{"id":"W2921135034","doi":"10.1111/bjep.12271","title":"The risk–return trade‐off: Performance assessments and cognitive validation of inferences","year":2019,"lang":"en","type":"article","venue":"British Journal of Educational Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Alberta Advanced Education; University of Alberta","funders":"Social Sciences and Humanities Research Council of Canada; American Institute of Certified Public Accountants","keywords":"Cognition; Psychology; Process (computing); Cognitive interview; Argument (complex analysis); Test (biology); Cognitive psychology; Task (project management); Applied psychology; Think aloud protocol; Cognitive test; Empirical evidence; Social psychology; Computer science; Usability","routes":{"ca_aff":true,"ca_fund":true,"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":[0.00628386,0.00007389243,0.0002520925,0.0002340057,0.0001673717,0.0001420449,0.000469804,0.00006373532,0.0004333173],"category_scores_gemma":[0.02688559,0.00005323796,0.00007164826,0.0006167457,0.0002074879,0.0003219065,0.00003422003,0.0003041873,0.000010339],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001005337,"about_ca_system_score_gemma":0.0001616033,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000111035,"about_ca_topic_score_gemma":0.000003406403,"domain_scores_codex":[0.9974549,0.00070538,0.0008586392,0.0001983902,0.0006338668,0.0001487698],"domain_scores_gemma":[0.9712426,0.02648292,0.001482239,0.0001304122,0.0005980413,0.00006377848],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00003799229,0.00005298697,0.6523326,0.000001957086,0.00002885275,4.755571e-7,0.00005685263,0.000005885902,0.00003939127,0.00009126294,0.001432789,0.345919],"study_design_scores_gemma":[0.000468527,0.0003090209,0.9719713,0.00007392874,0.00001715359,0.0006057375,0.000631518,0.00005749808,0.00004245503,0.02446021,0.00130608,0.00005654252],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9881376,0.003220886,0.000405924,0.001379015,0.001788973,0.00009102002,0.00001256142,0.000001428384,0.004962601],"genre_scores_gemma":[0.9951048,0.002289182,0.002098752,0.0001257018,0.0001470469,0.000002144801,0.000001822852,0.000003983836,0.0002265297],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3458624,"threshold_uncertainty_score":0.9813114,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2487111179184398,"score_gpt":0.5083836971060273,"score_spread":0.2596725791875875,"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."}}