{"id":"W2062618525","doi":"10.1186/1472-6947-8-18","title":"Script Concordance Tests: Guidelines for Construction","year":2008,"lang":"en","type":"article","venue":"BMC Medical Informatics and Decision Making","topic":"Clinical Reasoning and Diagnostic Skills","field":"Medicine","cited_by":253,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Université du Québec à Montréal","funders":"","keywords":"Concordance; Context (archaeology); Computer science; Test (biology); Task (project management); Process (computing); Health informatics; Quality (philosophy); Natural language processing; Information retrieval; Data science; Artificial intelligence; Medicine; Pathology","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":[0.000745735,0.0001240507,0.0003636674,0.00007831363,0.0001589457,0.00002672403,0.00007801577,0.0001651965,0.0001005582],"category_scores_gemma":[0.1391698,0.00008778623,0.00007380947,0.000139498,0.0002440623,0.00008728746,0.00006642341,0.0001514041,0.00001884177],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001879489,"about_ca_system_score_gemma":0.0003985158,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000003014756,"about_ca_topic_score_gemma":0.000003773572,"domain_scores_codex":[0.9979927,0.000009315787,0.00101227,0.0001259343,0.0006559169,0.0002038832],"domain_scores_gemma":[0.9839103,0.01483009,0.0001944629,0.0002069815,0.0005139771,0.0003442013],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002752545,0.00005303823,0.01374115,0.0001153848,0.00001429182,0.00002017845,0.00009855603,0.00002740518,0.000003192967,0.001595647,0.05859178,0.9254641],"study_design_scores_gemma":[0.01278586,0.001128219,0.01597109,0.01905524,0.0001601791,0.005600078,0.001512655,0.8637027,0.00007772635,0.01485239,0.06457726,0.00057659],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.3127335,0.000347344,0.6849474,0.0001726758,0.0004417649,0.0002410126,0.000007447718,0.00005148164,0.001057364],"genre_scores_gemma":[0.08486252,0.0008140043,0.9064167,0.007445702,0.0003620718,0.00002021012,0.00001478716,0.00001111948,0.00005285245],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9248875,"threshold_uncertainty_score":0.8680813,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1298384051838863,"score_gpt":0.4334338565504915,"score_spread":0.3035954513666053,"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."}}