{"as_of":"2026-08-18T19:07:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:82af1774177da1d5584a43c5fe700a3dffcb60ecf283060bf4c2bbc26404cedf","coverage":[{"denominator":63,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":63,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T18:14:08.712610Z","state":"measured"},{"denominator":63,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":63,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-18T06:34:40.430872+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/2507.18804/citation-record","integrity":"/paper/2507.18804/integrity","json":"/paper/2507.18804/citation-record.json","paper":"/paper/2507.18804"},"outbound":[{"citation":{"cited_paper":{"arxiv_id":"1609.02907","last_updated":"2017-02-22T09:55:36Z","snapshot_observed_at":"2026-08-17T10:49:36.026134Z","submitted_at":"2016-09-09T19:48:41Z","title":"Semi-Supervised Classification with Graph Convolutional Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.02907","snapshot_observed_at":"2026-08-15T18:14:08.506578Z","title":"Semi-supervised classification with graph convolutional networks,","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.506578Z"},"links":{"cited_paper":"/paper/1609.02907","citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:e4d6985c6326d25fafde0726482e881d13dd24c14735422a9b8b015e607fd68a","observation_id":"fcb48bae-4d24-464b-aa80-1f8be2876af6","resolution":{"observed_at":"2026-08-15T18:14:08.506578Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:09.325752Z","title":"Graph embedding on biomedical networks: methods, applications and evaluations,","venue":null,"work_id":"f2924b4c-f16c-4d9f-806a-564725874d65","year":2020},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.511622Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:af20cfab84e9683b35cad5375b6aa2e61abaef023cdc04764489eb29920f0e67","observation_id":"0cd008af-cea0-40ce-9e6c-29bdf460e681","resolution":{"observed_at":"2026-08-15T18:14:09.329307Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:09.315819Z","title":"A comprehensive survey on graph neural networks,","venue":null,"work_id":"cac5bf6e-e992-4310-a710-92a2fe8e97e6","year":2020},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.516030Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:852bc164fc0f9916ca3b85a0ea41d46395de58e0e5e059d6e4020864e247354c","observation_id":"16375d37-93c2-43c6-bd26-034ba5a105f0","resolution":{"observed_at":"2026-08-15T18:14:09.319298Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:09.306546Z","title":"Ironman: Gnn-assisted design space exploration in high- level synthesis via reinforcement learning,","venue":null,"work_id":"55d27a64-b26b-4f70-9c48-c95f65cd3cac","year":2021},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.519429Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:9302cca97f290fa3df58c249278c907f95767eb118c3bbdfc49df6b22cb559a4","observation_id":"a958f2f1-df54-416a-be3d-aa65d5d2f805","resolution":{"observed_at":"2026-08-15T18:14:09.309717Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:09.295891Z","title":"Build a gnn-based real-time fraud detection solution using amazon sagemaker, amazon neptune, and the deep graph library","venue":null,"work_id":"6e784121-ff69-454d-b57e-0a4feae9f9c4","year":2024},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.523789Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:eefca21fb9970a056288347f579fcecafb92a538f6e17b2ad4feb57e5d193368","observation_id":"213d8873-d979-45a5-b39d-3f245bd1b5c3","resolution":{"observed_at":"2026-08-15T18:14:09.300058Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:09.285135Z","title":"Financial fraud detection using graph neural networks: A systematic review,","venue":null,"work_id":"8c16d60d-0b6c-4fda-9e11-2d4da6b981b1","year":2023},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.527407Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:1cfa1fbeaada318c18a50c63f2064dd1343715f4128e814a1e6564ec2a2668fe","observation_id":"d8ba7f1a-3fc6-4cdd-bcbb-5fb3b48a914e","resolution":{"observed_at":"2026-08-15T18:14:09.289670Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2402.14708","last_updated":"2024-11-27T12:15:06Z","snapshot_observed_at":"2026-08-16T14:16:10.211477Z","submitted_at":"2024-02-22T17:08:09Z","title":"CaT-GNN: Enhancing Credit Card Fraud Detection via Causal Temporal Graph Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2402.14708","snapshot_observed_at":"2026-08-15T18:14:08.530947Z","title":"Cat-gnn: Enhancing