arXiv：cs.LG· Hyun Do Jung, Jungwon Choi, Soojung Choi, Yujin Oh, Hwiyoung Kim·· 6 小时前AI 评分23
CHARTER：计算病理学分层紧凑证据评估中的参考替换审计
CHARTER: Auditing Reference Substitution in Hierarchical Compact-Evidence Evaluation for Computational Pathology
AI 导读
CHARTER 是一个面向计算病理学的参考感知评估章程，要求研究者声明预期目标与评估参考、量化候选筛选引发的预测偏移，并审计比较结论的稳定性。在五种子 Random-K 审计的 15 组对比中，4 组出现确定性反转；匹配的原生排序压力测试中，ACMIL 对比从 REVERSED 变为 PRESERVED。该章程将候选筛选与参考选择从隐含操作转为可审计的评估规范。
正文
Abstract:In digital pathology, compact evidence is often used to explain or audit predictions made by whole-slide image multiple instance learning models. In hierarchical compact-evidence pipelines, candidate filtering introduces a strategy-specific candidate-conditioned prediction alongside the original full-bag prediction. If the evaluation reference changes while the intended target remains the original full-bag prediction, however, not only can the measured fidelity of the same compact evidence change, but comparisons between competing candidate strategies can also change. To make this dependence explicit, we introduce CHARTER, a reference-aware evaluation charter that asks researchers to DECLARE the intended target and reference, QUANTIFY candidate-induced prediction shift, and AUDIT the stability of comparative conclusions. Across the 15 comparisons in our main five-seed Random-K audit, 4 showed determinate reversals; in a matched native-ranking stress test, the ACMIL comparison changed from REVERSED to PRESERVED. CHARTER turns otherwise implicit candidate-filtering and reference choices into an auditable evaluation specification, helping distinguish genuine preservation of the intended prediction from apparent gains induced by changing the prediction being explained.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Machine Learning (cs.LG) |
| Cite as: | arXiv:2610.07843 [cs.CV] |
| (or arXiv:2610.07843v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.07843 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Hyun Do Jung [view email]
[v1]
Tue, 6 Oct 2026 06:45:56 UTC (671 KB)
来源：arXiv：cs.LG · arxiv.org