{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.001342984,0.0003515535,0.0003798677,0.0001466179,0.0005903516,0.00007764735,0.0003206748,0.0001412382,0.001281135],"category_scores_gemma":[0.0004317054,0.000283474,0.0001068285,0.0002689712,0.0003807555,0.0001065528,0.0003015999,0.0008001159,0.00009854054],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00015382,"about_ca_system_score_gemma":0.0004126594,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000120272,"about_ca_topic_score_gemma":0.0002925066,"domain_scores_codex":[0.9975053,0.0001739577,0.0006969477,0.0005823805,0.0004112682,0.0006301482],"domain_scores_gemma":[0.9971498,0.001778634,0.0003579855,0.0001965735,0.0003973473,0.0001196608],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001073031,0.0005282379,0.1523035,0.000115521,0.0009241539,0.00006021698,0.07840525,0.000001222082,0.04851529,0.004438224,0.0002227087,0.7143783],"study_design_scores_gemma":[0.002387211,0.000147066,0.8327443,0.0006766056,0.0001559056,0.0001351538,0.09803035,0.00005989657,0.0554737,0.001120777,0.007967005,0.001102037],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9120542,0.00005025978,0.001821312,0.0001109776,0.001445401,0.0007485799,0.00002379844,0.00008111177,0.08366431],"genre_scores_gemma":[0.9835745,0.000002413641,0.01425409,0.0004551021,0.0001853314,0.0003638897,0.0000318958,0.0000474937,0.00108533],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7132763,"threshold_uncertainty_score":0.9999617,"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."}}