{"id":"W4389518718","doi":"10.18653/v1/2023.emnlp-main.427","title":"Rather a Nurse than a Physician - Contrastive Explanations under Investigation","year":2023,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Berlin Center for Machine Learning; Novo Nordisk Fonden; Research Executive Agency; Banting and Best Diabetes Centre, University of Toronto; Novo Nordisk; European Commission","keywords":"Contrastive analysis; Computer science; Linguistics; Contrast (vision); Natural language processing; Artificial intelligence; Psychology","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00009384884,0.00005922135,0.00005743129,0.00008018326,0.00007308053,0.0000683062,0.0002221293,0.00002297743,0.000008988348],"category_scores_gemma":[0.00001352778,0.00005245112,0.00002377658,0.0004168511,0.0000203173,0.0003241469,0.00003587003,0.00004676908,0.0002729997],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002186664,"about_ca_system_score_gemma":0.0000453764,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004119528,"about_ca_topic_score_gemma":0.00004563886,"domain_scores_codex":[0.9994101,0.00002897102,0.00008844204,0.0001939659,0.0001387927,0.0001397405],"domain_scores_gemma":[0.9996138,0.00005789261,0.00002685132,0.0002154496,0.0000390718,0.00004695759],"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":[6.19861e-7,0.00001322825,0.0004955719,0.000001912179,0.00001351942,0.000002994538,0.003004514,0.002641335,0.001686199,0.9820571,0.002491234,0.007591801],"study_design_scores_gemma":[0.0002200641,0.0000143135,0.009358618,0.00001214977,0.000003191754,9.737236e-7,0.000725358,0.8828113,0.00158367,0.104872,0.0002770768,0.0001212937],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07612374,0.000004668931,0.9075011,0.005457869,0.0001784709,0.0001126826,0.00000107642,0.0004773525,0.01014306],"genre_scores_gemma":[0.9876462,7.927521e-7,0.008770699,0.001454684,0.00006350186,0.00002477644,0.000004614093,0.000005190052,0.002029601],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9115224,"threshold_uncertainty_score":0.350895,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0387413242078954,"score_gpt":0.2665800505663476,"score_spread":0.2278387263584522,"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."}}