{"id":"W41647797","doi":"10.1007/978-3-319-10061-6_14","title":"Answering Yes/No Questions in Legal Bar Exams","year":2014,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Topic Modeling","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Question answering; Sentence; Artificial intelligence; Natural language processing; Task (project management); Negation; Construct (python library); Knowledge base; Variety (cybernetics); Natural language; Domain (mathematical analysis); Programming language","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":[0.00542865,0.0005756828,0.0006538981,0.0008963827,0.001450375,0.003518612,0.001143494,0.002146115,0.03483853],"category_scores_gemma":[0.04641019,0.00043016,0.0005510755,0.000686685,0.0007860018,0.005833196,0.002516749,0.00227912,0.01199729],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007944166,"about_ca_system_score_gemma":0.001097895,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001506087,"about_ca_topic_score_gemma":0.002448929,"domain_scores_codex":[0.9942673,0.003053308,0.00031713,0.0006728102,0.001143175,0.0005462132],"domain_scores_gemma":[0.9780742,0.01712874,0.001185959,0.0007223326,0.001868595,0.001020191],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00122231,0.001769818,0.05380591,0.000611019,0.00007324704,0.0006697646,0.0107463,0.003392448,0.005468874,0.04741181,0.188613,0.6862156],"study_design_scores_gemma":[0.0002635177,0.0009946261,0.09658445,0.002066992,0.0002193251,0.001327031,0.0264571,0.04880375,0.01626843,0.2937201,0.5130827,0.0002120101],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4822134,0.002716968,0.12379,0.02021088,0.002510763,0.001008455,0.003864362,0.004039557,0.3596456],"genre_scores_gemma":[0.8593863,0.0007907717,0.05445115,0.002452452,0.000788016,0.0003821937,0.004715375,0.0005251567,0.07650866],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.03483853,"threshold_uncertainty_score":0.1165465,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0165287568741459,"score_gpt":0.2411456648454812,"score_spread":0.2246169079713353,"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."}}