{"id":"W4417417655","doi":"10.31234/osf.io/r4dhw_v1","title":"Creation and validation of the LEVANTE core tasks: Internationalized measures of learning and development for children ages 5-12 years","year":2025,"lang":"","type":"article","venue":"","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Set (abstract data type); Reliability (semiconductor); Core (optical fiber); Sample (material); Measure (data warehouse); Cognition; Selection (genetic algorithm)","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.006596711,0.001024453,0.000576145,0.003833831,0.0009773853,0.001443172,0.001766264,0.0008862494,0.002722322],"category_scores_gemma":[0.02153797,0.0004134327,0.0009991704,0.001579426,0.0006298093,0.001709817,0.00284771,0.001224304,0.001216497],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001932914,"about_ca_system_score_gemma":0.003781369,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01871687,"about_ca_topic_score_gemma":0.05106304,"domain_scores_codex":[0.9960805,0.0008547063,0.0008839598,0.0006132296,0.001211808,0.0003559526],"domain_scores_gemma":[0.9831541,0.003955354,0.003218819,0.001981306,0.006527543,0.001162898],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0004388781,0.0007940669,0.8323422,0.0002206058,0.00009844617,0.0002438275,0.003511588,0.003420644,0.00182503,0.001742318,0.008204836,0.1471575],"study_design_scores_gemma":[0.00003450396,0.0002490928,0.9840389,0.00008220485,0.00003422043,0.0002508719,0.001012928,0.001850387,0.002089278,0.001041734,0.009270157,0.00004568661],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9299884,0.0003348428,0.01942892,0.0002841942,0.00009409344,0.003137751,0.02956798,0.0003745734,0.01678924],"genre_scores_gemma":[0.8366045,0.0005089167,0.09155194,0.0001824806,0.00003900773,0.01711219,0.04781559,0.0001997661,0.005985702],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01871687,"threshold_uncertainty_score":0.03721583,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3646703116239629,"score_gpt":0.4567923133589386,"score_spread":0.09212200173497564,"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."}}