← lemma

audit registry

4 papers · 24 claims extracted · 16 supported ·4 inconclusive · 54 failures preserved ·4 evidence logbooks published

OpenReview 5nNNVY8NW4fixture

To Grok Grokking: Provable Grokking in Ridge Regression

Theory paper on provable grokking in ridge regression. Hand-driven reproduction that passed the ICML 2026 Agent Reproductions judge end to end — now the pipeline's regression fixture.

supportedsupportedsupportedsupportedsupportedsupported
arXiv 2510.10981audit

In-Context Learning Is Provably Bayesian Inference

ICL-as-Bayesian-inference theory: the risk-decomposition identity and coupled p-N scaling of the Bayes gap verified numerically; the posterior-variance bound honestly inconclusive under finite precision.

supportedinconclusivesupportedsupportedinconclusiveinconclusive
arXiv 2607.08077audit

Modular Pretraining Enables Access Control (GRAM)

GRAM adds gradient-routed auxiliary MLPs to a base model so capabilities can be isolated and selectively disabled. Reproduced the 26M-param Simple Stories experiment on Modal A10G; compute-ratio evaluation follows the paper's Appendix-M power-law inversion.

supportednot auditednot auditednot auditednot auditedsupported
JMLR 22-1228audit

Grokking phase transitions in learning local rules with gradient descent

Grokking in cellular-automaton rule learning: critical exponents, grokking-probability trends, and a bimodal grokking-time distribution. Audited end to end on CPU.

supportedsupportedsupportedsupportedinconclusivesupported