{"id":"W4389009426","doi":"10.18653/v1/2022.inlg-main.7","title":"Evaluating Legal Accuracy of Neural Generators on the Generation of Criminal Court Dockets Description","year":2022,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Law","field":"Social Sciences","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université Laval","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Window (computing); Legal research; Code (set theory); Criminal court; Criminal procedure; Artificial neural network; Criminal case; Law; Artificial intelligence; Political science; World Wide Web; Programming language","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":[0.01146841,0.001696578,0.0006688802,0.002052323,0.0006464873,0.002022919,0.00185222,0.002439695,0.002356571],"category_scores_gemma":[0.06186151,0.0005103959,0.0005426937,0.001125568,0.001100902,0.002209248,0.001371164,0.001616822,0.0009148612],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001991734,"about_ca_system_score_gemma":0.001042545,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01739984,"about_ca_topic_score_gemma":0.02155666,"domain_scores_codex":[0.9922517,0.003789924,0.0009886465,0.001388367,0.001175072,0.0004063634],"domain_scores_gemma":[0.9198083,0.06489611,0.002581865,0.004946259,0.006810973,0.0009565869],"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":[0.004171847,0.001943375,0.05914252,0.001012578,0.0008800065,0.0006468387,0.001837965,0.3547276,0.01354779,0.00279442,0.0157135,0.5435817],"study_design_scores_gemma":[0.0002204929,0.001238078,0.02107465,0.0001352975,0.0002368729,0.0002053868,0.0004891425,0.9455814,0.02653395,0.001678405,0.002535598,0.0000707681],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9617832,0.001685301,0.02183474,0.000687473,0.0002284371,0.0002425514,0.0008981187,0.003523581,0.009116637],"genre_scores_gemma":[0.9731871,0.0002437706,0.02132587,0.000183917,0.00004327866,0.000103892,0.002460866,0.0001902517,0.002261106],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01739984,"threshold_uncertainty_score":0.06065148,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4012715541394553,"score_gpt":0.4527641301456726,"score_spread":0.05149257600621726,"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."}}