{"id":"W6964124473","doi":"10.25384/sage.22670697","title":"Supplemental Material - Accuracy of Information and References Using ChatGPT-3 for Retrieval of Clinical Radiological Information","year":2023,"lang":"en","type":"article","venue":"Sage Journals Data","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Radiological weapon; Field (mathematics); Medical information; MEDLINE; Information system","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.004136879,0.001322622,0.001876596,0.007092774,0.001470679,0.004001277,0.003077663,0.003630801,0.9088168],"category_scores_gemma":[0.1059027,0.001256361,0.0009641934,0.006846361,0.0007361342,0.003124342,0.002590576,0.002006467,0.5841472],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002338375,"about_ca_system_score_gemma":0.004670996,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01013007,"about_ca_topic_score_gemma":0.01339951,"domain_scores_codex":[0.9949715,0.0008426526,0.00124047,0.0006070765,0.001993615,0.0003447649],"domain_scores_gemma":[0.9021032,0.05128485,0.004996984,0.006790404,0.03190412,0.002920384],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"observational","study_design_scores_codex":[0.00007172269,0.0000411778,0.0002996125,0.0005676567,0.000007103336,0.00003653666,0.00003035213,0.00007615068,0.00008214135,0.0004161625,0.9880605,0.01031073],"study_design_scores_gemma":[0.0003349007,0.00007313106,0.005634314,0.002679932,0.00003957919,0.0006373743,0.0002481113,0.0009262596,0.0008695055,0.0100226,0.9784284,0.0001059081],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.0004767534,0.0002102731,0.006125904,0.002449546,0.001395976,0.0006178503,0.9548883,0.008269533,0.02556575],"genre_scores_gemma":[0.00755392,0.00071134,0.02250585,0.003714739,0.001360588,0.003390498,0.8812638,0.00766556,0.07183372],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9958631,"threshold_uncertainty_score":0.1300617,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5383603456117746,"score_gpt":0.56073980414764,"score_spread":0.02237945853586543,"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."}}