credit card fraud detection via causal temporal graph neural networks,","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.530947Z"},"links":{"cited_paper":"/paper/2402.14708","citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:c332ebee1df5154a31acf0431f605f54e8a24e3ac752de4b2b686a770accfefc","observation_id":"1dc9f037-15fb-400f-985b-879db01ed55b","resolution":{"observed_at":"2026-08-15T18:14:08.530947Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1812.00076","last_updated":"2018-11-30T22:18:45Z","snapshot_observed_at":"2026-08-14T17:50:19.920026Z","submitted_at":"2018-11-30T22:18:45Z","title":"Scalable Graph Learning for Anti-Money Laundering: A First Look","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1812.00076","snapshot_observed_at":"2026-08-15T18:14:08.534400Z","title":"Scalable graph learning for anti-money laundering: A first look,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.534400Z"},"links":{"cited_paper":"/paper/1812.00076","citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:8a9cbdd69db168b0182ad9deb724079472680dd336a8b842bdd1d4ef70912816","observation_id":"a9e1ac29-d268-4e84-bfd4-c189e1ccd78b","resolution":{"observed_at":"2026-08-15T18:14:08.534400Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:09.274904Z","title":"Enhancing graph neural network-based fraud detectors against camouflaged fraudsters,","venue":null,"work_id":"a645b409-da72-4229-9e36-8dd0f0ad27e2","year":2020},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.537812Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:e558ddef5cfe9173e5d643b86aa96ac37d32ba38ceb37f4b1e994d4a0f4b07bf","observation_id":"8054dc5f-808f-469e-acf1-18dee2d6d33f","resolution":{"observed_at":"2026-08-15T18:14:09.278560Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:09.264467Z","title":"αcyber: Enhancing robustness of android malware detection system against adversarial attacks on heterogeneous graph based model,","venue":null,"work_id":"297ec926-1297-4943-af99-75f1e6da1e62","year":2019},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.540903Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:24b23eff022f1b8c41d795f9dbc36e5a1cda2968d24f169eb5bb935a0eae9a65","observation_id":"8ab9c7b5-2aaf-432e-a640-07f9891184dc","resolution":{"observed_at":"2026-08-15T18:14:09.267891Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:09.254402Z","title":"Graph neural networks for hardware vulnerability analysis—can you trust your gnn?,","venue":null,"work_id":"12274e6f-ede6-45a5-a97a-9fdb4ec413df","year":2023},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.544078Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:864c1962362a6341c8b1c0214e3f5096ee5566580cd2459acf87ee10920b8796","observation_id":"d66ecc91-ee00-4190-b14e-483a9a3a6f13","resolution":{"observed_at":"2026-08-15T18:14:09.257934Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:09.244576Z","title":"Graph neural networks for vulnerability detection: A counterfactual explanation,","venue":null,"work_id":"016e310d-39c0-4282-8b6a-7061586a5862","year":2024},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.547229Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:24ab038f24f0da8ea708bcdcbfca33a8866e64813131946df5561e6ae3dd4964","observation_id":"f36fe6d9-adb7-49c2-b278-6fd0eec62ace","resolution":{"observed_at":"2026-08-15T18:14:09.248169Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:09.236051Z","title":"Fraud Reports by Federal Trade Commission","venue":null,"work_id":"e2bce157-2a18-4c73-9137-fcb1997d908d","year":2024},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.550358Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:80d0ed0b63d5afd258a8e94eaf9c7bd6a02c4b74daf6949ad598766918eccd5a","observation_id":"be765412-e8dd-4e87-9998-f725237be21d","resolution":{"observed_at":"2026-08-15T18:14:09.239297Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:09.226945Z","title":"Value of fraud loss in the United States in 2022, by payment method","venue":null,"work_id":"1ba7f677-8a7e-4fe1-9f76-e32a42d569d6","year":2022},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.553430Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:3a917bf1943c25d23f6231413caaa1f09b79532f9743651921b8c730c9ef9fbc","observation_id":"2bf19992-4549-410a-9f67-db519f16e736","resolution":{"observed_at":"2026-08-15T18:14:09.230266Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:09.216938Z","title":"Robust machine learning systems: Challenges, current trends, perspectives, and the road