{"as_of":"2026-08-10T15:11:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:f38e0b567d668c66248dc6c538e5f2f09a06c1bcae1a5dca855f7fd33e831396","coverage":[{"denominator":42,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":42,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-28T02:58:52.293969Z","state":"measured"},{"denominator":42,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":42,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2606.06293/citation-record","integrity":"/paper/2606.06293/integrity","json":"/paper/2606.06293/citation-record.json","paper":"/paper/2606.06293"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T02:58:52.293969Z","title":"The graph neural network model,","venue":null,"work_id":null,"year":2009},"citing_paper":{"arxiv_id":"2606.06293","last_updated":"2026-06-04T15:31:21Z","snapshot_observed_at":"2026-08-08T10:51:57.500235Z","submitted_at":"2026-06-04T15:31:21Z","title":"PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-06-28T02:58:52.293969Z"},"links":{"citing_paper":"/paper/2606.06293"},"observation_digest":"sha256:2f6d666d941faa4b86bce9f90d7f4e04dc017c03684f3b78ba73f39887995f1d","observation_id":"57c5d3d0-480d-464c-82f0-8dc433cb0804","resolution":{"observed_at":"2026-06-28T02:58:52.293969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1806.01261","last_updated":"2018-10-17T17:51:36Z","snapshot_observed_at":"2026-07-06T06:42:54.610341Z","submitted_at":"2018-06-04T17:58:18Z","title":"Relational inductive biases, deep learning, and graph networks","version":3},"cited_work":{"arxiv_id":"1806.01261","doi":"10.48550/arxiv.1806.01261","metadata_source":"pith","pith_arxiv_id":"1806.01261","snapshot_observed_at":"2026-07-10T16:47:24.357908Z","title":"Relational inductive biases, deep learning, and graph networks","venue":"cs.LG","work_id":"858410c0-7a66-4b27-b4e5-49aee9725be0","year":2018},"citing_paper":{"arxiv_id":"2606.06293","last_updated":"2026-06-04T15:31:21Z","snapshot_observed_at":"2026-08-08T10:51:57.500235Z","submitted_at":"2026-06-04T15:31:21Z","title":"PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-06-28T02:58:52.293969Z"},"links":{"cited_paper":"/paper/1806.01261","citing_paper":"/paper/2606.06293"},"observation_digest":"sha256:0020d86e11b2c31d91080befec69a002c3477067e857898998ff9df0c5bc0f71","observation_id":"eb40861f-efc6-404d-9579-64dfc70b1d98","resolution":{"observed_at":"2026-07-02T11:46:55.896827Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-03T17:38:15.281147+00:00","source":"crossref_status_cache"},{"observed_at":"2026-08-03T17:38:15.281147+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T02:58:52.293969Z","title":"Semi-supervised classification with graph convolutional networks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.06293","last_updated":"2026-06-04T15:31:21Z","snapshot_observed_at":"2026-08-08T10:51:57.500235Z","submitted_at":"2026-06-04T15:31:21Z","title":"PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-06-28T02:58:52.293969Z"},"links":{"citing_paper":"/paper/2606.06293"},"observation_digest":"sha256:8b4c2c372983a7ca0f533cb910cd4de1b42cc639e6329f0f50ddbd1bb8849d54","observation_id":"40085d9f-274f-43dc-b42b-55830eba8fd1","resolution":{"observed_at":"2026-06-28T02:58:52.293969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T02:58:52.293969Z","title":"Inductive representation learning on large graphs,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.06293","last_updated":"2026-06-04T15:31:21Z","snapshot_observed_at":"2026-08-08T10:51:57.500235Z","submitted_at":"2026-06-04T15:31:21Z","title":"PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-06-28T02:58:52.293969Z"},"links":{"citing_paper":"/paper/2606.06293"},"observation_digest":"sha256:9265a75f8cd93e487b227167fc487cf2cf08ea2f171712ff96cae602dceef16f","observation_id":"8a9bd25d-552d-4b23-8a57-246fb4262505","resolution":{"observed_at":"2026-06-28T02:58:52.293969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T02:58:52.293969Z","title":"Modeling polypharmacy side