{"id":"W2022166848","doi":"10.1016/j.actpsy.2010.01.006","title":"Challenging the reliability and validity of cognitive measures: The case of the numerical distance effect","year":2010,"lang":"en","type":"article","venue":"Acta Psychologica","topic":"Cognitive and developmental aspects of mathematical skills","field":"Mathematics","cited_by":106,"is_retracted":false,"has_abstract":false,"ca_institutions":"Western University; University of British Columbia; University of Waterloo","funders":"Natural Sciences and Engineering Research Council of Canada; Killam Trusts","keywords":"Metric (unit); Reliability (semiconductor); Cognition; Psychology; Representation (politics); Numerical cognition; Cognitive psychology; Computer science; Artificial intelligence","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":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2647831,0.00110005,0.002276325,0.005334388,0.002733742,0.005822435,0.006789642,0.004827103,0.002407431],"category_scores_gemma":[0.6745748,0.001412748,0.001537996,0.003544051,0.018621,0.007455941,0.00470462,0.006522951,0.0006743358],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00290836,"about_ca_system_score_gemma":0.005414744,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01277981,"about_ca_topic_score_gemma":0.01425617,"domain_scores_codex":[0.7786069,0.1216971,0.01739438,0.02042685,0.06001883,0.00185592],"domain_scores_gemma":[0.1320269,0.7656822,0.01525232,0.0435326,0.04226817,0.001237902],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001273895,0.0003866007,0.4971848,0.002630759,0.002781556,0.001498129,0.02726278,0.005296104,0.004272427,0.1586467,0.01255074,0.2862154],"study_design_scores_gemma":[0.0003654453,0.001008621,0.4621826,0.004151009,0.00147514,0.00590544,0.01480671,0.03816724,0.01331074,0.401109,0.05678656,0.0007314749],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6231221,0.02360855,0.2286457,0.05396363,0.004601904,0.001203174,0.001144651,0.0003294156,0.06338082],"genre_scores_gemma":[0.9574783,0.001431971,0.03622342,0.001932737,0.0009619936,0.0003838346,0.0002053068,0.0001716995,0.001210769],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7352169,"threshold_uncertainty_score":0.9066533,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04541587751041336,"score_gpt":0.3358935264332365,"score_spread":0.2904776489228231,"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."}}