{"id":"W4288049515","doi":"10.1109/tnnls.2022.3151046","title":"Status-Aware Signed Heterogeneous Network Embedding With Graph Neural Networks","year":2022,"lang":"en","type":"article","venue":"IEEE Transactions on Neural Networks and Learning Systems","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Computer science; Embedding; Benchmarking; Signed graph; Scalability; Theoretical computer science; Robustness (evolution); Exploit; Graph embedding; Artificial intelligence; Graph; 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","sts","research_integrity"],"consensus_categories":[],"category_scores_codex":[0.0005440114,0.0007349565,0.000732597,0.0002829319,0.003757583,0.00059672,0.000830779,0.0001824974,0.00002648865],"category_scores_gemma":[0.000003400993,0.0006743101,0.0002676941,0.001982231,0.0001598153,0.0006458329,0.00004769615,0.003001075,0.000001592549],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001270755,"about_ca_system_score_gemma":0.00002794269,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001011367,"about_ca_topic_score_gemma":0.00003965876,"domain_scores_codex":[0.9940069,0.001424109,0.0007199618,0.001366565,0.0007546212,0.00172785],"domain_scores_gemma":[0.9973825,0.0007634184,0.0004639215,0.0007855366,0.0001033148,0.0005013407],"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":[0.0002205202,0.00006038215,0.0003253121,0.00001810343,0.0001015177,0.0002001459,0.0001648347,0.9807191,0.00000850864,0.00009154533,0.0001347636,0.01795522],"study_design_scores_gemma":[0.0008707936,0.001636726,0.00006116041,0.00006761914,0.00005383718,0.0008028147,0.00019578,0.9946017,0.000004252487,0.00001965718,0.0009136951,0.000771976],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.03202105,0.002309743,0.9600285,0.0001305959,0.003704941,0.0008230586,0.000007104733,0.000950537,0.00002442658],"genre_scores_gemma":[0.9973371,0.0001686804,0.0007041693,0.0005076138,0.0004798074,0.0003586088,0.0000152358,0.0001251211,0.000303672],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9653161,"threshold_uncertainty_score":0.9995708,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01072771018106191,"score_gpt":0.2262846392412846,"score_spread":0.2155569290602227,"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."}}