effects with graph convolutional networks,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2606.06293","last_updated":"2026-06-04T15:31:21Z","snapshot_observed_at":"2026-08-08T10:51:57.500235Z","submitted_at":"2026-06-04T15:31:21Z","title":"PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-06-28T02:58:52.293969Z"},"links":{"citing_paper":"/paper/2606.06293"},"observation_digest":"sha256:dc857193ac67551fb29e74b6c1cfa7a491486ffc9137583248ba233f25b7a97d","observation_id":"ae7eab79-444c-4c36-bfb6-c90870c4515c","resolution":{"observed_at":"2026-06-28T02:58:52.293969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T02:58:52.293969Z","title":"Graph convolutional neural networks for web-scale recommender systems,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2606.06293","last_updated":"2026-06-04T15:31:21Z","snapshot_observed_at":"2026-08-08T10:51:57.500235Z","submitted_at":"2026-06-04T15:31:21Z","title":"PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-06-28T02:58:52.293969Z"},"links":{"citing_paper":"/paper/2606.06293"},"observation_digest":"sha256:1d83bc3648c1852f8c238f662847b1ee54401b94c0b983ad4d29987a2593721f","observation_id":"c96bdcd6-352f-4444-93a5-597c85544b2c","resolution":{"observed_at":"2026-06-28T02:58:52.293969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T02:58:52.293969Z","title":"Graph neural networks for scalable radio resource management: Architecture design and theoretical analysis,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.06293","last_updated":"2026-06-04T15:31:21Z","snapshot_observed_at":"2026-08-08T10:51:57.500235Z","submitted_at":"2026-06-04T15:31:21Z","title":"PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-06-28T02:58:52.293969Z"},"links":{"citing_paper":"/paper/2606.06293"},"observation_digest":"sha256:a63ecdd84294ec80455bb4e9d9f32b0e060cd39b1446605064020d4606f2251e","observation_id":"65be6775-0a0c-42d3-a512-4fb6547b94b4","resolution":{"observed_at":"2026-06-28T02:58:52.293969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T02:58:52.293969Z","title":"Intriguing properties of neural networks,","venue":null,"work_id":null,"year":2014},"citing_paper":{"arxiv_id":"2606.06293","last_updated":"2026-06-04T15:31:21Z","snapshot_observed_at":"2026-08-08T10:51:57.500235Z","submitted_at":"2026-06-04T15:31:21Z","title":"PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-06-28T02:58:52.293969Z"},"links":{"citing_paper":"/paper/2606.06293"},"observation_digest":"sha256:1a6cbb1ed49a15420c655a6c620f87669bb76f1eef6ec9d33fcba7fd589f02de","observation_id":"fdaa1a16-e125-4f6c-87fe-8564792d8445","resolution":{"observed_at":"2026-06-28T02:58:52.293969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T02:58:52.293969Z","title":"Explaining and harnessing adversarial examples,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2606.06293","last_updated":"2026-06-04T15:31:21Z","snapshot_observed_at":"2026-08-08T10:51:57.500235Z","submitted_at":"2026-06-04T15:31:21Z","title":"PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-06-28T02:58:52.293969Z"},"links":{"citing_paper":"/paper/2606.06293"},"observation_digest":"sha256:8f0d5f9f641ebaf01063a85b4206e195796eda2bb953ba3f0395cb2003470221","observation_id":"08f01a51-b668-4cdd-85f2-778b7f277413","resolution":{"observed_at":"2026-06-28T02:58:52.293969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T02:58:52.293969Z","title":"Adversarial attacks on neural networks for graph data,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2606.06293","last_updated":"2026-06-04T15:31:21Z","snapshot_observed_at":"2026-08-08T10:51:57.500235Z","submitted_at":"2026-06-04T15:31:21Z","title":"PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-06-28T02:58:52.293969Z"},"links":{"citing_paper":"/paper/2606.06293"},"observation_digest":"sha256:8d8e1efbc620fc8fa0b230c20fdc27836ef8ed1c773ffbed8d2a8c322f03d08b","observation_id":"47b5ea68-8c8f-4f46-acb2-8fca1f7de996","resolution":{"observed_at":"2026-06-28T02:58:52.293969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T02:58:52.293969Z","title":"Adversarial