{"as_of":"2026-08-10T09:06:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:a294d3850c497b8ee1e18be26327fadaf6ef8d454c8baa70daa8efda4c201a47","coverage":[{"denominator":56,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":56,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-08T04:37:48.890342Z","state":"measured"},{"denominator":56,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":56,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-10T06:31:04.303077+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2502.08605/citation-record","integrity":"/paper/2502.08605/integrity","json":"/paper/2502.08605/citation-record.json","paper":"/paper/2502.08605"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:37:49.540933Z","title":"Constant curvature graph convolutional networks","venue":null,"work_id":"22d87a83-3f49-4a67-81dc-9d0fe3035ba1","year":2020},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":1,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.682152Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:8191f13168357c5315e32bf7cb560e702de2f195c2cffd111594b476c05d6428","observation_id":"2eb70b3a-8c0b-4eb3-842e-63b744a9cb60","resolution":{"observed_at":"2026-08-08T04:37:49.544769Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:37:49.529520Z","title":"Discrete laplace operator on meshed surfaces","venue":null,"work_id":"3eb18980-a9e5-44fc-92b9-5dc56162fdb6","year":2008},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":2,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.686872Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:db33b54ba5373cbf7636e1311bc3e19b7b580988108c2570365998c27053f259","observation_id":"87574b67-ec91-4d75-a079-47e952bd4cce","resolution":{"observed_at":"2026-08-08T04:37:49.533311Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:37:48.690969Z","title":"Hyperbolic graph convolutional neural networks","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":3,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.690969Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:de1506027bebd66dc29eaa9d195b9bafa2a536482408ce5d6fedcddd9dc844ac","observation_id":"bf627f85-b02f-4628-a6c7-2c858227379c","resolution":{"observed_at":"2026-08-08T04:37:48.690969Z","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":"2026-08-08T04:37:49.511798Z","title":"Detecting network anomalies using forman--ricci curvature and a case study for human brain networks","venue":null,"work_id":"1f2e42e5-54b9-426a-97be-7233453c2734","year":2021},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":4,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.696925Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:dc898729da3b10d640869f7c628f243f144f9d90f60ed1b7df81075e3744df73","observation_id":"71731454-7ac4-4cce-be70-0f5de46b097b","resolution":{"observed_at":"2026-08-08T04:37:49.515447Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:37:49.501613Z","title":"Hamilton’s Ricci flow, volume 77","venue":null,"work_id":"a3b27634-7fb6-4aaa-88bc-08362bc8c613","year":2023},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":5,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.701135Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:d5ea2118d7cfaed133b3f79f47136049d7d9c7db01d46d649582fdc4fbe978de","observation_id":"a664b414-e0d5-468a-b08c-51f7c603bf8b","resolution":{"observed_at":"2026-08-08T04:37:49.505036Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:37:49.490864Z","title":"The n-dimensional cotangent formula","venue":null,"work_id":"72d8fdbd-819b-4c37-92f1-ac761eaec2da","year":2019},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":6,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.705449Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:7a8f167a0587f26d582dfbb73925db4c8a0699700880de46b89025eb8602d420","observation_id":"dcf48927-f120-4284-8461-cd578727059a","resolution":{"observed_at":"2026-08-08T04:37:49.494907Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:37:49.479419Z","title":"Convolutional neural networks on graphs with fast localized spectral filtering","venue":null,"work_id":"840f8113-63f0-4db3-9067-5257af7483aa","year":2016},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":7,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.709809Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:e5ec5f8e89b4a6ece7052dce911e1b127eebb9d750425b971d627b65dbbe5be4","observation_id":"973d00b8-45f6-4988-ae23-b4bb55bb72e1","resolution":{"observed_at":"2026-08-08T04:37:49.483563Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:37:49.467945Z","title":"Deep anomaly detection on attributed