{"as_of":"2026-08-16T23:31:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:d8d35dab33d0a6d42e6997db44c6d2cdb299d8698e580d029e5694a106f69cdd","coverage":[{"denominator":53,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":53,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-15T16:18:23.084662Z","state":"measured"},{"denominator":54,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":54,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-16T06:30:59.297886+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-12T19:12:02.322390Z","state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"pith","source_observed_at":"2026-08-12T19:12:02.441708Z","state":"measured"}],"external_citation_measurements":[],"inbound":[{"citation":{"cited_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"cited_work":{"arxiv_id":"2509.06609","doi":null,"metadata_source":"pith","pith_arxiv_id":"2509.06609","snapshot_observed_at":"2026-08-12T19:12:02.441708Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","venue":"cs.LG","work_id":"c8d14de9-2b06-4920-a81c-871526524686","year":2025},"citing_paper":{"arxiv_id":"2608.10699","last_updated":"2026-08-11T09:20:04Z","snapshot_observed_at":"2026-08-15T06:16:45.855838Z","submitted_at":"2026-08-11T09:20:04Z","title":"ProTAGAD: A Foundation Model for TAG Anomaly Detection with Decoupled Topological and Textual Prototypes","version":1},"reference_index":34,"source":"arxiv_source","source_observed_at":"2026-08-12T19:12:02.322390Z"},"links":{"cited_paper":"/paper/2509.06609","citing_paper":"/paper/2608.10699"},"observation_digest":"sha256:9edf7cbc6e75a7a1fcc54682db999831bc151818399f67669bc4850ed729a66c","observation_id":"f1589428-8ab1-469a-b59d-a2c29d3cccd8","resolution":{"observed_at":"2026-08-12T19:12:02.447638Z","resolver_source":"local_arxiv","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"links":{"evidence":"/evidence","html":"/paper/2509.06609/citation-record","integrity":"/paper/2509.06609/integrity","json":"/paper/2509.06609/citation-record.json","paper":"/paper/2509.06609"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":"raw_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-15T16:18:25.511940Z","title":"How to use graph data in the wild to help graph anomaly detection? InKDD, page 61–72, 2025","venue":null,"work_id":"a3c622b7-f9a4-47b0-a8e0-89df6780fb98","year":2025},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:21.884193Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:9c5dad7339f94941c14c403fbadac501fe387aba30b18d742df09e1dfd96a7a6","observation_id":"2ac12df8-1a46-4752-8d9e-4621e0bd7796","resolution":{"observed_at":"2026-08-15T16:18:25.516118Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:25.421922Z","title":"Wirjanto, and Qinmu Peng","venue":null,"work_id":"6faabc35-0ac0-4570-b129-e51ff3eb9dd0","year":2024},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:21.890150Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:8ce43244bd9bd95c5403cdee8b8a0ff8bf7dc9f44ec18646ff52652ef13f508d","observation_id":"6f323ce5-7a3f-4c3d-ae3f-0877d98e6da1","resolution":{"observed_at":"2026-08-15T16:18:25.449144Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:25.322092Z","title":"Divide and denoise: Empowering simple models for robust semi-supervised node classification against label noise","venue":null,"work_id":"dddf52a2-f356-4c71-8515-8347a43c49ac","year":2024},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:21.895048Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:21f53d0a7bcc5a1422f2c91fb0a89dfb1a425aa81469fbe61897a9239b446afc","observation_id":"2c080474-c40d-47da-ab40-8305a0188641","resolution":{"observed_at":"2026-08-15T16:18:25.357330Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:25.307628Z","title":"Cross- domain graph anomaly detection.TNNLS, 33(6):2406–2415, 2021","venue":null,"work_id":"a0ca9d1d-71d5-4a30-8133-333482d00225","year":2021},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:21.900240Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:3d3007c5c04e5977affcf8951eec7a7173ae943d93655be2859f336b7ab7f01b","observation_id":"8b179126-af0e-4237-921f-ac17b4a30305","resolution":{"observed_at":"2026-08-15T16:18:25.312030Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:25.293512Z","title":"Simultaneously detecting node and edge level anomalies on heterogeneous attributed