ahead,","venue":null,"work_id":"fb868626-1623-418e-944d-2e8f290948fa","year":2020},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.557142Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:7a3df89688d5d8113875f9e60640dd032b81b3efd5bf84571cd95d7bd85600e0","observation_id":"9e22f67b-c56a-43e6-ae50-5c5ffa99d119","resolution":{"observed_at":"2026-08-15T18:14:09.220113Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:09.207908Z","title":"Neutron soft error rate measurements in a 90-nm cmos process and scaling trends in sram from 0.25-/spl mu/m to 90-nm generation,","venue":null,"work_id":"3582c836-6f9a-488c-8275-8034fe14549e","year":2003},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.560441Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:951a8f20403cf3b32bf2a545af4c6d97f6b5ed4fe935009fdf1e1350810f956a","observation_id":"17c1057e-24ea-40e6-a127-9f151499125b","resolution":{"observed_at":"2026-08-15T18:14:09.211330Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:09.198528Z","title":"Razor: circuit-level correction of timing errors for low- power operation,","venue":null,"work_id":"e126f004-2ac2-4e71-b8a7-08cbea82293c","year":2004},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.563518Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:a67fc17e1af90b6ab9d58dde53c0adbeb0f720be5fa5f5f18c3b68e3c6ec879a","observation_id":"4326ae73-8efd-4286-bdfb-58dd091463d9","resolution":{"observed_at":"2026-08-15T18:14:09.202183Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:09.188819Z","title":"Impact of technology and voltage scaling on the soft error susceptibility in nanoscale cmos,","venue":null,"work_id":"a4100a14-556d-4efa-adc9-6c0b68d47503","year":2008},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.566808Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:aca2e82a5cd662116e6fba76b1756974c9d5a148755902071972c1a30d10dd90","observation_id":"59c17fa4-ee16-4023-b37b-9385e05ed24d","resolution":{"observed_at":"2026-08-15T18:14:09.192807Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:09.178731Z","title":"Thundervolt: enabling aggressive voltage underscaling and timing error resilience for energy efficient deep learning accelera- tors,","venue":null,"work_id":"746941ac-0b9e-4396-9fee-5102dae20a1a","year":2018},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.570466Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:3f4f2af9e55c4adc82d377eab287b1b7e759c52dc0bc8889baae6e38ad6180ae","observation_id":"2432b886-0582-47ef-bd63-12b1fb31a1a8","resolution":{"observed_at":"2026-08-15T18:14:09.182150Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2203.08989","last_updated":"2022-03-16T23:29:09Z","snapshot_observed_at":"2026-08-16T17:13:56.987555Z","submitted_at":"2022-03-16T23:29:09Z","title":"Detecting silent data corruptions in the wild","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2203.08989","snapshot_observed_at":"2026-08-15T18:14:08.573645Z","title":"Detecting silent data corruptions in the wild,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.573645Z"},"links":{"cited_paper":"/paper/2203.08989","citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:7e34948d967deec371cfa668ef70b04584d00d31bf979b353b516cb2a4c1188a","observation_id":"c3ded546-bc53-4a35-b070-861ad9044534","resolution":{"observed_at":"2026-08-15T18:14:08.573645Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:09.168776Z","title":"Detection and prevention of silent data corruption in an exabyte-scale database system,","venue":null,"work_id":"c024d7ec-3a8c-4279-bfd6-124ca3aa331b","year":2022},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.577088Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:84fb1ac3bbf58e48280528517156f177b36120baa36ae241c9c1b05c490c1744","observation_id":"c6d47ddb-f4fe-47c4-bc25-a16c1f8c7266","resolution":{"observed_at":"2026-08-15T18:14:09.172113Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:09.159835Z","title":"An assessment of vulnerability of hardware neural networks to dynamic voltage and temperature variations,","venue":null,"work_id":"4c951589-2a8d-434c-a2e7-0d883a07df21","year":2017},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.579952Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:7778a97ac7f74f66f5c9392723206b389963791c440098d156b1497090ee730a","observation_id":"5fdee1f0-a851-47a5-aa6e-8a6d8ee68070","resolution":{"observed_at":"2026-08-15T18:14:09.163202Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:09.150289Z","title":"Dnn engine: A 28-nm timing-error