{"id":"W4403923053","doi":"10.1145/3686215.3688377","title":"Combining Generative and Discriminative AI for High-Stakes Interview Practice","year":2024,"lang":"en","type":"article","venue":"","topic":"Explainable Artificial Intelligence (XAI)","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Integrity Testing Laboratory (Canada)","funders":"","keywords":"Discriminative model; Generative grammar; Computer science; Artificial intelligence; Natural language processing; Machine learning","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":[0.000669536,0.0001436655,0.0001543754,0.00009898061,0.0001689,0.000845116,0.0003511435,0.00003889624,0.00002232756],"category_scores_gemma":[0.0003507681,0.0001141929,0.00004150195,0.0003001239,0.0000773685,0.002303486,0.0002203343,0.0001356698,0.0000531191],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004821366,"about_ca_system_score_gemma":0.00006596025,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001275938,"about_ca_topic_score_gemma":0.00007519045,"domain_scores_codex":[0.9987655,0.0001327808,0.0002269758,0.0004772773,0.0001475243,0.0002499547],"domain_scores_gemma":[0.9983369,0.001084455,0.00004317129,0.0002421326,0.0002212388,0.00007213686],"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":[0.000003516778,0.0000331897,0.000001005735,0.00005336346,0.00003088218,0.00001918681,0.008122724,0.0000163328,0.0004857674,0.8994334,0.003158547,0.08864205],"study_design_scores_gemma":[0.0001572562,0.0009383491,0.0000203724,0.0002821488,0.00006028826,0.00005627964,0.01057093,0.4604245,0.1452191,0.3068479,0.0748985,0.0005244095],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0006489983,0.001212151,0.9591902,0.03265165,0.0005618646,0.0003185695,0.000004055911,0.0002233899,0.005189076],"genre_scores_gemma":[0.8278096,0.0001114227,0.1647803,0.004182463,0.000101095,0.0001331653,0.000004004981,0.00001816032,0.002859771],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8271606,"threshold_uncertainty_score":0.8149473,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06798635015225182,"score_gpt":0.3544138994326959,"score_spread":0.2864275492804441,"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."}}