# Glossary — NoCap campaign terms

**Audience:** strangers and agents reading public evidence.  
**Evidence state:** 2026-07-16 · claim-stack v1 · **3/3** candidate seals.  
**Numbers:** prefer sealed summaries; do not invent. Workspace codes only on this page (no Modal profile names).

Canonical sealed table: `nocap-repo/results/claim_stack_v1/MULTI_SEED_CLAIM.md`  
Public denominator: `nocap-repo/results/f1_seal/SUMMARY.md`

---

## Challenge & quality

| Term | Meaning |
|------|---------|
| **NoCap / NoCap-Test** | BottleCapAI challenge: train GPT-2 ≈124M on FineWeb to official disjoint val ≤ **3.3821** on **one GPU**, faster than a stock baseline. Challenge repo: [BottleCapAI/NoCap-Test](https://github.com/BottleCapAI/NoCap-Test). |
| **Quality bar / hit** | First logged **val_disjoint ≤ 3.3821**. A run that never reaches this is a **quality miss** (no speed claim). |
| **val_disjoint** | Official validation loss on the disjoint FineWeb val set. Claims use this — not sliding/EMA curves alone. |
| **CE / terminal CE** | Cross-entropy (val loss). **Terminal CE** = val at the final logged step (usually 4768). Lower is better. |
| **Horizon / 4768** | Full claim horizon: **4768** optimizer updates. Tokens per update stay **524,288**. |

---

## Time metric (fair clock)

| Term | Meaning |
|------|---------|
| **train_time / train_time_ms** | Cumulative training wall clock logged by the trainer (includes compile warmup). Primary clock for speed. |
| **\(T\) / first-cross \(T\)** | `train_time` (usually in hours) at the **first** step where val_disjoint ≤ 3.3821. |
| **First-cross / first-passage** | The event of first hitting the quality bar; synonymous with first-cross \(T\) when discussing speed. High variance — single seed ≠ confidence interval. |
| **ΔT% (vs F1_seal)** | \(100 \times (T_{\mathrm{F1\_seal}} - T_M) / T_{\mathrm{F1\_seal}}\). Positive = faster than sealed F1. Public denom \(T_{\mathrm{F1\_seal}}\) = **3.866 h**. |
| **step_avg** | Mean step time (ms). Useful forensic, **not** the published speed metric. |
| **\(N^*\)** | Step index of first-cross (sample efficiency). Sealed candidates: all **4736**. |

See [FAIR_CLOCK.md](FAIR_CLOCK.md).

---

## Sealed denominators

| Term | Meaning |
|------|---------|
| **F1_seal** | Sealed stock **AdamW** baseline on **Clock-W**. First-cross @4736 · \(T\)=**3.866 h**. **Sole public speed denominator** for published ΔT%. |
| **F1_Claim-W2** (local file: `F1_BCAROL_SUMMARY.md`) | Same-class AdamW re-seal on **Claim-W2**. \(T\)=**3.858 h** (~+0.2% vs F1_seal). Used for same-workspace ratios on seed **2029**; not a replacement for public F1_seal. |
| **Historical F1** | Notebook-era stock cross (~229.1 min). Torch unlogged → **provisional only**. Never use for published %. |

---

## Claim-stack recipe language

| Term | Meaning |
|------|---------|
| **Claim-stack / claim-stack v1** | Full-horizon experiment family (Jul 15–16 seals): Muon B32 systems path ± timing-cheap split-QKV, three seeds. |
| **Candidate** | The claim arm: **timing-cheap split-QKV** (`muon_split_qkv=1`, `match_joint=0`) on the shared Muon B32 recipe. |
| **Stock control (claim-stack)** | Matched arm: **joint QKV** on the **same** Muon stack (not AdamW F1). Differs only on QKV treatment. |
| **Matched pair** | Same seed, same workspace, same pin, same shared recipe; only split vs joint differs. Seeds **1337** and **2029** are matched pairs; **4242** is candidate-only. |
| **Joint QKV** | Standard fused QKV projection (stock control). |
| **Timing-cheap split-QKV** | Campaign mechanism: split QKV path designed for low step-time tax vs dual-polar split. Banked @800/@2400; used in sealed candidates. |
| **Dual-polar split-QKV** | Earlier split variant: ~+0.015 CE but time ratio ≈ **1.026** → CE edge eaten by step tax → NO-GO for claim. |

