{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006461096,0.001400054,0.0005917388,0.001610596,0.0009017538,0.002299706,0.002447234,0.001520007,0.01114149],"category_scores_gemma":[0.01858496,0.0007394133,0.0007083167,0.0006958317,0.001722771,0.002465704,0.004996845,0.001696166,0.005264509],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00121119,"about_ca_system_score_gemma":0.001266649,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001411216,"about_ca_topic_score_gemma":0.003815886,"domain_scores_codex":[0.9918669,0.005706052,0.0002295817,0.0009759581,0.0009030485,0.0003184755],"domain_scores_gemma":[0.9827197,0.01348145,0.0003923327,0.001862657,0.0008767328,0.0006671117],"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":[0.001418998,0.001592601,0.008939901,0.001387828,0.0001404536,0.0008425254,0.01724054,0.04780321,0.1233918,0.037554,0.008769635,0.7509184],"study_design_scores_gemma":[0.0002415542,0.0009419873,0.00482364,0.0002160919,0.00007604979,0.001007024,0.004666354,0.8000573,0.05506801,0.07505132,0.05760005,0.000250676],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02401867,0.0001041462,0.9618713,0.0004104905,0.00003671269,0.0006414293,0.0001763098,0.006803297,0.00593764],"genre_scores_gemma":[0.2502175,0.0001010344,0.7437896,0.0002541322,0.00003666138,0.0008276206,0.000626519,0.0004786238,0.003668314],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01114149,"threshold_uncertainty_score":0.03727198,"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."}}