{"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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002147216,0.00007001661,0.0001013493,0.00005130378,0.0009777648,0.00004656443,0.0002893457,0.00002827372,0.002329481],"category_scores_gemma":[0.0009736519,0.0000548551,0.0000675546,0.0002657698,0.0002422694,0.0002412556,0.00006511946,0.0001395252,0.000006488352],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001153902,"about_ca_system_score_gemma":0.0001991032,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004392551,"about_ca_topic_score_gemma":0.001445772,"domain_scores_codex":[0.9976798,0.0007667379,0.0003477726,0.0001525829,0.0008819819,0.000171097],"domain_scores_gemma":[0.9990121,0.0003463186,0.0002367001,0.0001656235,0.000206886,0.00003236738],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00007125493,0.0001761961,0.0009425977,0.000007164789,0.00001840006,0.00000163058,0.02335952,0.03860283,0.2131304,0.680101,0.005029239,0.03855973],"study_design_scores_gemma":[0.00015606,0.001140856,0.0007446703,0.00001544472,0.00009902591,0.000003449798,0.09196518,0.3090252,0.5835503,0.00503009,0.007906454,0.000363299],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9905462,0.00002158505,0.0005067799,0.001850036,0.0006679184,0.0002748275,0.000004946417,0.00002038242,0.006107373],"genre_scores_gemma":[0.9985664,0.00000468204,0.0004746073,0.0003345476,0.0002820616,0.00003273904,0.000004025362,0.000006479471,0.0002944955],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6750709,"threshold_uncertainty_score":0.9985825,"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."}}