{"as_of":"2026-08-09T19:25:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:c7c08ea25234014ca34e9e58a33436598d9a3fcf4b94901ee2e8afd8a75daa66","coverage":[{"denominator":74,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":74,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-09T12:05:56.019965Z","state":"measured"},{"denominator":74,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":74,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+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/2502.02479/citation-record","integrity":"/paper/2502.02479/integrity","json":"/paper/2502.02479/citation-record.json","paper":"/paper/2502.02479"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-09T12:05:57.523891Z","title":"I., Grohe, M., and Lukasiewicz, T","venue":null,"work_id":"1f175f8f-7344-4fda-a806-30e269153ac4","year":2021},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.550685Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:804fca161b706734cdf237c57714144ed3de888871cd49c209c106dd754842ae","observation_id":"99d44308-eb30-4cd0-9931-a397c164f6ca","resolution":{"observed_at":"2026-08-09T12:05:57.530297Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:57.504758Z","title":"\\.I ., Grohe, M., and Lukasiewicz, T","venue":null,"work_id":"424dc62f-a519-4706-a112-cb2be72b559a","year":2021},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.558170Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:270d8c26775c449db961f3170900e524440d70f0e19c327b15ddc9601c5f1414","observation_id":"284ea08b-9f31-49be-ad12-a74db47c78c9","resolution":{"observed_at":"2026-08-09T12:05:57.510901Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:57.483836Z","title":null,"venue":null,"work_id":"018b7f4e-afe0-4bac-9fbe-383fe6f4d089","year":2003},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.564089Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:ed4de75a64acfd0e5fb1c5f9ef96baca413f6d79fdeebb1516309a492d6a3191","observation_id":"71040b04-5618-4de2-9797-bd8b40288622","resolution":{"observed_at":"2026-08-09T12:05:57.490332Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:57.461228Z","title":null,"venue":null,"work_id":"a43c8f48-9186-46ec-a3d9-384ef5c07303","year":2018},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.571852Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:2c8c564375132f5db2857d817bbd15bcd34405e048e8997cf1c29e38552c136b","observation_id":"c6adade2-067b-44be-9ff9-d707360b1100","resolution":{"observed_at":"2026-08-09T12:05:57.466667Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:57.443334Z","title":"and Yahav, E","venue":null,"work_id":"17adf513-f1f7-4254-99f1-a6c492bc2e7a","year":2021},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.579224Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:f8e6ff576abbef591aaf1c888aa459aaecf68893daedce49f559f0ba9f20b1de","observation_id":"703b6c69-2921-4063-ad10-70b98b7c9c34","resolution":{"observed_at":"2026-08-09T12:05:57.448905Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:57.425153Z","title":"G., Li, M","venue":null,"work_id":"f76d19ec-e26a-4448-b44a-38720db199ba","year":2020},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.585856Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:c91a5a747f08e3fab72c7352ba49cf5fe2bd09f0ed21afcd50ba457122319110","observation_id":"b3e84099-dea5-4cf1-aff0-28966017bd12","resolution":{"observed_at":"2026-08-09T12:05:57.431029Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2408.12334","last_updated":"2025-02-14T22:08:20Z","snapshot_observed_at":"2026-08-06T23:43:00.605927Z","submitted_at":"2024-08-22T12:22:00Z","title":"Boosting Graph Neural Network Expressivity with Learnable Lanczos Constraints","version":2},"cited_work":{"arxiv_id":"2408.12334","doi":null,"metadata_source":"pith","pith_arxiv_id":"2408.12334","snapshot_observed_at":"2026-08-09T12:05:56.203727Z","title":"Boosting Graph Neural Network Expressivity with Learnable Lanczos Constraints","venue":"cs.LG","work_id":"9dfcbfd6-1734-4e68-97d5-5ae25608a362","year":2024},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.594483Z"},"links":{"cited_paper":"/paper/2408.12334","citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:f387d62b898c4d42e226878864c681727381eca90ac76696bf004e5676c32b8a","observation_id":"89b6cb2b-6b60-417b-b962-5e4ae3898a9d","resolution":{"observed_at":"2026-08-09T12:05:56.210395Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:55.601899Z","title":"and Albert, R","venue":null,"work_id":null,"year":1999},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.601899Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:e10d023328177bea5ac8063b4cbdc4dc77284fea8e0e2b631456753a37ecfcc9","observation_id":"4aa152f4-33c6-4322-807b-9bb75d307c60","resolution":{"observed_at":"2026-08-09T12:05:55.601899Z","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":"2026-08-09T12:05:57.395840Z","title":"M., and