tolerant sparse deep neural network processor for iot applications,","venue":null,"work_id":"abc095a3-ee34-4d3e-9c04-477c66bd5e6d","year":2018},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.583180Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:bcd32de15a065af0d1989b8b975551f71ca41f5fb8bb010037d5f4c9ed54d4ec","observation_id":"cf4558b6-7c58-411c-9bae-7de1b06ce61a","resolution":{"observed_at":"2026-08-15T18:14:09.153702Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:09.139242Z","title":"Ares: A framework for quantifying the resilience of deep neural networks,","venue":null,"work_id":"69f7e0f8-e7f9-4403-a838-ec0887e3d4cf","year":2018},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.586320Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:8b6b7b3ece17268f48c09550e02896553a75fcfa23854b19f5f555ea5a0f818d","observation_id":"93ed2576-5863-4201-922b-d7067e9fb30c","resolution":{"observed_at":"2026-08-15T18:14:09.143506Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:09.129409Z","title":"Bit error robustness for energy-efficient dnn accelera- tors,","venue":null,"work_id":"adf987d7-bd05-4f4d-9706-cc4cc1026c79","year":2021},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.589182Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:4c593beab355b9212a5f748de3f1da2a12b4370db06b634d02307fa545566443","observation_id":"38409f5b-1627-4cd8-8042-f4aa6ab2b577","resolution":{"observed_at":"2026-08-15T18:14:09.133073Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:09.118728Z","title":"Adversarial attacks and defenses on graphs,","venue":null,"work_id":"3dfb0343-ac2c-43af-bf94-ab2c4480382a","year":2021},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.592108Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:cc1d7e4aa955a9fb6b41e762017df6caddb206dc7108712b95aac81d261be035","observation_id":"66680a04-c3cc-4833-b842-686441445084","resolution":{"observed_at":"2026-08-15T18:14:09.122755Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:09.108661Z","title":"Adversarial attack and defense on graph data: A survey,","venue":null,"work_id":"8a2f9356-0edc-4228-952c-3d3011866305","year":2022},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.595438Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:eabcf6aa85f6a62e3dadf82e9a558d5afe6b266a6bb6e9e163f22c8ce2b6f139","observation_id":"87f3a3a6-bbd2-4dbc-a689-85a85c486e81","resolution":{"observed_at":"2026-08-15T18:14:09.112409Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2212.03475","last_updated":"2023-04-24T15:38:27Z","snapshot_observed_at":"2026-08-16T16:10:25.795417Z","submitted_at":"2022-12-07T06:14:14Z","title":"PyGFI: Analyzing and Enhancing Robustness of Graph Neural Networks Against Hardware Errors","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2212.03475","snapshot_observed_at":"2026-08-15T18:14:08.598388Z","title":"Pygfi: Analyzing and enhancing robustness of graph neural networks against hardware errors,","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.598388Z"},"links":{"cited_paper":"/paper/2212.03475","citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:553472968fae6aa850c5f32da4169802d03e056a3a11666bc56b821bfd2afff2","observation_id":"4046f009-62c7-4916-8982-a79f970c5248","resolution":{"observed_at":"2026-08-15T18:14:08.598388Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:09.099499Z","title":"Graph structure learning for robust graph neural networks,","venue":null,"work_id":"9b9d5198-9369-49a7-804d-7b9283971ad4","year":2020},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.601612Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:92f91c0b3749f9305893533e5932c7e1a62abfb6c49e78c27e75cfb34d1224ed","observation_id":"69682af3-8db4-4f96-8153-9856be9a6179","resolution":{"observed_at":"2026-08-15T18:14:09.102965Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:09.089202Z","title":"Topology attack and defense for graph neural networks: an optimization perspective,","venue":null,"work_id":"7e269442-078b-49b9-beab-1c721393e18d","year":2019},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.604520Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:faa1f9073d5e29cf06784365646cf67ab6eff1f1fa362e843723b4c873ffad31","observation_id":"5086cea9-e826-455e-957a-806da225ab4d","resolution":{"observed_at":"2026-08-15T18:14:09.092376Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:09.080035Z","title":"Robustness of graph neural networks at