{"id":"W179309874","doi":"10.58948/2331-3528.1800","title":"Inconsistent Responsiveness Determination in Document Review: Difference of Opinion or Human Error?","year":2012,"lang":"en","type":"article","venue":"Pace law review","topic":"Legal Systems and Judicial Processes","field":"Social Sciences","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Ambiguity; Computer science; Human error; Quality (philosophy); Information retrieval; Psychology; Data science; Risk analysis (engineering); Epistemology; Medicine","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":[0.002601799,0.0001060382,0.0004852774,0.0000283927,0.0001590746,0.00001545899,0.0001815946,0.00005257427,0.0001288955],"category_scores_gemma":[0.0006922764,0.00007787577,0.00007452226,0.0003894258,0.0001242356,0.0002824263,0.00004768326,0.00007993258,0.00001929373],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001181433,"about_ca_system_score_gemma":0.0001112101,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006492675,"about_ca_topic_score_gemma":0.006215663,"domain_scores_codex":[0.9979517,0.0007771663,0.0005064097,0.0001465316,0.0003696356,0.000248524],"domain_scores_gemma":[0.9990876,0.0001579705,0.0003277721,0.0001854904,0.0001478304,0.00009328737],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00006360505,0.0005724577,0.0149139,0.1527165,0.00003851966,0.00001002546,0.008451799,3.942681e-7,0.0004709448,0.7026374,0.004018829,0.1161055],"study_design_scores_gemma":[0.0001451576,0.00006170986,0.002958626,0.07579434,0.00004844321,0.000002395471,0.0001906159,3.4353e-7,0.00008740863,0.0006062858,0.9199017,0.000202934],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"empirical","genre_scores_codex":[0.005989031,0.9606301,0.00002135497,0.00555252,0.0005025616,0.002080751,0.000004154659,0.0000345648,0.02518499],"genre_scores_gemma":[0.7329552,0.2655224,0.00003574947,0.0009430788,0.000109194,0.0001002077,0.000003127183,0.000006267459,0.0003247791],"genre_candidate":"review","genre_consensus":null,"teacher_disagreement_score":0.9158829,"threshold_uncertainty_score":0.9815026,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07820519774678054,"score_gpt":0.4173457186269999,"score_spread":0.3391405208802194,"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."}}