networks","venue":null,"work_id":"8d3f1d90-d315-473d-b2d4-c2ac081825e9","year":2019},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":8,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.713546Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:cb4e67cca15f47023436b4afda9f04fcb09494f7aff41c75e31e4b4c9d39dbdd","observation_id":"f9c990cb-a4a4-4d39-a3a4-aea6d4ca9de0","resolution":{"observed_at":"2026-08-08T04:37:49.471603Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:37:49.456365Z","title":null,"venue":null,"work_id":"3895ae67-c1c4-4b7c-8536-6cd5219afa4f","year":1992},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":9,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.717124Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:36212ae29e99032336bb34d5e1a0cd387da1ae30abb3e56ee40317277bba2fcf","observation_id":"5cc62ff2-ba14-4e53-a9dc-fea2fadcbcd2","resolution":{"observed_at":"2026-08-08T04:37:49.460187Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:37:49.444295Z","title":null,"venue":null,"work_id":"a1465e85-718a-421b-b9c1-d8a3a8472f1f","year":2020},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":10,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.720921Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:fc436558a01f4eb856ddd0a30a9e1725588d615b5e6c6e454212b5a5dcebd82c","observation_id":"277caa12-55e6-46f0-9967-89a2f1e69b94","resolution":{"observed_at":"2026-08-08T04:37:49.448157Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:37:49.432735Z","title":"Cascade-lstm: A tree-structured neural classifier for detecting misinformation cascades","venue":null,"work_id":"59243c6a-d5ea-4f52-9992-b94e4313571e","year":2020},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":11,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.724649Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:002b7a4d799d317dcbba87cef53540af1b2f7290205ae8355e1dbf32a359a2b2","observation_id":"53125307-6a9c-4f4b-be4d-f66441b1755e","resolution":{"observed_at":"2026-08-08T04:37:49.436840Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:37:49.420922Z","title":"Anomalydae: Dual autoencoder for anomaly detection on attributed networks","venue":null,"work_id":"21deabf7-96fd-4e15-b93e-86cbfe3de560","year":2020},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":12,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.728563Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:602163b488f4af6d3abf31233f9d986e4e63cb6264e5289b49cc3b41ba5b7510","observation_id":"ae188c9d-bed1-42b2-8018-a7659d562b67","resolution":{"observed_at":"2026-08-08T04:37:49.425048Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:37:49.408545Z","title":"Learning mixed-curvature representations in products of model spaces","venue":null,"work_id":"d16c8dba-477e-49b2-bc37-7d0f4d26b4fe","year":2019},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":13,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.732169Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:f70ba115670456d4ce56ac839ba34e96136d9e7bfc0bb14b73a28039a5220ffe","observation_id":"006ad955-cf64-400c-9593-521944a7ce99","resolution":{"observed_at":"2026-08-08T04:37:49.412930Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:37:49.393855Z","title":"L., Ying, R., and Leskovec, J","venue":null,"work_id":"92f1bdc7-5b38-46aa-a98f-391e3bcb3e16","year":2017},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":14,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.735742Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:be0b0cfdf03670613892e3d467251dcdd0bab47493f893b4ffdf4e5ca12cba0a","observation_id":"90a463e7-fd25-498e-aa8e-5f27b5cba9bf","resolution":{"observed_at":"2026-08-08T04:37:49.397697Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:37:49.380231Z","title":"ADB ench: Anomaly detection benchmark","venue":null,"work_id":"5d30ed87-f437-4e30-b427-19bd3760d4e6","year":2022},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":15,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.739304Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:0d0620bbfe90b1d079a23a2458b4bf4f9cc1adfc2626e4af52858c205337c653","observation_id":"ca36588e-bf96-4ba3-905c-9d03803c6519","resolution":{"observed_at":"2026-08-08T04:37:49.385351Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:37:49.367399Z","title":"Analyzing the effectiveness of graph metrics for anomaly detection in online social networks","venue":null,"work_id":"ba2e3411-9580-4643-aa0f-bfa88883f75a","year":2012},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":16,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.742842Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:62aa7a8c21eb8e25ecb89e2f9701c86f1ff75115be90abc6ac98e6dac1188770","observation_id":"c7c9b310-ae79-47e3-9004-068772b20ffa","resolution":{"observed_at":"2026-08-08T04:37:49.371789Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2312.14535","last_updated":"2023-12-22T09:02:01Z","snapshot_observed_at":"2026-07-06T17:07:02.626339Z","submitted_at":"2023-12-22T09:02:01Z","title":"ADA-GAD: Anomaly-Denoised Autoencoders for Graph Anomaly