{"id":"W3091261939","doi":"10.48550/arxiv.2010.02089","title":"CopulaGNN: Towards Integrating Representational and Correlational Roles of Graphs in Graph Neural Networks","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"ENCODE; Computer science; Leverage (statistics); Theoretical computer science; Graph; Correlation; Artificial neural network; Copula (linguistics); Node (physics); Artificial intelligence; Machine learning; Data mining; Mathematics; Econometrics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001585707,0.0003239518,0.0004300768,0.0003899549,0.00009222294,0.00006362767,0.001019072,0.0002541072,0.000006728763],"category_scores_gemma":[0.00008559426,0.0003727263,0.0001972223,0.001330727,0.0002389345,0.0005091472,0.001598498,0.00100463,7.174671e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005190398,"about_ca_system_score_gemma":0.00007761245,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001177508,"about_ca_topic_score_gemma":0.0001630935,"domain_scores_codex":[0.9978452,0.0001950295,0.0004029837,0.001106976,0.0001519024,0.000297857],"domain_scores_gemma":[0.9984438,0.0002907106,0.0004359527,0.0005270668,0.0001471513,0.0001552787],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004348249,0.00002741624,0.05053279,0.00002880853,0.00003210326,0.0001565591,0.0001670496,0.7446545,0.00001365153,0.2023267,0.00004744168,0.001969494],"study_design_scores_gemma":[0.0003678081,0.00004429174,0.02373525,0.00008608936,0.00001761342,0.000008181199,0.00006752658,0.7947186,0.000009524872,0.1806924,0.000003753844,0.0002489931],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3217474,0.0003555692,0.6765277,0.0002060709,0.0004901128,0.0002889484,0.00001453189,0.0001088337,0.0002607911],"genre_scores_gemma":[0.9945067,0.000264617,0.004966349,0.0001191971,0.00004758575,0.000001789287,0.00005103078,0.00001536068,0.00002733395],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.6727594,"threshold_uncertainty_score":0.9998724,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05592077022521464,"score_gpt":0.2100263340923151,"score_spread":0.1541055638671004,"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."}}