{"id":"W3177093549","doi":"","title":"Sum-Product Network Decompilation","year":2019,"lang":"en","type":"article","venue":"arXiv (Cornell University)","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Regina","funders":"","keywords":"Interpretability; Computer science; Graphical model; Theoretical computer science; Inference; Set (abstract data type); Converse; Probabilistic logic; Artificial intelligence; Product (mathematics); Bayesian network; Conditional independence; Machine learning; Mathematics; Programming language","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0001752115,0.0001035005,0.0001098568,0.00005509081,0.00009197372,0.00005960196,0.0006465988,0.00004492372,0.00005148099],"category_scores_gemma":[0.000007171583,0.0001147784,0.0000530242,0.0005729149,0.00002261494,0.0005261973,0.0001672885,0.0001192092,0.0007917326],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003972734,"about_ca_system_score_gemma":0.00004806205,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002746484,"about_ca_topic_score_gemma":0.00001018712,"domain_scores_codex":[0.9990563,0.00005193293,0.0000874804,0.0004982537,0.00005073614,0.0002553402],"domain_scores_gemma":[0.9991412,0.00004241201,0.00005827915,0.0006042686,0.00007163535,0.00008225236],"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":[0.000009058734,0.00002352361,0.02643739,0.000006260015,0.00001247129,0.00001816861,0.0000524037,0.3116223,0.000114303,0.6585217,0.0007284085,0.002454033],"study_design_scores_gemma":[0.0002206972,0.00004100687,0.007042583,0.00001606245,0.000006780798,0.000003493135,0.000008204225,0.9443977,0.0001208232,0.04666477,0.001274335,0.0002035018],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3152332,0.00002656755,0.6785886,0.00007757692,0.0003255913,0.00006633723,3.67445e-7,0.0001497667,0.005531969],"genre_scores_gemma":[0.9945525,0.0000192859,0.002959126,0.0001457816,0.00006913058,1.025982e-7,0.000002119913,0.000005471374,0.002246491],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6793193,"threshold_uncertainty_score":0.9999863,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05951240561976744,"score_gpt":0.1766822385727211,"score_spread":0.1171698329529537,"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."}}