Maron, H","venue":null,"work_id":"e598b761-601f-43bc-866c-12de174d2677","year":2022},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.609506Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:2128eb0f7ddce1838a405884f7f4c4be2b7a78c01bbb1e680d876e8851bae9ca","observation_id":"33f22b47-5fcf-4fae-bf77-a6e6878275c4","resolution":{"observed_at":"2026-08-09T12:05:57.400964Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:57.375324Z","title":"P., Shirobokov, S., Rossi, E., Frasca, F., Markovich, T., Hammerla, N., Bronstein, M","venue":null,"work_id":"ec69553f-76ed-4e77-9123-4c1aaf04f4e7","year":2023},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.615309Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:88a983796215c8685f47e5986a91ac3b15140b77362a87f38ab1fe0b6874e367","observation_id":"372befba-ab4f-4033-ae8e-f8a479bb1537","resolution":{"observed_at":"2026-08-09T12:05:57.382171Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:57.356661Z","title":"P., Shirobokov, S., Rossi, E., Frasca, F., Markovich, T., Hammerla, N., Bronstein, M","venue":null,"work_id":"388a7485-19b4-4ded-bb26-9d43e6408d8c","year":2023},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.621094Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:4310d03cb8d6c1766abaa337d6f793c0106322d49eef7412378f48529957562d","observation_id":"58748fc4-5e2e-4727-8b62-0deaf8dbe45e","resolution":{"observed_at":"2026-08-09T12:05:57.361940Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:55.627314Z","title":"Fastgcn: Fast learning with graph convolutional networks via importance sampling","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.627314Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:634698c30b034f07802f3fa17f778531b11e720e5b6bbca184a85748c6d84227","observation_id":"1acbc7bd-4dab-4994-b367-dbc25c113f25","resolution":{"observed_at":"2026-08-09T12:05:55.627314Z","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":"2026-08-09T12:05:57.329136Z","title":"Adaptive universal generalized pagerank graph neural network","venue":null,"work_id":"f8fb4d2e-7d40-4178-8d71-a74a0f5f61f8","year":2021},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.632396Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:837747ca133bb1d568c73fa4a0c3854ef7b20362c5b2693fd4cebf36fbf97008","observation_id":"16d8d503-20bb-462b-ad59-9a3c7f4e1494","resolution":{"observed_at":"2026-08-09T12:05:57.334320Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:57.311874Z","title":"Principal neighbourhood aggregation for graph nets","venue":null,"work_id":"1c2f9d63-4b50-4ccf-8553-43f766b532ab","year":2020},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.638034Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:9b66c9587100de3b2c206c8fa7ec17c22fe59d7d30b76374adee38b992f46482","observation_id":"e5386c8f-348b-48cc-a6f5-63b28ee4c7c2","resolution":{"observed_at":"2026-08-09T12:05:57.317750Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:55.643122Z","title":"Convolutional neural networks on graphs with fast localized spectral filtering","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.643122Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:a522afde56f09aee465add6d148b116827d815c91d072c3026793b052186c587","observation_id":"f9eb892f-caf3-4391-8247-4d5e9b7455cb","resolution":{"observed_at":"2026-08-09T12:05:55.643122Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2309.00976","last_updated":"2024-10-14T14:11:22Z","snapshot_observed_at":"2026-07-06T16:13:38.508734Z","submitted_at":"2023-09-02T16:20:41Z","title":"Pure Message Passing Can Estimate Common Neighbor for Link Prediction","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2309.00976","snapshot_observed_at":"2026-08-09T12:05:55.648037Z","title":null,"venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.648037Z"},"links":{"cited_paper":"/paper/2309.00976","citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:84dd02239ca18c8d4bbfbae699a81d19a161fdd045590d7a896cbc28ce3c8f45","observation_id":"d77687cc-aee9-47a1-aac2-fd8e05ec80a6","resolution":{"observed_at":"2026-08-09T12:05:55.648037Z","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":"2026-08-09T12:05:57.277438Z","title":null,"venue":null,"work_id":"37cf01a2-561a-4c6c-9ca8-81ca338eef83","year":2020},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.653859Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:658abfc81ec6ad4d755cb94d0fbed700f222af13c759dbff869df2d8c86afa49","observation_id":"efce3923-afd4-4654-9066-452857726cc3","resolution":{"observed_at":"2026-08-09T12:05:57.283435Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:57.257363Z","title":"P., Luu, A","venue":null,"work_id":"390b72a9-b217-445d-8f7f-f05d9353961d","year":2022},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.659493Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:b1085252156b3142c1ab39cd21653b2f5e39c493a8f77756e9c4a95ed7f94ef3","observation_id":"57773daf-3884-4501-ba00-35e39f093c5f","resolution":{"observed_at":"2026-08-09T12:05:57.263255Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:57.239330Z","title":"P., Ramp \\' a sek, L., Galkin, M., Parviz, A., Wolf, G., Luu, A","venue":null,"work_id":"c8d90e13-5010-4574-84cb-69658ce8a7e2","year":2022},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.668071Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:cf3e2123644de6ca0bb1021f9dfa37058fce56d6869aa5df868ebb0e334b77a6","observation_id":"2f714fef-3cdc-4d5a-9f32-9fa33fc67e02","resolution":{"observed_at":"2026-08-09T12:05:57.245007Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:57.221111Z","title":"and Maron, H","venue":null,"work_id":"e0b522b1-0179-4864-b3c3-d1c1850c0490","year":2021},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.675441Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:6ea54208e6ed0ea57395cbfd51e0facdf7d26c337911373e3ecfb9a89b84439f","observation_id":"5688feac-c853-4280-af76-391a3cbac2c6","resolution":{"observed_at":"2026-08-09T12:05:57.226451Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:57.201757Z","title":"Protein interface prediction using graph convolutional networks","venue":null,"work_id":"5ba7d518-9fbf-4459-9559-a7f92eac423e","year":2017},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.681727Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:6c409ccc7e774caee121340fced79f7be6a51f827e36a6d26ea7351759c30944","observation_id":"d68b1570-6abe-406a-89f3-b4d61d145aa7","resolution":{"observed_at":"2026-08-09T12:05:57.207810Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:57.179706Z","title":"M., and Maron, H","venue":null,"work_id":"377eca3b-61e7-4d16-a086-0f9306b7404d","year":2022},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.687823Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:f379f018f2fa8a23a3759d1d29de735039520b7a1d0c3025b14c9ae1741602b3","observation_id":"1e83bb09-dc85-449b-935e-644cf389921c","resolution":{"observed_at":"2026-08-09T12:05:57.186595Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:55.694881Z","title":"S., Riley, P","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.694881Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:9758531abfcd6a6414e091355b2b730b0792c43ba038a00e60f1a03b931274ac","observation_id":"cfcd6217-e7ae-44c2-9430-a67ff1db3a79","resolution":{"observed_at":"2026-08-09T12:05:55.694881Z","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":"2026-08-09T12:05:57.147796Z","title":"M., Aguilera - Iparraguirre, J., Hirzel, T","venue":null,"work_id":"ea2a2a9c-2e9c-4007-acd3-d06d2b210a52","year":2016},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.704901Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:57d8baa448db71d993af4a91abc20808fcb56fc8e295fc97b081dbef31efe0fc","observation_id":"a5c15f4a-1b39-470f-9875-b1d27ba59db8","resolution":{"observed_at":"2026-08-09T12:05:57.153243Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:57.130730Z","title":"L., Ying, R., and Leskovec, J","venue":null,"work_id":"b5805d6f-b682-4a4d-aa97-5b9eb744fda6","year":2017},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.710752Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:8f69a229db3953ea010ddadeb1211371c83a59497157c25068a108b560bdc9a1","observation_id":"648a5570-7cfb-4aa8-a30d-9ccb4002cb33","resolution":{"observed_at":"2026-08-09T12:05:57.135971Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:55.716319Z","title":"Bernnet: Learning arbitrary graph spectral filters via bernstein approximation","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.716319Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:1e7c9cdfda786b6416e84f807b08976f876eb3811564894501f923c6eafea04f","observation_id":"a106c4ca-927d-4625-86a1-682a1566dbd8","resolution":{"observed_at":"2026-08-09T12:05:55.716319Z","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":"2026-08-09T12:05:57.100594Z","title":"Open graph benchmark: Datasets for machine learning on graphs","venue":null,"work_id":"628fb6c6-528d-4b97-a957-264e8b9c297d","year":2020},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.721274Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:0f4aa1175e0a38b2059e666c200e7447e560e4c642acc94f26fa858f0b085b4a","observation_id":"b4150446-7cda-4df2-b38a-7e7c3928110e","resolution":{"observed_at":"2026-08-09T12:05:57.107671Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2310.02579","last_updated":"2024-06-08T16:09:55Z","snapshot_observed_at":"2026-07-06T16:27:31.403609Z","submitted_at":"2023-10-04T04:48:55Z","title":"On the Stability of Expressive Positional Encodings for Graphs","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2310.02579","snapshot_observed_at":"2026-08-09T12:05:55.726936Z","title":"On the stability of expressive positional encodings for graph neural networks","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.726936Z"},"links":{"cited_paper":"/paper/2310.02579","citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:a588a290d5a6a6e259f869f503f80d7bf4b74413e1e2a140b4ef6e739f80ec9a","observation_id":"087f6108-4ad7-4912-acd8-97e44c5e9c65","resolution":{"observed_at":"2026-08-09T12:05:55.726936Z","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":"2026-08-09T12:05:57.078933Z","title":"Boosting