{"id":"W1995530352","doi":"10.2466/pr0.2000.87.3.791","title":"Expertise Sensitive Item Selection","year":2000,"lang":"en","type":"article","venue":"Psychological Reports","topic":"Reliability and Agreement in Measurement","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute for Christian Studies; University of Toronto; Nipissing University","funders":"","keywords":"Certification; Index (typography); Test (biology); Selection (genetic algorithm); Psychology; Computer science; Applied psychology; Statistics; Artificial intelligence; Mathematics; World Wide Web; Management","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":["insufficient_payload"],"consensus_categories":["insufficient_payload"],"category_scores_codex":[0.003704144,0.0001401285,0.0002356082,0.00006299002,0.0001651724,0.0001399565,0.0001803631,0.0001021602,0.01154923],"category_scores_gemma":[0.002879668,0.00008547732,0.0001565027,0.0005261792,0.00009895057,0.0001596305,0.0000238069,0.0001727012,0.001161519],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005494615,"about_ca_system_score_gemma":0.000009902681,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001187638,"about_ca_topic_score_gemma":0.000004454621,"domain_scores_codex":[0.996077,0.0003135793,0.0008645236,0.0008635939,0.001595929,0.0002853463],"domain_scores_gemma":[0.9984762,0.0003721474,0.0001849764,0.0005776747,0.0002328347,0.0001561449],"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":[0.0001289094,0.0006316629,0.03546662,0.000001059835,0.00001314804,0.0005252873,0.000302282,0.0002099476,0.005371971,0.00006867169,0.04574989,0.9115306],"study_design_scores_gemma":[0.0002629601,0.0004779202,0.7654434,0.00001891699,0.00001069058,0.0009451143,0.0001490447,0.0004560495,0.002920943,0.04332236,0.1856387,0.0003539804],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8961761,0.0000316373,0.001057734,0.001131813,0.0004197185,0.0002171195,6.605945e-7,0.00008610785,0.1008791],"genre_scores_gemma":[0.9904013,0.0000249233,0.000635016,0.001246973,0.0001343843,0.00002245747,0.000001323519,0.000004588633,0.007529007],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9111766,"threshold_uncertainty_score":0.9996162,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1941270554244931,"score_gpt":0.4406536448886559,"score_spread":0.2465265894641628,"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."}}