{"id":"W4408141487","doi":"10.1093/gpbjnl/qzaf017","title":"Evaluative Methodology for HRD Testing: Development of Standard Tools for Consistency Assessment","year":2025,"lang":"en","type":"article","venue":"Genomics Proteomics & Bioinformatics","topic":"Human Resource Development and Performance Evaluation","field":"Psychology","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"MD Precision (Canada)","funders":"","keywords":"Consistency (knowledge bases); Computer science; Reliability engineering; Artificial intelligence; Engineering","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00664235,0.000301947,0.0006250343,0.0004797778,0.0004162217,0.00008543416,0.0003856528,0.0002530837,0.00007426381],"category_scores_gemma":[0.001322549,0.0002987119,0.0001415264,0.0003286526,0.0001365398,0.0001741212,0.0001195004,0.0001791456,0.00001709303],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004938198,"about_ca_system_score_gemma":0.002434628,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002126322,"about_ca_topic_score_gemma":0.000009673713,"domain_scores_codex":[0.9971043,0.0001497437,0.001695628,0.0002871939,0.0002475783,0.0005155655],"domain_scores_gemma":[0.9956405,0.002028686,0.000865931,0.0004020401,0.0009958885,0.00006694111],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.003244834,0.0002730657,0.003116002,0.002180577,0.001579904,4.03206e-7,0.06802333,0.00107098,0.01006371,0.1038761,0.003599695,0.8029714],"study_design_scores_gemma":[0.03545109,0.004828567,0.04064013,0.0009929814,0.001586859,0.00002397066,0.04883138,0.3033535,0.1196264,0.08618754,0.3547225,0.003755071],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2673252,0.00005808608,0.7141294,0.0001351266,0.0006629902,0.005381818,0.0001761254,0.00004553992,0.01208563],"genre_scores_gemma":[0.01837261,0.000006606891,0.9781704,0.0002566784,0.00005886111,0.001993967,0.0003441959,0.00002858741,0.0007681105],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7992163,"threshold_uncertainty_score":0.9999465,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2234653144906807,"score_gpt":0.441635837035023,"score_spread":0.2181705225443422,"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."}}