Record: Round 5 — L-BFGS Causal SLOT (1.0046) + Discriminative TTT (1.0807)#4
Closed
Record: Round 5 — L-BFGS Causal SLOT (1.0046) + Discriminative TTT (1.0807)#4
Conversation
…11473 (3-seed mean) AR self-generated calibration (no val/train data during quantization). Recreated from PR openai#728 at @valerio-oai's request for clarity. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
…ptq-xsa-bigramhash3072 Record: AR Self-Gen GPTQ + XSA-all + BigramHash 3072×112 — val_bpb 1.11473 (3-seed mean)
Lane A: L-BFGS Causal SLOT in Logit Space — 1.0046 BPP (3-seed mean, std 0.0003) Novel: L-BFGS + logit-space + causal constraint (no existing PR combines these) Compliance: provably causal — passes flip test, NoesisGenesis conditions satisfied Lane B: Discriminative TTT — 1.0807 BPP (3-seed mean, std 0.0005) Novel: per-block adaptive LR during pre-quant TTT (no existing PR does this) Compliance: Track A (fixed predictor) — zero eval-time adaptation Both beat merged SOTA (1.1147) by large margins. Seed logs pending extraction from Lepton. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Lane A: L-BFGS Causal SLOT in Logit Space — 1.0046 BPP (3-seed mean, std 0.0003) Novel: L-BFGS + logit-space + causal constraint (no existing PR combines these) Compliance: provably causal — passes flip test, NoesisGenesis conditions satisfied Lane B: Discriminative TTT — 1.0807 BPP (3-seed mean, std 0.0005) Novel: per-block adaptive LR during pre-quant TTT (no existing PR does this) Compliance: Track A (fixed predictor) — zero eval-time adaptation Both beat merged SOTA (1.1147) by large margins. 7 files per submission: train_gpt.py, README.md, submission.json, requirements.txt, 3 seed logs. Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
Owner
Author
|
Closing: need separate PRs per submission, squashed commits |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Two 3-seed-validated submissions from Round 5:
Lane A: L-BFGS Causal SLOT in Logit Space — 1.0046 BPP
Lane B: Discriminative TTT — 1.0807 BPP
Files per submission (7 each)
Review checklist
🤖 Generated with Claude Code