attacks on graph neural networks via meta learning,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.06293","last_updated":"2026-06-04T15:31:21Z","snapshot_observed_at":"2026-08-08T10:51:57.500235Z","submitted_at":"2026-06-04T15:31:21Z","title":"PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-06-28T02:58:52.293969Z"},"links":{"citing_paper":"/paper/2606.06293"},"observation_digest":"sha256:2cc67b0927815a97db4893ae0b2a3fe8aa47990d585dfe0112c68f72e3375e88","observation_id":"5dc56a1d-9661-4ddd-8d9e-b04ca31410e0","resolution":{"observed_at":"2026-06-28T02:58:52.293969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T02:58:52.293969Z","title":"Adversarial examples on graph data: Deep insights into attack and defense,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.06293","last_updated":"2026-06-04T15:31:21Z","snapshot_observed_at":"2026-08-08T10:51:57.500235Z","submitted_at":"2026-06-04T15:31:21Z","title":"PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-06-28T02:58:52.293969Z"},"links":{"citing_paper":"/paper/2606.06293"},"observation_digest":"sha256:0b14af34216f7037fe9e73ea07f4ec159518d3aa09ca243abe244b246bf23898","observation_id":"29cee604-8714-460b-9d6a-4cebb97e3fcd","resolution":{"observed_at":"2026-06-28T02:58:52.293969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T02:58:52.293969Z","title":"Adversarial attacks on graph classification via Bayesian optimisation,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.06293","last_updated":"2026-06-04T15:31:21Z","snapshot_observed_at":"2026-08-08T10:51:57.500235Z","submitted_at":"2026-06-04T15:31:21Z","title":"PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-06-28T02:58:52.293969Z"},"links":{"citing_paper":"/paper/2606.06293"},"observation_digest":"sha256:2af4649b48248707c37cdf7cf3f94b286cbf7f37b1a7194f3e8867fbe715268d","observation_id":"3b73bf0c-3d90-4813-9054-7853b96bc194","resolution":{"observed_at":"2026-06-28T02:58:52.293969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T02:58:52.293969Z","title":"Revisiting adversarial attacks on graph neural networks for graph classification,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.06293","last_updated":"2026-06-04T15:31:21Z","snapshot_observed_at":"2026-08-08T10:51:57.500235Z","submitted_at":"2026-06-04T15:31:21Z","title":"PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-06-28T02:58:52.293969Z"},"links":{"citing_paper":"/paper/2606.06293"},"observation_digest":"sha256:d673a616dd720d67c960340fe75fbeba657be30864b15a152b43cad1f51fc7db","observation_id":"75b3f129-e121-4f3a-8434-4cb5a3cdcf82","resolution":{"observed_at":"2026-06-28T02:58:52.293969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T02:58:52.293969Z","title":"GNNGuard: Defending graph neural net- works against adversarial attacks,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.06293","last_updated":"2026-06-04T15:31:21Z","snapshot_observed_at":"2026-08-08T10:51:57.500235Z","submitted_at":"2026-06-04T15:31:21Z","title":"PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-06-28T02:58:52.293969Z"},"links":{"citing_paper":"/paper/2606.06293"},"observation_digest":"sha256:2c42a3dfce2f8b288dbe8dace5844c9d6dcbd60780f9000bcbfec6b73a59b7a0","observation_id":"eb97e15d-f819-4043-a91e-9c2001221785","resolution":{"observed_at":"2026-06-28T02:58:52.293969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T02:58:52.293969Z","title":"All you need is low (rank): Defending against adversarial attacks on graphs,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.06293","last_updated":"2026-06-04T15:31:21Z","snapshot_observed_at":"2026-08-08T10:51:57.500235Z","submitted_at":"2026-06-04T15:31:21Z","title":"PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-06-28T02:58:52.293969Z"},"links":{"citing_paper":"/paper/2606.06293"},"observation_digest":"sha256:798a1ed597e465df86cd61d241d334cd54779614096314e9203f3f9188afe456","observation_id":"baf097a8-92ec-410e-9211-a598773a3b53","resolution":{"observed_at":"2026-06-28T02:58:52.293969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T02:58:52.293969Z","title":"A