{"id":"W2151169555","doi":"10.1016/j.actpsy.2012.02.008","title":"Nonsymbolic numerical magnitude comparison: Reliability and validity of different task variants and outcome measures, and their relationship to arithmetic achievement in adults","year":2012,"lang":"en","type":"article","venue":"Acta Psychologica","topic":"Cognitive and developmental aspects of mathematical skills","field":"Mathematics","cited_by":238,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University","funders":"Canadian Institutes of Health Research","keywords":"Fluency; Psychology; Task (project management); Cognition; Reliability (semiconductor); Correlation; Arithmetic; Cognitive psychology; Developmental psychology; Mathematics","routes":{"ca_aff":true,"ca_fund":true,"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":[],"consensus_categories":[],"category_scores_codex":[0.0009336962,0.0002328983,0.0005508441,0.00008018744,0.00007250164,0.00002169233,0.0001083491,0.0001090866,0.0000375521],"category_scores_gemma":[0.001899859,0.0001529009,0.00003624998,0.0001447649,0.0001158739,0.0000915552,0.0002135949,0.0002328515,0.000006025064],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003165396,"about_ca_system_score_gemma":0.000004556008,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001041558,"about_ca_topic_score_gemma":0.00001236427,"domain_scores_codex":[0.9983252,0.0002292472,0.0005872009,0.0003476848,0.0002026543,0.0003079929],"domain_scores_gemma":[0.9976348,0.001713557,0.0001282892,0.0002446905,0.00004516582,0.0002335432],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000118295,0.001939073,0.9895347,0.0001397434,0.00001907366,0.000001225196,0.002077089,3.01939e-8,0.0001882032,0.002667812,0.0001331465,0.003181633],"study_design_scores_gemma":[0.0007313323,0.0002168409,0.9441997,0.0001074804,0.00002114493,0.00001125097,0.0002704262,0.00001714076,0.0001056222,0.05408439,0.0000506767,0.0001840006],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9957601,0.00009494566,0.001409535,0.001021738,0.00004897176,0.0006128323,0.00001880125,0.00002683279,0.001006199],"genre_scores_gemma":[0.9913542,0.00002930983,0.008334349,0.0001915213,0.00001785513,0.00004269396,0.00000315483,0.00001097127,0.00001599465],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05141658,"threshold_uncertainty_score":0.6235116,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1115342095256831,"score_gpt":0.3574114040372997,"score_spread":0.2458771945116166,"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."}}