1 4736 3.553 h +8.1% no cross · ΔT% N/A
2029 Claim-W2 4736 3.567 h +7.7% no cross · ΔT% N/A
4242 Claim-W1 4736 3.511 h +9.2% not run · cand-only

All three candidates first-cross at step 4736. Seed 1337 is summary-only (no public cand CSV). Seed 2029 may also report +7.5% vs F1_Claim-W2 — that does not replace public F1_seal. Source: NUMBERS_CANON.

Problem 04 · homes workspace codes

Claim-W1 vs Claim-W2 homes

Volumes do not share across workspaces. Each seed’s artifacts live on a named claim workspace. Public pages name workspaces by code (Clock-W, Claim-W1, Claim-W2).

Claim-W1

Seeds 1337 (matched pair) and 4242 (candidate-only).

Claim-W2

Seed 2029 (matched pair) + same-class AdamW re-seal F1_Claim-W2 (3.858 h).

F1_seal itself lives on Clock-W. That is the sole public speed denominator.

Problem 05 · 4242 cand-only · no overclaim

4242 · candidate-only

Seed 4242 is a robustness seed: candidate arm only. No joint-QKV stock arm was run. It is not a matched pair.

  • It still counts toward the 3/3 candidate-vs-F1_seal seal.
  • It does not create a matched cand-vs-stock ΔT% (that endpoint is N/A for all three seeds).
  • Do not write “three matched pairs.” Only 1337 and 2029 are matched pairs — and even there, stock never crossed.

Without overclaiming. 4242’s +9.2% is candidate vs F1_seal only. It is not evidence that a stock twin would have missed or crossed. Ops note (non-metric): first spawn hit A100 80GB and was rejected; the sealed run is the relaunched 40GB pin.

Hedges / non-claims

Not an official organizer win. Accuracy hedges live on not-claimed-explained.

Published ΔT% is vs sealed F1_seal only. Matched candidate-vs-stock first-cross ΔT% = N/A.

Single seed ≠ interval. Cand-only 4242 ≠ matched pair. Numbers from NUMBERS_CANON / RECIPE_CARD — invent nothing.