{"as_of":"2026-08-10T12:40:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:daf840b48c8c94f5dd9504e88d0c1b76edf3b07e8f82492debbdec53781afcae","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":"2026-06-29T20:00:56.643179Z","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/2605.27470/citation-record","integrity":"/paper/2605.27470/integrity","json":"/paper/2605.27470/citation-record.json","paper":"/paper/2605.27470"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":"2601.22037","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:03:56.242993Z","title":"Optimizing agentic workflows using meta-tools","venue":null,"work_id":"d192ec01-3410-4027-86ab-8c8e1d8c7524","year":2026},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:9f9122f7f6e11a9a94bc8f331f942835f4ad00765aac6d8c2a1e8a681fc4b8fd","observation_id":"15152634-9bda-499f-9154-76da6a475122","resolution":{"observed_at":"2026-06-29T20:03:56.244770Z","resolver_source":"arxiv_id","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Semi-supervised graph anomaly detection via robust homophily learning.Advances in Neural Information Processing Systems, 38:133988–134013, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:8336c2d301b0b84d3d882e8a07b203da1b468d8f188b68d9158695e1a65f7424","observation_id":"9f2c36fd-b720-4a62-922a-c7b694cc1b75","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Geoflow: Agentic workflow automation for geospatial tasks","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:e035c8c616a2da49191fbda37594ec3d8a78e8c2da86c10ba4ca1a41d989b52d","observation_id":"08f2141d-8d0e-4b56-8e71-50e43d57bfff","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"How attentive are graph attention networks? InInternational Conference on Learning Representations, pages 1315–1324, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:abe095bc00ee68bff116f3187736737e252eed11dab9b23ffd9172dc552a8b68","observation_id":"cb0fce11-3bdf-4d17-ac75-3a1fc894f53f","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Towards multiple missing values- resistant unsupervised graph anomaly detection","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:630a81ec13d6c905113d7c30a2624dd9a6ecd6f22d9651460bb11e9e8eb4112c","observation_id":"1237a6b5-50cc-4a50-ba4d-433e7b063eb9","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Consistency training with learnable data augmentation for graph anomaly detection with limited supervision","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:0cea6a1fb918756241996acabea146174f42607eec1b5f20c03c313e119c8a0f","observation_id":"b57d71c2-5147-4d8e-a0c1-1ad9f3176e20","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Agent4edu: Advancing ai for education with agentic workflows","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:1e884691d0cf6299f1c6dc0e143d8cb0c57c1911b19c8a8f540d0735a03cdb35","observation_id":"15360755-a62f-4f40-be22-6fd2bcc61f40","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Spacegnn: Multi-space graph neural network for node anomaly detection with extremely limited labels","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:e553676cc14a47b5d53e0d56c82f0c82aca38e9db9ac7b16963ff1bef521be08","observation_id":"a10f2faf-cbbf-47e8-b2df-cd19b32f3f3f","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Enhancing graph neural network-based fraud detectors against camouflaged fraudsters","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:c7ace0a15206e96a4689e2e0451a31a60a20a79ca7797be4bd0174a0e8b091b5","observation_id":"4e01e6d1-03e9-4acb-a5ea-cae9dabf23c9","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Alleviating structural distribution shift in graph anomaly detection","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:5a11207e74543abda42a410d9193f970c96c53861ea1a321222ce2aeca5fdf1f","observation_id":"b2e6d76d-11dc-4be7-b1b9-c37fd1ee49ad","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Addressing heterophily in graph anomaly detection: A perspective of graph spectrum","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:d9fa23227f40aef7e01662902bc7433980e7532695471e1bbd3705db27d4f295","observation_id":"47f1a5c8-70bd-4a76-a595-e45a6fa779b3","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Naast-gnn: Neighborhood adaptive aggregation and spectral tuning for graph anomaly detection","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:19c94b8ba92620cb5e65ba348441259bf6a7da7ffc5650e4597b3184880f3327","observation_id":"0b1d5d4b-6ca9-4c52-bf71-54bd4f166288","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Topological anomaly quantification for semi-supervised graph anomaly detection","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:5932af500ed09eee5b1490faeac94ba83713a2d6f7cc824c60b3c66dd5b924cd","observation_id":"efaa1dd2-5f20-4207-8024-5ec91f1e06bf","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Inductive representation learning on large graphs","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:1533161b7d8f7712f25b7af6aba430cf2303a1c75d0c96655722dfd9f4c42104","observation_id":"7bf60e39-2945-42c8-b44b-717625472ab2","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Tdflow: Agentic workflows for test driven development","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:4e08fe6583ed6ba57036aaf095631f216cb02cae5294e5aae985db64502760f4","observation_id":"c202389a-4b9e-479d-94a1-2481e4708280","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Tempasd: Temporal anomalous subgraph discovery in large-scale dynamic financial networks","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:5600a2309fef23798de2d09fa1a504821c900ef83b26c72e4facdfd14950d232","observation_id":"793dcefa-b3d4-4c01-9344-64e711091a79","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Revisiting low- homophily for graph-based fraud detection.Neural Networks, 188:107407, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:5c80c7d0215d4bbc59b5aaccb7b41af3fc20b14adca6382455785bd323403f88","observation_id":"0bc1961d-512d-49b2-8c67-c456fce83320","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Can llms find fraudsters? multi-level llm enhanced graph fraud detection","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:5a589bd05801e21e33d549cc09fc1224df6ab9e1c7a9bd87c681a91ad590fd1b","observation_id":"ed002a6d-bde3-4870-8104-bddc2b3762fe","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Rethinking reconstruction-based graph-level anomaly detection: limitations and a simple remedy","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:6ed13ae0a752a7ee02556f1e75aa88269dfe88d4360f120559b8f1248a4d1cbb","observation_id":"84498b2b-6224-4723-b9d8-5b785a8258a5","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Semi-supervised classification with graph convolutional networks","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:b8065aae5e9e76fca16cd7b61d2c18f441a11450c80e1111913bb5912ee298ef","observation_id":"6f85b480-6dcb-4e14-9d7c-7ce6be527e90","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Slade: Detecting dynamic anomalies in edge streams without labels via self-supervised learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:906465401bccc71bac4e0ff58dc762914977a1bd075adb11b901c04279c0ed21","observation_id":"e8f743d1-aba6-4a5e-9394-5f086584d30c","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Dual-augment graph neural network for fraud detection","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:431e0a62d80eae857bc71a6cfc957593a2b53b195ae30d5624312f6a2793370a","observation_id":"9dad7b7f-4094-4b5a-8568-e3d3daacb9b6","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Pick and choose: a gnn-based imbalanced learning approach for fraud detection","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:9e858df9c0ec6da61a8711332c8bb319498cc51577fd2c7c0e45b3cc1b03369f","observation_id":"7a0748fe-6b01-4567-b634-5b3aff561bb6","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Multi-dimensional adaptive mix-hop contextual learning framework for universal graph anomaly detection","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:151819da93705e250202e7dff9af442b2ed8dc50a72f87f7bb64afe9315aeec8","observation_id":"dd9dfc26-098b-4ec8-b3e9-4c5dcd1ffea0","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Alleviating the inconsistency problem of applying graph neural network to fraud detection","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:8184bb07f89d1965e5c66ee636c177ef71d13cad29bc04533924ed8d98e4a67c","observation_id":"628bd421-fbe7-425f-8113-f05eb02b8e38","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"From amateurs to connoisseurs: modeling the evolution of user expertise through online reviews","venue":null,"work_id":null,"year":2013},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:5e38f1261fef32251365b8dcd7ecca5bd0e2947e77b27a29e00a205b25204d07","observation_id":"3c3da61d-edd3-478c-b963-265c7d16890b","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Correcting false alarms from unseen: Adapting graph anomaly detectors at test time","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:8d01418f5c2d22e6b41e92ee05bdd8a7d8919b7099513b6b07e9d46e9ef54ce8","observation_id":"d39f6db9-0122-494d-bb26-0ed6cd18d7ee","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Benchmarking agentic workflow generation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:0307195d1c0ebc36ce3259ea5daabd89f140e3efeedc887fa071cf3f735b46ca","observation_id":"438a8f34-a1af-421b-8392-bb0b72389501","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Collective opinion spam detection: Bridging review networks and metadata","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:bf33176527f6dbd0cd1300fe507f5d69e336e20728d8e8437b7685642005d354","observation_id":"cd1822d8-f555-4866-8cda-55f5e53c0c89","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Heterogeneous graph neural network with multi-view representation learning.IEEE Transactions on Knowledge and Data Engineering, 35:11476–11488, 2022","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:e352f89b07e0c1d114d6685c811a687b5e502f8264a6b5cb9d9694883e502160","observation_id":"b3de25de-3894-4555-8949-27bc2c51ad14","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"H2-fdetector: A gnn-based fraud detector with homophilic and heterophilic connections","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:1c23d94629461c4e1130b7aafd67632965904ff68b95f96958dbcdfc3f01ab69","observation_id":"1976c9f9-8131-44ef-b946-b00f6bd3e497","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Kronos: A foundation model for the language of financial markets","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:16ec3453021148c4cf90d393c2c7e25c6370cd3c9bda3f907fd2e0f367b28035","observation_id":"1f5ae895-b429-45f4-913d-684a4ef455ac","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Uniform: Towards unified framework for anomaly detection on graphs","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:561f7eb2639a07e2682db1c923c0b4e628c5d3500cd6a2f0599e474faf832a2b","observation_id":"2d12c881-6cec-4cdf-9de0-b05b98972311","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Mitigating message imbalance in fraud detection with dual-view graph representation learning","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:d4c9a0a98d26f674f95c3811224413e80488030b606c8cad99ecb37d2010028d","observation_id":"b9b2a302-c4a5-4c4f-883f-3e2513b76d00","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Anomaly subgraph detection through high-order sampling contrastive learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:57b9995014038082d0d51df943029a2265462a93e9f2bac12fe7d8b9794a878c","observation_id":"5c9f23f4-3754-4d73-9152-54e3aca3989b","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Rethinking graph neural networks for anomaly detection","venue":null,"work_id":null,"year":2022},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:77cbe0b69337a4756149702fc9b8fbe177911b5252c74524c3d50d28a5330a1c","observation_id":"7371b13f-2223-4295-bc59-9b378f5355e9","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Sad: semi-supervised anomaly detection on dynamic graphs","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:d649da5d28c881a5685b393dd11dd8616fc693a1a35aa997fab011cd9251e2b9","observation_id":"6321e3db-8faa-48d6-ba78-ad3d4be505ae","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Mlp-mixer: An all-mlp architec- ture for vision.Advances in Neural Information Processing Systems, 34(2):24261–24272, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:8bc6bd0f1efcebc871137d8019aa0b6108b84f89ecefbe5c122d1cda93b78001","observation_id":"0b96dc2c-d4c3-496b-b0fd-96a8f7a87343","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Graph attention networks","venue":null,"work_id":null,"year":2018},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:e6a81b93e5ba8dd08bd040f60398021ff136d2df193723e9909be4082936eb4e","observation_id":"2c75fa39-f73c-4a8c-b085-44caa044c7dc","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Attention-based conditional random field for financial fraud detection","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:bf6aac7a088fdf671811ba139253455f16e1230e9cd9215826f797bb21d7024d","observation_id":"8bd96151-52c2-41ac-b59a-c7e31739c867","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Dyflow: Dynamic workflow framework for agentic reasoning","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:861f9a5af76bbacdb19bda46aa09a1500ce9954b5ef28672cc57c25d5e9e7dbf","observation_id":"3e4ccb1b-2f46-4f0c-9ab1-41e3c87499f1","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Simple and efficient heterogeneous temporal graph neural network.Advances in Neural Information Processing Systems, 2025","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:17c4a6d3fca59ce6c70ca8e347eed77d476ad4e80659630df7d1d65e7ccd0ed9","observation_id":"3e9bda9c-84e7-47f4-a1fe-7619d83f54cb","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Evoagentx: An automated framework for evolving agentic workflows","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:fd8e7782c8f00f308b7aec379f58a353accad4b0b5961fc609f7898a9f86d87b","observation_id":"4a358fb7-83fd-4769-98d0-f75c8a8ab478","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Label information enhanced fraud detection against low homophily in graphs","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:8cd0b1fdff71444ef60ab8d5658fe0c8fc04b3ba527096697255db7767662dd3","observation_id":"d4edda25-6f4f-4138-bc9a-71d6d363bede","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Cats: cross-platform e-commerce fraud detection","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:05d91118727cf86ae618ea75f4e07c38f6ad86c3f527502bb90e2cb522bbdf2e","observation_id":"5d0e6163-6c56-438a-8773-2195500ebd1b","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Gif: A general graph unlearning strategy via influence function","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:a9272dba30231c04d37c0355b92fd269a9c99088ea5d890472a4b2e501183da1","observation_id":"6e3cf969-e36c-4d13-9ab3-c59af26cb632","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Deltagrad: Rapid retraining of machine learning