{"id":"W2194321275","doi":"10.1126/science.aab3050","title":"Human-level concept learning through probabilistic program induction","year":2015,"lang":"en","type":"article","venue":"Science","topic":"Machine Learning and Algorithms","field":"Computer Science","cited_by":2930,"is_retracted":false,"has_abstract":true,"ca_institutions":"Canada Research Chairs; University of Toronto","funders":"Army Research Office; Office of Naval Research; Natural Sciences and Engineering Research Council of Canada; Canadian Institute for Advanced Research","keywords":"Computer science; Alphabet; Artificial intelligence; Probabilistic logic; Turing; Natural language processing; Machine learning; Programming language; Linguistics","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":[0.001137606,0.0005862978,0.000456491,0.0005217223,0.0004270935,0.0009554061,0.001979226,0.0007705244,0.003336357],"category_scores_gemma":[0.006216398,0.0004005588,0.0008089835,0.0005583171,0.001421365,0.002670102,0.001461319,0.002121679,0.0007415737],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0009249291,"about_ca_system_score_gemma":0.001043139,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002478987,"about_ca_topic_score_gemma":0.004061829,"domain_scores_codex":[0.9995297,0.0001532395,0.00001518824,0.0001685258,0.0001020594,0.0000313109],"domain_scores_gemma":[0.9968842,0.002087188,0.000214081,0.0004799764,0.0002233595,0.0001112624],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00023731,0.0003462886,0.00461263,0.0002368768,0.0001064363,0.0001578637,0.0004544803,0.5284888,0.007181862,0.1522976,0.009606091,0.2962736],"study_design_scores_gemma":[0.00001039095,0.00002223955,0.0001466318,0.000008880661,0.000006287802,0.00002387936,0.00001069877,0.9359944,0.001360743,0.06157638,0.0008335547,0.000005804284],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03114822,0.00009986915,0.9638201,0.000590424,0.00002032371,0.00005825394,0.0001580911,0.001217752,0.002886912],"genre_scores_gemma":[0.6250239,0.00022816,0.3690214,0.0003126681,0.00004325946,0.0002859587,0.0006471467,0.00015829,0.004279123],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003336357,"threshold_uncertainty_score":0.01116127,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08790062134160331,"score_gpt":0.3568765479819589,"score_spread":0.2689759266403556,"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."}}