{"id":"W2804917593","doi":"10.1111/emip.12201","title":"Methodologies for Investigating and Interpreting Student–Teacher Rating Incongruence in Noncognitive Assessment","year":2018,"lang":"en","type":"article","venue":"Educational Measurement Issues and Practice","topic":"Education, Achievement, and Giftedness","field":"Psychology","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"American Psychological Association; American Educational Research Association","keywords":"Psychology; Construct (python library); Variety (cybernetics); Congruence (geometry); Predictive validity; Interpretation (philosophy); Divergence (linguistics); Construct validity; Descriptive statistics; Mathematics education; Social psychology; Psychometrics; Developmental psychology; Statistics","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":[0.007374536,0.0001667263,0.0001824999,0.0001072429,0.0002954731,0.0001430535,0.0001174868,0.00006626463,0.0001960817],"category_scores_gemma":[0.0093787,0.0001637703,0.00001937431,0.0001501405,0.0002059686,0.0004627889,0.00005894245,0.0001980329,0.000005266024],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001180374,"about_ca_system_score_gemma":0.0002212604,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001012596,"about_ca_topic_score_gemma":0.000344201,"domain_scores_codex":[0.9975345,0.00110893,0.0003840627,0.0004443146,0.0002812851,0.0002469729],"domain_scores_gemma":[0.9948756,0.003849062,0.0003224825,0.0001475114,0.0007255664,0.0000797432],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001708966,0.0008017028,0.8063116,0.0001051029,0.0002867258,6.634256e-7,0.1377367,0.000001370091,0.00298296,0.02595911,0.002705243,0.02293794],"study_design_scores_gemma":[0.0009069818,0.0004410142,0.7945104,0.0003315842,0.0001217125,0.00001676177,0.1825566,0.00006784064,0.000254247,0.008598365,0.01184341,0.0003510791],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.907374,0.004166922,0.005021853,0.04782296,0.002670334,0.001411702,0.000009611162,0.0000436294,0.03147903],"genre_scores_gemma":[0.8900746,0.00005784324,0.1067968,0.001353623,0.0007967387,0.0004189632,0.00001397529,0.00001671799,0.0004707178],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.101775,"threshold_uncertainty_score":0.9989657,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2581577380829526,"score_gpt":0.5537707121933004,"score_spread":0.2956129741103478,"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."}}