Tag
The paper introduces ClaimNov, a fine-grained claim-level novelty checking module for AI scientific discovery pipelines, which catches 97% of disguised papers at a 1.5% false-alarm rate while preserving genuinely novel proposals.
FaithSieve is a Lean-assisted framework for fine-grained evaluation of mathematical proofs that uses semantic alignment scoring to ensure faithful formal evidence, achieving higher accuracy than baseline methods on expert-verified datasets.
This paper provides a comprehensive review of recent deep learning approaches for drug-target binding affinity prediction, analyzing benchmark datasets and identifying key challenges such as cold-start scenarios and dataset bias.