causality-aligned structure rationalization scheme against adversarial biased perturbations for graph neural networks,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2606.06293","last_updated":"2026-06-04T15:31:21Z","snapshot_observed_at":"2026-08-08T10:51:57.500235Z","submitted_at":"2026-06-04T15:31:21Z","title":"PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-06-28T02:58:52.293969Z"},"links":{"citing_paper":"/paper/2606.06293"},"observation_digest":"sha256:7d86608c67d4590dcd289224e53efbd719e5bcd3e1ecf181049a329a2da90384","observation_id":"8a098ecd-491a-4fea-afc6-0a1c3c0a917f","resolution":{"observed_at":"2026-06-28T02:58:52.293969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T02:58:52.293969Z","title":"Adversarial training for graph neural networks via graph subspace energy optimization,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2606.06293","last_updated":"2026-06-04T15:31:21Z","snapshot_observed_at":"2026-08-08T10:51:57.500235Z","submitted_at":"2026-06-04T15:31:21Z","title":"PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-06-28T02:58:52.293969Z"},"links":{"citing_paper":"/paper/2606.06293"},"observation_digest":"sha256:0ab5e655d74385a3d9a40c87fe60c5470c4459e4efc5428d123af8e971002ec3","observation_id":"c6552631-3864-4d9c-b3e9-f4b3b06444bd","resolution":{"observed_at":"2026-06-28T02:58:52.293969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T02:58:52.293969Z","title":"The Vapnik-Chervonenkis dimension of graph and recursive neural networks,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2606.06293","last_updated":"2026-06-04T15:31:21Z","snapshot_observed_at":"2026-08-08T10:51:57.500235Z","submitted_at":"2026-06-04T15:31:21Z","title":"PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-06-28T02:58:52.293969Z"},"links":{"citing_paper":"/paper/2606.06293"},"observation_digest":"sha256:8d4bcf8716b5f0c4f9d415f1122271c9d58bdf02aaf3b6a977d9f34715bcb26c","observation_id":"7189e351-4722-402e-8570-6479aadb2d96","resolution":{"observed_at":"2026-06-28T02:58:52.293969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T02:58:52.293969Z","title":"Learning theory can (sometimes) explain generalisation in graph neural networks,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.06293","last_updated":"2026-06-04T15:31:21Z","snapshot_observed_at":"2026-08-08T10:51:57.500235Z","submitted_at":"2026-06-04T15:31:21Z","title":"PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-06-28T02:58:52.293969Z"},"links":{"citing_paper":"/paper/2606.06293"},"observation_digest":"sha256:fc67a8c90c516e0b49a80072ada8fd3e290c98e4d551b7154d55aee9f3d43dda","observation_id":"6a204f64-7ad0-47b1-a8f9-2ca90bb613de","resolution":{"observed_at":"2026-06-28T02:58:52.293969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T02:58:52.293969Z","title":"Generalization and represen- tational limits of graph neural networks,","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2606.06293","last_updated":"2026-06-04T15:31:21Z","snapshot_observed_at":"2026-08-08T10:51:57.500235Z","submitted_at":"2026-06-04T15:31:21Z","title":"PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-06-28T02:58:52.293969Z"},"links":{"citing_paper":"/paper/2606.06293"},"observation_digest":"sha256:7a65ee3956b6205078fd912cbeb1489e79fd5b9ae780c7f83cdb7d78dd89a8bd","observation_id":"af858be6-a7cc-4e31-8a77-8c3658a0ebec","resolution":{"observed_at":"2026-06-28T02:58:52.293969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2102.10234","last_updated":"2021-02-20T02:51:13Z","snapshot_observed_at":"2026-07-06T10:43:02.182568Z","submitted_at":"2021-02-20T02:51:13Z","title":"Generalization bounds for graph convolutional neural networks via Rademacher complexity","version":1},"cited_work":{"arxiv_id":"2102.10234","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2102.10234","snapshot_observed_at":"2026-07-02T11:46:55.889503Z","title":"arXiv preprint