{"id":"W3206860570","doi":"10.48550/arxiv.2110.09767","title":"Pre and Post Counting for Scalable Statistical-Relational Model Discovery","year":2021,"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":"Simon Fraser University","funders":"","keywords":"Statistical relational learning; Computer science; Scalability; Relational database; Relational model; Bottleneck; Conjunctive query; Set (abstract data type); Relational calculus; Dependency (UML); Theoretical computer science; Artificial intelligence; Data mining; Database; 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":[],"consensus_categories":[],"category_scores_codex":[0.0001913655,0.0002037035,0.0002311452,0.0000811002,0.0001953584,0.0004140236,0.0005108469,0.0001964701,0.000004830602],"category_scores_gemma":[0.00006308215,0.0002393522,0.00007951702,0.0001414126,0.00008390402,0.0007286304,0.001047692,0.0003294323,0.000003054028],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007754361,"about_ca_system_score_gemma":0.0004642374,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009508523,"about_ca_topic_score_gemma":0.00002009287,"domain_scores_codex":[0.9985379,0.00004219178,0.000164385,0.0009061031,0.00008656139,0.0002628654],"domain_scores_gemma":[0.9987951,0.000208972,0.0001221405,0.0004702787,0.0002917726,0.0001117386],"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":[0.00001109385,0.00002776859,0.0003725458,0.00007574333,0.00002647525,0.00001322856,0.00009893093,0.4603769,0.00005568106,0.5385969,0.00005599831,0.0002887405],"study_design_scores_gemma":[0.0001932322,0.00001981807,0.0009031701,0.00009337241,0.00003904888,0.000002522603,0.00002776905,0.8994396,0.00001932925,0.09900029,0.00001085587,0.0002509968],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1529239,0.00006197229,0.8461,0.0000848102,0.0001365384,0.0001550465,0.0001158133,0.00007213035,0.0003497849],"genre_scores_gemma":[0.9259026,0.00005194557,0.07213792,0.0001176873,0.00003017211,0.000001704376,0.00008806875,0.0000114293,0.001658488],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.7739621,"threshold_uncertainty_score":0.9760501,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0744042408828902,"score_gpt":0.2070764175662529,"score_spread":0.1326721766833627,"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."}}