Do AI Scientists Know What's New?
ClaimNov is introduced, a fine-grained, interpretable claim-level novelty module that catches 97% of disguised papers at a 1.5% false-alarm rate, and cuts the LLM judge's false alarms from 11.8% to 1.5%.
Miri Liu, Xi-Yu Zhao, En-Cheng Xie et al.
· 0 citations