FactReview extracts claims from ML papers, positions them via literature retrieval, and verifies them through code execution, labeling each as Supported, Partially supported, or In conflict, as shown in a CompGCN case study.
Smith, Yian Yin, Daniel A
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
AI reviewers of POMP data analyses detect technical and methodological errors effectively but underperform humans on interpretive, narrative, and domain-informed critique, showing consistent jaggedness.
citing papers explorer
-
FactReview: Evidence-Grounded Reviews with Literature Positioning and Execution-Based Claim Verification
FactReview extracts claims from ML papers, positions them via literature retrieval, and verifies them through code execution, labeling each as Supported, Partially supported, or In conflict, as shown in a CompGCN case study.
-
Jagged AI in Scientific Peer Review: Evidence from POMP Data Analysis
AI reviewers of POMP data analyses detect technical and methodological errors effectively but underperform humans on interpretive, narrative, and domain-informed critique, showing consistent jaggedness.