the cycle counting power of graph neural networks with i \\^ 2 -gnns","venue":null,"work_id":"32e58062-5ff8-4a82-91ae-7173534c52e2","year":2023},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.732592Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:e76aeef18947dceeb0e1782058876678fea9b1e7f5cadf602fc721bcd30adc42","observation_id":"571817a5-3d7a-46fa-9b87-75ddeb8f4d8f","resolution":{"observed_at":"2026-08-09T12:05:57.086960Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:57.057055Z","title":"Transformers generalize deepsets and can be extended to graphs & hypergraphs","venue":null,"work_id":"d381b7c3-85a8-4e17-b6ed-9c4c6aab3b42","year":2021},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.737767Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:5940495868c7694314e75fe36a2a5e2363510378669a12abe446df8f1a6510c6","observation_id":"ccbc7d60-290a-4713-83e3-567c0919ddc9","resolution":{"observed_at":"2026-08-09T12:05:57.063246Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1609.02907","last_updated":"2017-02-22T09:55:36Z","snapshot_observed_at":"2026-07-06T05:10:16.862707Z","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":"2026-08-09T12:05:55.742746Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.742746Z"},"links":{"cited_paper":"/paper/1609.02907","citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:b8d18606895c4abe18ea22e6aa00ebeb3bdbc83d0c75e24e155e99ddda743ecd","observation_id":"5fe51930-35c3-4ad6-a1e0-874c31f0f7e3","resolution":{"observed_at":"2026-08-09T12:05:55.742746Z","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":"2026-08-09T12:05:57.032512Z","title":"Predict then propagate: Graph neural networks meet personalized pagerank","venue":null,"work_id":"9a159c80-5ce8-402a-913d-301ff2e85c82","year":2019},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.748458Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:1e5275f4fa8be57769e23bfd940a9ffd676b8d9fb80113dfe7d4de152f65708d","observation_id":"bba071b8-90a2-4222-94b2-8a351435d5ad","resolution":{"observed_at":"2026-08-09T12:05:57.040853Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:57.014242Z","title":"L., L \\' e tourneau, V., and Tossou, P","venue":null,"work_id":"4034511d-03d6-4bfc-b682-f3adddca362a","year":2021},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.754209Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:1b3aec36d021fb12d76b89f22d612415b99b8d2bd35834c98cbfc41c48ab10e5","observation_id":"566bfd77-5393-44b2-8057-bfa4a3a90cd7","resolution":{"observed_at":"2026-08-09T12:05:57.019865Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:56.993449Z","title":"Distance encoding: Design provably more powerful neural networks for graph representation learning","venue":null,"work_id":"e50f073f-f735-4dc2-a71a-1846afe4efb2","year":2020},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.759675Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:e83f60c48b928deefd3f627305c03d98582f50f8f95445405d76ca8475f3ef24","observation_id":"b84ca130-d3e4-4bba-8a81-b041c902abe7","resolution":{"observed_at":"2026-08-09T12:05:57.000713Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:56.968684Z","title":"Deeper insights into graph convolutional networks for semi-supervised learning","venue":null,"work_id":"cb107a5b-86ea-43a8-b4a0-641d55e9cfc0","year":2018},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.766448Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:83ea7cad1c35f1d8d370fb3f4bb7911bcc7a951f371122c1b95ab59439a8e581","observation_id":"a5ffb695-4577-4c47-8da8-62f5ecd20299","resolution":{"observed_at":"2026-08-09T12:05:56.975575Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:56.946226Z","title":"D., Zhao, L., Smidt, T","venue":null,"work_id":"c03a9cdd-e421-48ff-9713-38ecb87bbaf5","year":2023},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.772192Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:933a2e3c9e84a835c057bccec8078da539564d856a86a75d4ae8a123bb0a03b0","observation_id":"0f3060fa-819f-4e02-8bea-d888cd15fe33","resolution":{"observed_at":"2026-08-09T12:05:56.952099Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:56.927085Z","title":"Laplacian canonization: A minimalist approach to sign and basis invariant spectral embedding","venue":null,"work_id":"2f53b970-9ddb-4026-801f-728a60cb8887","year":2023},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.781425Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:abe6c84bb62360aa64dfb5fb38a70b9b3365b79619d69906e3169a8186f72731","observation_id":"a40c5257-a235-48b0-bec3-499f9c4a2db8","resolution":{"observed_at":"2026-08-09T12:05:56.933202Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:56.910015Z","title":"Provably powerful graph