graphs","venue":null,"work_id":"16cecd97-8d04-4781-8b31-02228719c5c9","year":2024},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:21.906175Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:5240e0b2dd51639fc08237dbb846803dfceaa9e3f6dd744a9f36ffef5a7e5329","observation_id":"265862ff-ac70-4b21-a70a-81b3654e47a5","resolution":{"observed_at":"2026-08-15T16:18:25.298823Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:25.279216Z","title":"Alleviating structural distribution shift in graph anomaly detection","venue":null,"work_id":"90d315a1-955f-488d-bbe8-6007e08dbb1a","year":2023},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:21.911912Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:a5222502b3837e0320bf3359d44f1c728b54ccd02e42eaa7e52e2a18ba9b8c8f","observation_id":"c5697bd4-2e4c-4336-9660-7541cbee6eba","resolution":{"observed_at":"2026-08-15T16:18:25.283690Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:25.260497Z","title":"Anomaly detection in the open world: Normality shift detection, explanation, and adaptation","venue":null,"work_id":"3c2ff328-cbe4-439f-9b16-30295e44abb4","year":2023},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:21.984022Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:8b35fcc33b9fb58fb40495b3882e6975e7fe60d1fe38a34e20377848487c294b","observation_id":"e6e986dc-67ec-475a-983a-7de4684280bb","resolution":{"observed_at":"2026-08-15T16:18:25.270154Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:25.204383Z","title":"Hybrid-order anomaly detection on attributed networks.TKDE, 35(12):12249–12263, 2021","venue":null,"work_id":"d542d62f-247a-4878-96e5-d4a818236e30","year":2021},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:22.015144Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:9cee57ba57ce08019fc1e5778309c6a491e39860c149d09a474658a9f5cfd4c8","observation_id":"7678a219-b778-4398-b608-6a2f19c7758a","resolution":{"observed_at":"2026-08-15T16:18:25.228075Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:25.105094Z","title":"Assemble your crew: Automatic multi-agent communication topology design via autoregressive graph generation.arXiv, 2025","venue":null,"work_id":"770b789f-3641-449b-b76f-b8165c6eedb0","year":2025},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:22.020982Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:52395c9489c2ff2139b52d1759b40a5a30279c5f186f2bd00e1e3377e9686358","observation_id":"2b62f005-6a34-4c51-a29c-6fff66151a67","resolution":{"observed_at":"2026-08-15T16:18:25.159414Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:25.044867Z","title":"Graph anomaly detection with domain-agnostic pre-training and few-shot adaptation","venue":null,"work_id":"b330ca20-a6c0-48db-93a0-a85f116d3992","year":2024},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:22.026603Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:dbdb8edd43cfedb847d0af621100401c2534145baca91ea68debcb3067196553","observation_id":"acea3628-52b5-4b63-82d4-12f2fe57d92e","resolution":{"observed_at":"2026-08-15T16:18:25.056768Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:25.026476Z","title":"Relevance-aware anomalous users detection in social network via graph neural network","venue":null,"work_id":"1be4ea64-2cc5-4243-9840-0f391094a7c9","year":2021},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:22.030868Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:00dffafa1156a7c8eb5754f0c748bc21a7b350f5c72edc4a8f95b8c8aa0282f8","observation_id":"837e3728-6f14-4757-9134-a8859a94909b","resolution":{"observed_at":"2026-08-15T16:18:25.033740Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:24.996867Z","title":"Cross- domain graph level anomaly detection.TKDE, 2024","venue":null,"work_id":"ef66e78a-9482-4dd0-82ec-a75b1270e0f8","year":2024},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:22.035855Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:5bed39146e7e41491f1d4eb026fe0b99ceaa34147a767834abb059a8d2f7e3f4","observation_id":"324f7073-e8da-4e97-9a13-d3e10cb00c58","resolution":{"observed_at":"2026-08-15T16:18:25.006858Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:24.982914Z","title":"Vicky Zhao, Yuan Yao, and Jia Li","venue":null,"work_id":"b1fb74a3-d861-4908-aa6a-6532a6f2cd46","year":2024},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:22.040846Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:61b15769ad8c76fb84b9a6266b8cc370399ed1938005ddaec58e652b134ea5db","observation_id":"3ed13f9a-ae15-4efa-ad8f-8eb8e6f4da8f","resolution":{"observed_at":"2026-08-15T16:18:24.987334Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:24.969441Z","title":"Bourne: