{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001597384,0.0001464091,0.000225333,0.0001780299,0.0002397907,0.00003781238,0.0005782854,0.00007915979,0.00002569788],"category_scores_gemma":[0.0004497444,0.0001176751,0.00004922659,0.0007180744,0.000137919,0.000123432,0.0001866112,0.0002411137,0.000007192675],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001042418,"about_ca_system_score_gemma":0.00007469267,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002269908,"about_ca_topic_score_gemma":0.0000271622,"domain_scores_codex":[0.9984819,0.0001352508,0.000512569,0.0002114445,0.0003552064,0.0003036731],"domain_scores_gemma":[0.9975441,0.001074565,0.0004155559,0.0004674293,0.0004032359,0.00009510239],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006720368,0.0001814138,0.0006507174,0.00006238949,0.0001641758,0.000005641329,0.0165386,0.009733577,0.008798529,0.9210965,0.0006005215,0.04149589],"study_design_scores_gemma":[0.0004153797,0.0002156012,0.003629248,0.00006710214,0.00007154745,0.00000518637,0.00147629,0.6351608,0.09820084,0.2595783,0.0008729588,0.0003068008],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1376094,0.00003082987,0.861544,0.00006308993,0.0001563047,0.0001529222,0.0001098097,0.00005291263,0.0002807587],"genre_scores_gemma":[0.8363841,0.00001700424,0.1633866,0.0001352786,0.00002110706,0.000003563279,0.00002683284,0.00001101431,0.00001451759],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6987748,"threshold_uncertainty_score":0.4798653,"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."}}