{"id":"W2981608876","doi":"10.48550/arxiv.1910.12132","title":"Bayesian Graph Convolutional Neural Networks Using Non-Parametric Graph Learning","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Inference; Graph; Artificial intelligence; Random graph; Theoretical computer science; Machine learning","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","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0003127476,0.0007356157,0.0007214479,0.001304864,0.0004972917,0.0002426191,0.00280603,0.0006688525,0.00001982881],"category_scores_gemma":[0.00004411241,0.0008935953,0.0006831173,0.004201906,0.0002868742,0.0009371274,0.002979826,0.002707545,0.00002628704],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000278336,"about_ca_system_score_gemma":0.0001657067,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001146796,"about_ca_topic_score_gemma":0.00001380599,"domain_scores_codex":[0.9957014,0.0003522772,0.0004343548,0.002184615,0.0002600817,0.001067294],"domain_scores_gemma":[0.9966577,0.0003940497,0.0007078121,0.001593067,0.0002786328,0.0003687578],"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":[0.00003065541,0.00004625219,0.01910001,0.00003378519,0.00009884896,0.0002490925,0.00002641608,0.9654173,0.00001200056,0.01455289,0.00008106623,0.0003517212],"study_design_scores_gemma":[0.0005643711,0.00008368537,0.002431426,0.00009990316,0.00008348924,0.00002912184,0.00002019812,0.9712219,0.000008705042,0.02451974,0.00005103883,0.0008864898],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1515702,0.0002968381,0.8448282,0.00002769696,0.002141375,0.0004811038,0.000005419538,0.0003403771,0.0003087642],"genre_scores_gemma":[0.9927769,0.0002426014,0.006149919,0.0001575216,0.0002114488,0.000001403764,0.00003757008,0.00005706116,0.0003656159],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8412067,"threshold_uncertainty_score":0.9995933,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04824507224445967,"score_gpt":0.1962572986112704,"score_spread":0.1480122263668107,"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."}}