arXiv:2102.10234 , year=","venue":null,"work_id":"207507cc-481a-4dd7-a470-62f612b7c661","year":2021},"citing_paper":{"arxiv_id":"2606.06293","last_updated":"2026-06-04T15:31:21Z","snapshot_observed_at":"2026-08-08T10:51:57.500235Z","submitted_at":"2026-06-04T15:31:21Z","title":"PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-06-28T02:58:52.293969Z"},"links":{"cited_paper":"/paper/2102.10234","citing_paper":"/paper/2606.06293"},"observation_digest":"sha256:c5e08e5af0545a1e29a730de02f19246c5e9a5cdbc2c6005af2500f49d416dd8","observation_id":"9da708f2-5979-4fc7-a8f2-ca337408492d","resolution":{"observed_at":"2026-07-02T11:46:55.890927Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T02:58:52.293969Z","title":"Stability and generalization of graph convolutional neural networks,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.06293","last_updated":"2026-06-04T15:31:21Z","snapshot_observed_at":"2026-08-08T10:51:57.500235Z","submitted_at":"2026-06-04T15:31:21Z","title":"PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-06-28T02:58:52.293969Z"},"links":{"citing_paper":"/paper/2606.06293"},"observation_digest":"sha256:bd763899f929b09c9b8ecd8a755895b1ff5c8dcc5b2cb6578aa48886ee87dd1a","observation_id":"ba44d2fa-f82a-47a5-a90f-1ec45c9919aa","resolution":{"observed_at":"2026-06-28T02:58:52.293969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T02:58:52.293969Z","title":"The generalization error of graph convolutional networks may enlarge with more layers,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.06293","last_updated":"2026-06-04T15:31:21Z","snapshot_observed_at":"2026-08-08T10:51:57.500235Z","submitted_at":"2026-06-04T15:31:21Z","title":"PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-06-28T02:58:52.293969Z"},"links":{"citing_paper":"/paper/2606.06293"},"observation_digest":"sha256:829cfe7e8025cf37996732db18bb9daf7467f01c789e213a74dc678bd95dfbb1","observation_id":"fcd6da1a-229a-4ec8-bd1d-e01dac4ad882","resolution":{"observed_at":"2026-06-28T02:58:52.293969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T02:58:52.293969Z","title":"Graph neural tangent kernel: Fusing graph neural networks with graph kernels,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2606.06293","last_updated":"2026-06-04T15:31:21Z","snapshot_observed_at":"2026-08-08T10:51:57.500235Z","submitted_at":"2026-06-04T15:31:21Z","title":"PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-06-28T02:58:52.293969Z"},"links":{"citing_paper":"/paper/2606.06293"},"observation_digest":"sha256:e53b95d360c0887146c755b6901408b57fd217d38578d1550f132564b92dbb2d","observation_id":"e877cb99-61b3-4430-a797-dfe4cd9e7b6b","resolution":{"observed_at":"2026-06-28T02:58:52.293969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T02:58:52.293969Z","title":"Simplified PAC-Bayesian margin bounds,","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2606.06293","last_updated":"2026-06-04T15:31:21Z","snapshot_observed_at":"2026-08-08T10:51:57.500235Z","submitted_at":"2026-06-04T15:31:21Z","title":"PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-06-28T02:58:52.293969Z"},"links":{"citing_paper":"/paper/2606.06293"},"observation_digest":"sha256:dd60bce5c26bfc05649eeef0bbee764342f2aae176678a9705c049fb5a7b38f4","observation_id":"9093698e-f414-42eb-b3b5-612e6665c869","resolution":{"observed_at":"2026-06-28T02:58:52.293969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T02:58:52.293969Z","title":"PAC-Bayes & margins,","venue":null,"work_id":null,"year":2003},"citing_paper":{"arxiv_id":"2606.06293","last_updated":"2026-06-04T15:31:21Z","snapshot_observed_at":"2026-08-08T10:51:57.500235Z","submitted_at":"2026-06-04T15:31:21Z","title":"PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-06-28T02:58:52.293969Z"},"links":{"citing_paper":"/paper/2606.06293"},"observation_digest":"sha256:cc7a43a0910bebbaf79c0ef191d7a98b3a2d4ba18ac8be6a0cb0e24db4c33a27","observation_id":"9ab4493c-9a98-4dc6-80c1-8ce00f011fb3","resolution":{"observed_at":"2026-06-28T02:58:52.293969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T02:58:52.293969Z","title":"Catoni,PAC-Bayesian