{"as_of":"2026-08-17T18:15:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:73a476a6f187beaf45701cede2e6ea6b24c085d1f454b1c22ae0c8787c998f44","coverage":[{"denominator":47,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":47,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-07T15:28:57.644469Z","state":"measured"},{"denominator":47,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":47,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-17T06:30:58.91139+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/2505.15177/citation-record","integrity":"/paper/2505.15177/integrity","json":"/paper/2505.15177/citation-record.json","paper":"/paper/2505.15177"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:29:06.473679Z","title":"Spectral graph theory","venue":null,"work_id":"ef93d153-d2b2-4d07-92b4-5854dfa11a72","year":1997},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:50.832213Z"},"links":{"citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:05b1ee802c0879d6cad67bf98c9da94819de5f06923acce568e7a5cd36a465da","observation_id":"2b45e70a-7560-4c02-a3b8-4243a1c3c91b","resolution":{"observed_at":"2026-08-07T15:29:06.575494Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T15:28:58.447322Z","title":"the correct side","venue":null,"work_id":"401b1cbc-de77-4279-b587-510e8a48d283","year":2021},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:57.498348Z"},"links":{"citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:b8dfdd73bc76c1aa9931597311576f55cbed1a051fee994f5cb9d58f1b491ad9","observation_id":"2b4ae3b5-2613-4501-a93f-91552a197e82","resolution":{"observed_at":"2026-08-07T15:28:58.617586Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T15:29:05.231787Z","title":"Expander graphs and their applications","venue":null,"work_id":"e78ece94-372e-42e2-8a2d-748c4c1e3249","year":2006},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:51.620243Z"},"links":{"citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:f0852abe1376a776439ab0c44eae1e3e4b714efc8b7d2b3d639da280072a7dcd","observation_id":"0889daab-16fc-404d-beb2-027f25ccaf44","resolution":{"observed_at":"2026-08-07T15:29:05.318727Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T15:29:04.408078Z","title":"A comprehensive survey on deep graph representation learning","venue":null,"work_id":"658e74a0-9287-498c-a389-7459ebbba0ce","year":2024},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:52.184050Z"},"links":{"citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:3a5d1d5a1218f2e2e19fc50225f66ee3a9705f496410825a4c15ced23482277b","observation_id":"64d1548a-de43-4ec2-a0f0-0684f238a7c6","resolution":{"observed_at":"2026-08-07T15:29:04.542510Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1609.02907","last_updated":"2017-02-22T09:55:36Z","snapshot_observed_at":"2026-08-17T10:49:36.026134Z","submitted_at":"2016-09-09T19:48:41Z","title":"Semi-Supervised Classification with Graph Convolutional Networks","version":4},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1609.02907","snapshot_observed_at":"2026-08-07T15:28:52.396495Z","title":"Semi-supervised classification with graph convolutional networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:52.396495Z"},"links":{"cited_paper":"/paper/1609.02907","citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:762c1fec1e587de54ddd2dcd9f08979678a170977ad03de321d7d685df8ed656","observation_id":"61d142e9-571a-478c-bce5-6cc3dff809f5","resolution":{"observed_at":"2026-08-07T15:28:52.396495Z","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":"2026-08-07T15:29:04.173824Z","title":"Rethinking graph transformers with spectral atten- tion","venue":null,"work_id":"7e13ff79-c644-4d7f-946f-ae44b9c54cd4","year":2021},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:52.657722Z"},"links":{"citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:3bd15731c1fa9a29e1e3577ddaa0478c0733fdd00c0fd15634641c9300d7a934","observation_id":"be0339e1-5157-49ea-bf74-e0b3757c2ee5","resolution":{"observed_at":"2026-08-07T15:29:04.287486Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T15:29:03.167912Z","title":"Good-d: On unsupervised graph out-of- distribution