{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001309534,0.0001456802,0.000292462,0.0011472,0.000659934,0.0004122102,0.0001285397,0.0001569515,0.0001881164],"category_scores_gemma":[0.00116055,0.0001101835,0.00004523253,0.002091482,0.001073463,0.0007725154,0.00006180946,0.000369334,0.00007129029],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009261828,"about_ca_system_score_gemma":0.0005405265,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008908744,"about_ca_topic_score_gemma":0.0008111202,"domain_scores_codex":[0.997702,0.0005591041,0.00024382,0.000421749,0.0006361081,0.0004371947],"domain_scores_gemma":[0.9978758,0.0008707852,0.00005631776,0.0004229572,0.0004997275,0.0002744374],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.003405878,0.0006125542,0.2399283,0.001096492,0.0002553285,0.000101433,0.007218472,0.0003220689,0.001001855,0.697925,0.02195304,0.02617959],"study_design_scores_gemma":[0.0005739212,0.007723878,0.2958024,0.001171335,0.000439214,0.00001037618,0.1074143,0.2476937,0.07054124,0.179508,0.08811001,0.001011599],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9583037,0.0003536434,0.0007233831,0.03700178,0.0002746742,0.0007219653,0.00009132624,0.0003283686,0.002201142],"genre_scores_gemma":[0.9904033,0.0002744982,0.00045739,0.0002406093,0.0003544321,0.0001177054,0.0005258684,0.00002064442,0.007605547],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5184169,"threshold_uncertainty_score":0.5075745,"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."}}