arXiv:2606. 10066v1 Announce Type: cross Abstract: Medical vision-language models (VLMs) are evaluated on public benchmarks whose images and question-answer pairs have been freely downloadable for years, yet reported accuracy assumes these examples were absent from pretraining.
By Bruce Changlong Xu, Lan Wu, Alexander Ryu
arXiv:2608. 12652v1 Announce Type: cross Abstract: Benchmark contamination is diagnosed today with n-gram overlap, with likelihood-based membership inference, or with canary strings, and each needs something usually unavailable: the training corpus, a well-chosen test statistic, or foresight at dataset release.
By Florian Braun
arXiv:2608. 10216v1 Announce Type: cross Abstract: Agent frameworks ship quality gates that compare text blocks by embedding-cosine similarity and decide at a fixed cutoff.
By Scott E. Frias
arXiv:2607. 19442v1 Announce Type: cross Abstract: Machine unlearning is commonly evaluated by matching a retrained oracle on trained probes.
By Sen Yang, Yuen-Hei Yeung
arXiv:2608. 07299v1 Announce Type: cross Abstract: Radiology reports describe clinical observations but do not specify executable segmentation targets.
By Chengyi Peng, Haoyu Yang, Meixing Shi, Yuxiang Cai, Yankai Jiang
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.
By Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma