{"id":"W2044921851","doi":"10.1145/2661829.2662010","title":"Computing Multi-Relational Sufficient Statistics for Large Databases","year":2014,"lang":"en","type":"preprint","venue":"","topic":"Bayesian Modeling and Causal Inference","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada; China Scholarship Council","keywords":"Computer science; Relational database; Database; Information retrieval; Data mining; Data science","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0007204169,0.0002493111,0.0002769399,0.00009287221,0.0002096006,0.0002179765,0.0008799134,0.0001224116,0.00001911695],"category_scores_gemma":[0.0001833792,0.0002352673,0.00008430545,0.00006897441,0.00002505137,0.00008387667,0.001657569,0.0003658016,0.00004582888],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004391829,"about_ca_system_score_gemma":0.0002773115,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004699543,"about_ca_topic_score_gemma":0.00002794942,"domain_scores_codex":[0.9980565,0.00006594132,0.0004276319,0.0007496209,0.0003067078,0.000393638],"domain_scores_gemma":[0.9980739,0.0004911398,0.0002189144,0.0007537081,0.0003463225,0.0001160569],"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":[0.000001763917,0.0001325942,0.0001478421,0.0001002633,0.00001889519,0.00000115494,0.000166445,0.04350789,0.000005753966,0.9455253,0.006309734,0.00408234],"study_design_scores_gemma":[0.0002789523,0.00002304921,0.0004700737,0.00008639528,0.00001158857,0.000001899971,0.000007141738,0.9904618,0.00002834718,0.005448904,0.002875924,0.0003059432],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.000370134,0.00006711293,0.9968064,0.0001997928,0.001073017,0.0003067219,0.0006720053,0.0002734066,0.0002313546],"genre_scores_gemma":[0.2369454,0.000004219276,0.7616972,0.0003868332,0.0001244779,0.00001546783,0.0005132719,0.00001227616,0.0003008654],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9469539,"threshold_uncertainty_score":0.9593921,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1120781166882575,"score_gpt":0.3458678401406248,"score_spread":0.2337897234523673,"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."}}