scale,","venue":null,"work_id":"be0baf78-16bc-46a4-8835-2b3fbc4d3ce0","year":2021},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.607431Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:7f5040128133d7eaf43b29840405558809fb03a8cd0121dfdf687156b1ea38bd","observation_id":"41895313-45b3-4853-9c4d-73379018c200","resolution":{"observed_at":"2026-08-15T18:14:09.083449Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T18:14:08.611304Z","title":"Fast graph representation learning with PyTorch Geometric,","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.611304Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:4740a418e7085988ba4554e36144bbdb7833af67f2072b4565322946bb4fdda2","observation_id":"c7183d44-8830-417a-94ee-31d0579651ad","resolution":{"observed_at":"2026-08-15T18:14:08.611304Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:09.063769Z","title":"How powerful are graph neural networks?,","venue":null,"work_id":"be4d3cc9-71a6-4b4a-a08b-afac86a76cb2","year":2018},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.614506Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:49d535f896981a540973e3091122a46f3a27ee5cbc29cd1af35b7fa880975679","observation_id":"1567428c-814a-4616-917e-6922aee260d5","resolution":{"observed_at":"2026-08-15T18:14:09.067418Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:09.054057Z","title":"Computing graph neural networks: A survey from algorithms to accelerators,","venue":null,"work_id":"962c6dd0-4ace-4009-af06-3f17faca3388","year":2021},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.617404Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:6a1081819dd857696d80e433937d93b8c72554196d11e08f45c8470e183c16cf","observation_id":"f5346f65-8a37-47e8-a8e4-fc079cad802e","resolution":{"observed_at":"2026-08-15T18:14:09.057466Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:09.044461Z","title":"Empowering graph representation learning with test-time graph transformation,","venue":null,"work_id":"1c4b07c7-41a9-42e3-8a52-452d9ac84b00","year":2023},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.620553Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:ced256f84dd9750a375290889282a47f356cae8ade0290622bf60d12a3f6e091","observation_id":"8f6413d4-f87c-4307-9195-741ba9f21610","resolution":{"observed_at":"2026-08-15T18:14:09.047991Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:09.035828Z","title":"Resilient low voltage accelerators for high energy efficiency,","venue":null,"work_id":"d1e88c05-e195-4866-bcfc-41310e891014","year":2019},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.623917Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:3d4bfe4f35ff9f81ae80d38dfa1701ee412555995bce86bd101a7cee3eb98cee","observation_id":"f78dca07-f126-4a35-9074-199407af31cf","resolution":{"observed_at":"2026-08-15T18:14:09.039029Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:09.026924Z","title":"On characterizing near-threshold sram failures in finfet technology,","venue":null,"work_id":"15837f43-ef91-4e99-9cd2-495f7a6b9600","year":2017},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.627029Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:3462ebce966611120df1109836a69f916cfa2f1a0f7c147c9054cbb013426696","observation_id":"fb29bf03-fdf2-44a5-bc1a-9c5524d75572","resolution":{"observed_at":"2026-08-15T18:14:09.030186Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:09.017637Z","title":"Matic: Learning around errors for efficient low-voltage neural network accelerators,","venue":null,"work_id":"f2290683-b854-449d-a220-788b3fbe2235","year":2018},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.631059Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:6ea3d1ddfdf3cb279e39c9f56f20e787f96d39c393e5628261a04a87875e1c57","observation_id":"b1a6660e-511f-4cbb-a523-e48f601a098b","resolution":{"observed_at":"2026-08-15T18:14:09.020897Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:09.008280Z","title":"The theory of error-correcting codes,","venue":null,"work_id":"fe739997-9df3-438e-8e73-7e117206fff1","year":1977},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.633902Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:b4eeab77f5b5f516e658654561b7652ce001f48dba75dcf9d0f9a7c561f2e716","observation_id":"00beae5e-de2b-4286-bc82-f5990509ecfe","resolution":{"observed_at":"2026-08-15T18:14:09.011438Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:08.998966Z","title":"Chapter 5 - error coding