{"id":"W2258138870","doi":"10.1111/jedm.12095","title":"Rutkowski, L., vonDavier, M., & Rutkowski, D. (Eds.). (2014). Handbook of International Large‐Scale Assessments: Background, Technical Issues, and Methods of Data Analysis. Boca Raton, FL: CRC Press.","year":2015,"lang":"en","type":"article","venue":"Journal of Educational Measurement","topic":"Educational Assessment and Pedagogy","field":"Social Sciences","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Victoria","funders":"","keywords":"Library science; Curriculum; Christian ministry; Citation; Sociology; Political science; Computer science; Law; Pedagogy","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.01274795,0.0002171106,0.0006433449,0.0004668273,0.0001703864,0.0001184793,0.001222322,0.0001461417,0.001344955],"category_scores_gemma":[0.00127166,0.0001977466,0.0002015162,0.0004194893,0.0003253647,0.001003487,0.0002223656,0.0003142237,0.000006814988],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004619776,"about_ca_system_score_gemma":0.004435346,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008765811,"about_ca_topic_score_gemma":0.002426635,"domain_scores_codex":[0.9941118,0.0009550806,0.001377924,0.000373659,0.002875248,0.0003062319],"domain_scores_gemma":[0.9927987,0.0005647423,0.001505396,0.0005349906,0.00420022,0.0003958842],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007192523,0.009434647,0.275816,0.0001965614,0.006314106,0.000002391492,0.01374417,0.0002510526,0.007412273,0.03518944,0.6379415,0.01297858],"study_design_scores_gemma":[0.001269218,0.0001961914,0.03516963,0.0001994334,0.001133053,0.0000158219,0.004877959,0.00006751272,0.0003644636,0.008367374,0.9480168,0.0003225482],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"review","genre_gemma":"methods","genre_scores_codex":[0.0929963,0.3745171,0.2462174,0.1539546,0.02477576,0.003919349,0.001560368,0.00009909857,0.1019601],"genre_scores_gemma":[0.3929185,0.009596073,0.5875651,0.0004005759,0.003603125,0.00005590264,0.0005332574,0.00005239111,0.005275086],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.364921,"threshold_uncertainty_score":0.9995679,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2646006784507445,"score_gpt":0.5359710732399001,"score_spread":0.2713703947891556,"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."}}