Bootstrapped self-supervised learning framework for unified graph anomaly detection","venue":null,"work_id":"c3ed7e43-7bd2-4103-8729-ba2bed1f1731","year":2024},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:22.045070Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:c5c9d398c3ff0a1d9d5f470806e419e7383a8abb86b0ac6b22aafaab0f4aaae3","observation_id":"4bb2a2e0-8cbc-4e44-a3ce-7ad02b49b3eb","resolution":{"observed_at":"2026-08-15T16:18:24.973683Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:24.955713Z","title":"Pygod: A python library for graph outlier detection.JMLR, 25(141):1–9, 2024","venue":null,"work_id":"41fa129c-feaa-46c2-a64b-53d2b3e84df1","year":2024},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:22.052287Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:820e1f5eb20f2f256a9af7e1034f200ceba5762a2c23edc951e31fb49e2fa2d4","observation_id":"ef873f57-b55d-42a3-b9d2-3bd3782ac2b3","resolution":{"observed_at":"2026-08-15T16:18:24.960205Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:24.863086Z","title":"Bond: Benchmarking unsupervised outlier node detection on static attributed graphs","venue":null,"work_id":"6d82b81a-f8c7-4ea3-926f-84fe9863fb5f","year":2022},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:22.057728Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:dd9b69a4df77bbfe3877af6b69463bc2b56cc5ecbba8d708b001eec66f033e72","observation_id":"f483e409-af3e-4536-abb0-6eddbf20b81a","resolution":{"observed_at":"2026-08-15T16:18:24.916360Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:24.850009Z","title":"Anomalyllm: Few-shot anomaly edge detection for dynamic graphs using large language models","venue":null,"work_id":"88d69e53-a60f-403f-bac2-a04c635ac526","year":2024},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:22.074988Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:ff7b880115d1516509033c583119c76ef5658ad0fe19364b81cf6e89013131dc","observation_id":"35a2cbba-cf41-475d-a8d0-bb2e55909a30","resolution":{"observed_at":"2026-08-15T16:18:24.854262Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:24.835949Z","title":"Test-time adaptation on recommender system with data-centric graph transformation.IJCAI, 2025","venue":null,"work_id":"aadf4b9d-57b5-46e8-8741-055402fd3d6b","year":2025},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:22.146121Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:dc39e526ac126929e8dc6b0f29b2d32b2403d7671b59f53349f3a9443b97c03f","observation_id":"d0bb1d40-b3fc-4ae8-90b9-c4a413060db6","resolution":{"observed_at":"2026-08-15T16:18:24.840804Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:24.820632Z","title":"Self-supervision improves diffusion models for tabular data imputation","venue":null,"work_id":"d831c3b9-9fad-4a5b-b21f-12e846f2d2fb","year":2024},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:22.232747Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:92294a4d2784ea2ffaee0a4b39a3d5868614a92b73110fd04c303180bd7849c9","observation_id":"ffd75202-09dd-48ce-8b02-e94bfea5a4dd","resolution":{"observed_at":"2026-08-15T16:18:24.825153Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:24.806834Z","title":"Towards self-interpretable graph-level anomaly detection","venue":null,"work_id":"19e26e45-a673-4a76-bfbb-9845bf1ae747","year":2023},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:22.284768Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:ac73d9ff21a7967d8a39f4292083bde6dee29d6f4133f358de0e5e46466927a8","observation_id":"fc4bed9e-43a6-4443-b8ae-e7a4b1c46040","resolution":{"observed_at":"2026-08-15T16:18:24.811361Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:24.729178Z","title":"ARC: A generalist graph anomaly detector with in-context learning","venue":null,"work_id":"d712764d-917b-4fdb-b6e0-1250cb75a51c","year":2024},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:22.315093Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:f46dc351f0cf81819ff17845769dde31c4a538c5edd37e878d55523cc1511e1c","observation_id":"71974e9f-b5f5-42ba-bcac-3e7ee7398e25","resolution":{"observed_at":"2026-08-15T16:18:24.773588Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:24.643701Z","title":"Anomaly detection on attributed networks via contrastive self- supervised learning.TNNLS, 33(6):2378–2392, 