{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001157956,0.0004980217,0.0005339073,0.0008945523,0.0001832493,0.0006143691,0.003650182,0.0003333047,0.00002513423],"category_scores_gemma":[0.0001577105,0.0004948686,0.0001079987,0.0004676362,0.0003640983,0.0006741838,0.001436851,0.001092651,0.0001373347],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003786164,"about_ca_system_score_gemma":0.000483815,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001768954,"about_ca_topic_score_gemma":0.0002751794,"domain_scores_codex":[0.9959512,0.00005166049,0.000624984,0.001738749,0.0008591767,0.0007742757],"domain_scores_gemma":[0.9973863,0.0003340591,0.0001899993,0.001745913,0.0001605606,0.0001832207],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000002368956,0.00001890869,0.00013377,0.00004401513,0.000004844414,0.0001350405,0.0005299174,0.1667344,0.0001619297,0.1303474,0.00001685464,0.7018705],"study_design_scores_gemma":[0.0002058708,0.00008292995,0.0001925655,0.0005788371,0.000002902221,0.00006265222,7.243808e-8,0.9423875,0.0001948548,0.0483648,0.007293332,0.0006336594],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0002496479,0.0002293404,0.9873825,0.0006440709,0.002712087,0.0002752333,0.000001383546,0.000201005,0.008304699],"genre_scores_gemma":[0.3785197,0.00003426931,0.6175216,0.001670792,0.001029307,0.00001469014,0.000002645124,0.0000462582,0.001160634],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7756531,"threshold_uncertainty_score":0.9997503,"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."}}