arXiv AI
Jul 23
Decodable but Not Detectable: A Leakage Fingerprint for Near-OOD Benchmarks
arXiv:2607. 19393v1 Announce Type: cross Abstract: While auditing a perturbation-based OOD detector on a document benchmark, we recorded an AUROC of 0.
Self-Poisoning in Adaptive Out-of-Distribution Detection: A Sharp-Threshold Theory and Certified Label-Free Calibration
arXiv:2607. 21673v1 Announce Type: new Abstract: Test-time adaptive out-of-distribution (OOD) detectors update a memory bank from the unlabelled stream.
Related stories
arXiv AI
Aug 11
When Is Benchmark Contamination Detectable? Information Limits and Power-Calibrated Audits
arXiv:2608. 07914v1 Announce Type: new Abstract: Behavioral contamination detectors can return "no evidence" either because a benchmark is clean or because the audit has little power.
arXiv AI
Aug 7
ASAT: Adaptive Scoring and Thresholding with Human Feedback for Robust Out-of-Distribution Detection
arXiv:2505. 02299v2 Announce Type: replace-cross Abstract: Machine Learning (ML) models are trained on in-distribution (ID) data but often encounter out-of-distribution (OOD) inputs during deployment---posing serious risks in safety-critical domains.
arXiv Machine Learning
Jul 28
When Can You Correct Distribution Drift in Temporal Graph Generation? A Sharpening--Drift Tension and an Impossibility for Observation-Based Correction
arXiv:2607. 24662v1 Announce Type: new Abstract: Generative models of temporal graphs are trained on one stretch of an evolving network and deployed on the next, and they degrade badly in the gap.
arXiv AI
Jul 8
Full-range Binary Classifier Calibration for Stable Model Updates in Production
arXiv:2607. 05481v1 Announce Type: cross Abstract: Detection models running in adversarial environments face a malicious distribution that drifts rapidly while the benign distribution stays comparatively stable, so teams retrain and redeploy constantly to stay ahead of new threats.
arXiv AI
Jul 9
The Blind Curator: How a Biased Judge Silently Disables Skill Retirement in Self-Evolving Agents
arXiv:2607. 07436v1 Announce Type: new Abstract: A self-evolving agent retires its bad skills by watching them fail, so what happens when the judge cannot see the failures?
arXiv AI
Jun 19
Calibration Without Comprehension: Diagnosing the Limits of Fine-Tuning LLMs for Vulnerability Detection in Systems Software
arXiv:2606. 20502v1 Announce Type: cross Abstract: Whether LLMs scoring well on vulnerability benchmarks genuinely reason about security or merely pattern-match on contaminated data remains unresolved.
Hugging Face Trending Papers
Jul 8
The Blind Curator: How a Biased Judge Silently Disables Skill Retirement in Self-Evolving Agents
A self-evolving agent retires its bad skills by watching them fail, so what happens when the judge cannot see the failures? Skill retirement is the structural constraint that keeps a growing library from drifting below the no-skill baseline, but its guarantee assumes an unbiased reward, which is false for the LLM judges that reference-free tasks force upon us.
Hugging Face Trending Papers
Jul 27
When Can You Correct Distribution Drift in Temporal Graph Generation? A Sharpening--Drift Tension and an Impossibility for Observation-Based Correction
Generative models of temporal graphs are trained on one stretch of an evolving network and deployed on the next, and they degrade badly in the gap. We show this degradation is derivable, general, and not fixable from observations.
arXiv Machine Learning
Aug 7
Velocity- and Regime-Aware Detection of Intraday Options Market Manipulation, with Explainable Attribution
arXiv:2608. 05373v1 Announce Type: cross Abstract: Intraday market manipulation is hard to detect because its footprint is brief, buried in millions of quotes, and statistically similar to ordinary volatility.
arXiv AI
Jun 16
Who Drifted: the System or the Judge? Anytime-Valid Attribution in LLM Evaluation Pipelines
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 Machine Learning
Jul 20
Label-Free Concept Drift Assessment for Reliable AI in Emerging Wireless Applications
arXiv:2508. 00042v2 Announce Type: replace-cross Abstract: Machine learning models deployed in non-stationary environments degrade silently, since as the input distribution drifts their accuracy decays without an error signal and without labels to reveal it.