2021","venue":null,"work_id":"b680509a-e931-4ba1-8ae5-f0706a7657f5","year":2021},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:22.320783Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:b16d23a07ac33e6d97cfee2b51de51234aef75e0433ed380b2461e1b016736d1","observation_id":"54695c56-dac3-4ce7-a026-f04ba83b9d19","resolution":{"observed_at":"2026-08-15T16:18:24.682304Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:24.630621Z","title":"Graph- augmented large language model agents: Current progress and future prospects.arXiv, 2025","venue":null,"work_id":"3f653433-a198-4f6b-a53d-edf51845e6e3","year":2025},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:22.324783Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:5f795db96c9fdcf97a87365838358cf6e4a3f980aa258d0a963750f849178a97","observation_id":"8a477e86-1495-4362-bfa3-fd7a1a0cb63c","resolution":{"observed_at":"2026-08-15T16:18:24.634989Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:24.613760Z","title":"Grace: Empowering llm-based software vulnerability detection with graph structure and in-context learning.Journal of Systems and Software, 212:112031, 2024","venue":null,"work_id":"4535af1c-5a7d-495e-b071-e6ae84841f61","year":2024},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:22.329322Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:56f25ae7a3eaba864324ae80034650be57b306ec40cc7b56396a3982ec6d8dd6","observation_id":"d71ee8b2-f46d-469b-a0a4-492091e9f5ec","resolution":{"observed_at":"2026-08-15T16:18:24.620748Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:24.594456Z","title":"A comprehensive survey on graph anomaly detection with deep learning.TKDE, 35(12):12012–12038, 2021","venue":null,"work_id":"600dd2ba-258d-46ab-a818-4cef45c4fa64","year":2021},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:22.333930Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:fc0d599e491a1e27993e3b34dbd5706d5d0ff126ff022343ba1077ea1919ded1","observation_id":"d150f04b-5b17-43d6-b924-0ca2de4dd38e","resolution":{"observed_at":"2026-08-15T16:18:24.599965Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:24.580086Z","title":"Blindguard: Safeguarding llm-based multi-agent systems under unknown attacks.arXiv, 2025","venue":null,"work_id":"7b6272cf-10e3-4fe4-80fe-40a2e3adc2da","year":2025},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:22.338334Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:3a4418a057b03d3c7f5fd6047385a4e9a8b161daadc1dd443607c5894b0fb0a3","observation_id":"a52c766e-1840-40c5-8cd8-953941e0ee40","resolution":{"observed_at":"2026-08-15T16:18:24.584040Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:24.528822Z","title":"Zero-shot generalist graph anomaly detection with unified neigh- borhood prompts.IJCAI, 2025","venue":null,"work_id":"21099566-7bee-495c-bb4d-227c8f0492c6","year":2025},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:22.343310Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:df3526657f3e29ccaf3c25f7af9775c59248d05c2f6b64b79941761893f870db","observation_id":"9d770218-5bb9-4bb5-b521-e48d3224f64c","resolution":{"observed_at":"2026-08-15T16:18:24.570779Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:24.474052Z","title":"A label-free heterophily-guided approach for unsupervised graph fraud detection","venue":null,"work_id":"b00d25cd-8458-43ca-a99a-ffd3840657b5","year":2025},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:22.347630Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:ea8507b891c6559d19bc20d4baedf6a659b0683bfc307dc281b643202dcdca62","observation_id":"962dd7a8-d065-4f96-bc09-f077f8883cfa","resolution":{"observed_at":"2026-08-15T16:18:24.478587Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:24.460382Z","title":"Integrating graphs with large language models: Methods and prospects.IEEE Intelligent Systems, 39(1):64–68, 2024","venue":null,"work_id":"674bc04a-14ef-4ae1-a846-0e975e028770","year":2024},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:22.412718Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:20ca135a571759d6505736acf8e1b8dcd0b2d17630701d6ffc8f27159f221461","observation_id":"f1af6761-2368-461b-a7c4-ca2750ba0ca3","resolution":{"observed_at":"2026-08-15T16:18:24.465004Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:24.446962Z","title":"Graph anomaly detection via adap- tive test-time representation learning across out-of-distribution domains","venue":null,"work_id":"727b780b-37f2-48fa-8cc0-d65f36e83b75","year":2025},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:22.488259Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:e618e279b05dc7eebbcf98aa234c3c116e1015ef8693a1c68784de73e35b7ef6","observation_id":"80e0ab0d-7d28-434c-a3ee-f6423a12fad1","resolution":{"observed_at":"2026-08-15T16:18:24.451465Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:24.383477Z","title":"Anomalygfm: Graph foundation model for zero/few-shot anomaly detection","venue":null,"work_id":"d0c7accc-d4b6-4dc6-ba54-0f4b94a70236","year":2025},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:22.542802Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:1585126f60155b111a6f7249540cda276c196d25cbf2af9907ec7ab1400c766a","observation_id":"107d844a-4b07-44a7-b78e-99e09fa90fdd","resolution":{"observed_at":"2026-08-15T16:18:24.437410Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:24.323861Z","title":"Deep graph anomaly detection: A survey and new perspectives.TKDE, 37(9):5106–5126, 2025","venue":null,"work_id":"4380b70f-1379-4f16-90ee-61532137cc23","year":2025},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:22.559898Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:1347e4c087684f9dad5b1b24652bba6da269624c5b4c07c439df5999095d2b00","observation_id":"61035334-605b-48c7-9eb1-d8972675ad5e","resolution":{"observed_at":"2026-08-15T16:18:24.342803Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:24.308100Z","title":"Heterophilic graph invariant learning for out-of-distribution of fraud detection","venue":null,"work_id":"a9ca5953-ba10-4a10-995c-bc81160caf8a","year":2024},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:22.564669Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:5dfc2839e38bc59af3997b2d688e9342694044317e171ba9fb645b2cef21035b","observation_id":"68e78d98-06d6-4bd0-a94c-295a60a4fc58","resolution":{"observed_at":"2026-08-15T16:18:24.312881Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:24.266937Z","title":"Understanding the information propagation effects of communication topologies in llm-based multi-agent systems","venue":null,"work_id":"e4b82ea2-13dc-4c49-9a6c-57bbcf2bbcc1","year":2025},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:22.569733Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:8f039ebdf257549996e15766690493989f8934f6b201cc7d6fda89ce2f00226a","observation_id":"7957bccd-468e-4fce-b172-43b5026d05bc","resolution":{"observed_at":"2026-08-15T16:18:24.298725Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:24.108669Z","title":"Uniform: Towards unified framework for anomaly detection on graphs","venue":null,"work_id":"00f70b16-758a-4fe3-92ab-6dc0abd851e8","year":2025},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:22.576303Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:52858906ae7413188c08015c0028f873e33db509581ad1d00faf555cb72b11e0","observation_id":"3accecb7-f280-4bf7-ad9c-c2bfc3a8ce4b","resolution":{"observed_at":"2026-08-15T16:18:24.215841Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:24.056571Z","title":"Anomaly subgraph detection through high-order sampling contrastive learning","venue":null,"work_id":"5ee3ee64-08ed-4a30-96a1-6825ef06a12b","year":2024},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:22.641937Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:1234fda2d58f5411d305c52ae998708c93056629c6f43b0df43fd7205007f229","observation_id":"58b12900-4594-49a3-8511-2d611576b686","resolution":{"observed_at":"2026-08-15T16:18:24.061176Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:24.042972Z","title":"Gadbench: Revisiting and benchmarking supervised graph anomaly detection","venue":null,"work_id":"cf3945f8-81fd-4c46-a865-65a1fb038d53","year":2023},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:22.749910Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:6879013971f2f1b14e514eb584fa5620d5777642561107b71c38070c1c9ed1a8","observation_id":"51586e25-54cf-4abc-af4a-a4704b220a15","resolution":{"observed_at":"2026-08-15T16:18:24.048105Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:24.011815Z","title":"Goodat: towards test-time graph out-of- distribution detection","venue":null,"work_id":"8fc091ed-cbbb-4bf3-82e7-7fa5d75df3b2","year":2024},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:22.787314Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:0c88ae7c7f61bfe2c3f7be3f7071dfcae10f3fcf738749d39cbe6df835113efa","observation_id":"f2e999db-4c78-4c3a-b0f1-0c507d60f1f7","resolution":{"observed_at":"2026-08-15T16:18:24.034035Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:23.935647Z","title":"Cross-domain graph anomaly