Detection","version":1},"cited_work":{"arxiv_id":"2312.14535","doi":null,"metadata_source":"pith","pith_arxiv_id":"2312.14535","snapshot_observed_at":"2026-08-08T04:37:48.979972Z","title":"ADA-GAD: Anomaly-Denoised Autoencoders for Graph Anomaly Detection","venue":"cs.LG","work_id":"452a2b0b-7171-4d70-9662-e7bf4a98ed29","year":2023},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":17,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.746493Z"},"links":{"cited_paper":"/paper/2312.14535","citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:ce6b1d02393105bac985013671376f3eb07a9e35dbeca0a530bc9693398aed9a","observation_id":"b35c7f4e-4ece-4c31-a85a-60e02de50887","resolution":{"observed_at":"2026-08-08T04:37:48.984092Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:37:49.354302Z","title":"Ada-gad: Anomaly-denoised autoencoders for graph anomaly detection","venue":null,"work_id":"6abedb66-418b-4140-8215-c3e774b2cb00","year":2024},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":18,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.750767Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:c22e7a563d3ad37ea5ac8282738b178f96bbff51df83252be7303ac7c305ea50","observation_id":"2adaa976-9500-4bb8-a787-2f7a155aa0c5","resolution":{"observed_at":"2026-08-08T04:37:49.358659Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:37:49.342272Z","title":"Bernnet: Learning arbitrary graph spectral filters via bernstein approximation","venue":null,"work_id":"9b3bf73e-2d0c-449a-85f7-c3dfd4dc7f62","year":2021},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":19,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.754398Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:3d33f0bd2aa8ed8b64bb158d7f398a2660000604817cc65f9d108da7fd4eafe2","observation_id":"9725e2df-223a-4047-a14f-085476adc9e3","resolution":{"observed_at":"2026-08-08T04:37:49.346131Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2012.13637","last_updated":"2020-12-25T22:36:22Z","snapshot_observed_at":"2026-07-06T10:27:54.164256Z","submitted_at":"2020-12-25T22:36:22Z","title":"Graph Convolutional Networks for traffic anomaly","version":1},"cited_work":{"arxiv_id":"2012.13637","doi":null,"metadata_source":"pith","pith_arxiv_id":"2012.13637","snapshot_observed_at":"2026-08-08T04:37:48.962473Z","title":"Graph Convolutional Networks for traffic anomaly","venue":"cs.LG","work_id":"69be75cc-13d7-441c-8707-448fe896eff4","year":2020},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":20,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.758279Z"},"links":{"cited_paper":"/paper/2012.13637","citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:4f9d5a62744966fbcb52371989be4bc56e4df92896a26586b9ff66a01a359b37","observation_id":"66c169e5-6b88-42a8-ad6f-d94f5f6e2a3b","resolution":{"observed_at":"2026-08-08T04:37:48.968395Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:37:49.331576Z","title":"Dgraph: A large-scale financial dataset for graph anomaly detection","venue":null,"work_id":"6136147c-a303-4d00-b3da-951ae8a66bf7","year":2022},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":21,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.762552Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:5b5435eff81ae5726b7585119ed4117fddfc5ded2963c9fdd795f7d2ca0c236c","observation_id":"7b979849-b963-489f-9535-da4b0b5fde86","resolution":{"observed_at":"2026-08-08T04:37:49.335273Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:37:49.319057Z","title":"and Liu, S","venue":null,"work_id":"158d6f04-658b-4da4-851f-a144f1a1e3c8","year":2014},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":22,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.766264Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:e16e7516de3ee7da606907ec805806c8394d2733237c97103f48f8d283c1b25b","observation_id":"245b31fe-6a76-4790-b4c6-b9ed416d5bc9","resolution":{"observed_at":"2026-08-08T04:37:49.323171Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:37:49.307233Z","title":null,"venue":null,"work_id":"5e76ff83-215a-4a8b-9c16-87b04323ae66","year":2017},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":23,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.770000Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:74bb28048d7dc40d5b7705b7412f2cf67823c3d058031ea499ada2bd8310fc00","observation_id":"2ff45b50-c566-4d9c-8bb1-0f1b36752a5c","resolution":{"observed_at":"2026-08-08T04:37:49.311050Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:37:49.295949Z","title":"The hungarian method for the assignment problem","venue":null,"work_id":"50f6aeb1-28e9-48fb-84f2-c166540bb89a","year":1955},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":24,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.773622Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:3f56506121c3370326ad0f85d6d456ed7c8a6d64ce64bf2d06bb7e5951d9e7fc","observation_id":"091bd3b6-9266-4679-8ad3-2b3fb46e0ea1","resolution":{"observed_at":"2026-08-08T04:37:49.300161Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:37:49.283077Z","title":"Predicting