{"id":"W3011257201","doi":"","title":"Scattering GCN: Overcoming Oversmoothness in Graph Convolutional Networks.","year":2020,"lang":"en","type":"preprint","venue":"PubMed","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mila - Quebec Artificial Intelligence Institute","funders":"National Institutes of Health; Institut de Valorisation des Données","keywords":"Graph; Computer science; Scattering; Artificial intelligence; Convolutional neural network; Residual; Pattern recognition (psychology); Theoretical computer science; Algorithm; Physics","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00036154,0.0004646409,0.0005604054,0.0003085926,0.00009985511,0.0002788136,0.002038782,0.0003261676,0.000004163886],"category_scores_gemma":[0.00006738675,0.0005312307,0.000249832,0.0008053649,0.0001221633,0.0005307446,0.003687088,0.001481307,0.000005418889],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002392227,"about_ca_system_score_gemma":0.00005798658,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004099388,"about_ca_topic_score_gemma":0.00002629545,"domain_scores_codex":[0.9964964,0.0001334867,0.0005704357,0.001333525,0.0004650722,0.001001121],"domain_scores_gemma":[0.9982119,0.0002096653,0.000323478,0.0009098301,0.00005225197,0.0002928603],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"observational","study_design_scores_codex":[0.00007175258,0.0001024882,0.01827034,0.0002135646,0.0001243682,0.0003747852,0.000240603,0.7820987,0.00001931892,0.04407915,0.003422876,0.1509821],"study_design_scores_gemma":[0.0008582623,0.00001003763,0.5340121,0.0001779009,0.00001701312,0.00002424548,0.000006097294,0.3723374,0.00004790197,0.08938169,0.002002011,0.001125265],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01610343,0.002034417,0.9698765,0.003201579,0.00527506,0.001741264,0.00001373623,0.0007631643,0.0009908054],"genre_scores_gemma":[0.9877694,0.0001305416,0.00833095,0.001395658,0.0005507688,0.001709714,0.00002591289,0.00004331478,0.00004376818],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9716659,"threshold_uncertainty_score":0.9997139,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03333962040462993,"score_gpt":0.2303594570777287,"score_spread":0.1970198366730988,"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."}}