techniques,","venue":null,"work_id":"3c8eeee4-1205-41ac-92fc-f13687a31584","year":2008},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.637857Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:535dd496a40a35a96fc272a2d016d33af53f52a7275e10680945165adc29a204","observation_id":"44346e8a-9c50-4cd4-84a6-75ed43aedef6","resolution":{"observed_at":"2026-08-15T18:14:09.002346Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:08.988995Z","title":"Berry: Bit error robustness for energy-efficient reinforce- ment learning-based autonomous systems,","venue":null,"work_id":"09019ef4-a4cc-489f-8033-2cbd16e94c0d","year":2023},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.641723Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:9b6800247e6ef7d0dc228dabcc9edf17d0b0ab9a92307e08e59762ac3b7a9fa2","observation_id":"3bf35214-18b8-4b3d-99a2-bd037a687b07","resolution":{"observed_at":"2026-08-15T18:14:08.992415Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:08.978290Z","title":"Mulberry: Enabling bit-error robustness for energy- efficient multi-agent autonomous systems,","venue":null,"work_id":"58801320-d419-456e-a15b-a47ea77353f2","year":2024},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.645017Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:c1bf625093c2c901c18f1cca01300e9108a1d291a114bf8f3db13e69ceb0b561","observation_id":"5f8f6170-4eab-415f-802a-e6499ec4ece5","resolution":{"observed_at":"2026-08-15T18:14:08.982169Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:08.968019Z","title":"Greentpu: Improving timing error resilience of a near- threshold tensor processing unit,","venue":null,"work_id":"aa530e9e-3384-430f-ba21-7af4089f9fc6","year":2019},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.648261Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:677a5179c8b35f77b620bef80293b31defc7611c532dd0be1f62ff9ddb788e00","observation_id":"587dee62-4aa2-4131-bad1-77046a83ada7","resolution":{"observed_at":"2026-08-15T18:14:08.971575Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:08.958434Z","title":"Read: Reliability-enhanced accelerator dataflow opti- mization using critical input pattern reduction,","venue":null,"work_id":"d7d9f044-b7f7-466e-b765-abcdf4e4da35","year":2023},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.651499Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:5364c91779c43a7b547531a3db7f423afbbdbd9b9d5a73a20caa1c63a8788574","observation_id":"2b463a22-47be-4103-b3aa-1b4afb50ea4d","resolution":{"observed_at":"2026-08-15T18:14:08.962542Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:08.949257Z","title":"Sparse dnns with improved adversarial robustness,","venue":null,"work_id":"3c9f4642-415e-4d53-8cf0-421d04fb95ff","year":2018},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.654437Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:451169954ae1e68fcc940d27f598e4d7802917d6ce5f978ffa1d84443d35e8fd","observation_id":"c2f3d749-f633-4021-8fb5-e0507e00fd4f","resolution":{"observed_at":"2026-08-15T18:14:08.952666Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:08.940084Z","title":"Reliability evaluation of pruned neural networks against errors on parameters,","venue":null,"work_id":"e35d6b52-aa06-4787-9d06-28c4e104ceac","year":2020},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.658089Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:9600d1af1bb4c6ba5dd610056afc7221ff9bff747c9e1bb0ac0a3a17ae517330","observation_id":"5730fe1b-2a5e-4be1-91a5-b52e73ae8a56","resolution":{"observed_at":"2026-08-15T18:14:08.943299Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:08.931080Z","title":"Understanding structural vulnerability in graph convo- lutional networks,","venue":null,"work_id":"3f32f84b-0ca6-49dd-a2e9-d810e49177c0","year":2021},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.661187Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:c28bc156cfe57555cd91893f58fc69a4592cafd741fc827f64f48281ddde0501","observation_id":"0d2ecfda-3fdb-4080-9080-502b2c74153d","resolution":{"observed_at":"2026-08-15T18:14:08.934402Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:08.921939Z","title":"Link prediction based on graph neural net- works,","venue":null,"work_id":"9c38a256-c2d9-44cc-adf2-715c12e2445b","year":2018},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.664869Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:6d4fa0c5af4a2c2ffe7d2705992605f6dfa28218782c9ef38e52b9eb4c7ab94f","observation_id":"acdfa1dc-201f-4899-8661-51a0e35cddff","resolution":{"observed_at":"2026-08-15T18:14:08.925421Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:08.912484Z","title":"Evaluating graph neural networks for link