models","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":47,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:403f645b0a76391987bbb0d995b3f5a1ff4936ef9b7314f7901c0182e389c959","observation_id":"04e1c01a-8726-4bc3-83e9-311b946d88cd","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Howpowerfularegraphneuralnetworks? InInternational Conference on Learning Representations, pages 215–224, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":48,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:a7704ea9d50a66aad84b7080f33dd3aac9d27fd92512ac6ae63c4554a2b4aad8","observation_id":"3b5381b4-5309-4c38-83d8-16f5c2c4cabb","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Geogen: A two-stage coarse-to-fineframeworkforfine-grainedsyntheticlocation-basedsocialnetworktrajectorygeneration","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":49,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:09ee6becb8a374f40b8fafcfd00ea560e75f99b4c01a4bf8b40b051124ef9f85","observation_id":"306cde92-5e1c-4865-9eda-2714eeef1a9d","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Grad: Guided relation diffusion generation for graph augmentation in graph fraud detection","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":50,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:d62bf197d8fb25d740e529c9fe654d091f8cbc7234e01d2b9f6ae822eed96bd8","observation_id":"97453d06-744e-42ad-8b6e-c4fb28645d76","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Sfga: Similarity-constrained fusion learning for unsu- pervised anomaly detection in multiplex graphs","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":51,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:dbd788006618fb1fc2e7ebdbb5c3c78542d84d1a32bdd1e011ef8367584f3e4f","observation_id":"8a866761-5b9a-4e51-a809-2d57470273b8","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Aflow: Automating agentic workflow generation","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":52,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:c22eb7d465df55002b67c922cd0d9eb0d5df357a377f950077a8b42979451097","observation_id":"5046088a-c387-4136-abc4-4516a53f17f3","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Dig-in-gnn: Discriminative feature guided gnn-based fraud detector against inconsistencies in multi-relation fraud graph","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":53,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:e925dbf7d7060ac304c7d0f028af4336df41860db26f0dbfbaff1a87997e35fb","observation_id":"f2b2878c-f49f-43cc-aa3a-755d5279d816","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Multi-domain deep learning from a multi-view perspective for cross-border e-commerce search","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":54,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:d2d7dddc28c546537148d944d9c2840aef4a758b4f6b61e80613344ce0d4a822","observation_id":"1de19f56-cab7-4b0f-9a88-492bc115b792","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2503.11301","last_updated":"2025-03-14T11:11:00Z","snapshot_observed_at":"2026-08-07T17:04:18.665724Z","submitted_at":"2025-03-14T11:11:00Z","title":"GNNs as Predictors of Agentic Workflow Performances","version":1},"cited_work":{"arxiv_id":"2503.11301","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2503.11301","snapshot_observed_at":"2026-07-04T09:39:46.488434Z","title":"arXiv preprint arXiv:2503.11301 , year=","venue":null,"work_id":"caf3d3df-bfae-4ddc-a297-b1cfa4e0c922","year":2025},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":55,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"cited_paper":"/paper/2503.11301","citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:bd0cfed08fb8a6f3441b852ce3da22dde435f94233bd9948c0f8a34391fec8e3","observation_id":"e474f33e-b495-4c54-8c24-5a6b48fe7d26","resolution":{"observed_at":"2026-06-29T20:03:56.241707Z","resolver_source":"arxiv_id","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":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-29T20:00:56.643179Z","title":"Partitioning message passing for graph fraud detection","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection","version":1},"reference_index":56,"source":"pdf_text","source_observed_at":"2026-06-29T20:00:56.643179Z"},"links":{"citing_paper":"/paper/2605.27470"},"observation_digest":"sha256:e5915d147b2982f3e55e6c9a1287f4586b57ab0f7b902b872e60e65e6204d351","observation_id":"0e074fa0-997d-4b0f-815d-fcf8207255e3","resolution":{"observed_at":"2026-06-29T20:00:56.643179Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2605.27470","last_updated":"2026-05-26T09:16:34Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-01T16:05:13.714289Z","submitted_at":"2026-05-26T09:16:34Z","title":"Detect by Yourself: Self-Designing Agentic Workflows for Few-Shot Graph Anomaly Detection"},"reference_resolution":{"displayed":56,"state_counts":{"malformed_identifier":0,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":54,"verified_exact":2,"verified_fuzzy":0},"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:2605.27470."}