{"id":"W2950887295","doi":"","title":"GMNN: Graph Markov Neural Networks","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Statistical relational learning; Computer science; Artificial intelligence; Conditional random field; Graph; Markov random field; Artificial neural network; Convolutional neural network; Pattern recognition (psychology); Object (grammar); Theoretical computer science; Machine learning; Relational database; Data mining","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":[0.000205796,0.0006492778,0.0006010194,0.000398412,0.0002066721,0.0002087548,0.004102266,0.0005898942,0.0000284568],"category_scores_gemma":[0.00001748488,0.0007442645,0.0005510569,0.001429197,0.0001863973,0.0007722315,0.004559487,0.00175371,0.00007808149],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001458809,"about_ca_system_score_gemma":0.00007965995,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003953696,"about_ca_topic_score_gemma":0.0000258365,"domain_scores_codex":[0.9963008,0.0002435718,0.0003207621,0.002095879,0.0001514136,0.0008876264],"domain_scores_gemma":[0.9960319,0.0002348463,0.0004355452,0.002814147,0.0001685926,0.0003150128],"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":[0.00003167048,0.00003942457,0.003287924,0.00003072399,0.0000652638,0.0004289509,0.00002562164,0.9478707,0.00000267491,0.04473905,0.001237076,0.002240891],"study_design_scores_gemma":[0.0004288412,0.00006304705,0.001404113,0.00006599037,0.00004666861,0.0000142796,0.000009735409,0.9578275,0.000007373119,0.03897014,0.0003959425,0.0007663767],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04480255,0.000363424,0.9476995,0.000158297,0.003532381,0.0005490421,0.000008680853,0.0006820326,0.002204055],"genre_scores_gemma":[0.9942953,0.0004434842,0.002640682,0.0005045217,0.0002329377,0.000001661892,0.00002676093,0.00004768349,0.00180697],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9494928,"threshold_uncertainty_score":0.9995008,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0398459198662946,"score_gpt":0.1781134981141955,"score_spread":0.1382675782479009,"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."}}