{"id":"W4386073897","doi":"10.17275/per.23.74.10.5","title":"A Comparison of Covariates, Equating Designs, and Methods in Equating TIMSS 2019 Science Tests","year":2023,"lang":"en","type":"article","venue":"Participatory Educational Research","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Equating; Covariate; Statistics; Mathematics; Test (biology); Econometrics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.1274196,0.0001103986,0.0003819465,0.002729719,0.0005115757,0.0002368508,0.0009796689,0.00006164776,0.0002834626],"category_scores_gemma":[0.6500897,0.00009183774,0.00003480171,0.01468823,0.0008806667,0.0003142002,0.0005857917,0.0004083994,0.0001437461],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001301991,"about_ca_system_score_gemma":0.001520287,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003064422,"about_ca_topic_score_gemma":0.0000186913,"domain_scores_codex":[0.9904652,0.003680412,0.00118546,0.0007438421,0.003026344,0.000898738],"domain_scores_gemma":[0.6363509,0.3607232,0.0004002172,0.0006712,0.001535428,0.0003190837],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001464204,0.0001180858,0.8853026,0.00001800796,0.000004297425,6.520709e-7,0.003012598,0.0007530397,0.02752545,0.01132772,0.00130197,0.07062094],"study_design_scores_gemma":[0.0001530914,0.00008721245,0.8166829,0.00005671235,0.000002317844,0.000001124246,0.004492591,0.1028651,0.003146644,0.07225229,0.0001575805,0.0001024268],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9892569,0.0007339661,0.005578647,0.0009938444,0.0003456016,0.0002841884,0.000004356604,0.00001987825,0.002782604],"genre_scores_gemma":[0.8865601,0.000009589132,0.1129498,0.00001584848,0.00005926424,0.00007885043,0.00000183357,0.000008689627,0.0003159538],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5226702,"threshold_uncertainty_score":0.8985052,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.9561788602789288,"score_gpt":0.7700835773416688,"score_spread":0.1860952829372601,"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."}}