detection via anomaly-aware contrastive alignment","venue":null,"work_id":"86d430ef-747d-4344-8b0c-ca31b502621d","year":2023},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:22.801201Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:ab9c815c022c5c94df082f65e15682c5a3c1263af76c490239bcc428b5375cba","observation_id":"3dca1312-c71a-4f9d-9447-bf5d88da36d6","resolution":{"observed_at":"2026-08-15T16:18:23.987652Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:23.790334Z","title":"Open-set graph anomaly detection via normal structure regularisation","venue":null,"work_id":"11b620d2-c844-4b55-a719-e13fb458fbe4","year":2025},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:22.828039Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:a4b866c0becd5724cf0afcf6e420b06a3acb458e4a63a612e6f01f2a7277ae74","observation_id":"fd62945d-b330-44cf-b6fa-bc4ee66469cb","resolution":{"observed_at":"2026-08-15T16:18:23.829306Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:23.777199Z","title":"Unifying unsupervised graph-level anomaly detection and out-of-distribution detection: A benchmark","venue":null,"work_id":"e00e7f4f-3742-4fe3-bc63-fc4cc5371431","year":2025},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:22.838688Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:ae57943410a2533a44867a8037f7fc578968da779ac0af2318ac241da211bb77","observation_id":"a1facd0d-22cc-41f8-851c-76ef31f1f38a","resolution":{"observed_at":"2026-08-15T16:18:23.781267Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:23.764065Z","title":"Graph learning under distribution shifts: A comprehensive survey on domain adaptation, out-of-distribution, and continual learning.arXiv, 2024","venue":null,"work_id":"86ffc70f-fd6c-4718-bc46-716d3f56e424","year":2024},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:22.843680Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:e5c0ece9561f09c5847bf00848db95037cf3dc80c86ec5e53b9cb60c4c63af0f","observation_id":"27ba43bc-1783-49de-84ba-d4d5e5ea4c37","resolution":{"observed_at":"2026-08-15T16:18:23.768800Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:23.691980Z","title":"Dynamic weighted learning for unsupervised domain adaptation","venue":null,"work_id":"3db742ae-a5d5-496d-be90-2ba269be12d8","year":2021},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:22.847333Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:a0a13eab17f26ba27fac698807f298f85ef3bc65da0bb06e2fe443133dd514df","observation_id":"007fd32e-b7fb-421a-aeb0-32888e923daf","resolution":{"observed_at":"2026-08-15T16:18:23.723195Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:23.597905Z","title":"Relation-aware graph convolutional networks for agent-initiated social e-commerce recommendation","venue":null,"work_id":"e4b9d4aa-1c98-4ff2-b7ae-cc76d8392b0a","year":2019},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:22.852127Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:21d06e8b74611a15f3ca47f8a576cdc9269040ae73e7b53149ede127acfc2c96","observation_id":"cdf7897a-137e-44ce-9de0-be9d156fd0b3","resolution":{"observed_at":"2026-08-15T16:18:23.636845Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:23.573991Z","title":"Metagad: Meta representation adaptation for few-shot graph anomaly detection","venue":null,"work_id":"4d99f8c3-1035-4e4c-bf7b-294289594091","year":2024},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:22.856408Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:b9a5ae9591912a3fba1031726094ecd529507bc6e18351e3a41da62e0b5aa90a","observation_id":"c4400bd3-6293-457f-aa98-a41caac402b6","resolution":{"observed_at":"2026-08-15T16:18:23.580605Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:23.557711Z","title":"Ad- agent: A multi-agent framework for end-to-end anomaly detection","venue":null,"work_id":"a25db3d5-66e2-423c-a8ab-e02a5047f609","year":2025},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:22.861175Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:38795d4458e01df450c2b368501786fc8801d3ea9e62bd5a1de5b4b2db172455","observation_id":"80851796-02ac-41b4-9ae4-66ab1359f7e3","resolution":{"observed_at":"2026-08-15T16:18:23.563863Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:23.542217Z","title":"Gram: An interpretable approach for graph anomaly detection using gradient attention maps.Neural Networks, 178, 