{"id":"W2148429219","doi":"10.1214/10-aoas378","title":"Detecting multiple authorship of United States Supreme Court legal decisions using function words","year":2011,"lang":"en","type":"article","venue":"The Annals of Applied Statistics","topic":"Authorship Attribution and Profiling","field":"Computer Science","cited_by":30,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Supreme court; Style (visual arts); Function (biology); Legal writing; Writing style; Statistical analysis","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":[0.00575741,0.0004954014,0.0004931457,0.01025941,0.001046472,0.002671517,0.0004690576,0.0007387932,0.001435474],"category_scores_gemma":[0.08043879,0.0002283329,0.0003710158,0.005525404,0.00118372,0.002737869,0.001476462,0.0007525908,0.0005552983],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005420168,"about_ca_system_score_gemma":0.0006207642,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008307722,"about_ca_topic_score_gemma":0.001241353,"domain_scores_codex":[0.992353,0.003857824,0.001169582,0.0009074754,0.00130895,0.0004031732],"domain_scores_gemma":[0.8277453,0.1250159,0.02660729,0.009003758,0.009429147,0.002198548],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0005703649,0.0001551373,0.8283071,0.0001797888,0.0001352689,0.0005070437,0.008539611,0.001753425,0.008934806,0.003688864,0.001065399,0.1461632],"study_design_scores_gemma":[0.00005359523,0.0004381701,0.8638601,0.0001906005,0.0002016015,0.002242994,0.01326714,0.06342433,0.02217809,0.02719643,0.006750641,0.0001963639],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9905393,0.0001814239,0.007059358,0.00007097789,0.00002763042,0.00002321938,0.000244178,0.00006341421,0.001790432],"genre_scores_gemma":[0.9962519,0.00003719314,0.003156318,0.00001005826,0.00001995221,0.0000147895,0.0002245507,0.00001441085,0.0002708788],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01025941,"threshold_uncertainty_score":0.03044844,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2448864315332253,"score_gpt":0.347889792177648,"score_spread":0.1030033606444227,"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."}}