Supervised Classification: The Thermodynamics of Statistical Learning","venue":null,"work_id":null,"year":2007},"citing_paper":{"arxiv_id":"2606.06293","last_updated":"2026-06-04T15:31:21Z","snapshot_observed_at":"2026-08-08T10:51:57.500235Z","submitted_at":"2026-06-04T15:31:21Z","title":"PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-06-28T02:58:52.293969Z"},"links":{"citing_paper":"/paper/2606.06293"},"observation_digest":"sha256:45454f34093f58b8506613b6d7f7ae485389d5e7df2566c782154868a7828e1f","observation_id":"c8c11fcb-e30e-41cc-be88-d8cf0146f516","resolution":{"observed_at":"2026-06-28T02:58:52.293969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T02:58:52.293969Z","title":"PAC-Bayes bounds with data dependent priors,","venue":null,"work_id":null,"year":2012},"citing_paper":{"arxiv_id":"2606.06293","last_updated":"2026-06-04T15:31:21Z","snapshot_observed_at":"2026-08-08T10:51:57.500235Z","submitted_at":"2026-06-04T15:31:21Z","title":"PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-06-28T02:58:52.293969Z"},"links":{"citing_paper":"/paper/2606.06293"},"observation_digest":"sha256:49a80f0a41a776e6300018872e04b49b76bace0194cae8d73fad6a743a2def44","observation_id":"6647122e-9faa-49b3-bcec-abfdda3e9991","resolution":{"observed_at":"2026-06-28T02:58:52.293969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T02:58:52.293969Z","title":"Computing nonvacuous generalization bounds for deep (stochastic) neural networks with many more parameters than training data,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.06293","last_updated":"2026-06-04T15:31:21Z","snapshot_observed_at":"2026-08-08T10:51:57.500235Z","submitted_at":"2026-06-04T15:31:21Z","title":"PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-06-28T02:58:52.293969Z"},"links":{"citing_paper":"/paper/2606.06293"},"observation_digest":"sha256:e7785df8afb279413d4dde640fa4b929bf87ef31424e991d425299ef0239c4d0","observation_id":"f5db0292-d91c-4d61-ac99-45e36f3a2e4e","resolution":{"observed_at":"2026-06-28T02:58:52.293969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T02:58:52.293969Z","title":"Spectrally-normalized margin bounds for neural networks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2606.06293","last_updated":"2026-06-04T15:31:21Z","snapshot_observed_at":"2026-08-08T10:51:57.500235Z","submitted_at":"2026-06-04T15:31:21Z","title":"PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-06-28T02:58:52.293969Z"},"links":{"citing_paper":"/paper/2606.06293"},"observation_digest":"sha256:d01ea78eda9426ee9362d5bfbb4cc50165eee6e0259370e7625e0aa07a7e5d08","observation_id":"6566bbae-ba60-434c-a8ee-eb5fd5ad1f90","resolution":{"observed_at":"2026-06-28T02:58:52.293969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T02:58:52.293969Z","title":"A PAC-Bayesian approach to spectrally-normalized margin bounds for neural networks,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2606.06293","last_updated":"2026-06-04T15:31:21Z","snapshot_observed_at":"2026-08-08T10:51:57.500235Z","submitted_at":"2026-06-04T15:31:21Z","title":"PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-06-28T02:58:52.293969Z"},"links":{"citing_paper":"/paper/2606.06293"},"observation_digest":"sha256:7983040babd356f09e521cb01d8bdde4cea74a540aa029e37c40febf62105a2a","observation_id":"111c6d87-f5b3-4a7a-9ceb-235da15256d4","resolution":{"observed_at":"2026-06-28T02:58:52.293969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T02:58:52.293969Z","title":"A PAC-Bayesian approach to generalization bounds for graph neural networks,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.06293","last_updated":"2026-06-04T15:31:21Z","snapshot_observed_at":"2026-08-08T10:51:57.500235Z","submitted_at":"2026-06-04T15:31:21Z","title":"PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-06-28T02:58:52.293969Z"},"links":{"citing_paper":"/paper/2606.06293"},"observation_digest":"sha256:9d140e892f31697ac29e35068bc5d8e61dea6b45a3f88beac137e4ca2f8d2f40","observation_id":"197c256b-cc82-48aa-ab36-a4a7eaf201c9","resolution":{"observed_at":"2026-06-28T02:58:52.293969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T02:58:52.293969Z","title":"Generalization