The paper demonstrates that emergent capabilities in machine learning models can be forecasted with lead time, calibrated uncertainty, and controlled false‑alarm rates. Using per‑seed analysis on transformers, the authors show that the formation time of a previous‑token head predicts the emergence of an induction head with Spearman ρ = 0.977 and a median lead of 975 training steps. Conformal intervals, blind pre‑registered tests, and a multiplicative rule relating anchor and event times further validate the predictive framework across multiple model families and configurations.
arXiv:2608. 13063v1 Announce Type: new Abstract: Prior work on LLM behavior under anomalous conditions asks whether a model notices anomalies.
arXiv:2607. 27281v1 Announce Type: new Abstract: A capability appears in a language model when the last parts of its circuit align in one stochastic attempt, and getting all but one right is worth nothing.
The paper investigates the safety of Code World Models, where a language model generates executable world models that a planner uses. It shows that accepting a model based on sampled transitions only guarantees sample consistency, not full safety, because the probability of missing critical events decays as (1‑r)^N. Experiments on hybrid instruments reveal that omitted mode‑boundaries can severely limit planner performance, and that even sophisticated LLMs (GPT‑5.x) struggle to repair such omissions in higher‑dimensional settings.
arXiv:2606. 26050v1 Announce Type: new Abstract: Midway through an ordinary pretraining run, a small language model learns the pronoun-gender rule: cued with a girl's name ("Sue cried because"), it resolves the next pronoun to she, generalizing to held-out probes (0.
Grokking -- where a transformer on modular arithmetic suddenly transitions from near-chance to near-perfect validation accuracy -- is attributed to a Fourier circuit, but its timing, causal structure, and controllability remain poorly understood. We introduce the Frequency Synchronization Degree (FSD), a normalised, permutation-tested metric for Fourier circuit synchronisation requiring no prior circuit knowledge.
arXiv:2608. 11822v1 Announce Type: cross Abstract: A growing body of work reports that language models represent task-relevant latent structure that they fail to use.
arXiv:2607. 00871v1 Announce Type: new Abstract: Self-evolving agents violate the assumption behind most learning-theoretic guarantees: the data, evaluator, components, and hypothesis space are produced by the policy being updated.
arXiv:2609.06934v1 Announce Type: cross Abstract: Post-hoc safety training (RLHF, DPO) is the dominant way to align large language models, yet jailbreaks (Zou et al., 2023b), fine-tuning attacks (Qi...
arXiv:2607. 13070v2 Announce Type: replace-cross Abstract: Safety claims for self-improving agent runtimes are almost always self-graded: a policy file, a guardrail, a promise in a README.
arXiv:2608.30502v1 Announce Type: new Abstract: Machine learning systems are increasingly corrected while they run, and the decision of when to intervene is increasingly delegated to statistical moni...
arXiv:2607. 10972v1 Announce Type: new Abstract: Many evaluations of model outputs rely either on contracts checkable at evaluation time or on feedback that arrives within the operating loop.
Many evaluations of model outputs rely either on contracts checkable at evaluation time or on feedback that arrives within the operating loop. We study the complementary setting in which ground truth is delayed, censored, or private, so deterministic code cannot check correctness at scoring time and must instead issue a code-owned provisional forecast.