networks","venue":null,"work_id":"0aefe63a-0a93-4216-a674-34e399a8fb65","year":2019},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.787228Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:a776a13296316967c84eeec95fa48e7325e7852cb8d85b563c9abf4c86d3634d","observation_id":"1f3d28e3-eeb8-4149-84d1-ebd76cc89132","resolution":{"observed_at":"2026-08-09T12:05:56.915790Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:56.887355Z","title":"Invariant and equivariant graph networks","venue":null,"work_id":"57c2fddc-6db2-4e78-a6b9-df1f01b1be7a","year":2019},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.792849Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:40dab4bae31a79ce46be0d83f02bdf9136e762bfaa0cd6d266653ba2c819c56c","observation_id":"50bf2af1-4d19-420f-95d2-c269a3f58152","resolution":{"observed_at":"2026-08-09T12:05:56.893745Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:56.865565Z","title":"On learning sets of symmetric elements","venue":null,"work_id":"b761da50-ce62-40b8-a63e-5c1e30bafdc3","year":2020},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.799674Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:3a72debc1fa17ff16a9e8224fba0b363bd0f69ce1af512e4db1190aa50f2a671","observation_id":"f5ac3aa1-0459-437f-9173-b39ef3ad23e6","resolution":{"observed_at":"2026-08-09T12:05:56.871751Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:56.847509Z","title":"Graphit: Encoding graph structure in transformers, 2021","venue":null,"work_id":"5f35df3b-9e09-444f-8f3d-13ca67b2ab0a","year":2021},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.811419Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:d3b8a5831a217df8ca231c529168485f1010ba783fce9c5361d1328b0ebdc365","observation_id":"c7aa7cc1-1cc9-4ce3-b973-2be8582b310e","resolution":{"observed_at":"2026-08-09T12:05:56.853192Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:56.830786Z","title":"A., Martinkus, K., Faber, L., and Wattenhofer, R","venue":null,"work_id":"8d71968f-93d0-410a-aaaa-ff3144a2b1ce","year":2021},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.817528Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:f3ececbab110b0720a5430f6c5777bcec049bdc1cdfe53fa0f0ccd10cd8d1825","observation_id":"7bd3b996-e35f-43ab-9d37-8fe9e4d85d80","resolution":{"observed_at":"2026-08-09T12:05:56.836078Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:56.812966Z","title":"C., Lei, Y., and Yang, B","venue":null,"work_id":"2e2067e1-4d95-464d-a74a-2a4bbd6f89bf","year":2020},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.822687Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:d540bb1fa79a00aa4a712c6ab1fad48047d55da34e32932ccac41886b63b9253","observation_id":"cd737435-6c09-4001-9d60-32d534a3328e","resolution":{"observed_at":"2026-08-09T12:05:56.818908Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:56.793835Z","title":"Ordered subgraph aggregation networks","venue":null,"work_id":"d45e9d74-df34-4182-bbe9-135a2a80e06e","year":2022},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.829133Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:4832e18a19f995c8e94d4eea1bafd34733edbb4ab0efa440dd8441cd4056f117","observation_id":"29ea73af-1dcb-4591-b04e-1624dd24a13c","resolution":{"observed_at":"2026-08-09T12:05:56.800072Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:56.775026Z","title":"P., Luu, A","venue":null,"work_id":"e69e5f37-c671-4b33-994e-0f2e4a6455cd","year":2022},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.834014Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:58f031f558386bfe26243bd6660de2fa108c134c1751a0bdadfe294965f8d988","observation_id":"c08320ac-3ebf-4b77-bd17-9c34b13b9e81","resolution":{"observed_at":"2026-08-09T12:05:56.781476Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:56.755886Z","title":"Multi-scale attributed node embedding","venue":null,"work_id":"40694ff7-4b5d-43c7-951b-5b45a3a631bc","year":2021},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.839888Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:658a4d270d0f7ec91dca2158b1dbf79a4a0c58b72a9ccadac27c2163f1f3ff3a","observation_id":"dabf1181-ace5-4cef-9e36-88b2b8e4f595","resolution":{"observed_at":"2026-08-09T12:05:56.761785Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:56.738488Z","title":"Random features strengthen graph neural networks","venue":null,"work_id":"fceab7e0-3434-43b9-8224-cbe7fb23152a","year":2021},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.844933Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:497b0d194bbb2e8933c595a16ff56fa288a44b6bce6b972e61c0fbc325e3c483","observation_id":"0a287d45-652d-4837-8010-12f1cc4a2076","resolution":{"observed_at":"2026-08-09T12:05:56.743887Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:56.720573Z","title":"and Lipman, Y","venue":null,"work_id":"2f1b941f-805a-4f21-a8b4-9c5a438e2405","year":2020},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.852120Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:77c0b1d161841ccb87ec14b73cac0738e5b2f1b72a362d7a6768cc0e433663e2","observation_id":"c30cb4d1-5225-4892-b458-8192f1ac4180","resolution":{"observed_at":"2026-08-09T12:05:56.726337Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1811.05868","last_updated":"2019-06-18T13:15:39Z","snapshot_observed_at":"2026-07-06T07:14:41.761512Z","submitted_at":"2018-11-14T15:53:19Z","title":"Pitfalls