{"id":"W2985105421","doi":"","title":"Understanding Graph Neural Networks with Asymmetric Geometric Scattering Transforms","year":2019,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal","funders":"","keywords":"Euclidean geometry; Scattering; Graph; Computer science; Deep learning; Wavelet; Wavelet transform; Stability (learning theory); Theoretical computer science; Artificial intelligence; Topology (electrical circuits); Mathematics; Machine learning; Combinatorics; Physics; Geometry; Quantum mechanics","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":[0.0002458805,0.0007076233,0.0006687717,0.002350311,0.0003062009,0.0003148056,0.002807375,0.0004448535,0.000007870101],"category_scores_gemma":[0.00001091213,0.0006893236,0.0003911642,0.008835766,0.0002045415,0.001152472,0.001360452,0.001659274,0.00001635226],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005381943,"about_ca_system_score_gemma":0.00008045274,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004261469,"about_ca_topic_score_gemma":0.00003427131,"domain_scores_codex":[0.9963168,0.0001182588,0.0003321828,0.001942629,0.0002549119,0.001035241],"domain_scores_gemma":[0.9971389,0.0003018031,0.0004133511,0.00171244,0.0001109661,0.0003226047],"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":[0.00005000225,0.00003819503,0.00843319,0.00006493404,0.0001158847,0.0003280016,0.00003867915,0.9663323,0.000001698221,0.02324533,0.00006112547,0.001290621],"study_design_scores_gemma":[0.0008631295,0.0001945638,0.002219807,0.0001419297,0.00009018272,0.00003382587,0.00005329366,0.9797348,0.00001575833,0.01567142,0.00002801298,0.0009532358],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.06123333,0.0002536232,0.934909,0.00008676287,0.001158319,0.000631518,0.000005975394,0.0005240652,0.001197412],"genre_scores_gemma":[0.9968883,0.0004542392,0.002091769,0.0001735347,0.00009935974,0.000001975083,0.00001766031,0.0000631669,0.0002099596],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.935655,"threshold_uncertainty_score":0.9995558,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1012546212396433,"score_gpt":0.1859714681033655,"score_spread":0.08471684686372223,"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."}}