{"id":"W4287198239","doi":"10.48550/arxiv.2104.13014","title":"Node Embedding using Mutual Information and Self-Supervision based\\n Bi-level Aggregation","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Artificial Intelligence in Medicine (Canada)","funders":"","keywords":"Computer science; Aggregate (composite); Leverage (statistics); Exploit; Node (physics); Embedding; Theoretical computer science; Cluster analysis; Graph; Range (aeronautics); Data mining; Artificial intelligence; Computer security","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":[0.0001833665,0.0003076764,0.0002643761,0.0003973654,0.0002664098,0.0003463762,0.0007120363,0.0003003105,0.000006506248],"category_scores_gemma":[0.0000383062,0.0003370832,0.0001239672,0.000839031,0.00005260701,0.002837136,0.001662692,0.0005122789,0.000008926264],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002194317,"about_ca_system_score_gemma":0.0001846482,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006040752,"about_ca_topic_score_gemma":0.00001562315,"domain_scores_codex":[0.9984176,0.0001282074,0.0002604126,0.0007340899,0.0001463973,0.0003133631],"domain_scores_gemma":[0.9984022,0.0001148402,0.0003235807,0.0007672391,0.0002446803,0.0001474165],"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":[0.00001059267,0.00003289829,0.001277879,0.00009544312,0.00002707759,0.00008454457,0.0003742014,0.9884047,0.0000543115,0.004212026,0.00001689318,0.005409447],"study_design_scores_gemma":[0.0003885664,0.0000213933,0.0007793169,0.0002481,0.00003887103,0.00001173504,0.00008827133,0.9954692,0.0002296144,0.002224514,0.0001122673,0.0003882139],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3782345,0.00004330016,0.6209699,0.00003377506,0.0003224673,0.0001463698,0.000005715183,0.0001830879,0.00006089134],"genre_scores_gemma":[0.89656,0.0001865004,0.102944,0.0001860759,0.00004401728,4.782919e-7,0.00004612143,0.00001236451,0.00002044018],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5183254,"threshold_uncertainty_score":0.9999081,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06614258378080558,"score_gpt":0.2064764152930668,"score_spread":0.1403338315122612,"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."}}