{"id":"W2963995608","doi":"10.1609/aaai.v33i01.33011303","title":"Cognitive Deficit of Deep Learning in Numerosity","year":2019,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Cognitive and developmental aspects of mathematical skills","field":"Mathematics","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Numerosity adaptation effect; Cognition; Number sense; Artificial intelligence; Cognitive psychology; Black box; Computer science; Task (project management); Numerical cognition; Cognitive science; Psychology; Neuroscience","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":[0.001266508,0.001324917,0.0005593749,0.001442838,0.0002635836,0.001301892,0.0008365374,0.0007714726,0.008005706],"category_scores_gemma":[0.009170779,0.0002265261,0.0003217281,0.0003409898,0.003238637,0.002910688,0.001940122,0.002736273,0.0005617611],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008360345,"about_ca_system_score_gemma":0.0007742429,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00181233,"about_ca_topic_score_gemma":0.001090736,"domain_scores_codex":[0.999131,0.00009030889,0.00007720243,0.0002393599,0.0003687518,0.0000933664],"domain_scores_gemma":[0.9950275,0.002056871,0.0009525203,0.0009813105,0.0004239973,0.0005578285],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003062767,0.002398361,0.1173354,0.001533597,0.0005944425,0.01020252,0.004342851,0.01504469,0.2811567,0.1515512,0.0186339,0.3941435],"study_design_scores_gemma":[0.0004063004,0.002087632,0.1916957,0.0004428307,0.0004784991,0.02161794,0.002505997,0.06750233,0.1795983,0.509059,0.0243773,0.0002283644],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9577519,0.0003584183,0.01670283,0.003317581,0.0001212217,0.0000503507,0.0007969563,0.0009011745,0.01999952],"genre_scores_gemma":[0.9904993,0.0001653358,0.005510685,0.0005289581,0.00002203082,0.00003821836,0.0002515304,0.00007270972,0.002911167],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.008005706,"threshold_uncertainty_score":0.02678174,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07226652101280862,"score_gpt":0.3199975851005814,"score_spread":0.2477310640877728,"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."}}