{"id":"W4289523162","doi":"10.1073/pnas.2123433119","title":"A neural network solves, explains, and generates university math problems by program synthesis and few-shot learning at human level","year":2022,"lang":"en","type":"article","venue":"Proceedings of the National Academy of Sciences","topic":"Topic Modeling","field":"Computer Science","cited_by":182,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Artificial neural network; Benchmark (surveying); Linear algebra; Code (set theory); Artificial intelligence; Algorithm; Algebra over a field; Machine learning; Theoretical computer science; Mathematics; Programming language; Pure mathematics; Set (abstract data type)","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":[],"consensus_categories":[],"category_scores_codex":[0.001145484,0.00007954322,0.0001113124,0.00007398979,0.001227988,0.0001045915,0.0008432157,0.00002997532,0.000002639145],"category_scores_gemma":[0.00005787356,0.00006416405,0.00002615666,0.0004588848,0.000340006,0.0008002956,0.001100355,0.000172619,5.588567e-8],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004416551,"about_ca_system_score_gemma":0.00001623837,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001207288,"about_ca_topic_score_gemma":2.213131e-7,"domain_scores_codex":[0.9986641,0.00001958509,0.0001565845,0.0003252601,0.0006649886,0.0001695091],"domain_scores_gemma":[0.9995449,0.00009309837,0.0002503133,0.00000973563,0.00006536275,0.00003654853],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003080734,0.0002380222,0.08626932,0.0003208616,0.00007989255,1.767747e-7,0.00589235,0.04983503,0.3088397,0.5028808,0.003228744,0.04238427],"study_design_scores_gemma":[0.0003431093,0.00024524,0.02340033,0.0001293217,0.00002163434,0.00006100313,0.001481083,0.9320207,0.01678629,0.02179136,0.003368813,0.00035108],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9966279,0.0004876576,0.00003053072,0.002373788,0.00001518837,0.000177876,0.000003989278,0.00003122175,0.0002518139],"genre_scores_gemma":[0.9911911,0.00005285436,0.008425225,0.00008494515,0.00002327926,0.00001057353,1.283767e-7,0.000002391343,0.0002094353],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8821857,"threshold_uncertainty_score":0.9444815,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07421882056051196,"score_gpt":0.269741645150327,"score_spread":0.195522824589815,"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."}}