dynamic embedding trajectory in temporal interaction networks","venue":null,"work_id":"92903a3d-e611-4c84-be29-187348048ce5","year":2019},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":25,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.777085Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:24ed23f2a692cec3cb71c554f0d0f5e5b7e8993f5913d4f7bbe709efa4a71872","observation_id":"8b0980f2-2ef6-47b2-a235-88befe17e0bf","resolution":{"observed_at":"2026-08-08T04:37:49.287386Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:37:49.270826Z","title":"Ricci curvature of graphs","venue":null,"work_id":"6a0a9332-07ba-43ac-af3c-8cc4830cd247","year":2011},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":26,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.780430Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:eab285817be73c6cfc6038a26c2e53952bd890d048e3101cd762c2ad1754173a","observation_id":"ab7960fd-57fe-45e0-9991-8cac43ce76e6","resolution":{"observed_at":"2026-08-08T04:37:49.274949Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:37:49.258061Z","title":"H., Jia, Z., and Yu, P","venue":null,"work_id":"4f93682e-b241-4451-bdbd-6605429f1abb","year":2022},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":27,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.783750Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:d78b95dd168116fbfae4d422ac7a9d9cb8c2c99d3bdfd269a2380b3caf462e37","observation_id":"f229c164-365b-43a8-8c6e-5a9621cfdcd6","resolution":{"observed_at":"2026-08-08T04:37:49.262461Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:37:48.787710Z","title":"Sphereface: Deep hypersphere embedding for face recognition","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":28,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.787710Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:2519aba107971205d304ff85ebbaf2b556913c2cd232ffdc029b3e7f2ef96839","observation_id":"07aedf05-6290-40d2-84e4-d190a34e6386","resolution":{"observed_at":"2026-08-08T04:37:48.787710Z","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":"2026-08-08T04:37:49.239667Z","title":"Pick and choose: A gnn-based imbalanced learning approach for fraud detection","venue":null,"work_id":"3e35e77f-b332-4c7b-b734-11e5d0a8ad78","year":2021},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":29,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.791222Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:a5cf0b355879cecbc0075a24e53eb33b191865cf5538242c9522b6d1afab5a6e","observation_id":"7d80a50a-0e63-46c8-bc5f-acd0b0343c5a","resolution":{"observed_at":"2026-08-08T04:37:49.243362Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:37:49.229220Z","title":null,"venue":null,"work_id":"cf3f303a-aabf-4841-bb20-156d48095488","year":2013},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":30,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.794799Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:03684a5773f98dc697a37209f9c991adf61b7230ba523c8f25c49da534b56ca6","observation_id":"dc5f3e4b-25d0-4034-bfee-9fa06f45eb1d","resolution":{"observed_at":"2026-08-08T04:37:49.232761Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:37:49.218176Z","title":"Network alignment by discrete ollivier-ricci flow","venue":null,"work_id":"ec09772d-627e-4b19-9172-83af05427e7d","year":2018},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":31,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.798402Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:5e7c39ccaf6b8bcc90d2aa53c9b63599e78ecfbae6f923ea9019fa44b6cb0c57","observation_id":"3d25619e-f1d4-41ee-a50a-cb1ac343971a","resolution":{"observed_at":"2026-08-08T04:37:49.222027Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:37:49.207257Z","title":"Ricci curvature of metric spaces","venue":null,"work_id":"f76d28b7-2051-4811-85d8-3749a6749eff","year":2007},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":32,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.801870Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:618d5f76fa9e58ecda5c5aa5bd5757f5a6cb0d7f8d8dcfd8a3275014ed76b8d5","observation_id":"55764fb5-6420-4e95-9b1a-ef8aa915bef0","resolution":{"observed_at":"2026-08-08T04:37:49.211403Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:37:49.196454Z","title":"Ricci curvature of markov chains on metric spaces","venue":null,"work_id":"39efcb1c-fba1-4202-9519-a5d802d84983","year":2009},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":33,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.805350Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:0eaa05f1f680f90ed3b34bdea52a9de5dc3a805eeca6666a0ae2a2828c75f4be","observation_id":"38b1dd66-947f-4743-b54f-365f194d05f3","resolution":{"observed_at":"2026-08-08T04:37:49.200378Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:37:49.185220Z","title":"and