in graph neural networks: Improved PAC-Bayesian bounds on graph diffusion,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.06293","last_updated":"2026-06-04T15:31:21Z","snapshot_observed_at":"2026-08-08T10:51:57.500235Z","submitted_at":"2026-06-04T15:31:21Z","title":"PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-06-28T02:58:52.293969Z"},"links":{"citing_paper":"/paper/2606.06293"},"observation_digest":"sha256:a48ce3b607358155bd8f61f93041dafc813a52c1aebb03e945036b554902ae1f","observation_id":"98462212-f2b3-48e7-b246-f19cde4cd099","resolution":{"observed_at":"2026-06-28T02:58:52.293969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2604.10553","last_updated":"2026-04-12T09:52:27Z","snapshot_observed_at":"2026-07-06T22:59:09.778842Z","submitted_at":"2026-04-12T09:52:27Z","title":"Topology-Aware PAC-Bayesian Generalization Analysis for Graph Neural Networks","version":1},"cited_work":{"arxiv_id":"2604.10553","doi":null,"metadata_source":"pith","pith_arxiv_id":"2604.10553","snapshot_observed_at":"2026-07-02T11:46:55.892684Z","title":"Topology-Aware PAC-Bayesian Generalization Analysis for Graph Neural Networks","venue":"cs.LG","work_id":"f8882fb6-1298-4fe4-8d77-3c9c8374f2c4","year":2026},"citing_paper":{"arxiv_id":"2606.06293","last_updated":"2026-06-04T15:31:21Z","snapshot_observed_at":"2026-08-08T10:51:57.500235Z","submitted_at":"2026-06-04T15:31:21Z","title":"PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-06-28T02:58:52.293969Z"},"links":{"cited_paper":"/paper/2604.10553","citing_paper":"/paper/2606.06293"},"observation_digest":"sha256:adccc12e6766444a3185015dc4c2f7bd9c7c3a3530e650e5a33794a215654cca","observation_id":"2f408fa7-3789-4764-ac95-233a6a676fe7","resolution":{"observed_at":"2026-07-02T11:46:55.894000Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T02:58:52.293969Z","title":"A PAC-Bayes analysis of adversarial robustness,","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2606.06293","last_updated":"2026-06-04T15:31:21Z","snapshot_observed_at":"2026-08-08T10:51:57.500235Z","submitted_at":"2026-06-04T15:31:21Z","title":"PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-06-28T02:58:52.293969Z"},"links":{"citing_paper":"/paper/2606.06293"},"observation_digest":"sha256:16b13191f73b48486f45479943890805672535288091224cb204adf8a9808f94","observation_id":"9dec34f9-2754-490f-974c-ae568d073d44","resolution":{"observed_at":"2026-06-28T02:58:52.293969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T02:58:52.293969Z","title":"PAC-Bayesian spectrally-normalized bounds for adversarially robust generalization,","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2606.06293","last_updated":"2026-06-04T15:31:21Z","snapshot_observed_at":"2026-08-08T10:51:57.500235Z","submitted_at":"2026-06-04T15:31:21Z","title":"PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-06-28T02:58:52.293969Z"},"links":{"citing_paper":"/paper/2606.06293"},"observation_digest":"sha256:cef7bc1b041cdd959848f16ba1a9dd06668b5c89f7141942727090c7b89c9fd0","observation_id":"238d3564-e4db-4cee-8d1f-200a7c951117","resolution":{"observed_at":"2026-06-28T02:58:52.293969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2402.04038","last_updated":"2024-07-06T05:42:19Z","snapshot_observed_at":"2026-08-10T11:25:58.597232Z","submitted_at":"2024-02-06T14:34:17Z","title":"PAC-Bayesian Adversarially Robust Generalization Bounds for Graph Neural Network","version":2},"cited_work":{"arxiv_id":"2402.04038","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2402.04038","snapshot_observed_at":"2026-07-02T11:46:55.898163Z","title":"PAC-Bayesian adversarially robust generalization bounds for graph neural