{"id":"W4389778193","doi":"10.1016/j.patcog.2023.110209","title":"A contrastive variational graph auto-encoder for node clustering","year":2023,"lang":"en","type":"article","venue":"Pattern Recognition","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université du Québec à Montréal","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cluster analysis; Randomness; Computer science; Feature (linguistics); Upper and lower bounds; Inference; Algorithm; Encoder; Pattern recognition (psychology); Artificial intelligence; Mathematics; Statistics","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":[],"consensus_categories":[],"category_scores_codex":[0.0001772396,0.0001252075,0.0001188424,0.0001662544,0.000149381,0.00008323854,0.0002315132,0.00005944141,0.00001584988],"category_scores_gemma":[0.00004954257,0.0001296266,0.00008568069,0.0004629514,0.00001935052,0.0004865997,0.00009322273,0.0001020884,0.0001421128],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002486008,"about_ca_system_score_gemma":0.0000146095,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000006546232,"about_ca_topic_score_gemma":0.00001769136,"domain_scores_codex":[0.9988998,0.00004095567,0.0001956839,0.000373422,0.000177523,0.000312574],"domain_scores_gemma":[0.9992004,0.000354466,0.00009734846,0.0001576929,0.0001300398,0.00006004805],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00003607802,0.00005747114,0.001491718,0.00006031161,0.00006488436,0.00002303646,0.0005836857,0.007618644,0.001551341,0.0004961854,0.002381191,0.9856355],"study_design_scores_gemma":[0.0006658247,0.00005746776,0.01267165,0.00005796153,0.000009473746,0.00001156367,0.00001429548,0.9238975,0.000323461,0.06184957,0.0002240825,0.0002171233],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.005112422,0.000009676288,0.9922916,0.0008052137,0.0007473577,0.0003494488,0.00006625384,0.0004701064,0.0001478871],"genre_scores_gemma":[0.9083406,0.00003264265,0.0877791,0.00224032,0.0004513504,0.0006009236,0.0004097467,0.00003779736,0.0001074624],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9854183,"threshold_uncertainty_score":0.5286021,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0409770510361664,"score_gpt":0.2727985179681225,"score_spread":0.2318214669319562,"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."}}