arXiv:2607. 02587v2 Announce Type: replace-cross Abstract: Trust-benchmark scores reported on a chat-LLM release line are often carried across several checkpoints of the same line, as if the underlying model had not shifted between releases.
arXiv:2607. 02587v1 Announce Type: cross Abstract: Model cards quote trust-benchmark scores without recording when they were measured, and the same number is routinely carried across successive checkpoints of one release line as if the model behind it had not shifted.
arXiv:2608. 02685v1 Announce Type: cross Abstract: Coding-agent benchmarks increasingly cover long-horizon, end-to-end, and interactive development, but typically retain one requested outcome or a fixed change sequence.
arXiv:2608. 17718v1 Announce Type: new Abstract: Long-horizon agents increasingly operate across many steps, tools, and observa- tions.
arXiv:2607. 18867v1 Announce Type: new Abstract: Large language models leak parametric knowledge of realized outcomes into historical financial decision tasks.
arXiv:2606. 15474v1 Announce Type: new Abstract: Continuous evaluation of LLM products relies on a strong LLM judge treated as ground truth: a cheap monitor scores every interaction and a team is paged when the score drifts down.
arXiv:2608. 17671v1 Announce Type: cross Abstract: Automated security patch backporting is critical for mitigating N-day vulnerabilities.
arXiv:2607. 20436v1 Announce Type: cross Abstract: Safety evaluations often assume that behavior observed during testing reflects behavior in ordinary use, but fine-tuning can break this assumption.
arXiv:2604. 03447v2 Announce Type: replace-cross Abstract: LLM-based software engineering assistants often reason over multiple artifacts, including code, documentation, signatures, and tests, even when those artifacts are incomplete or mutually inconsistent.
arXiv:2607. 08535v1 Announce Type: cross Abstract: An LLM-as-judge score can move even when the candidate responses stay fixed, simply because the evaluator has changed.
arXiv:2608. 13840v1 Announce Type: cross Abstract: Audits of generative AI (GenAI) systems often summarize behavior as a reported rate: how often the audited system complies with policy.
arXiv:2608. 04278v1 Announce Type: cross Abstract: Coding agents increasingly work across sessions, but prose notes can preserve a conclusion without the program state that supported it.
Automated security patch backporting is critical for mitigating N-day vulnerabilities. Recent tools report success rates above 80% on their respective datasets.