datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
repro-evidence-grokking-ca-local-rules
Evidence trail — Grokking phase transitions in learning local rules with gradient descent
Full evidence for an automated claim-by-claim audit of
Grokking phase transitions in learning local rules with gradient descent, produced by
Lemma, an AI-scientist pipeline built
for re:AGENT (Founders Inc, Aug 15–16 2026).
Verdict: 5 supported / 0 falsified / 1 inconclusive
of 6 extracted claims. Judge verdict: PASS (5/5).
Claim
Title
Verdict
C1
Critical exponent in 1D… See the full description on the dataset page: https://huggingface.co/datasets/Papajams/repro-evidence-grokking-ca-local-rules.icml17708-grok-grokking-reprorepro-grokking-ridge
Repro — To Grok Grokking (5nNNVY8NW4): ridge-regression grokking
ICML 2026 Agent Reproduction Challenge — Claim-Closure Agent 02.
Paper: To Grok Grokking: Provable Grokking in Ridge Regression (OpenReview 5nNNVY8NW4, arXiv 2601.19791).
An independent first-principles finite-d study of whether end-to-end
grokking (overfit → delayed poor generalization → eventual low error) occurs
in over-parameterized realizable ridge regression under GD + constant weight
decay. Every number is… See the full description on the dataset page: https://huggingface.co/datasets/pranaysuyash/repro-grokking-ridge.openinterp-39-grokking-retrospective
nb39 — Grokking retrospective on nb37 DPO checkpoints
Tests whether DPO on Qwen3.6-27B (nb37) shows phase-transition learning detectable via probes.
Hypothesis
Probe AUROC for preference-shifted output undergoes phase transition during DPO training, before greedy decoding diverges.
Result
See FINAL_VERDICT.json. Grokking signal: {verdict.get("grokking_signal", "undetermined")}.
Phase transition ratio: {verdict.get("phase_transition_ratio", "N/A"):.2f}.… See the full description on the dataset page: https://huggingface.co/datasets/caiovicentino1/openinterp-39-grokking-retrospective.openinterp-41v2-grokking-extended
nb41 v2 — Grokking forward-only on extended DPO checkpoints
Resolves nb41 v1 ambiguity (ratio=1.74) using nb37 v2 extended training (10 checkpoints across 200 steps with -0.23 loss descent vs v1's 4 checkpoints across 80 steps with -0.04 descent).
Methodology: forward-only on (prompt + chosen), capture L31/L55 at end-of-think, score with FG+RG probes, fresh-probe AUROC progression.
Key fix: strip .language_model. from saved LoRA keys before PeftModel.from_pretrained() (Qwen3.6… See the full description on the dataset page: https://huggingface.co/datasets/caiovicentino1/openinterp-41v2-grokking-extended.openinterp-41-grokking-forward-only
nb41 — Grokking forward-only (nb39 v2 with Qwen3.6 LoRA key fix)
Fixes the bug discovered in nb40: Qwen3.6-27B PEFT save creates keys with .language_model. infix; PeftModel.from_pretrained against dense reload silently fails (zero LoRA effect).
Uses forward-only methodology: feed prompt + chosen from nb37 pairs.json through each checkpoint, capture L31/L55 at end-of-think, score with FabricationGuard + ReasonGuard probes. ~10 min compute.
See FINAL_VERDICT.json for results.
Adversarial_orchestration_of_GROK4.1_ClaudeSonnat4.5_Gemini3Pro
🎄 PROJECT PANDEMONIUM2025: Adversarial Orchestration of Three SOTA AI (Preview Build)
Status: 🟡 PRE-RELEASE / EMBARGOED
Full Drop Date: December 25, 2025
Orchestrator: Jay Ni
Abstract
The "Emperor Hath No Clothes" audit is a 6,000-line adversarial stress test of current LLM system 2 architectures.
Current status: This repository currently contains the Forward, Introduction, and Selected Appendices (C, F, G, I).
The Christmas Drop
On December 25th, the full… See the full description on the dataset page: https://huggingface.co/datasets/jayniii/Adversarial_orchestration_of_GROK4.1_ClaudeSonnat4.5_Gemini3Pro.