detection","venue":null,"work_id":"3b977b91-af93-479c-9b69-cd33a580f3ed","year":2023},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:53.318464Z"},"links":{"citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:c72986b83599e95a29190b14f51867550ddd2a985191a84bf0f71486e6aad992","observation_id":"f38e36eb-bc6c-4a3f-927a-abc97a2fd352","resolution":{"observed_at":"2026-08-07T15:29:03.291051Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T15:29:02.898497Z","title":"Towards self- interpretable graph-level anomaly detection","venue":null,"work_id":"e6b0f0ec-10b8-46ae-b7d6-bcb02c077d91","year":2024},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:53.446885Z"},"links":{"citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:a29dc1bdb6861b5765780e9f7793f454adde567581e405baa21fede2d3b7764d","observation_id":"a3032a17-5c52-4989-bb12-44c6ebabfebf","resolution":{"observed_at":"2026-08-07T15:29:03.014032Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T15:29:02.640663Z","title":"Deep graph-level anomaly de- tection by glocal knowledge distillation","venue":null,"work_id":"5401ecb0-0b7d-47d4-a1ad-01cd40f9ee0f","year":2022},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:53.590051Z"},"links":{"citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:dca14c123d4e44b0d8b78d245d7bb1c120e8a90a2f343650f263e57e45025053","observation_id":"9e84f9e9-cd99-4e2a-8253-bb291181e08f","resolution":{"observed_at":"2026-08-07T15:29:02.775983Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T15:29:02.362895Z","title":"Towards graph-level anomaly detection via deep evolutionary mapping","venue":null,"work_id":"56fd2cc7-ca6e-4a05-b1b1-17bc38511e6f","year":2023},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:53.698110Z"},"links":{"citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:421785576ea4a9a2e2bf403f7abbaac3658483f665cc1034303bd6231463871a","observation_id":"94d5a882-766e-4e80-b679-7556b52b14ba","resolution":{"observed_at":"2026-08-07T15:29:02.521129Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T15:29:02.192622Z","title":"Provably powerful graph networks","venue":null,"work_id":"caa5cfd0-c02d-406b-a2db-4c3656fd6360","year":2019},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:53.822740Z"},"links":{"citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:86212b632606879c597818bdd9cdc32780b468c5a9ef9c2b807986ada77dc5e9","observation_id":"deeeb3b6-3cdc-4397-be57-5792fb367b05","resolution":{"observed_at":"2026-08-07T15:29:02.279764Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2106.05667","last_updated":"2021-06-10T11:36:22Z","snapshot_observed_at":"2026-08-16T18:18:07.548544Z","submitted_at":"2021-06-10T11:36:22Z","title":"GraphiT: Encoding Graph Structure in Transformers","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2106.05667","snapshot_observed_at":"2026-08-07T15:28:54.016306Z","title":"Graphit: Encod- ing graph structure in transformers","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:54.016306Z"},"links":{"cited_paper":"/paper/2106.05667","citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:92e37c4ce04a7dfcf871420a75b5d0f8cbdc22edcaf7edf049a66f2790d87b17","observation_id":"7c6c03c8-7764-407a-8908-3c81b6c9681f","resolution":{"observed_at":"2026-08-07T15:28:54.016306Z","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":"2026-08-07T15:29:01.881674Z","title":"A new method to predict anomaly in brain network based on graph deep learning","venue":null,"work_id":"1b4bd11c-f25b-4a97-848d-87bb37cb1418","year":2020},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:54.171821Z"},"links":{"citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:9608ab8dc6494172b16083854fcaf789a417552f891f1bd063bd3fb66c820155","observation_id":"ab295051-db82-4176-b024-db4f07a462a8","resolution":{"observed_at":"2026-08-07T15:29:02.045004Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2007.08663","last_updated":"2020-07-16T21:46:33Z","snapshot_observed_at":"2026-08-13T19:42:12.787378Z","submitted_at":"2020-07-16T21:46:33Z","title":"TUDataset: A collection of benchmark datasets for learning with graphs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2007.08663","snapshot_observed_at":"2026-08-07T15:28:54.317480Z","title":"Tudataset: A collection of bench- mark datasets for learning with graphs","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:54.317480Z"},"links":{"cited_paper":"/paper/2007.08663","citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:c2eb93b3fe92df36242278256d733034e899168fc1b8ba6b4beae5a3b902a0e1","observation_id":"397f4d14-0846-4fc4-80f0-356158873db1","resolution":{"observed_at":"2026-08-07T15:28:54.317480Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:28:54.463203Z","title":"Semi-supervised domain adaptation in graph transfer learning","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:54.463203Z"},"links":{"citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:008bababc677ce7387da62463769514a4c1790d7672caee6b7255ff328a9671d","observation_id":"21a88b25-5c34-448c-b601-80c84f1faeee","resolution":{"observed_at":"2026-08-07T15:28:54.463203Z","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":"2026-08-07T15:29:01.609582Z","title":"Information filtering and in- terpolating for semi-supervised graph domain adaptation","venue":null,"work_id":"106bf483-c36d-4e47-aa37-1082fcd94110","year":2024},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:54.607743Z"},"links":{"citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:609adbabfc7664f561191c8fbfe1039525a1cad0b4c57c53a9a212e888fb9a52","observation_id":"e488babc-c5a0-4d7b-8c2b-9eeae22355b2","resolution":{"observed_at":"2026-08-07T15:29:01.736914Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T15:28:54.789522Z","title":"Towards contin- uous reuse of graph models via holistic memory diversi- fication","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:54.789522Z"},"links":{"citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:6450f682437c619c44178c4d3bfe9b6a2a97e381043e8c150fa62faab77a6b92","observation_id":"ef9dde21-b767-498c-9ecf-a5e19ec93a3e","resolution":{"observed_at":"2026-08-07T15:28:54.789522Z","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":"2026-08-07T15:29:01.362605Z","title":"Optimizing ood detection in molecular graphs: A novel approach with diffusion mod- els","venue":null,"work_id":"1c5294ab-e227-4a08-b646-89b4a62c55b1","year":2024},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:55.094877Z"},"links":{"citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:e492493ea3c3a9f70ef86aada7572dd9f45c158fe45af691fc56632c726aebc2","observation_id":"30ef0a07-4d35-41f1-a378-fcecc07b7265","resolution":{"observed_at":"2026-08-07T15:29:01.470874Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T15:29:01.147300Z","title":"Rankfeat: Rank-1 feature removal for out-of-distribution detection","venue":null,"work_id":"013bec0d-7045-439b-b049-cf7963141416","year":2022},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:55.260573Z"},"links":{"citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:a0f4bf094dc85ddcdf03ac8401ef0f21356fa540297e258e35da55535270651f","observation_id":"a0d58d79-dc32-4f98-94ab-f28c0bc9d3c7","resolution":{"observed_at":"2026-08-07T15:29:01.240011Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T15:29:00.895633Z","title":"Spectral graph the- ory and its applications","venue":null,"work_id":"4431df08-2533-434b-ade9-f314f568e40e","year":2007},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:55.405233Z"},"links":{"citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:504055b753320ec4b217d7a5cdc6bbfd938ed65939035c3924ea23c89a698e93","observation_id":"920d69a6-324f-4ba4-971f-e1a6e790794c","resolution":{"observed_at":"2026-08-07T15:29:01.032833Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T15:29:00.687156Z","title":"Large margin deep networks for out- of-distribution detection","venue":null,"work_id":"ebc8efd8-989c-434c-842a-6ef0fe544af1","year":2021},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:55.692621Z"},"links":{"citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:ac3c1b54d8d19bf2d8cf9f74c4568d6065413d2460fb8995eff5299f9d930c85","observation_id":"29a22533-5659-4c0e-8e98-3df93415c449","resolution":{"observed_at":"2026-08-07T15:29:00.785077Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T15:29:00.401734Z","title":"Goodat: Towards test-time graph out-of-distribution