{"id":"W2051055840","doi":"10.1016/j.cogdev.2010.07.001","title":"Misleading cues improve developmental assessment of working memory capacity: The color matching tasks","year":2010,"lang":"en","type":"article","venue":"Cognitive Development","topic":"Cognitive Abilities and Testing","field":"Psychology","cited_by":43,"is_retracted":false,"has_abstract":false,"ca_institutions":"York University","funders":"","keywords":"Psychology; Working memory; Cognitive psychology; Task (project management); Matching (statistics); Constructive; Developmental psychology; Cognition; Process (computing); Computer science","routes":{"ca_aff":true,"ca_fund":false,"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":[0.001347251,0.001124626,0.0004920996,0.0008527422,0.0001806401,0.0005452646,0.001020592,0.001194324,0.001859867],"category_scores_gemma":[0.01207739,0.0004139604,0.0002761105,0.0003852715,0.0005069842,0.001107218,0.000781257,0.001108688,0.0002076268],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002586261,"about_ca_system_score_gemma":0.0007049651,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002153082,"about_ca_topic_score_gemma":0.002264554,"domain_scores_codex":[0.9991297,0.0001893998,0.0001187441,0.0001519108,0.0003478091,0.00006247446],"domain_scores_gemma":[0.9950771,0.00212209,0.001534114,0.0003863944,0.0003792529,0.0005011357],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"observational","study_design_scores_codex":[0.008852822,0.00541467,0.04642815,0.0006712948,0.0003130988,0.002380373,0.001031302,0.002833039,0.7478641,0.001560396,0.003297696,0.1793532],"study_design_scores_gemma":[0.0009312777,0.01333047,0.3522962,0.0002416243,0.0006381266,0.005759883,0.0007091053,0.01582011,0.5989343,0.006935548,0.004194642,0.0002085387],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9940776,0.0003820998,0.004118853,0.0002181025,0.00007170908,0.00003622939,0.0001414529,0.000101841,0.0008521039],"genre_scores_gemma":[0.9871551,0.0007640392,0.01036403,0.0002184481,0.00002712629,0.00006709724,0.0002195054,0.0000920989,0.001092527],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.002153082,"threshold_uncertainty_score":0.00712508,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06304965540502525,"score_gpt":0.3232998173859606,"score_spread":0.2602501619809353,"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."}}