{"id":"W2792554342","doi":"10.1080/00313831.2017.1420687","title":"PISA Country Rankings Valid? Results for Canada and Finland","year":2018,"lang":"en","type":"article","venue":"Scandinavian Journal of Educational Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"","keywords":"Item response theory; Normalization (sociology); Contrast (vision); Econometrics; Mathematics education; Mathematics; Statistics; Psychology; Psychometrics; Computer science; Sociology; Social science; Artificial intelligence","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01405855,0.0007509094,0.001331175,0.006081844,0.00352008,0.006167863,0.001753295,0.0009050299,0.01049118],"category_scores_gemma":[0.07152152,0.0003644076,0.002335895,0.01209713,0.001823361,0.002018758,0.00464617,0.001633815,0.002380274],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01240102,"about_ca_system_score_gemma":0.02194416,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.866607,"about_ca_topic_score_gemma":0.837438,"domain_scores_codex":[0.9831858,0.003214858,0.001111604,0.002102629,0.007266608,0.003118611],"domain_scores_gemma":[0.9381853,0.01991949,0.006095254,0.00627985,0.02658328,0.002936759],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00107241,0.0001744377,0.8653399,0.000506566,0.001147955,0.0007263631,0.004931994,0.005358254,0.0003448838,0.01459658,0.02803841,0.07776221],"study_design_scores_gemma":[0.00004593655,0.0001032502,0.9639139,0.0002323941,0.0002679829,0.0002052446,0.01019629,0.003361713,0.0007362036,0.001887103,0.01893934,0.0001105208],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8454394,0.00435221,0.00318234,0.003162045,0.0004073267,0.0002692115,0.0422831,0.0003976676,0.1005066],"genre_scores_gemma":[0.9711607,0.000620201,0.001476483,0.0002879243,0.00003619512,0.0001093201,0.01908475,0.0001349353,0.007089483],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.133393,"threshold_uncertainty_score":0.2683572,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.5919838220888495,"score_gpt":0.574699651340387,"score_spread":0.01728417074846245,"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."}}