network","venue":null,"work_id":"0c131df6-d276-420b-99e5-780e654d039b","year":2024},"citing_paper":{"arxiv_id":"2606.06293","last_updated":"2026-06-04T15:31:21Z","snapshot_observed_at":"2026-08-08T10:51:57.500235Z","submitted_at":"2026-06-04T15:31:21Z","title":"PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-06-28T02:58:52.293969Z"},"links":{"cited_paper":"/paper/2402.04038","citing_paper":"/paper/2606.06293"},"observation_digest":"sha256:9fff8f7895dd03f45d57255e7a8d244fe4b5cb4ba9e31ae9a87a5354bd12e045","observation_id":"a9003edb-75cf-423a-bf33-1106b786d6cd","resolution":{"observed_at":"2026-07-02T11:46:55.899885Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2601.08100","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-07-02T11:46:55.901068Z","title":"Towards a unified pac-bayesian framework for norm-based generalization bounds","venue":null,"work_id":"ac280742-ff86-43ef-822b-3b78683f7914","year":2026},"citing_paper":{"arxiv_id":"2606.06293","last_updated":"2026-06-04T15:31:21Z","snapshot_observed_at":"2026-08-08T10:51:57.500235Z","submitted_at":"2026-06-04T15:31:21Z","title":"PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-06-28T02:58:52.293969Z"},"links":{"citing_paper":"/paper/2606.06293"},"observation_digest":"sha256:a103eca24d13c0fb38c20a655ffb46540215f9c6b6989426c16163def468bf81","observation_id":"05dce1fe-ca48-4184-bd4e-69c347606e9e","resolution":{"observed_at":"2026-07-02T11:46:55.902682Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T02:58:52.293969Z","title":"Discriminative embeddings of latent variable models for structured data,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2606.06293","last_updated":"2026-06-04T15:31:21Z","snapshot_observed_at":"2026-08-08T10:51:57.500235Z","submitted_at":"2026-06-04T15:31:21Z","title":"PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-06-28T02:58:52.293969Z"},"links":{"citing_paper":"/paper/2606.06293"},"observation_digest":"sha256:06c81227a3fc0c1aada6355ee3dbe7ad4a5a0964323c8bebcbc594d728a4e436","observation_id":"8f84a057-7678-4a1e-810d-6784fdc667f5","resolution":{"observed_at":"2026-06-28T02:58:52.293969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T02:58:52.293969Z","title":"Pardo,Statistical Inference Based on Divergence Measures","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2606.06293","last_updated":"2026-06-04T15:31:21Z","snapshot_observed_at":"2026-08-08T10:51:57.500235Z","submitted_at":"2026-06-04T15:31:21Z","title":"PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-06-28T02:58:52.293969Z"},"links":{"citing_paper":"/paper/2606.06293"},"observation_digest":"sha256:ecb96ed0d38d5de5cee8b4fb9391027f404a3b943c7652f57166b926d6c206e4","observation_id":"4e8d67fe-a7ca-4d0a-b834-2e54f36783a1","resolution":{"observed_at":"2026-06-28T02:58:52.293969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-28T02:58:52.293969Z","title":"Hanson-Wright inequality and sub- gaussian concentration,","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2606.06293","last_updated":"2026-06-04T15:31:21Z","snapshot_observed_at":"2026-08-08T10:51:57.500235Z","submitted_at":"2026-06-04T15:31:21Z","title":"PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-06-28T02:58:52.293969Z"},"links":{"citing_paper":"/paper/2606.06293"},"observation_digest":"sha256:24caff0e275817b4990e1a17a6be91d4f270268144e79e29cd3feffb1db83f7b","observation_id":"e3da2fcc-259c-42c0-abd3-5c4e063b0d1a","resolution":{"observed_at":"2026-06-28T02:58:52.293969Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2606.06293","last_updated":"2026-06-04T15:31:21Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-08T10:51:57.500235Z","submitted_at":"2026-06-04T15:31:21Z","title":"PAC-Bayesian Adversarially Robust Generalization for Message Passing Graph Neural Networks: A Sensitivity Analysis"},"reference_resolution":{"displayed":42,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":37,"verified_exact":4,"verified_fuzzy":0},"total_outbound_references":42},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 42 of 42 outbound references and 0 inbound Pith citation observations for arXiv:2606.06293."}