{"id":"W3211702131","doi":"10.26615/978-954-452-072-4_139","title":"Exploiting Domain-Specific Knowledge for Judgment Prediction is no Panacea","year":2021,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Law","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Research Unit on Children's Psychosocial Maladjustment; Université de Montréal","funders":"Université de Montréal","keywords":"Computer science; Panacea (medicine); Verdict; Artificial intelligence; Task (project management); Scalability; Transformer; Machine learning; Engineering; Law; Political science; Database","routes":{"ca_aff":true,"ca_fund":true,"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":[0.002213348,0.0009928122,0.0008300265,0.001978531,0.0004846834,0.002246199,0.001911185,0.001431875,0.005635799],"category_scores_gemma":[0.01459932,0.000430723,0.0009305545,0.001561586,0.000663116,0.006550346,0.001157023,0.003015427,0.003884641],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009794561,"about_ca_system_score_gemma":0.001193686,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00593486,"about_ca_topic_score_gemma":0.01775671,"domain_scores_codex":[0.9985195,0.0004466986,0.0001450843,0.0004908409,0.0002886309,0.0001092758],"domain_scores_gemma":[0.9890226,0.006456101,0.0009918206,0.001849898,0.001320148,0.000359513],"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":[0.0004487674,0.001255309,0.0620873,0.001106844,0.0004320676,0.0003935718,0.0004309036,0.133992,0.01026537,0.006735012,0.02757423,0.7552786],"study_design_scores_gemma":[0.00002664544,0.0002660392,0.02135924,0.0002483888,0.0001179122,0.0003263147,0.0004897857,0.9098766,0.008077368,0.04281413,0.0163124,0.00008527533],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.322303,0.003958154,0.617139,0.006593122,0.0005648474,0.0005320699,0.01133273,0.007616624,0.02996049],"genre_scores_gemma":[0.8956245,0.0006962611,0.09300031,0.0004041624,0.0001546759,0.00009082217,0.006563698,0.0001418854,0.003323717],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00593486,"threshold_uncertainty_score":0.0188536,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1171803476763433,"score_gpt":0.3732003122322491,"score_spread":0.2560199645559058,"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."}}