{"id":"W2992462208","doi":"10.48550/arxiv.1912.02765","title":"On the Sample Complexity of Learning Sum-Product Networks","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"McMaster University","funders":"","keywords":"Mathematics; Gaussian; Combinatorics; Tree (set theory); Logarithm; Product (mathematics); Distribution (mathematics); Set (abstract data type); Base (topology); Total variation; Discrete mathematics; Class (philosophy); Sample complexity; Statistics; Computer science; Mathematical analysis; Artificial intelligence; Geometry","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":[0.005061972,0.001648286,0.002362337,0.001039509,0.001023587,0.002902974,0.003006688,0.00266811,0.004650225],"category_scores_gemma":[0.04559179,0.001117951,0.001427031,0.001365041,0.003181685,0.009253265,0.003958941,0.00597348,0.0006031484],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003516524,"about_ca_system_score_gemma":0.00202832,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003889373,"about_ca_topic_score_gemma":0.004225855,"domain_scores_codex":[0.9959744,0.001633464,0.0002434237,0.0009083635,0.0009262934,0.0003140924],"domain_scores_gemma":[0.9401146,0.05354702,0.001440234,0.002846527,0.001356739,0.0006948576],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.000936674,0.0001979282,0.006007439,0.0004280283,0.000202296,0.0002166677,0.0002912765,0.836499,0.00245432,0.08724307,0.004713741,0.06080949],"study_design_scores_gemma":[0.00002372214,0.00004460607,0.000273,0.00001571261,0.00001394299,0.00003616077,0.00001953343,0.9422364,0.000433421,0.05664373,0.0002498996,0.000009865641],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1959129,0.002472799,0.7860315,0.005748041,0.000136866,0.0002224165,0.001252521,0.001749105,0.00647393],"genre_scores_gemma":[0.8318432,0.001632491,0.1553866,0.001292532,0.0003667622,0.0007324734,0.003566947,0.0005801264,0.004598788],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.005061972,"threshold_uncertainty_score":0.02677059,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1615524356826214,"score_gpt":0.2069945756050774,"score_spread":0.04544213992245597,"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."}}