{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001667934,0.000413063,0.0003151138,0.001099255,0.000296514,0.0009123642,0.0005403988,0.0005580859,0.001834284],"category_scores_gemma":[0.01696432,0.0002411247,0.000362957,0.0006322336,0.000486343,0.001260322,0.0008737951,0.0003999199,0.0005928992],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002067863,"about_ca_system_score_gemma":0.0002056785,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001425768,"about_ca_topic_score_gemma":0.002333245,"domain_scores_codex":[0.9987495,0.0002988524,0.0002225551,0.0003477117,0.0003162278,0.00006513685],"domain_scores_gemma":[0.9893443,0.004721194,0.003192977,0.001145797,0.001184089,0.0004116221],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.002299436,0.000487782,0.9693848,0.00007118325,0.000140248,0.00006476983,0.0007891334,0.0002870231,0.005763067,0.0003329056,0.0002425918,0.02013704],"study_design_scores_gemma":[0.00005491951,0.0005924966,0.9962096,0.000007897484,0.00003894573,0.0001828073,0.0002033993,0.0007652935,0.001430711,0.0003139452,0.000190072,0.000009757766],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9990067,0.00007064283,0.0002590383,0.00001058105,0.000007982731,0.00001145807,0.00008896896,0.000007178606,0.0005374341],"genre_scores_gemma":[0.9989462,0.00003539793,0.0004468091,0.00001107917,0.00001013047,0.00002152855,0.0002027518,0.00000824338,0.0003178355],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.001834284,"threshold_uncertainty_score":0.008820951,"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."}}