{"id":"W2011276392","doi":"10.1080/08957347.2011.607061","title":"An Experimental Test of Student Verbal Reports and Teacher Evaluations as a Source of Validity Evidence for Test Development","year":2011,"lang":"en","type":"article","venue":"Applied Measurement in Education","topic":"Science Education and Pedagogy","field":"Social Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Test (biology); Psychology; CLARITY; Test validity; Set (abstract data type); Association (psychology); Standards for Educational and Psychological Testing; Mathematics education; Content validity; Applied psychology; Social psychology; Psychometrics; Computer science; Higher education; Clinical psychology; Education theory","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":[],"consensus_categories":[],"category_scores_codex":[0.004424853,0.00007828305,0.0001137153,0.0001015613,0.0001945582,0.00001913482,0.0001488858,0.00004661857,0.0001539545],"category_scores_gemma":[0.001175666,0.00008236722,0.00001752254,0.00020666,0.00014949,0.0001719296,0.00001461044,0.00004613694,0.000002121533],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003331387,"about_ca_system_score_gemma":0.002664418,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001525512,"about_ca_topic_score_gemma":0.0008193405,"domain_scores_codex":[0.9983953,0.00009194715,0.0003899654,0.0002525097,0.0007218582,0.0001483917],"domain_scores_gemma":[0.9989337,0.000182288,0.0002681196,0.0001871187,0.0003333165,0.00009548009],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002256877,0.004755626,0.5436107,0.00002435073,0.000005885652,3.222234e-8,0.3546158,0.000002871036,0.07450552,0.001630919,0.000203308,0.02062247],"study_design_scores_gemma":[0.0002192968,0.0001927495,0.6756202,0.00008735392,0.00002496963,7.994364e-7,0.2036429,0.000005275479,0.1176183,0.0008852561,0.001544873,0.0001580306],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9936035,0.000167909,0.0001996531,0.0001120276,0.0003284138,0.0009284915,2.9693e-7,0.00001150483,0.004648169],"genre_scores_gemma":[0.9968539,0.00001215565,0.002461854,0.00004254041,0.00007325351,0.0004754603,0.000003369563,0.000005368463,0.00007210209],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1509729,"threshold_uncertainty_score":0.4726562,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4437717804134738,"score_gpt":0.4947924416640539,"score_spread":0.05102066125058008,"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."}}