Rossi, F","venue":null,"work_id":"ab1c8c8a-711c-4498-9582-2e48cd62f159","year":2016},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.808584Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:c29ab2defca96ebc08fdbcd50ce50167d7599e2b3074672fe9404f08be84c304","observation_id":"900eb7ba-e2ff-488b-9e7a-0384791e8dc8","resolution":{"observed_at":"2026-08-08T04:37:49.189463Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:37:49.174291Z","title":"A critical look at the evaluation of gnns under heterophily: are we really making progress? In ICLR, 2023","venue":null,"work_id":"1c5d874e-9433-4710-94ed-db38f8e45950","year":2023},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":35,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.811924Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:799abcd4b00fafdaff92128e8d7b250b995da6da1c70f91ee1de21a50595aaa0","observation_id":"f9a41ec2-2af8-4552-809d-5661ff840cfa","resolution":{"observed_at":"2026-08-08T04:37:49.178228Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:37:49.162802Z","title":"and Akoglu, L","venue":null,"work_id":"b0aadc3b-340d-4a80-a866-d36b145d880a","year":2015},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":36,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.815608Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:74cc216967c1c3ff61355f83a5318047ba614a4128b31464e89ea67df1d41167","observation_id":"04331234-c91b-4d22-a2e9-fd4100c36f50","resolution":{"observed_at":"2026-08-08T04:37:49.166513Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:37:49.151786Z","title":"Gad-nr : Graph anomaly detection via neighborhood reconstruction","venue":null,"work_id":"4fbab671-fd4b-4b11-9e25-45ab8b66129c","year":2024},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":37,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.819046Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:8f298ec218780089594f2e7fcdb5fc3c88e89b72a5157028f73b792998297ec4","observation_id":"15596e27-cd59-47bb-a11e-0cced3a1456b","resolution":{"observed_at":"2026-08-08T04:37:49.155604Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:37:49.141183Z","title":"Karate club: an api oriented open-source python framework for unsupervised learning on graphs","venue":null,"work_id":"fbcdf2aa-be94-4091-9671-af35b36c43b9","year":2020},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":38,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.822738Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:50613a50ac0b707c42b30723c696f05103539630a203e7eb1c5bde7074ed3927","observation_id":"41da7bf6-ecb5-4921-9fbe-c58a1827bfa2","resolution":{"observed_at":"2026-08-08T04:37:49.144972Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:37:49.130783Z","title":"Representation tradeoffs for hyperbolic embeddings","venue":null,"work_id":"87e4d247-3650-4739-bc2d-b1eab27fac29","year":2018},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":39,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.826298Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:60e055d452fd7efbc904fed2fc32ec01f525ddcc0490f99fd6d4f70e409bcc62","observation_id":"594d0a71-ecb6-4b18-a739-223db28b1627","resolution":{"observed_at":"2026-08-08T04:37:49.134488Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:37:49.120803Z","title":null,"venue":null,"work_id":"3350d192-b34e-4246-921b-0310ec82b8fc","year":2017},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":40,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.830003Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:e9f5a7918c3f4eda301440aaa80a0e2136e934483f30271cdc458fb6386beef6","observation_id":"3b3d98b1-0bcd-4895-83ce-91c5fe15bf62","resolution":{"observed_at":"2026-08-08T04:37:49.124207Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:37:49.110584Z","title":"and Knopp, P","venue":null,"work_id":"44d01892-d541-4d13-8d5d-ebef746cf04e","year":1967},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":41,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.833402Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:0d40cd229abad9a9091e408eeebad5e84da2fc656e2859a9f303df4505dfc954","observation_id":"b9867406-7574-4b17-a70f-1e9484588d0e","resolution":{"observed_at":"2026-08-08T04:37:49.114325Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:37:49.100115Z","title":"Rethinking graph neural networks for anomaly detection","venue":null,"work_id":"b51625c7-c15f-48ff-817d-5879f01bcaff","year":2022},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":42,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.836931Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:19899e193b847bdcb5bdfffc9bf15dcc27ba50d590c78be99d7f4a4c2f3a1da5","observation_id":"dd37dec1-69d8-450f-9cb9-c86742d9c527","resolution":{"observed_at":"2026-08-08T04:37:49.103890Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:37:49.089303Z","title":"Ricci