2024","venue":null,"work_id":"d08785b3-57b8-4de1-87fa-6b3b0b0760ff","year":2024},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:22.865317Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:8bbbd7fe46aac36d979a7815cd9125b9f5a1fe8f984a0448ad920abf483d76b3","observation_id":"2ba46e3b-0213-441e-8a13-35ac51945507","resolution":{"observed_at":"2026-08-15T16:18:23.546392Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:23.451188Z","title":"Freegad: A training-free yet effective approach for graph anomaly detection","venue":null,"work_id":"72b8ba42-18cb-485d-a93e-5554a15b2d4e","year":2025},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:22.870295Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:0fe4f415ab2f93dfc7d5adaf0f432951472813fc2320a2b1a1446a4411f0f3dc","observation_id":"fe630df1-c3ed-4a62-b1e7-8aba76663563","resolution":{"observed_at":"2026-08-15T16:18:23.527335Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:23.367302Z","title":"Test- time graph neural dataset search with generative projection","venue":null,"work_id":"4d9113a7-1d51-41b7-915c-4f28a26ba999","year":2025},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:22.910695Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:c04c61638a66001e853b51e6b95fb1d9dea1d138bc1289692a242c3b5c9baa12","observation_id":"c1cdd882-b23c-4878-9940-657e7dbb6403","resolution":{"observed_at":"2026-08-15T16:18:23.376390Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:23.344945Z","title":"Online gnn evaluation under test-time graph distribution shifts","venue":null,"work_id":"a52e605e-baaf-4eb2-9544-5f7faa333478","year":2024},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:22.993585Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:7205b8d219fc1e05d514427b8793ea2c4e05b977f327b653504ec2adefcbbc14","observation_id":"4e029cf7-215d-4387-9a4b-073a8a98f457","resolution":{"observed_at":"2026-08-15T16:18:23.354851Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:23.281435Z","title":"Training- free graph anomaly detection: A simple approach via singular value decomposition","venue":null,"work_id":"24ac493f-a414-418c-b365-be271846be54","year":2025},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:23.036058Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:384a06afff92afe158494fa74b9c3b7898ced2a4fb064f1f208bbd94ac1a71b7","observation_id":"42edecf8-6308-4dad-a56a-06b3a0ff6bf5","resolution":{"observed_at":"2026-08-15T16:18:23.324120Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:23.141010Z","title":"Domain generalization: A survey.TPAMI, 45(4):4396–4415, 2022","venue":null,"work_id":"c31dca85-c41f-4317-9d99-78b9d3e8b94e","year":2022},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:23.060474Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:6bec9aa5a65f50039cac684111e53a385ca878aea0a17308d15042c31d8bc298","observation_id":"1b420630-d000-4a61-94af-9dadfa932453","resolution":{"observed_at":"2026-08-15T16:18:23.212581Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+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":"2026-08-15T16:18:23.124080Z","title":"Improving generalizability of graph anomaly detection models via data augmentation.TKDE, 35(12):12721–12735, 2023","venue":null,"work_id":"feae268a-b736-4e68-98cf-9c8d7b84e6b5","year":2023},"citing_paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-08-15T16:18:23.084662Z"},"links":{"citing_paper":"/paper/2509.06609"},"observation_digest":"sha256:558442dbfca41e553856e0f39f2f3ac5bed2c36364553d40eda30c67df9e1cae","observation_id":"dd48e426-9a35-45bf-9c6d-9788827089d1","resolution":{"observed_at":"2026-08-15T16:18:23.130339Z","resolver_source":"raw_fallback","status":"verified_fuzzy"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-16T06:30:59.297886+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2509.06609","last_updated":"2025-09-08T12:26:32Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-15T16:12:54.226707Z","submitted_at":"2025-09-08T12:26:32Z","title":"A Survey of Generalization of Graph Anomaly Detection: From Transfer Learning to Foundation Models"},"reference_resolution":{"displayed":53,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":0,"verified_exact":0,"verified_fuzzy":53},"total_outbound_references":53},"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":"2026-08-16T06:30:59.297886+00:00","source":"crossref"},{"observed_at":"2026-08-16T06:30:54.164669+00:00","source":"retraction_watch"}],"thesis":"As of 16 August 2026, this Paper Citation Record lists 53 of 53 outbound references and 1 inbound Pith citation observation for arXiv:2509.06609."}