{"id":"W2798978891","doi":"10.1145/3209978.3210015","title":"A Dataset and an Examination of Identifying Passages for Due Diligence","year":2018,"lang":"en","type":"article","venue":"","topic":"Artificial Intelligence in Law","field":"Social Sciences","cited_by":13,"is_retracted":false,"has_abstract":true,"ca_institutions":"Cisco Systems (Canada)","funders":"","keywords":"Computer science; Sequence labeling; Conditional random field; Due diligence; Task (project management); Sequence (biology); Artificial intelligence; Annotation; Sentence; Natural language processing; Diligence; Hidden Markov model; Information retrieval; Information extraction; Machine learning; Data science","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":[0.001024429,0.00003937177,0.00006428179,0.00003309429,0.0003251963,0.00005322419,0.0001500623,0.00004134222,0.0002000502],"category_scores_gemma":[0.000404588,0.00003735255,0.00001015753,0.0001076764,0.0006205845,0.0005044844,0.00002943058,0.00001803771,0.00001055869],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001264905,"about_ca_system_score_gemma":0.0000257083,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001797327,"about_ca_topic_score_gemma":0.01526732,"domain_scores_codex":[0.9993588,0.00007714334,0.0001360013,0.0001465465,0.0001512323,0.0001302272],"domain_scores_gemma":[0.9994565,0.0001818641,0.00005629161,0.00011737,0.0001387588,0.00004923689],"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":[0.00002619311,0.0001282549,0.00332071,0.00004908752,0.0000157207,0.000001265346,0.05423265,0.000001957433,0.0133646,0.5838273,0.004591257,0.340441],"study_design_scores_gemma":[0.000239703,0.001159086,0.05501161,0.0001152526,0.00009884122,0.000002454743,0.1419963,0.006515551,0.5249646,0.1310027,0.1380083,0.0008856283],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9403981,0.00002952415,0.0499974,0.0003383383,0.000305596,0.0004358994,0.0002098801,0.00004342275,0.008241814],"genre_scores_gemma":[0.996959,0.00001440885,0.002465026,0.00004633032,0.0001945545,0.000009620031,0.00004196853,0.000003421977,0.0002656335],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5116,"threshold_uncertainty_score":0.8519526,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1640491185197676,"score_gpt":0.4630750503782688,"score_spread":0.2990259318585013,"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."}}