{"id":"W4417267046","doi":"10.1007/s10618-025-01180-w","title":"Certifying robustness of graph convolutional networks for node perturbation with polyhedra abstract interpretation","year":2025,"lang":"en","type":"article","venue":"Data Mining and Knowledge Discovery","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"McGill University","funders":"Fonds de recherche du Québec – Nature et technologies; Nemzeti Kutatási Fejlesztési és Innovációs Hivatal; Mitacs; Knut och Alice Wallenbergs Stiftelse","keywords":"Robustness (evolution); Graph; Convolutional neural network; Adversarial system; Polyhedron; Training set","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004447351,0.001502866,0.001682944,0.002016071,0.0008619669,0.002860314,0.003617936,0.002804296,0.003980623],"category_scores_gemma":[0.04567223,0.0007803928,0.00199867,0.001131194,0.004147538,0.005383641,0.005294321,0.004495289,0.0005867841],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002671786,"about_ca_system_score_gemma":0.001719799,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004125218,"about_ca_topic_score_gemma":0.003024269,"domain_scores_codex":[0.9960362,0.0009125374,0.0002245861,0.001318504,0.001108008,0.0004002006],"domain_scores_gemma":[0.9753036,0.01531375,0.001831755,0.005014525,0.001963158,0.000573186],"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":[0.0006589548,0.00008332142,0.003397385,0.000299231,0.0002563552,0.0003751158,0.0001680826,0.7384124,0.007003783,0.1924198,0.00511218,0.05181354],"study_design_scores_gemma":[0.00001149241,0.00002769238,0.0002884245,0.00001876611,0.00001826079,0.0000372759,0.00001570373,0.8305683,0.0022788,0.1663998,0.0003245323,0.00001104777],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.08703447,0.0003745577,0.9038057,0.001303002,0.0001777101,0.00008572472,0.0007600314,0.002387424,0.004071386],"genre_scores_gemma":[0.9225166,0.0003207202,0.07161448,0.0004674892,0.0002165443,0.0001212186,0.001573608,0.0005769086,0.002592405],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.004447351,"threshold_uncertainty_score":0.02352017,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03197076562914049,"score_gpt":0.2958814579966345,"score_spread":0.263910692367494,"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."}}