of Graph Neural Network Evaluation","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1811.05868","snapshot_observed_at":"2026-08-09T12:05:55.857531Z","title":"Pitfalls of graph neural network evaluation","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.857531Z"},"links":{"cited_paper":"/paper/1811.05868","citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:dfbaac8d790cbe7efe8fcc99bb5811f139f1dfd912111048c355ed354203fd47","observation_id":"8dd41f05-c1cd-450e-be3d-c453d7709938","resolution":{"observed_at":"2026-08-09T12:05:55.857531Z","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":"2026-08-09T12:05:56.701840Z","title":"J., and Sinop, A","venue":null,"work_id":"6f59f71c-757e-45cd-8762-ee2f51924550","year":2023},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.864428Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:704581dcb5f9822fce04479643d8979037d9c8fe69c5dff35b3d467869775fc3","observation_id":"9311c9b9-dbfb-4046-8c80-7d0a8f0ba9a7","resolution":{"observed_at":"2026-08-09T12:05:56.708782Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:56.680069Z","title":"Equivariant and stable positional encoding for more powerful graph neural networks","venue":null,"work_id":"fb47c673-2d02-4bb5-bb5e-a6b4f839b44b","year":2022},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.870725Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:0a1a2766ac28fb8f004f4db20de92701026c91002a6129c696e4176bdfd38bfa","observation_id":"80eb31f1-0c75-4c9a-b302-785a98d41a59","resolution":{"observed_at":"2026-08-09T12:05:56.687501Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:56.657381Z","title":"and Zhang, M","venue":null,"work_id":"d88c915b-a190-4a3d-8558-e8634d3047fc","year":2022},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.877764Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:9d6e9ca594f3fa73e5c2c62cc01b0ee43b66eb3ca22e0a39b1b9cf6349ea34ce","observation_id":"55bcf427-5ea9-4299-b343-1f23778b6cc0","resolution":{"observed_at":"2026-08-09T12:05:56.663239Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:56.639465Z","title":"and Zhang, M","venue":null,"work_id":"66967594-5cec-4042-8959-14c6ea2c8c88","year":2022},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.886063Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:8b606466149d7c8a1c88891f90d337e480d3e449f24eaeb93e083ec139d7ab1a","observation_id":"2faa3ec8-ae8b-43b2-980e-bc690cf2c765","resolution":{"observed_at":"2026-08-09T12:05:56.645149Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2311.16670","last_updated":"2023-11-28T10:34:48Z","snapshot_observed_at":"2026-08-03T16:20:18.580483Z","submitted_at":"2023-11-28T10:34:48Z","title":"PyTorch Geometric High Order: A Unified Library for High Order Graph Neural Network","version":1},"cited_work":{"arxiv_id":"2311.16670","doi":null,"metadata_source":"pith","pith_arxiv_id":"2311.16670","snapshot_observed_at":"2026-08-09T12:05:56.069847Z","title":"PyTorch Geometric High Order: A Unified Library for High Order Graph Neural Network","venue":"cs.LG","work_id":"12e63bee-daf5-4012-b2de-1b2e6f05fcb6","year":2023},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.896131Z"},"links":{"cited_paper":"/paper/2311.16670","citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:e684959dbf9bfc7248e8938a2b4eb444204bb0ad5ab287dd5a797c172ddc57c6","observation_id":"137bfce6-11ad-4c9a-a6cf-89845fe1b2ae","resolution":{"observed_at":"2026-08-09T12:05:56.078413Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:56.622984Z","title":"Graph as point set","venue":null,"work_id":"7b01f8a9-3016-43e2-8106-e47ea4b00fa9","year":2024},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.903198Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:9616c398ed62d98fd20dda905c435c6168cc7ebded337f14415c68f2129fea84","observation_id":"dfd2ed42-d602-45ec-a16a-9319b4b57eb8","resolution":{"observed_at":"2026-08-09T12:05:56.628064Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:56.605452Z","title":"Neural common neighbor with completion for link prediction","venue":null,"work_id":"c2fe1785-4b56-4858-b1bf-983f4589aa51","year":2024},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.912331Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:ff2236a538fe130abba465d7bda246008296e678fc8ca6fe1c51fdacb385de03","observation_id":"20b4cdcc-8b2d-46b7-91e3-b291ce85318f","resolution":{"observed_at":"2026-08-09T12:05:56.611592Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:56.582791Z","title":"A., Mirhoseini, A., Gonzalez, J","venue":null,"work_id":"e577095c-6aaf-4b36-9271-410f7b317222","year":2021},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":57,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.917907Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:285a5d03538028cf8cf447a19481b580dce459f8744d6530c5aa7a4cb8f30f39","observation_id":"b58f09e7-3fd0-4f2c-aac4-d7372b261809","resolution":{"observed_at":"2026-08-09T12:05:56.589383Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:55.923412Z","title":"How