{"id":"W3138069980","doi":"10.6339/jds.201207_10(3).0006","title":"A Data Mining Approach to Comparing American and Canadian Grade 10 Students’ PISA Science Test Performance","year":2021,"lang":"en","type":"article","venue":"Journal of Data Science","topic":"Online Learning and Analytics","field":"Computer Science","cited_by":20,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Test (biology); Academic achievement; Mathematics education; Achievement test; Psychology; Political science; Standardized test","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":["scholarly_communication","open_science"],"consensus_categories":[],"category_scores_codex":[0.004324073,0.0001194834,0.0002479314,0.0005661916,0.0007169619,0.001708918,0.01360755,0.00001246183,0.00000158472],"category_scores_gemma":[0.001720924,0.0001038905,0.00001256683,0.004309228,0.001097888,0.005762088,0.005574811,0.0002825989,0.000005799383],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001210666,"about_ca_system_score_gemma":0.003398544,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0006905925,"about_ca_topic_score_gemma":0.001122176,"domain_scores_codex":[0.9968207,0.0000318846,0.0003520878,0.0007855649,0.001448606,0.0005611897],"domain_scores_gemma":[0.9964073,0.0001028206,0.0002727047,0.001984949,0.0004081513,0.0008240441],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000006256724,0.0006922846,0.8462794,0.00005394688,0.00003425064,0.0002329053,0.003046144,0.002528361,0.006256429,0.0009613115,0.005582249,0.1343264],"study_design_scores_gemma":[0.0001984357,0.0001612949,0.1744384,0.000113229,0.00001547629,0.0006936764,0.0008877355,0.8144599,0.0001365018,0.00000920536,0.008658362,0.000227815],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9720128,0.0001083208,0.02204034,0.004433875,0.0002779155,0.00005616598,0.00005105435,0.0000194266,0.001000153],"genre_scores_gemma":[0.7565812,0.00003571608,0.2428893,0.0003521005,0.0000796419,1.420572e-7,0.00000521869,0.000003538297,0.00005312094],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8119315,"threshold_uncertainty_score":0.9993274,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1098757292940929,"score_gpt":0.3657505192465182,"score_spread":0.2558747899524254,"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."}}