{"id":"W2948598318","doi":"10.48550/arxiv.1906.02174","title":"Break the Ceiling: Stronger Multi-scale Deep Graph Convolutional Networks","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Computer science; Theoretical computer science; Graph; Deep learning; Expressive power; Convolution (computer science); Artificial intelligence; Artificial neural network","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":[0.000276925,0.0005246176,0.0004336842,0.0002075917,0.0003793362,0.0001600165,0.003682044,0.0004756776,0.00002534454],"category_scores_gemma":[0.00001503883,0.0004789996,0.0004892224,0.000929295,0.0003866804,0.0004943002,0.003194721,0.001646708,0.0000866664],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001706624,"about_ca_system_score_gemma":0.000135079,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000532117,"about_ca_topic_score_gemma":0.0001359094,"domain_scores_codex":[0.9968939,0.0002701768,0.0002990952,0.001609817,0.0001723118,0.0007546559],"domain_scores_gemma":[0.9965907,0.0003577372,0.0003989464,0.002199211,0.0002351601,0.0002182389],"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":[0.00002161508,0.00006521874,0.006045842,0.00001356451,0.0000840256,0.00005846373,0.00006559512,0.9542232,0.000006077676,0.03862498,0.0003343203,0.0004571032],"study_design_scores_gemma":[0.0005565021,0.00003120289,0.005970708,0.00004989661,0.00005678532,0.00001085757,0.00004246359,0.9769184,0.000009018684,0.01532431,0.0004933755,0.0005364944],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02243541,0.0005441494,0.9732229,0.0001658348,0.00216066,0.0005840329,0.00001360531,0.0003390222,0.0005344425],"genre_scores_gemma":[0.9911673,0.0003230205,0.006454012,0.0003002855,0.0002245628,0.000002969044,0.00003405942,0.00003455285,0.001459247],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9687319,"threshold_uncertainty_score":0.9997662,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05255833454735805,"score_gpt":0.1868676544841212,"score_spread":0.1343093199367631,"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."}}