{"id":"W4388144473","doi":"10.5860/crl.84.6.974","title":"How Well Does ChatGPT Handle Reference Inquiries? An Analysis Based on Question Types and Question Complexities","year":2023,"lang":"en","type":"article","venue":"College & Research Libraries","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Rubric; Computer science; Information retrieval; Question answering; Data science; Psychology; Mathematics education","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":[0.05260706,0.0009647448,0.001557939,0.004700515,0.0009268143,0.004402877,0.001852668,0.001216452,0.002499776],"category_scores_gemma":[0.378412,0.0005573547,0.00127474,0.004167129,0.001377555,0.007999251,0.004246234,0.001635608,0.001630205],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001948848,"about_ca_system_score_gemma":0.002010809,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004786362,"about_ca_topic_score_gemma":0.004919263,"domain_scores_codex":[0.9403617,0.03795276,0.006467197,0.003497896,0.01008705,0.001633299],"domain_scores_gemma":[0.4173478,0.494789,0.02016488,0.01606786,0.04759005,0.004040293],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.002405792,0.0009888349,0.3871362,0.004485788,0.0006775729,0.0009806278,0.1012154,0.00573196,0.01183544,0.00220606,0.01105929,0.4712771],"study_design_scores_gemma":[0.0003726043,0.00419991,0.7451305,0.00262202,0.001215821,0.002849738,0.07002026,0.07990466,0.02044306,0.008248617,0.06426097,0.0007319015],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9300224,0.001158203,0.04697616,0.001750004,0.0001609043,0.002217103,0.001288105,0.002461253,0.01396593],"genre_scores_gemma":[0.9615105,0.0006407422,0.0304184,0.0005643618,0.0001042104,0.001474066,0.001607201,0.0004355948,0.003245071],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05260706,"threshold_uncertainty_score":0.2782161,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3212286290210191,"score_gpt":0.4800208691422215,"score_spread":0.1587922401212024,"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."}}