prediction: Current pitfalls and new benchmarking,","venue":null,"work_id":"3e8d8476-2863-4d7b-b952-69389cda8849","year":2024},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.668423Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:9af8fe92a1afbcb60ebffa75214b09203ed8fc2009dbc19d5699b8fafce52660","observation_id":"a6744941-e104-4963-a2d8-28cfa000a553","resolution":{"observed_at":"2026-08-15T18:14:08.915978Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:08.902091Z","title":"Birds of a feather: Homophily in social networks,","venue":null,"work_id":"96c6cc7a-dee6-4f3a-a9d0-444f1a3223f4","year":2001},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.671346Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:3fabc62727d140ebe9bb4ca34815b0b0a927341335f44e2864bc3bb3f33a0629","observation_id":"d4c30283-232d-4b6b-bb94-f32d158d8bf4","resolution":{"observed_at":"2026-08-15T18:14:08.905708Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:08.891840Z","title":"Principal neighbourhood aggregation for graph nets,","venue":null,"work_id":"458468c6-5522-40cb-bc07-e22e27d04fa2","year":2020},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.674530Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:e85b4ce285e186e34c47eecfae147baa039aabee9bf0006690d192b06788c390","observation_id":"5864b1b6-ab04-4705-b978-f2b88730362f","resolution":{"observed_at":"2026-08-15T18:14:08.895828Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1710.10903","last_updated":"2018-02-04T19:13:29Z","snapshot_observed_at":"2026-08-13T22:35:40.714745Z","submitted_at":"2017-10-30T12:41:12Z","title":"Graph Attention Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.10903","snapshot_observed_at":"2026-08-15T18:14:08.677321Z","title":"Graph attention networks,","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.677321Z"},"links":{"cited_paper":"/paper/1710.10903","citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:ac8674583e06622a47bf16e65f1854bb0f877552b6049c5cab98ff46b56c2f46","observation_id":"9a5b3182-4354-4263-9430-d9df8fea37f2","resolution":{"observed_at":"2026-08-15T18:14:08.677321Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:08.882197Z","title":"Revisiting semi-supervised learning with graph embed- dings,","venue":null,"work_id":"06b07c4b-2bfb-4d30-ad8a-7965934408cc","year":2016},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.680941Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:09a0594c9add29767574fbcbacff5f36e2fde76fa6b70d8fd5207cb32e2fd393","observation_id":"a9ef8b30-1dc8-40f7-8054-abfc4eb07792","resolution":{"observed_at":"2026-08-15T18:14:08.885641Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:08.872858Z","title":"Pubmed dataset","venue":null,"work_id":"bc4d0115-62fa-4857-ab2b-71937bd6fb14","year":2024},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.683978Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:ef66884081b63b6ba70fb5e89c0ee71dca2770cfcd4e675044c3159a9580087e","observation_id":"efbcf338-82f9-4418-a0de-7aefbae51a74","resolution":{"observed_at":"2026-08-15T18:14:08.876180Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:08.863070Z","title":"Subgraph matching kernels for attributed graphs,","venue":null,"work_id":"fb818c63-aa1a-440a-80e4-94588585fcf6","year":2012},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.687004Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:9d121c02135b06cd10482d4c4bcc1710d115b943f16a78cd2b85364dd559a6e5","observation_id":"81dda0a7-a66e-4373-9a3f-bc51d8ae60a6","resolution":{"observed_at":"2026-08-15T18:14:08.866548Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:08.853563Z","title":"Protein function prediction via graph kernels,","venue":null,"work_id":"6ee5ac61-9c60-463f-8c82-cc2aec0be749","year":2005},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.689810Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:c63347c8ff4e68cb47e5886e49c12b7552de67375775aa86bbd6fd944433dcb2","observation_id":"7a70ec93-0d60-43a7-ad09-98839bde6f26","resolution":{"observed_at":"2026-08-15T18:14:08.856997Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+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":"2026-08-15T18:14:08.693584Z","title":"The network data repository with interactive graph analytics and visualization,","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":57,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.693584Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:f1aee60504ee4219fdeaebf601d0b74cb17041685b164f4ee607147284e6ff4f","observation_id":"848d026f-01c9-4f6e-938c-6bc119d33ec1","resolution":{"observed_at":"2026-08-15T18:14:08.693584Z","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":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:08.838408Z","title":"Microsoft