{"id":"W4288019948","doi":"10.48550/arxiv.1912.01111","title":"Use of Artificial Intelligence to Analyse Risk in Legal Documents for a\\n Better Decision Support","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Artificial Intelligence in Law","field":"Social Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"PricewaterhouseCoopers (Canada)","funders":"","keywords":"Computer science; Paragraph; Word embedding; Artificial intelligence; Machine learning; Context (archaeology); Scalability; Support vector machine; Document classification; Natural language processing; Information retrieval; Data science; Knowledge management; Embedding; World Wide Web; Database","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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001282012,0.0002924775,0.0005397598,0.000639889,0.0002193739,0.0001604289,0.001164777,0.0004679855,0.0003942754],"category_scores_gemma":[0.001074387,0.0003521705,0.000357055,0.0009992978,0.0003825448,0.0006198316,0.0007036912,0.0004990089,0.0002853796],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005182379,"about_ca_system_score_gemma":0.0004903754,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.02147114,"about_ca_topic_score_gemma":0.03168466,"domain_scores_codex":[0.9971402,0.0003059887,0.0006670744,0.001037341,0.000270197,0.0005791836],"domain_scores_gemma":[0.9970969,0.0009688729,0.0004838026,0.0008034179,0.000417859,0.000229153],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0009244154,0.0003355575,0.07473773,0.00005042645,0.000127725,0.00008391794,0.004187899,0.7252102,0.00006748245,0.1550829,0.0007552105,0.03843646],"study_design_scores_gemma":[0.000234511,0.0006730947,0.003670027,0.000712574,0.0007204094,7.34954e-7,0.01222229,0.2054928,0.009538755,0.728437,0.03578345,0.002514404],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6718417,0.000003736062,0.325562,0.00009492274,0.000806823,0.0009778279,0.00009884125,0.0000317274,0.0005823942],"genre_scores_gemma":[0.9942247,0.0001189562,0.004382394,0.0001135298,0.0001475439,0.000004203647,0.00001957645,0.00002552565,0.0009635792],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5733541,"threshold_uncertainty_score":0.999893,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1927989205076086,"score_gpt":0.3117018278638882,"score_spread":0.1189029073562796,"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."}}