AI RESEARCH
Are Compact Rationales Free? Measuring Tile Selection Headroom in Frozen WSI-MIL
arXiv CS.AI
•
ArXi:2605.12575v1 Announce Type: cross Whole-slide image (WSI) multiple instance learning (MIL) classifiers can achieve strong slide-level AUC while leaving the full-bag prediction opaque. Attention scores are widely reused as post-hoc explanations, but high attention can reflect aggregation preference rather than a compact, model-sufficient rationale. We study post-hoc rationale highlighting for frozen WSI-MIL: given a trained classifier, can its slide-level prediction be recovered from a compact, output-consistent tile subset without re.