academic graph: When experts are not enough,","venue":null,"work_id":"63e6016f-1b36-4d30-b30e-8da84f645cf7","year":2020},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":58,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.696678Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:b69595fbec6e8af2920985c336b2c7dbd205a5fffd8861bca651b465c4d0b54d","observation_id":"c12e6b14-9d17-4229-852c-9d6375fd401b","resolution":{"observed_at":"2026-08-15T18:14:08.841943Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:08.827847Z","title":"The extreme classification repository: Multi-label datasets and code,","venue":null,"work_id":"706abfc2-186c-4076-8164-f997eacc99e5","year":2016},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":59,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.699747Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:a7bc78d49bddd53712941a0d883fb33c31728c5424a0f7b432615a0675ceb4f0","observation_id":"07693846-6665-4380-aca1-843f2da199a6","resolution":{"observed_at":"2026-08-15T18:14:08.831288Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:08.817627Z","title":"Towards sparsification of graph neural networks,","venue":null,"work_id":"1f3fefe2-98d9-4f33-879b-118274a9dd90","year":2022},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":60,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.702642Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:eb2b14d8d25366b15880c78df77863471a260678c191af8dbd74af9aa359f605","observation_id":"dd68dedd-fa0d-4d04-9e55-f2dc87cba325","resolution":{"observed_at":"2026-08-15T18:14:08.821209Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:08.807697Z","title":"Hydra: Pruning adversarially robust neural networks,","venue":null,"work_id":"b436b5a1-f5e3-4ba0-bb84-b5403821803b","year":2020},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":61,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.705744Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:c7825b24a043caf152109b9a36f67e0807b6a7f2b23d1c3f33b8b65072276263","observation_id":"c1f630a2-ea1e-4d84-a19e-979046e3ce99","resolution":{"observed_at":"2026-08-15T18:14:08.811715Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:08.798088Z","title":"Sparsity winning twice: Better robust generalization from more efficient training,","venue":null,"work_id":"d06069fe-97b4-463f-a7ef-ba0908c5df9c","year":2022},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":62,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.709450Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:047800f8bec7ecb6b15eebccbca86b22995fc925b0c64b52c35a0c71eca8edfd","observation_id":"26fe8c91-574f-4f83-bb5a-9f8adfa5e82a","resolution":{"observed_at":"2026-08-15T18:14:08.801452Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T18:14:08.786055Z","title":"Time and space complexity of graph convolutional networks,","venue":null,"work_id":"131ddb26-db65-4993-a7c8-64b49161aef1","year":2021},"citing_paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors","version":1},"reference_index":63,"source":"pdf_text","source_observed_at":"2026-08-15T18:14:08.712610Z"},"links":{"citing_paper":"/paper/2507.18804"},"observation_digest":"sha256:ae7f963b4b7920ccfe48c7efc41a5c373c35bf7e230e632671fd4f61ee7ef486","observation_id":"b8e297ce-6d0d-44e5-9a62-72ff3510b8f7","resolution":{"observed_at":"2026-08-15T18:14:08.791596Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-18T06:34:40.430872+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2507.18804","last_updated":"2025-07-24T21:03:44Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-17T09:24:18.177684Z","submitted_at":"2025-07-24T21:03:44Z","title":"Ralts: Robust Aggregation for Enhancing Graph Neural Network Resilience on Bit-flip Errors"},"reference_resolution":{"displayed":63,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":8,"verified_exact":0,"verified_fuzzy":55},"total_outbound_references":63},"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":"2026-08-18T06:34:40.430872+00:00","source":"crossref"},{"observed_at":"2026-08-18T06:34:34.496301+00:00","source":"retraction_watch"}],"thesis":"As of 18 August 2026, this Paper Citation Record lists 63 of 63 outbound references and 0 inbound Pith citation observations for arXiv:2507.18804."}