{"id":"W2083551948","doi":"10.1186/1472-6920-12-20","title":"Expert validation of fit-for-purpose guidelines for designing programmes of assessment","year":2012,"lang":"en","type":"article","venue":"BMC Medical Education","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":60,"is_retracted":false,"has_abstract":true,"ca_institutions":"The Wilson Centre; University of Toronto","funders":"","keywords":"Rubric; Competence (human resources); Brainstorming; Computer science; Context (archaeology); Judgement; Management science; Set (abstract data type); Process management; Medical education; Psychology; Medicine; Engineering; Artificial intelligence; Pedagogy","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01588758,0.00007866164,0.0002643609,0.0002491391,0.00005737637,0.00002390598,0.0003495681,0.00009395998,0.0001532002],"category_scores_gemma":[0.4438886,0.00005391234,0.0001098931,0.0006310213,0.00006124732,0.0001761488,0.00003660479,0.00004204783,0.000001070152],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002529479,"about_ca_system_score_gemma":0.001082617,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003503648,"about_ca_topic_score_gemma":0.000001831785,"domain_scores_codex":[0.9972916,0.0002843097,0.0009979048,0.0001980972,0.00102899,0.0001991245],"domain_scores_gemma":[0.9655533,0.03127122,0.0007797999,0.0003383119,0.00186475,0.0001925471],"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":[0.00002479529,0.0003312608,0.08680783,0.00007429082,0.000007677419,4.984879e-9,0.000476269,0.00001808204,0.0007156357,0.001954925,0.02984883,0.8797404],"study_design_scores_gemma":[0.00611675,0.002330307,0.3228977,0.001926254,0.0002516369,0.00003057651,0.05954146,0.06794459,0.1365137,0.1521475,0.2488676,0.001431873],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1454097,0.0008788073,0.8503226,0.0008643784,0.001717346,0.0005623492,0.000002991201,0.0000150322,0.0002267722],"genre_scores_gemma":[0.2901309,0.00001980704,0.7088968,0.0001544219,0.0004590299,0.0002154915,0.00001291915,0.000005469928,0.0001051241],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.8783085,"threshold_uncertainty_score":0.5607958,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.8167830120164873,"score_gpt":0.6580040613090576,"score_spread":0.1587789507074296,"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."}}