{"id":"W6958801555","doi":"10.6084/m9.figshare.c.6591548","title":"Reliability and validity of an innovative high performing healthcare system assessment tool","year":2024,"lang":"en","type":"other","venue":"Figshare","topic":"Genetic and Environmental Crop Studies","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Reliability (semiconductor); Health care; Consistency (knowledge bases); Construct (python library); Validity; The Internet; Relevance (law)","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.00006619716,0.0001587604,0.0002435864,0.000009162627,0.00005351774,0.00001999511,0.00009921043,0.000143929,0.02631484],"category_scores_gemma":[0.00002654493,0.00006022077,0.00003195271,0.0001150207,0.00001853424,0.00002221518,0.0001950607,0.0001252081,0.000121663],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004992012,"about_ca_system_score_gemma":0.000007410282,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004152708,"about_ca_topic_score_gemma":0.0001844063,"domain_scores_codex":[0.9991735,0.00005023649,0.0001622119,0.0003223981,0.0001620341,0.0001296547],"domain_scores_gemma":[0.9997178,0.00003271836,0.0001158825,0.00006698724,0.00002870787,0.0000378905],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00001108459,0.0001215418,0.002571999,0.00876944,0.00009299799,0.000018255,0.0002572238,0.000001408231,0.0009455945,0.0000967293,0.9316996,0.05541407],"study_design_scores_gemma":[0.00009354756,0.0007318868,0.3797268,0.005885288,0.00002868647,0.000007021701,0.001730802,0.00002658116,0.0002155682,0.00006091578,0.6110156,0.0004772814],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.2492934,0.00223431,7.590208e-8,0.0002886188,0.0002517011,0.001170186,0.6699297,0.0002690122,0.07656305],"genre_scores_gemma":[0.9516018,0.00003347695,0.0001504204,0.00003141961,0.0002588215,0.0001130578,0.03076075,0.00001148975,0.01703873],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7023085,"threshold_uncertainty_score":0.9745752,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04712022508243588,"score_gpt":0.2671972508238067,"score_spread":0.2200770257413709,"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."}}