{"id":"W2100487390","doi":"10.1177/0022022105284492","title":"Evaluating the Effectiveness of Two-Stage Testing on English and French Versions of a Science Achievement Test","year":2006,"lang":"en","type":"article","venue":"Journal of Cross-Cultural Psychology","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Test (biology); Ethnic group; Achievement test; Psychology; Differential item functioning; Sample (material); Mathematics education; Standardized test; Developmental psychology; Item response theory; Psychometrics; Sociology","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03373864,0.0001552499,0.000511663,0.0004959166,0.0004331761,0.00021248,0.001058239,0.00006647703,0.00002413928],"category_scores_gemma":[0.2391281,0.00007762541,0.0001367526,0.002775219,0.002588946,0.0005231047,0.0001841991,0.0003864517,0.000001354127],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004519997,"about_ca_system_score_gemma":0.00008929193,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007783158,"about_ca_topic_score_gemma":0.000003783492,"domain_scores_codex":[0.9955671,0.0009457241,0.001316266,0.000370105,0.001482645,0.0003181297],"domain_scores_gemma":[0.9305409,0.06260883,0.002062175,0.0003805353,0.004324977,0.00008257695],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0002168598,0.0002147453,0.6462756,0.00001852506,0.00001683278,0.000006757658,0.0003705038,0.00217482,0.3280591,0.0008348002,0.00014593,0.0216656],"study_design_scores_gemma":[0.001588422,0.002202298,0.9776633,0.000114142,0.00001640231,0.00007287588,0.0004367112,0.0004573503,0.005405389,0.01184957,0.0001042701,0.00008924223],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9909627,0.0002210496,0.0004074668,0.0001335168,0.001086318,0.0001541057,0.00001018382,0.000006777417,0.007017868],"genre_scores_gemma":[0.9895878,0.000005408539,0.01012064,0.00005690569,0.0001666362,0.0000017713,2.303276e-7,0.000004982991,0.00005565001],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3313878,"threshold_uncertainty_score":0.9949694,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4485049263862267,"score_gpt":0.5900866364199733,"score_spread":0.1415817100337465,"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."}}