---

## Systems & optimizers

| Term | Meaning |
|------|---------|
| **B32×accum16** | Microbatch 32 × gradient accumulation 16 (with seq 1024 → 524,288 tokens/update). Systems path ~**6%** faster core step-time vs B16 path (matched systems_v1). |
| **Muon** | Keller Jordan’s Muon optimizer ([Muon](https://github.com/KellerJordan/Muon)). Claim recipe uses Muon on matrix groups + Adam on embed/head. **Attribution required.** |
| **NS / Newton–Schulz** | Orthogonalization steps inside Muon. Claim pin: **NS 5**. |
| **Warmup / warmdown (wu / wd)** | WSD schedule lengths. Claim pin: **wu 476 / wd 1192**. (Proxy Tier A used shorter warmdowns; do not confuse.) |
| **zloss** | Z-loss term. Claim pin: **0**. |
| **Prior / frozen unigram prior** | Frozen `prior_full.pt` logit prior on claim-stack. F1_seal uses **no** prior. |
| **EMA** | Exponential moving average of weights. Off for claim-stack and F1_seal. Late EMA-as-train-CE was a NO-GO. |
| **Parallel block** | Parallel transformer block (banked ~1.6% step in notebook-era family). On for claim-stack. |
| **Compile warmup** | Torch compile startup cost. **Included** in \(T\); do not strip it. |

---

## Hardware attestation

| Term | Meaning |
|------|---------|
| **A100-SXM4-40GB attestation** | Exact GPU class required for sealed claims. Seed **4242** first spawn hit **80GB** and was rejected by guard; seal is the relaunched **40GB** run. |
| **torch 2.13 / 2.13.0+cu130** | Sealed pin. Log full `torch.__version__`. Historical notebook images used other builds → infra drift. |

---

## Workspaces (public codes)

| Code | Role |
|------|------|
| **Clock-W** | Host of public **F1_seal**. |
| **Claim-W1** | Claim-stack seeds **1337** (matched pair) and **4242** (candidate-only). |
| **Claim-W2** | Claim-stack seed **2029** + **F1_Claim-W2** AdamW re-seal. |
| **Research-W1…W6** | Component bank, proxies, screens (ordinal / mechanism era). |
| **Archive-W1…W3** | Historical / archive hosts. |

Real Modal profile names are **not** public; agents see `WORKSPACE_MAP.local.md` (local only).

---

## Evidence & ops shorthand

| Term | Meaning |
|------|---------|
| **Seal / sealed** | Written SUMMARY + (when present) pulled CSV that freezes a run’s numbers for claims. |
| **Proxy (@800)** | Short-horizon screen. May **rank** methods; must **not** produce published ΔT%. |
| **Noise floor (~6%)** | Empirical infra/step-time drift prior. Single-seed \|ΔT%\| < ~6% → do not publish as win. |
| **Under-claim / under-baseline** | Candidate \(T\) meaningfully below F1_seal (campaign bar ≥6%). Language stays bounded — not “officially won.” |
| **Fire-and-forget spawn** | GPU train via `spawn()` + `modal run --detach` so local disconnect does not cancel A100 work. Ops detail for agents. |
| **Volume isolation** | Modal volumes do **not** share across workspaces. Data/priors must be seeded per workspace. |

---

## Non-claims (do not redefine these as wins)

See [FAIR_CLOCK.md](FAIR_CLOCK.md#explicit-non-claims) and [FAILURE_LEDGER.md](FAILURE_LEDGER.md). Short list:

- No **official NoCap win** (organizer acceptance not in local seals).
- No **matched first-cross ΔT% vs joint stock** (stock never crossed where measured).
- No published % vs **historical F1**.
- F2b quality hit ≠ speed win (historical −2.9% **retracted**).