{"id":"W3093959361","doi":"10.1109/tmm.2020.3034530","title":"Anisotropic Graph Convolutional Network for Semi-Supervised Learning","year":2020,"lang":"en","type":"preprint","venue":"IEEE Transactions on Multimedia","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"Concordia University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Graph; Smoothing; Node (physics); Artificial intelligence; Theoretical computer science; Pattern recognition (psychology); Machine learning; Computer vision","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":[0.0001557939,0.0005950445,0.0006014436,0.0002090822,0.0005488644,0.0001570944,0.001307214,0.0005040176,0.00003686432],"category_scores_gemma":[0.0000227032,0.0006470763,0.0006479785,0.0006203852,0.0001455456,0.0002792161,0.00003149785,0.002195489,0.00006082164],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001215094,"about_ca_system_score_gemma":0.0001893291,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001727028,"about_ca_topic_score_gemma":0.0000236125,"domain_scores_codex":[0.9966419,0.0001840723,0.0005618859,0.001359381,0.0004988708,0.0007538543],"domain_scores_gemma":[0.9975775,0.0008359312,0.0002596076,0.0007717023,0.0001994739,0.0003557345],"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":[0.00007638789,0.00008518223,0.00003223459,0.00007121787,0.0001457344,0.00001248973,0.0002629554,0.9598563,0.0003686751,0.0004071131,0.00173782,0.03694395],"study_design_scores_gemma":[0.00112364,0.0002307239,0.000131584,0.000142133,0.00007311762,0.000009070878,0.00001178032,0.9838064,0.0007341023,0.01086073,0.002222273,0.0006544685],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0006475078,0.00027945,0.98988,0.001213266,0.005673896,0.001164409,0.0001146322,0.000984582,0.00004224467],"genre_scores_gemma":[0.4491241,0.0003677994,0.5472665,0.0008987398,0.001024269,0.0008022287,0.0001176922,0.000105011,0.0002936421],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4484766,"threshold_uncertainty_score":0.999598,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0311097313989207,"score_gpt":0.2649050099372052,"score_spread":0.2337952785382845,"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."}}