detection","venue":null,"work_id":"b33aaf09-4911-44ae-9fe9-3d5f6a2b50a2","year":2024},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:55.818154Z"},"links":{"citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:36aa6bbd0fb92e13defb381941bf75881097a7047e5b7bb50ecb89416c65b95d","observation_id":"cc2e684a-d92e-4402-a9fe-5cea9f97607b","resolution":{"observed_at":"2026-08-07T15:29:00.531732Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T15:29:00.183382Z","title":"A com- prehensive survey on graph neural networks","venue":null,"work_id":"f5841c6f-1a45-409b-aa9c-513eda0df7f3","year":2020},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:55.961484Z"},"links":{"citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:56aaa8e638452425a81abc5ee842889c66f8b69046341454c1f924554165d0dd","observation_id":"04d75754-ab31-458b-9bdb-36e67a5e5d59","resolution":{"observed_at":"2026-08-07T15:29:00.279042Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2302.02914","last_updated":"2023-03-09T06:24:02Z","snapshot_observed_at":"2026-08-16T15:57:21.408661Z","submitted_at":"2023-02-06T16:38:43Z","title":"Energy-based Out-of-Distribution Detection for Graph Neural Networks","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2302.02914","snapshot_observed_at":"2026-08-07T15:28:56.113695Z","title":"Energy-based out-of-distribution de- tection for graph neural networks","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:56.113695Z"},"links":{"cited_paper":"/paper/2302.02914","citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:bdc62b14acb3722587918fee8b54a7c494861ba13d207db37b87aa3e331b4385","observation_id":"94529623-7904-48c2-8eb4-de3780bbd500","resolution":{"observed_at":"2026-08-07T15:28:56.113695Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-07T15:28:56.242519Z","title":"Graph learning: A survey","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:56.242519Z"},"links":{"citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:fd8a5143f6af55b33dc3eac890a1dcc85390c8ef1c4d6de0063f9692b9614833","observation_id":"0dfc0bf2-bcca-4924-815e-69e18e8e5c02","resolution":{"observed_at":"2026-08-07T15:28:56.242519Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1810.00826","last_updated":"2019-02-22T19:15:54Z","snapshot_observed_at":"2026-08-13T05:06:48.606308Z","submitted_at":"2018-10-01T17:11:31Z","title":"How Powerful are Graph Neural Networks?","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1810.00826","snapshot_observed_at":"2026-08-07T15:28:56.381257Z","title":"How powerful are graph neural net- works? arXiv preprint arXiv:1810.00826,","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:56.381257Z"},"links":{"cited_paper":"/paper/1810.00826","citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:fe896fd9a743ea1e344009185c98c583854ac7b1ce7d7a534945439b0a567d6f","observation_id":"af2d81c7-3f96-4a50-97df-c82daa0dd33c","resolution":{"observed_at":"2026-08-07T15:28:56.381257Z","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":"2026-08-07T15:28:59.924531Z","title":"Openood: Benchmarking generalized out-of-distribution detection","venue":null,"work_id":"786f859d-7b78-4817-8735-519c026ba579","year":2022},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:56.660413Z"},"links":{"citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:668958feb1a997bbe5ff930d625f75eebb6a50e02726e9f9a176ec6573eb3218","observation_id":"034fa015-f17c-41cd-8786-e6e6a151fd9b","resolution":{"observed_at":"2026-08-07T15:29:00.081152Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T15:28:56.822736Z","title":"Graph con- trastive learning with augmentations","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:56.822736Z"},"links":{"citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:ae6eb3995488fc1ac0b5060f9b5c8a7a519f4443f220db4b524bfce3c4cadb32","observation_id":"28a5b5f9-51c1-40d0-aa00-549a58666c15","resolution":{"observed_at":"2026-08-07T15:28:56.822736Z","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":"2026-08-07T15:28:59.680660Z","title":"Graph contrastive learning