The paper investigates how to evaluate bounded model updates for ICU prediction models using the MIMIC‑IV database. After auditing the data for recording artifacts and cleaning it, the authors compare a bounded update that retrains only treatment‑context and fusion parameters with full fine‑tuning across two model families and two targets, finding that bounded updates are non‑inferior or superior in most cases but depend on target, model family, and learning‑rate tuning. The study also shows that audits should precede update evaluation and that the update boundary should be chosen per target.
arXiv:2607. 19020v2 Announce Type: replace-cross Abstract: Clinical decision support degrades as treatment protocols evolve, but the obstacle to updating a deployed model is governance as much as accuracy: once retraining touches every parameter, no one can say afterwards where the update acted.
The paper introduces a bounded updating framework for ICU prediction models that freezes the physiological encoder while allowing updates only to the treatment pathway and fusion head. Experiments on 84,792 MIMIC-IV ICU stays across four temporal shifts show that selective adaptation yields more stable explanations—higher rank correlation, better top‑5 feature agreement, and improved retrieval stability—compared to full model adaptation. Predictive performance varies by outcome, but the results demonstrate that explanation stability is governed by the structural boundaries of allowed adaptation rather than merely by freezing components.
arXiv:2607. 19020v1 Announce Type: cross Abstract: Background: Clinical decision support systems degrade silently as treatment protocols evolve, yet standard adaptation methods treat models as monolithic blocks, unable to distinguish stable patient physiology from shifting institutional practice.
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.
arXiv:2607. 14984v1 Announce Type: new Abstract: Per-subgroup fairness audits of medical image classifiers face a sample-size problem: minority subgroups in held-out test sets have so few samples that the resulting confidence intervals on per-subgroup performance are wider than the bias the audit is meant to detect.
The paper introduces CELLAUDIT, a method for auditing whether inputs claimed to influence predictive models actually do so. By testing if an input can enter the computation, whether predictions depend on it, and if that dependence improves observed responses, the authors evaluate agent-generated predictors on a morphology‑transcriptomics benchmark (BBBC047). Their findings show that many models claim compound contributions that are not supported by the data, and that falsification‑guided revisions can recover genuine input effects while improving performance.
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.
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.
arXiv:2607. 26752v1 Announce Type: new Abstract: Medical world models aim to learn a latent state of patient or organ physiology and a transition function that forecasts how that state evolves under interventions, supporting downstream tasks from imaging-based diagnosis to digital-twin treatment planning.
arXiv:2608. 20290v1 Announce Type: new Abstract: Whether a language model has improved itself is increasingly judged not by mean accuracy but by which individual problems it gains and loses.
arXiv:2610.02957v1 Announce Type: new Abstract: World models learn state evolution from trajectories, making access to temporal context a central training requirement. Federated learning can use dist...
The paper introduces a framework that distinguishes two causes of saturation in clinical prediction: a learner gap, where the model fails to use available information, and a measurement‑channel ceiling, where the recorded variables limit performance. It provides theoretical characterizations, finite‑sample diagnostics, and empirical audits across three large cohorts, showing that well‑tuned models approach the frontier while deficient learners leave large gaps. A PRISMA‑guided synthesis across 104 tasks reveals consistent channel‑level patterns, suggesting that improving the learner or the measurement channel can audit and potentially lift performance.