{"id":"W4415583954","doi":"10.1145/3755881.3755908","title":"Enhancement Report Approval Prediction: A Comparative Study of Large Language Models","year":2025,"lang":"","type":"article","venue":"","topic":"Artificial Intelligence in Law","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Natural language; Language model; Key (lock); Field (mathematics); Feature (linguistics)","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02142628,0.0008656539,0.001044465,0.001515214,0.0007785577,0.002789015,0.002538499,0.00129904,0.005786857],"category_scores_gemma":[0.08206971,0.0005782727,0.001431211,0.001439497,0.0007214614,0.005548051,0.001095909,0.002578686,0.00246505],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001675257,"about_ca_system_score_gemma":0.001484175,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0125559,"about_ca_topic_score_gemma":0.01111021,"domain_scores_codex":[0.992241,0.005751263,0.0002974349,0.0008002531,0.0007219081,0.0001880407],"domain_scores_gemma":[0.7010313,0.2807992,0.004153844,0.007131459,0.005820083,0.001064215],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.01535386,0.006754803,0.3143566,0.001015614,0.001990513,0.0007687557,0.002788931,0.2714161,0.002261992,0.01266443,0.03238243,0.338246],"study_design_scores_gemma":[0.0005305007,0.001200042,0.04224923,0.00007056902,0.0006729708,0.0002132097,0.0005545122,0.9418356,0.001639075,0.006998436,0.003934644,0.0001012249],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9644642,0.00160403,0.02120481,0.001595429,0.0001415659,0.0002101518,0.001820636,0.001156869,0.007802323],"genre_scores_gemma":[0.9867952,0.0003382083,0.006755396,0.0002024395,0.0001186566,0.00008934619,0.003161535,0.0001746953,0.002364483],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.02142628,"threshold_uncertainty_score":0.1133143,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09149538898364608,"score_gpt":0.4320685945447368,"score_spread":0.3405732055610908,"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."}}