auto- mated","venue":null,"work_id":"26aba451-01d2-4ab0-ae12-e30968af8280","year":2021},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:56.935279Z"},"links":{"citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:03bbdab8c0571486e6849553d2114d8a136100d3ec57183484ceae2272631395","observation_id":"4bd337d9-6e34-4230-a096-6d0fad4928e1","resolution":{"observed_at":"2026-08-07T15:28:59.772013Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T15:28:59.389845Z","title":"Dual-discriminative graph neural network for imbalanced graph-level anomaly detection","venue":null,"work_id":"8f5aa935-4c67-45fe-88f8-096c6c5deb2e","year":2022},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:57.057119Z"},"links":{"citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:c872f27a8da138b9c58fdbe03efd87fde10a1e4a0d12d5bae966e00be5829edf","observation_id":"fd3a8cbb-91c2-485f-b97a-cde564807258","resolution":{"observed_at":"2026-08-07T15:28:59.539759Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T15:28:59.134990Z","title":"On using classification datasets to evaluate graph outlier detection: Peculiar observations and new insights","venue":null,"work_id":"48724785-c779-4475-b46c-01da04e3417e","year":2023},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:57.188970Z"},"links":{"citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:463e1a695cbe85915ba5d2edb1ec431571fe3d94129a1270e4ab72f621312ec2","observation_id":"97d85c06-8c9a-4f86-85c5-cb8718d2f215","resolution":{"observed_at":"2026-08-07T15:28:59.237986Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T15:28:58.760262Z","title":"gap-only","venue":null,"work_id":"599ebf32-0741-48a3-945e-b39e330dba18","year":2016},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:57.329968Z"},"links":{"citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:1147f73b0365b71f2cae9f0971af4eab4ab9bd2c43ef7ad491361bca59676bd6","observation_id":"5e7d3ade-3eac-4cfb-8bec-5d9159b34fcb","resolution":{"observed_at":"2026-08-07T15:28:58.948501Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T15:28:58.175789Z","title":"fixed” data-level Laplacian and “learned","venue":null,"work_id":"ca9f7bb6-2f58-48a4-9e08-4411b99e3640","year":null},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:57.644469Z"},"links":{"citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:f2cd87eb5103b168368710c013df89fb1c6cc8a3f4c5ead3ddf1441c55f2341b","observation_id":"a9ae3f9e-7ac5-4e46-b82b-ec640b89cdf0","resolution":{"observed_at":"2026-08-07T15:28:58.280694Z","resolver_source":"raw_fallback","status":"malformed_identifier"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T15:29:06.293681Z","title":"Convolutional neural net- works on graphs with fast localized spectral filtering","venue":null,"work_id":"66f75c17-7475-446b-91d1-5c350e6fea6f","year":2016},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":1997,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:50.915577Z"},"links":{"citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:ab8d8c80ce51228f14d495065b684a9a59d2e715fd1a2c0bef0e80bfbb030152","observation_id":"4b8a8982-96f4-42f6-8476-9103fc3858c9","resolution":{"observed_at":"2026-08-07T15:29:06.386787Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T15:29:04.943578Z","title":"Open graph benchmark: Datasets for machine learning on graphs","venue":null,"work_id":"bf7f1b9c-8f98-4a6d-bdf0-224a9bbc7457","year":2020},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":2006,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:51.748543Z"},"links":{"citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:0843bf6d97c631f5f268382740e18262c819f19afa61db1ad2178a5257bab1c9","observation_id":"c0462600-ab61-48fe-90a7-2f1743aa5bce","resolution":{"observed_at":"2026-08-07T15:29:05.110105Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1710.10903","last_updated":"2018-02-04T19:13:29Z","snapshot_observed_at":"2026-08-13T22:35:40.714745Z","submitted_at":"2017-10-30T12:41:12Z","title":"Graph Attention Networks","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1710.10903","snapshot_observed_at":"2026-08-07T15:28:55.568168Z","title":"Graph attention networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":2007,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:55.568168Z"},"links":{"cited_paper":"/paper/1710.10903","citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:2595ae45ef83d91d3b45c84bf0dbcf9ca94e75b1e479f895ba6087e15367d74b","observation_id":"8011f2bb-a229-4a00-af37-9cac84a9a48f","resolution":{"observed_at":"2026-08-07T15:28:55.568168Z","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":"2026-08-07T15:29:05.926980Z","title":"A data-centric framework to endow graph neural networks with out-of- distribution detection ability","venue":null,"work_id":"6739fca7-6a57-413f-a3b2-16134d32398c","year":2023},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":2010,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:51.229363Z"},"links":{"citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:9ad66bc91873825853f5caf0599655ad015d5f1beb7155304d1e6c1b32be3686","observation_id":"6f41c9c6-e866-4a91-8f1e-9c30d040c7c1","resolution":{"observed_at":"2026-08-07T15:29:06.005549Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T15:29:06.102866Z","title":"Lee, and Yuval Peres","venue":null,"work_id":"20183d97-0fca-4734-8041-02bed1e17c84","year":2010},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:51.056672Z"},"links":{"citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:a80b3d460f554bb9832a4c064829736ffdf81c420681b50a5e5cc21954e81942","observation_id":"16c53a27-011c-481f-88b6-0a3dffedc802","resolution":{"observed_at":"2026-08-07T15:29:06.207767Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T15:29:05.435629Z","title":"A baseline for detecting misclassified and out-of- distribution examples in neural networks","venue":null,"work_id":"89763886-103c-4ce7-90fc-e3b23506b7dd","year":2016},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":2017,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:51.511171Z"},"links":{"citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:213cb450a6d9c3ad2a14d9e45c87e629c16b13a03293941454c3389b2546898a","observation_id":"b1289217-a360-4d52-8842-f1c2afd5499c","resolution":{"observed_at":"2026-08-07T15:29:05.566913Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2110.11334","last_updated":"2024-01-23T07:36:33Z","snapshot_observed_at":"2026-08-16T19:00:19.697522Z","submitted_at":"2021-10-21T17:59:41Z","title":"Generalized Out-of-Distribution Detection: A Survey","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2110.11334","snapshot_observed_at":"2026-08-07T15:28:56.495972Z","title":"Generalized out-of-distribution detec- tion: A survey","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":2018,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:56.495972Z"},"links":{"cited_paper":"/paper/2110.11334","citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:b77ff157242551bd15dd364d40be35645be7346e1f85be7e394b79d5cd0ef248","observation_id":"33d4f645-1801-4cef-9b43-b6a1d5831eef","resolution":{"observed_at":"2026-08-07T15:28:56.495972Z","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":"2026-08-07T15:29:03.650957Z","title":"Graphde: A generative framework for debiased learn- ing and out-of-distribution detection on graphs","venue":null,"work_id":"f16a3631-7fde-4748-8695-5a2b2e82bfae","year":2022},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":2019,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:52.977500Z"},"links":{"citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:0fc713bef4f845085154e90e16e4f5ed020bce1fafc13a3d0b916ec506a353b5","observation_id":"e1ee09aa-6b78-4c73-84ea-34d77cf22fec","resolution":{"observed_at":"2026-08-07T15:29:03.780061Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T15:28:51.925019Z","title":"Praga: Prototype-aware graph adaptive aggregation for spatial multi-modal omics analysis","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:51.925019Z"},"links":{"citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:d248c54bdea54a65fa8b8f40750f4d4bdc34a2cedfa68e59ce06527fefa170bd","observation_id":"265a9e8e-4e8f-4915-b3d7-adfb155ec505","resolution":{"observed_at":"2026-08-07T15:28:51.925019Z","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":"2026-08-07T15:29:03.913684Z","title":"Label efficient semi- supervised learning via graph