{"id":"W7116213154","doi":"","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":"preprint","venue":"PsyArXiv (OSF Preprints)","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":[0.006691466,0.001084752,0.0005856912,0.003804258,0.001002326,0.001519678,0.001698622,0.001001059,0.003064506],"category_scores_gemma":[0.02328856,0.0004408146,0.001008352,0.001601485,0.0006805368,0.001817442,0.003038208,0.001323549,0.001534436],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001819485,"about_ca_system_score_gemma":0.003555862,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01708826,"about_ca_topic_score_gemma":0.04296154,"domain_scores_codex":[0.9959332,0.0008638799,0.0008618244,0.000721987,0.001219531,0.000399603],"domain_scores_gemma":[0.9810224,0.004662414,0.003324094,0.002438802,0.007266488,0.001285737],"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":[0.0005238982,0.0008830444,0.8036191,0.0002787269,0.0001065627,0.0002805027,0.004628733,0.003640011,0.002369762,0.002113871,0.01004649,0.1715092],"study_design_scores_gemma":[0.00003601204,0.0002503875,0.9824442,0.00008364535,0.00003426652,0.0002572378,0.001017711,0.001701932,0.002346637,0.001338534,0.01044009,0.00004924037],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9222565,0.0003373906,0.02115536,0.0003016937,0.000104066,0.003395207,0.0335231,0.0004618667,0.01846479],"genre_scores_gemma":[0.8218969,0.0005135885,0.09636515,0.0002079441,0.00004726692,0.01947373,0.05424947,0.0002608169,0.006985169],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01708826,"threshold_uncertainty_score":0.03538829,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2953755882102296,"score_gpt":0.4220356792820552,"score_spread":0.1266600910718256,"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."}}