Add non-record pre-TTT anchor submission

[amrayach]

Adds a non-record submission under records/track_non_record_16mb/2026-03-28_pre_ttt_anchor.

Summary:

• Pegasus 8xH100 SXM5
• sliding s64 val_bpb=1.12904446
• pre-quant EMA val_bpb=1.14472403
• int6 roundtrip val_bpb=1.15247273
• total artifact size 15751324 bytes

This submission includes:

• README.md
• submission.json
• requirements.txt
• train_gpt.py
• train.log

[MatoTeziTanka]

Community Review — Add non-record pre-TTT anchor submission

BPB: 1.1290 | Compliance: LOOKS CLEAN — pure-neural submission, no TTT/SLOT/n-gram-cache

What I found in the code (head SHA 46f4486db4dd, file records/track_non_record_16mb/2026-03-28_pre_ttt_anchor/train_gpt.py):

Static code review found no TTT adaptation function, no SLOT optimization loop, no n-gram-cache class, and no pre-quant val-token fine-tune. The eval path uses the standard sliding-window stride-64 pattern. The submission is a pure-neural architecture iteration on the standard SP1024/SP4096/SP8192 baseline.

CPU smoke test (CT2038 proteus-engine, 2026-04-11): import OK in 0.11s, dim=512, layers=11, vocab=1024, code=58573 B, SMOKE_TEST_PASS

Verdict: LOOKS CLEAN.

Recommendation to @cocohearts @valerio-oai @0hq @yuzhougu-oai @notapplica: MERGE pending the usual record-track checks (3-seed validation, under-16MB artifact cap, ≤600s train + ≤600s eval on 8×H100 SXM). No compliance flags from the classification pass — this looks like a clean pure-neural iteration on the standard baseline.

Auto-classification caveat: this review was drafted by the AST-based classifier. If there's a non-standard eval mechanism (logit postprocessing, hedge mixing, etc.) that I missed because it's factored into a helper file or a non-standard function name, please flag it and I'll re-run the audit manually.

---

Reviewed by @MatoTeziTanka — The Agora. CPU smoke test (CT2038 proteus-engine, 2026-04-11): import OK in 0.11s, dim=512, layers=11, vocab=1024, code=58573 B, SMOKE_TEST_PASS. Classification via deterministic AST-based classify_prs.py (pattern bank derived from ~65 manually-reviewed PRs earlier in the 2026-04-11 sweep). This review was auto-drafted from a template and spot-checked before posting — if the template misread your code, please call it out so I can iterate the classifier.