{"id":"W6961093132","doi":"10.1371/journal.pone.0284469.s001","title":"Included 49 studies.","year":2023,"lang":"en","type":"article","venue":"Figshare","topic":"Occupational Health and Performance","field":"Health Professions","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Rasch model; Observational study; Psychometrics; Scale (ratio); Inter-rater reliability; Quality (philosophy); Item response theory; Reliability (semiconductor)","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.0001477298,0.0000716087,0.0001199508,0.00007403573,0.0007416036,0.000002104851,0.0001101031,0.00009090062,0.1478659],"category_scores_gemma":[0.001511171,0.00006002442,0.00002446146,0.0004161069,0.000003205275,0.0000830221,0.0001681032,0.0002842591,0.2161863],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007882822,"about_ca_system_score_gemma":0.0002765147,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006730043,"about_ca_topic_score_gemma":0.00004530501,"domain_scores_codex":[0.999003,0.00007441001,0.0002348006,0.0001287296,0.0001687011,0.0003903378],"domain_scores_gemma":[0.9987757,0.0006748154,0.00008305514,0.0001563741,0.0002034305,0.0001065847],"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":[0.000009980314,0.000003092294,0.002925703,0.0008084155,0.000004599766,0.000003289416,0.0008402744,0.00000417387,0.000001370086,0.00002696261,0.9942029,0.001169278],"study_design_scores_gemma":[0.0002321907,0.00001773328,0.1244809,0.001226623,0.000001076093,1.923774e-7,0.0004088942,0.0002241289,0.00000675271,0.0001518029,0.8731809,0.0000687418],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.08637281,0.002636552,2.520899e-7,0.00816418,0.003155508,0.003047504,0.7133639,0.002554447,0.1807048],"genre_scores_gemma":[0.5622951,0.0002276762,0.0000672919,0.01552303,0.003021301,0.003658677,0.3720611,0.00006649172,0.04307935],"genre_candidate":"dataset","genre_consensus":null,"teacher_disagreement_score":0.4759223,"threshold_uncertainty_score":0.8529131,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5981753269732442,"score_gpt":0.6273357430421328,"score_spread":0.02916041606888864,"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."}}