{"id":"W3134253081","doi":"10.1038/s41539-021-00085-9","title":"The International Science and Evidence-based Education Assessment","year":2021,"lang":"en","type":"article","venue":"npj Science of Learning","topic":"Global Educational Policies and Reforms","field":"Social Sciences","cited_by":17,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"National Center for Advancing Translational Sciences; United Nations Educational, Scientific and Cultural Organization","keywords":"Political science; Mathematics education; Engineering ethics; Psychology; Engineering","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2578083,0.001931432,0.003290817,0.02435155,0.004770998,0.02270303,0.006262393,0.01519324,0.008933593],"category_scores_gemma":[0.5451686,0.0009933667,0.004500744,0.0127231,0.01756063,0.02043226,0.01723774,0.02166162,0.003091556],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.01999297,"about_ca_system_score_gemma":0.09672817,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005714814,"about_ca_topic_score_gemma":0.008254788,"domain_scores_codex":[0.6741652,0.1677899,0.06400978,0.007886465,0.08157819,0.004570452],"domain_scores_gemma":[0.3840823,0.4053871,0.02687769,0.02573331,0.1489909,0.008928718],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00008205646,0.0001810743,0.002554852,0.034885,0.0005925886,0.0002623551,0.004117163,0.001642899,0.0002955305,0.3636497,0.2456493,0.3460875],"study_design_scores_gemma":[0.0000425468,0.000090887,0.001830846,0.07995147,0.0004294605,0.0002388821,0.002882439,0.0009476846,0.0004284664,0.1647571,0.7482917,0.0001084157],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"commentary","genre_gemma":"empirical","genre_scores_codex":[0.001700673,0.1021555,0.04602564,0.6682224,0.03431312,0.003665857,0.001983616,0.0002801559,0.1416529],"genre_scores_gemma":[0.1529056,0.2282959,0.2651685,0.2753546,0.02515801,0.01986077,0.005175745,0.0003922302,0.02768865],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7421917,"threshold_uncertainty_score":0.9152545,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03041235968047466,"score_gpt":0.4095394612712803,"score_spread":0.3791271015908056,"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."}}