filtering","venue":null,"work_id":"bfff0014-df08-4748-8471-8f580751a306","year":2019},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":2021,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:52.838185Z"},"links":{"citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:c0500d1fc026562b59cd2c184ab3d2a101775a19b0c020fd20656fc7ab50ee16","observation_id":"0b08f09a-2c62-4658-968e-1083bbc53697","resolution":{"observed_at":"2026-08-07T15:29:04.040997Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T15:29:03.407340Z","title":"Enhancing the reliability of out-of-distribution image detection in neural networks","venue":null,"work_id":"b6be8a30-e3e0-4c75-bd7f-da45626c93f4","year":2017},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":2022,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:53.151970Z"},"links":{"citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:302c09da8690f57e52f7f1802bd3196810dfd264d8517e77b6138071aa579dd6","observation_id":"2d568418-f087-476b-b553-30978db648a7","resolution":{"observed_at":"2026-08-07T15:29:03.499341Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T15:29:05.662474Z","title":"Inductive representation learning on large graphs","venue":null,"work_id":"bf19964b-bad1-4d22-be0d-db10d5434e33","year":2017},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":2023,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:51.363041Z"},"links":{"citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:9eebf493dbdf689a7bdefc53d590931f2df7d878af3f1c5fef6ef768b809605d","observation_id":"be74c054-3462-4fe7-8296-ad75e4b25499","resolution":{"observed_at":"2026-08-07T15:29:05.838629Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+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":"2026-08-07T15:29:04.701187Z","title":"Drugood: Out-of- distribution dataset curator and benchmark for ai-aided drug discovery–a focus on affinity prediction problems with noise annotations","venue":null,"work_id":"4c0eaecf-796a-4702-b7cf-ee6a561cbfa9","year":2023},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":2024,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:52.043297Z"},"links":{"citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:70a7fc4a85aabc2499d88640e0cb35527cefeeb0012fe7c6b8e4cbdf49a2abe1","observation_id":"4dde5fc6-a735-4f8e-873b-3090b4fcee86","resolution":{"observed_at":"2026-08-07T15:29:04.811757Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2205.13845","last_updated":"2022-05-27T09:17:57Z","snapshot_observed_at":"2026-08-16T16:57:14.972841Z","submitted_at":"2022-05-27T09:17:57Z","title":"Raising the Bar in Graph-level Anomaly Detection","version":1},"cited_work":{"arxiv_id":"2205.13845","doi":null,"metadata_source":"pith","pith_arxiv_id":"2205.13845","snapshot_observed_at":"2026-08-07T15:28:57.810245Z","title":"Raising the Bar in Graph-level Anomaly Detection","venue":"cs.LG","work_id":"7c42c813-64aa-4f27-bf89-9250cc86fde6","year":2022},"citing_paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps","version":2},"reference_index":2025,"source":"pdf_text","source_observed_at":"2026-08-07T15:28:54.941725Z"},"links":{"cited_paper":"/paper/2205.13845","citing_paper":"/paper/2505.15177"},"observation_digest":"sha256:98d67ced0c98039d3ba347da2ff4d65cbbfc61f63e6214a35cbfbdf38f0b40d0","observation_id":"2ffce582-33b4-4a4b-aec6-0a695a8c6c21","resolution":{"observed_at":"2026-08-07T15:28:57.950323Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-17T06:30:58.91139+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2505.15177","last_updated":"2025-05-23T09:32:51Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-13T19:43:08.204748Z","submitted_at":"2025-05-21T06:47:44Z","title":"SpectralGap: Graph-Level Out-of-Distribution Detection via Laplacian Eigenvalue Gaps"},"reference_resolution":{"displayed":47,"state_counts":{"malformed_identifier":1,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":12,"verified_exact":1,"verified_fuzzy":33},"total_outbound_references":47},"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":"2026-08-17T06:30:58.91139+00:00","source":"crossref"},{"observed_at":"2026-08-17T06:30:54.323127+00:00","source":"retraction_watch"}],"thesis":"As of 17 August 2026, this Paper Citation Record lists 47 of 47 outbound references and 0 inbound Pith citation observations for arXiv:2505.15177."}