powerful are graph neural networks? In ICLR, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":58,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.923412Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:76457f80effad3b9ebd627106abb7376dda00bf776cd9ce958b16a8c5499d967","observation_id":"eaf57bf2-d627-450c-bb24-2fda0fa5aa7f","resolution":{"observed_at":"2026-08-09T12:05:55.923412Z","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":"2026-08-09T12:05:56.549564Z","title":"W., and Salakhutdinov, R","venue":null,"work_id":"9da46a08-b88a-4304-b868-e683117dafdf","year":2016},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":59,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.929165Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:11730263e2281bb15fb0a7de0c5017c85f46c1e66d827a65471d423b35ce75c4","observation_id":"eb093a2e-8517-490e-8e2b-753dfdf11a88","resolution":{"observed_at":"2026-08-09T12:05:56.555164Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:56.531224Z","title":"Graph convolutional networks for text classification","venue":null,"work_id":"cd5f8bb4-3fc8-4adb-a87f-2275cea1375e","year":2019},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":60,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.934812Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:ed06ee5d3c6c2223ee421f6c6dae98b06e7412cfcd7a99bab21db1d4399f9f5f","observation_id":"8760fddb-87f5-4e32-99ea-f224ed31b40e","resolution":{"observed_at":"2026-08-09T12:05:56.536477Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:56.513903Z","title":"Do transformers really perform badly for graph representation? In NeurIPS, 2021","venue":null,"work_id":"d7cbbe19-bc65-4e22-ab79-611b56abea5a","year":2021},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":61,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.940128Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:cb97947d30076931a57c67a64504855fe8e101744dfb642342e60c07cb485d4f","observation_id":"a864d37c-69e5-4d2a-bed0-f0261b7f5c3e","resolution":{"observed_at":"2026-08-09T12:05:56.519147Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:56.492819Z","title":"M., Ying, R., and Leskovec, J","venue":null,"work_id":"240c8911-2238-4c9c-b453-fa7f919df1c7","year":2021},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":62,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.945062Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:427d844c33bc96aa66bad9c7fd8798230e17359e7bfbee99e9605476da1a1ae4","observation_id":"9245f21b-c2ad-4aa3-99d9-4910ab16065e","resolution":{"observed_at":"2026-08-09T12:05:56.499616Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:56.465190Z","title":null,"venue":null,"work_id":"ae2137e4-df02-42a3-a815-40cf1b465d66","year":2021},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":63,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.951159Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:b2c93f8788bfaf491e3dad34e5a44371d2afe0a7a1a114c5bee221d290f126fe","observation_id":"da474363-96f5-4d3a-ba69-12df18ca741f","resolution":{"observed_at":"2026-08-09T12:05:56.472967Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:56.444750Z","title":null,"venue":null,"work_id":"a160cc5b-40c8-4fd5-9e9d-1438e755fd65","year":2021},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":64,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.956088Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:15d0219c38b71540572251114f2850d1ad2c5c1a08ce95a53c78dd649c4731f0","observation_id":"b5dec0e6-4760-4b7d-9cf0-0a3fba1eca6c","resolution":{"observed_at":"2026-08-09T12:05:56.449976Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:56.428328Z","title":null,"venue":null,"work_id":"9e41871b-eb3b-4a0f-be43-050c978084bb","year":2017},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":65,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.964310Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:8c15c12ffaf41497170f839dd71bcd97d0217e7b54a8550e04a7e02b9eff5cfe","observation_id":"1d85cb84-3233-462c-b7ea-3368d58abd68","resolution":{"observed_at":"2026-08-09T12:05:56.433596Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:56.409839Z","title":"A complete expressiveness hierarchy for subgraph gnns via subgraph weisfeiler-lehman tests","venue":null,"work_id":"a7d4f405-1007-46a3-9b01-2192bc7abcc9","year":2023},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":66,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.969877Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:9cbff2812930df1f4c9c0ecd62382dd5fad0c8789302c3d8bd95e6f5f8cff64e","observation_id":"8dfc68ec-98e6-4a64-9677-501fd574d6f6","resolution":{"observed_at":"2026-08-09T12:05:56.415975Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:56.389075Z","title":"and