curvatures of contact riemannian manifolds","venue":null,"work_id":"d5bfb274-714c-41a4-aa37-a81e62bd63b6","year":1988},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":43,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.840301Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:ac7e07a35188fc869541f463f71115546c48272ba013f9b9dd5d030d584d1065","observation_id":"cbf63fb0-341f-4ab7-9b54-3dcf7f2024c8","resolution":{"observed_at":"2026-08-08T04:37:49.093006Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2307.10155","last_updated":"2023-07-19T17:35:08Z","snapshot_observed_at":"2026-07-06T15:55:59.949673Z","submitted_at":"2023-07-19T17:35:08Z","title":"Curvature-based Clustering on Graphs","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2307.10155","snapshot_observed_at":"2026-08-08T04:37:48.844277Z","title":"Curvature-based clustering on graphs","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":44,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.844277Z"},"links":{"cited_paper":"/paper/2307.10155","citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:29fc95a31e8578470539cbab70c41f697a50435d955f419da97e6c8ee4264ed7","observation_id":"3dd0e992-1a19-43b1-b342-95dad1451f23","resolution":{"observed_at":"2026-08-08T04:37:48.844277Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2111.14522","last_updated":"2022-11-12T16:11:19Z","snapshot_observed_at":"2026-07-06T12:13:06.745394Z","submitted_at":"2021-11-29T13:27:56Z","title":"Understanding over-squashing and bottlenecks on graphs via curvature","version":3},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2111.14522","snapshot_observed_at":"2026-08-08T04:37:48.848237Z","title":"P., Dong, X., and Bronstein, M","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":45,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.848237Z"},"links":{"cited_paper":"/paper/2111.14522","citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:683cba18fb9418f212f063d38b628e2619fdd69a2eb7f7ef674763e7a76cd68a","observation_id":"3101780f-f191-4272-933c-5c7301f4db5d","resolution":{"observed_at":"2026-08-08T04:37:48.848237Z","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":"2026-08-08T04:37:49.078240Z","title":null,"venue":null,"work_id":"2e6ef498-bfaf-418f-813d-e8682ee5b9ec","year":2001},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":46,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.852033Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:84e0e22048d29a5fc95a907d9d512bd0a421a9d6c575326574ba6e66a0ee3bfd","observation_id":"2c9a1767-e8f4-4ffc-b7b2-00b191c550c6","resolution":{"observed_at":"2026-08-08T04:37:49.082039Z","resolver_source":"raw_fallback","status":"unresolved"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:37:49.067507Z","title":"Geometry of laplace-beltrami operator on a complete riemannian manifold","venue":null,"work_id":"0b5d4d6b-e5d7-4c80-b225-5607641e5bcd","year":1993},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":47,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.855577Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:fb1aa041ccd74c555b7ee6560a73dc0be96397cba936f87274fd30ad51952d87","observation_id":"f740fbf6-7a33-4510-903a-b66951b9cef5","resolution":{"observed_at":"2026-08-08T04:37:49.071348Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1710.10903","last_updated":"2018-02-04T19:13:29Z","snapshot_observed_at":"2026-07-06T02:11:23.670680Z","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":"2026-08-08T04:37:48.859401Z","title":"Graph attention networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":48,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.859401Z"},"links":{"cited_paper":"/paper/1710.10903","citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:d6f6b92e133f201ce8ab978abf6a91ff0d9179af65537723966834ad597bfba1","observation_id":"8118e529-efb3-4db6-98af-e9f5f4214440","resolution":{"observed_at":"2026-08-08T04:37:48.859401Z","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":"2026-08-08T04:37:49.056384Z","title":"and Zhu, H","venue":null,"work_id":"06986830-365b-4d7f-82d6-19cbbeaf31b1","year":2022},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":49,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.863360Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:3f79330beea3154ef45f8a27579809976b123dfa126c0f0a18bdab23604f52ed","observation_id":"4ff787a0-9356-47f9-a969-b5a296dbc475","resolution":{"observed_at":"2026-08-08T04:37:49.060118Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:37:49.044753Z","title":"Decoupling representation learning and classification for gnn-based anomaly