{"id":"W4389368227","doi":"10.61838/hn.1.1.12","title":"The Need for More Attention to The Validity and Reliability of AI-Generated Exercise Programs","year":2023,"lang":"en","type":"article","venue":"Health Nexus","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Realm; Reliability (semiconductor); Bridge (graph theory); Risk analysis (engineering); Psychology; Computer science; Dual (grammatical number); Management science; Applied psychology; Knowledge management; Engineering ethics; Medicine; Engineering; Political science","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":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.3139466,0.0006948466,0.001885795,0.005111937,0.002195586,0.008410484,0.004561809,0.003168052,0.003445717],"category_scores_gemma":[0.6985399,0.0006215166,0.001561914,0.003058443,0.01611344,0.009920814,0.006303931,0.005729733,0.0008867541],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003670344,"about_ca_system_score_gemma":0.00815795,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006968886,"about_ca_topic_score_gemma":0.006453289,"domain_scores_codex":[0.6983857,0.205228,0.01535345,0.01677696,0.06262196,0.001633996],"domain_scores_gemma":[0.1740507,0.653181,0.03083011,0.08395107,0.05584133,0.002145788],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.001248007,0.0008132042,0.324304,0.004728521,0.001866421,0.0001950427,0.03209199,0.006761753,0.001823053,0.1154462,0.00981931,0.5009025],"study_design_scores_gemma":[0.0003650138,0.003361929,0.4370577,0.01687568,0.0008594136,0.00100644,0.02002105,0.03448197,0.00681723,0.3536274,0.1248305,0.0006958435],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"commentary","genre_scores_codex":[0.302914,0.02564289,0.443148,0.0962247,0.004822679,0.003654615,0.001278194,0.0008506606,0.1214642],"genre_scores_gemma":[0.8550839,0.003354357,0.1252362,0.009986322,0.001169837,0.002252602,0.0004805745,0.0002867721,0.002149337],"genre_candidate":"commentary","genre_consensus":null,"teacher_disagreement_score":0.6860534,"threshold_uncertainty_score":0.846026,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2350424647258777,"score_gpt":0.4713021198102795,"score_spread":0.2362596550844018,"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."}}