Chen, Y","venue":null,"work_id":"98f065e5-1352-4c05-97be-34fe79917eeb","year":2018},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":67,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.975499Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:b04dcff35ec98d5144c28aaad1cc35e0641b3c168e0f8fa5beda0664e53ce864","observation_id":"88f907a4-09e7-4799-92ca-a821df2b249e","resolution":{"observed_at":"2026-08-09T12:05:56.394973Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:56.354185Z","title":"and Li, P","venue":null,"work_id":"afe46971-4058-4a99-afae-3efc78d349fb","year":2021},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":68,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.981532Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:9ecc8cafc4779e96209289e8c8b56af6ec9373b0b33a0c893569d840a3c5d07c","observation_id":"bf49b103-99c9-4a29-872c-30507d5f42fc","resolution":{"observed_at":"2026-08-09T12:05:56.360833Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:56.335362Z","title":"Labeling trick: A theory of using graph neural networks for multi-node representation learning","venue":null,"work_id":"981ff5a7-e6b1-4d09-a9bd-ec0175969c97","year":2021},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":69,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.989273Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:4278aeadeab6cfd00b1a3f013a0b5fb45ba1a0a1230d9bb4812b13c15a1532d7","observation_id":"750ed9ec-8d62-4426-8425-219b20db3dd2","resolution":{"observed_at":"2026-08-09T12:05:56.340548Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:56.314297Z","title":"From stars to subgraphs: Uplifting any GNN with local structure awareness","venue":null,"work_id":"9402e0d7-5a9d-4e9c-af16-23ebe583d5c1","year":2022},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":70,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:55.995348Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:0a1f82c96c15cf2203ae99ea1a470ab498a0eed63b16efeeb068ef35c4d7c65a","observation_id":"a78bd93c-3cbe-4229-a1db-8796d64509a9","resolution":{"observed_at":"2026-08-09T12:05:56.321440Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:56.293234Z","title":"Distance-restricted folklore weisfeiler-leman gnns with provable cycle counting power, 2023","venue":null,"work_id":"defd56be-9005-4031-8456-9a7b6c03092c","year":2023},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":71,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:56.002698Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:6abc4af7792beb62b497659bc2fd540af5d24a7fbe0f2a5a91f9ae74b2a48ae8","observation_id":"05051c4d-e43e-4851-8822-4ad2978ea9ab","resolution":{"observed_at":"2026-08-09T12:05:56.299748Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:56.270623Z","title":"Predicting missing links via local information","venue":null,"work_id":"447053ae-ad36-402f-8757-59fe723bc5d4","year":2009},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":72,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:56.008056Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:5a5de67bb5cf428835f81ee760d1e3a51be769a2db54aa58a40b21833b936f6f","observation_id":"86fa72fc-68f2-48d9-9cb0-a973c9b8c566","resolution":{"observed_at":"2026-08-09T12:05:56.277360Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:56.243884Z","title":null,"venue":null,"work_id":"0c1e0ca5-4c20-4cf2-8f38-965d02c38615","year":2021},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":73,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:56.014327Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:306facc1910bbfd08a53dae4db76fbfb31f64baecb2fde7b0787a66527f77ca4","observation_id":"f3d6eb0b-f5e0-4598-b68d-6b95f912db54","resolution":{"observed_at":"2026-08-09T12:05:56.250466Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+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":"2026-08-09T12:05:56.019965Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally","version":1},"reference_index":74,"source":"arxiv_source","source_observed_at":"2026-08-09T12:05:56.019965Z"},"links":{"citing_paper":"/paper/2502.02479"},"observation_digest":"sha256:8c931c1bb3c35b2f32c320ccbdb7c08ce4adfb0d3440ef69d1989fd52e7df95f","observation_id":"0986fe36-8b5d-4b42-98dd-cec80e187a76","resolution":{"observed_at":"2026-08-09T12:05:56.019965Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2502.02479","last_updated":"2025-02-04T16:54:28Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T18:26:41.757443Z","submitted_at":"2025-02-04T16:54:28Z","title":"Using Random Noise Equivariantly to Boost Graph Neural Networks Universally"},"reference_resolution":{"displayed":74,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":18,"verified_exact":2,"verified_fuzzy":54},"total_outbound_references":74},"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":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 74 of 74 outbound references and 0 inbound Pith citation observations for arXiv:2502.02479."}