{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001573441,0.00006858229,0.0001596311,0.00003739804,0.0004272788,0.00001775098,0.00005800709,0.00005211555,0.000002824369],"category_scores_gemma":[0.0004443394,0.00003908943,0.00004199117,0.0004504971,0.00008044032,0.00002885523,0.00001955215,0.0001191529,0.00001472566],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000640577,"about_ca_system_score_gemma":0.0003540601,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002147255,"about_ca_topic_score_gemma":0.0003459301,"domain_scores_codex":[0.9989181,0.00007652369,0.0003909432,0.0001760591,0.0001585404,0.0002798763],"domain_scores_gemma":[0.9988847,0.0002288148,0.00008874977,0.0003024686,0.0003339821,0.0001612972],"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":[0.000829635,0.0002212476,0.09559944,0.001517172,0.000009885446,7.023717e-7,0.009988026,0.000125464,0.0002648361,0.0004681275,0.07179729,0.8191782],"study_design_scores_gemma":[0.0005804893,0.005871267,0.6773319,0.00134333,0.00017992,0.00002114831,0.04154321,0.04638055,0.007902921,0.02209807,0.1962985,0.0004486902],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8230133,0.000176382,0.0003439494,0.1734018,0.0006123537,0.002384162,0.000008756416,0.00004960866,0.000009758319],"genre_scores_gemma":[0.9965724,0.000327215,0.0001755067,0.001776998,0.0002345832,0.000435142,0.00009010114,0.00001132118,0.0003767564],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8187295,"threshold_uncertainty_score":0.3286326,"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."}}