{"id":"W4412889754","doi":"10.18653/v1/2025.acl-long.1420","title":"DeepReview: Improving LLM-based Paper Review with Human-like Deep Thinking Process","year":2025,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Law","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"National Natural Science Foundation of China; Westlake University; Institute for Catastrophic Loss Reduction","keywords":"Computer science; Process (computing); Artificial intelligence; Programming language","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001590004,0.0001870932,0.0003302656,0.00006295338,0.00126588,0.0001607807,0.0006838742,0.00009837359,0.001893559],"category_scores_gemma":[0.0004396944,0.0001418532,0.00009757731,0.0008636047,0.0004151529,0.0004626533,0.00005338634,0.0002150523,0.0001050883],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001273179,"about_ca_system_score_gemma":0.0004891545,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001937466,"about_ca_topic_score_gemma":0.01901952,"domain_scores_codex":[0.9978889,0.0002207396,0.0004419871,0.0004244391,0.0005632748,0.0004606272],"domain_scores_gemma":[0.9988164,0.0002051267,0.0001578759,0.0003727723,0.0003496909,0.00009808781],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00003114427,0.0004216355,0.00650477,0.006228845,0.00009536187,0.00002533592,0.007576064,0.000236237,0.0002549251,0.6405392,0.00668952,0.331397],"study_design_scores_gemma":[0.0003257713,0.000248446,0.0002465568,0.0160436,0.0006105504,0.000001627436,0.009313968,0.000943128,0.003235586,0.05204171,0.9154528,0.001536233],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.005088493,0.06089189,0.06057231,0.01827197,0.0007954925,0.003899814,0.000001522147,0.001112646,0.8493659],"genre_scores_gemma":[0.9163904,0.005704362,0.00681542,0.05962354,0.0003239635,0.0004451413,0.000009633313,0.00005721876,0.01063037],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9113019,"threshold_uncertainty_score":0.9990188,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02684378825721569,"score_gpt":0.3791996728400586,"score_spread":0.3523558845828429,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}