arXiv:2608. 14717v1 Announce Type: cross Abstract: A query-relation deletion can improve the edited slot while reducing the utility of the prediction set that contains it.
arXiv:2609.08618v1 Announce Type: new Abstract: Benchmark scores describe what a checkpoint can do now, but they do not determine how it will respond to the next training episode. We measure this mis...
The audit examines 263 batch‑normalized checkpoints released by arXiv, finding that refitting models on retained data at identical weights shifts 47 of 221 checkpoints beyond the spread indicated by their own release seeds. This movement is attributed to checkpoint properties rather than the survival of removed data, as swapping removed records for kept ones barely changes the published state. The study concludes that releases should specify the fitting convention used, especially for batch‑normalized vision models.
arXiv:2607. 27539v2 Announce Type: replace Abstract: Exact deletion from persistent language-model memory depends on whether a record's effect remains addressable after later computation.
arXiv:2607. 27539v1 Announce Type: new Abstract: Exact deletion from persistent language-model memory depends on how that memory represents a record.
arXiv:2607. 12204v1 Announce Type: new Abstract: Attention can be viewed as an online learner over context, yet existing test-time memories cannot certify that dropping a token leaves outputs unchanged or delete its influence outright.
arXiv:2609.06872v1 Announce Type: new Abstract: When a user asks an assistant to forget a record, the test is whether the memory now matches the state it would hold if the record had never been store...
arXiv:2607. 12204v2 Announce Type: replace Abstract: Auditable memory requires a precise contract: which output is preserved, relative to which reference solve, and across which updates.
arXiv:2609.36569v1 Announce Type: cross Abstract: Checkpoint selection is a routine decision in supervised fine-tuning (SFT): training produces multiple checkpoints, but only one is retained. Yet fix...
arXiv:2608.22577v1 Announce Type: new Abstract: Long-horizon GUI agents can retain a complete interaction trace cheaply as textual action records, but expose only a few past events to the policy in h...
arXiv:2609.39934v1 Announce Type: cross Abstract: Checkpoint selection in domain generalization often relies on source-validation accuracy, yet the selected checkpoint need not provide reliable proba...
The paper investigates what a steerable valence direction in large language models (LLMs) actually represents, focusing on a good‑bad outcome direction in a maze task. By using controlled interventions that separate the realized outcome from the informational history that led to it, the authors find that directions trained on one explicit outcome encoding transfer well to another, suggesting the readout is not tied to surface form. However, when the same outcome is achieved through announced versus unannounced histories, transfer performance drops sharply, indicating that the post‑event readout remains strongly conditioned on the earlier announcement. In a matched maze‑reinforcement‑learning run, the post‑RL direction becomes more predictive of reference‑MDP return and the policy depends more on it, yet the history dependence persists. These findings support a functional, value‑related interpretation of the direction but argue against identifying it with a history‑invariant scalar valence state.
The paper investigates how memory systems can answer a current query correctly yet fail to retain distinctions needed for later updates. Using a paired‑history audit, the authors evaluate 24 history pairs across six synthetic mechanisms and two model backends, achieving perfect reveal accuracy on DeepSeek and high accuracy on GLM. Record‑level audits reveal specific failures in structured reveal memories and frontier late‑reference adequacy, and the authors test a label‑equivariant repair that only partially restores correctness.