detection","venue":null,"work_id":"7a11148e-2620-44b2-9dbb-db62b5ec42ae","year":2021},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":50,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.866985Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:e4f075e68f4a9597c93ce070c7593855077cd40ec2cc55200ed47a7f12cf9d40","observation_id":"0580729d-4fe3-421e-8280-60fe9a5e4ee3","resolution":{"observed_at":"2026-08-08T04:37:49.048823Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"1908.02591","last_updated":"2019-07-31T22:10:01Z","snapshot_observed_at":"2026-08-07T09:37:01.633122Z","submitted_at":"2019-07-31T22:10:01Z","title":"Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensics","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1908.02591","snapshot_observed_at":"2026-08-08T04:37:48.870949Z","title":null,"venue":null,"work_id":null,"year":1908},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":51,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.870949Z"},"links":{"cited_paper":"/paper/1908.02591","citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:56d4cac71ac6460ab9dd18392e12cbe206e28e6f144d395a66e09f05cbff203d","observation_id":"70add1b4-5b43-47ce-8446-3c2058ff85b2","resolution":{"observed_at":"2026-08-08T04:37:48.870949Z","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":"2026-08-08T04:37:49.033378Z","title":"Pseudo-riemannian graph convolutional networks","venue":null,"work_id":"e1e06f3f-576a-4621-ac03-0535f95836a4","year":2022},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":52,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.875573Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:7f67a6747a99bd0f4ee3b47c72f5417b9f08165b8ace4461e25c7d48da7368fd","observation_id":"63736e00-24c4-4e83-8420-beeb2812d590","resolution":{"observed_at":"2026-08-08T04:37:49.037221Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:37:49.021474Z","title":"Casflow: Exploring hierarchical structures and propagation uncertainty for cascade prediction","venue":null,"work_id":"ba5df890-68f4-445c-993d-1a6a2ad3295d","year":2021},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":53,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.879204Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:1c317708e0ef489f0a3cd66bb39cc89c5f6b3b530a2655fd5387d25c5acf7c36","observation_id":"f30753ed-464d-4e07-a3dd-38ce3584148e","resolution":{"observed_at":"2026-08-08T04:37:49.026012Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:37:49.010190Z","title":"Hyperbolic graph attention network","venue":null,"work_id":"97a6c026-ddd4-44a7-b28f-0288e725ed89","year":2021},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":54,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.882980Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:4c0bb6dd23b46c3fea31156f65d1f580cfc3f5d75a7b2e51c21065a773171801","observation_id":"c2e62ce1-dedb-4eae-8beb-3631908f838b","resolution":{"observed_at":"2026-08-08T04:37:49.013996Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:37:48.998591Z","title":"Error-bounded graph anomaly loss for gnns","venue":null,"work_id":"71ab2b06-492f-4fa6-8e20-b490d408fb02","year":2020},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":55,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.886622Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:ec2917700b0e120ae2d9b66b3b478206c72956239b6183f8c58dd12d9cc7734c","observation_id":"764dbd75-7072-43f5-8bec-5ceedd8e278f","resolution":{"observed_at":"2026-08-08T04:37:49.002592Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-10T06:31:04.303077+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-08T04:37:48.890342Z","title":"write newline","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection","version":2},"reference_index":56,"source":"arxiv_source","source_observed_at":"2026-08-08T04:37:48.890342Z"},"links":{"citing_paper":"/paper/2502.08605"},"observation_digest":"sha256:850770dd1337df51afb8f7db662f88e5f60cfdee5a1e514e42a6ea1004bea80a","observation_id":"532338af-19b9-4c7c-9b2b-755ba15bedb7","resolution":{"observed_at":"2026-08-08T04:37:48.890342Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2502.08605","last_updated":"2025-06-04T20:09:51Z","latest_version":2,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-08T18:45:32.403051Z","submitted_at":"2025-02-12T17:49:46Z","title":"CurvGAD: Leveraging Curvature for Enhanced Graph Anomaly Detection"},"reference_resolution":{"displayed":56,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":13,"verified_exact":2,"verified_fuzzy":41},"total_outbound_references":56},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-10T06:31:04.303077+00:00","source":"crossref"},{"observed_at":"2026-08-10T06:30:57.382061+00:00","source":"retraction_watch"}],"thesis":"As of 10 August 2026, this Paper Citation Record lists 56 of 56 outbound references and 0 inbound Pith citation observations for arXiv:2502.08605."}