{"id":"W2797709357","doi":"10.56645/jmde.v14i30.501","title":"Customizing the Standard to the Purpose of the Assessment","year":2018,"lang":"en","type":"article","venue":"Journal of MultiDisciplinary Evaluation","topic":"Evaluation and Performance Assessment","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Psychology","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":[0.04721186,0.0001231923,0.0002483894,0.0001792748,0.0008100446,0.0001709943,0.00145318,0.00004486865,0.0007954811],"category_scores_gemma":[0.002702649,0.00004417997,0.0002311331,0.0009896084,0.0002051129,0.0004481355,0.0003563197,0.0002939054,0.00006713737],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002568292,"about_ca_system_score_gemma":0.001260054,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000399215,"about_ca_topic_score_gemma":0.0001276374,"domain_scores_codex":[0.9903857,0.001768763,0.001315082,0.0001806289,0.006173948,0.0001758862],"domain_scores_gemma":[0.9920549,0.001204615,0.001568584,0.0008012665,0.004298581,0.00007205031],"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":[0.001125118,0.0004226338,0.113124,0.00001413691,0.000203593,0.000001858339,0.0469129,0.1446871,0.01312502,0.002738802,0.07555421,0.6020906],"study_design_scores_gemma":[0.001550451,0.001107152,0.7384084,0.0001236672,0.0001851738,0.00003637719,0.01246138,0.201395,0.003378215,0.01001053,0.03121085,0.0001327487],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9189567,0.0001097715,0.01464775,0.05967933,0.002606291,0.001007529,0.00000879224,0.000003888149,0.00297997],"genre_scores_gemma":[0.9966023,0.00001555066,0.002119578,0.0003085457,0.0005968587,0.00001871228,5.702761e-7,0.000007635706,0.0003302536],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6252844,"threshold_uncertainty_score":0.9810959,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2134546959921358,"score_gpt":0.5487707242592667,"score_spread":0.3353160282671309,"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."}}