{"as_of":"2026-08-09T19:52:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:8a78ee842caf69bb8b5839abf489edf4007eb701ad8b09f0fb2213fe7630fe30","coverage":[{"denominator":32,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":32,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T12:58:49.057313Z","state":"measured"},{"denominator":32,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":32,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-09T06:31:02.800959+00:00","state":"measured"},{"denominator":0,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":0,"source":"paper_references, paper_reference_links","source_observed_at":null,"state":"measured"},{"denominator":1,"lane":"external_citation_measurements","note":"A source-named dated measurement, never combined with another source.","records_observed":0,"source":"cited_works","source_observed_at":null,"state":"measured"}],"external_citation_measurements":[],"inbound":[],"links":{"evidence":"/evidence","html":"/paper/2607.19266/citation-record","integrity":"/paper/2607.19266/integrity","json":"/paper/2607.19266/citation-record.json","paper":"/paper/2607.19266"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T12:58:45.744613Z","title":"Xgboost: A scal- able tree boosting system","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.19266","last_updated":"2026-07-21T16:37:41Z","snapshot_observed_at":"2026-08-09T01:03:08.006963Z","submitted_at":"2026-07-21T16:37:41Z","title":"Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agentic Case Investigation","version":1},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-08-01T12:58:45.744613Z"},"links":{"citing_paper":"/paper/2607.19266"},"observation_digest":"sha256:3574439098b76b9cd7de8315c7320b6bc656b953cce7798e42dba29368c2ca8c","observation_id":"638fbad9-2234-4343-b716-ea32e4698168","resolution":{"observed_at":"2026-08-01T12:58:45.744613Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2606.08146","last_updated":"2026-06-06T12:48:45Z","snapshot_observed_at":"2026-07-06T23:47:43.942733Z","submitted_at":"2026-06-06T12:48:45Z","title":"SAGE: An LLM-driven Self Reflective Agentic Framework for Fraud Detection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2606.08146","snapshot_observed_at":"2026-08-01T12:58:45.908231Z","title":"Sage: An llm-driven self reflective agentic framework for fraud detection.arXiv preprint arXiv:2606.08146, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.19266","last_updated":"2026-07-21T16:37:41Z","snapshot_observed_at":"2026-08-09T01:03:08.006963Z","submitted_at":"2026-07-21T16:37:41Z","title":"Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agentic Case Investigation","version":1},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-08-01T12:58:45.908231Z"},"links":{"cited_paper":"/paper/2606.08146","citing_paper":"/paper/2607.19266"},"observation_digest":"sha256:e93b9c2a673edffae3b3c13e3097b60d0d933d2fd374cf55b89f8cac1428dd35","observation_id":"fbdcc08a-7230-47a5-9eea-bb19d24bf4b8","resolution":{"observed_at":"2026-08-01T12:58:45.908231Z","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":"10.1007/s11704-024-40474-y","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"Graph neural networks for financial fraud detec- tion: A review.Frontiers of Computer Science, 2025","venue":"Frontiers of Computer Science","work_id":"7e1af2d4-c85d-41ba-8911-2a77bcf0be7b","year":2025},"citing_paper":{"arxiv_id":"2607.19266","last_updated":"2026-07-21T16:37:41Z","snapshot_observed_at":"2026-08-09T01:03:08.006963Z","submitted_at":"2026-07-21T16:37:41Z","title":"Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agentic Case Investigation","version":1},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-08-01T12:58:46.033198Z"},"links":{"citing_paper":"/paper/2607.19266"},"observation_digest":"sha256:85fda1351bdf3d2b7cdb2f1555b58f362218e536eb39ef84a046b69a41d07c7b","observation_id":"a50554d4-2764-4784-82ea-f465869ffeeb","resolution":{"observed_at":"2026-08-01T13:04:35.501271Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T12:58:46.204750Z","title":"How paypal’s ai blocks$500 million in fraud per quarter, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.19266","last_updated":"2026-07-21T16:37:41Z","snapshot_observed_at":"2026-08-09T01:03:08.006963Z","submitted_at":"2026-07-21T16:37:41Z","title":"Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agentic Case Investigation","version":1},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-08-01T12:58:46.204750Z"},"links":{"citing_paper":"/paper/2607.19266"},"observation_digest":"sha256:5a4b760ecf906e367170a3e2c7067b8b553d72166460f98e6f9082aff2050824","observation_id":"5244ddcd-b6f3-4373-9232-3f3c6b1d6dbb","resolution":{"observed_at":"2026-08-01T12:58:46.204750Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T12:58:46.269543Z","title":"Ai fraud detection in banking 2026 guide,","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.19266","last_updated":"2026-07-21T16:37:41Z","snapshot_observed_at":"2026-08-09T01:03:08.006963Z","submitted_at":"2026-07-21T16:37:41Z","title":"Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agentic Case Investigation","version":1},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-08-01T12:58:46.269543Z"},"links":{"citing_paper":"/paper/2607.19266"},"observation_digest":"sha256:06a952010a74e98876e8ffafda8a5f8aaddfeaa5cbcc53cf586af0bc5ae539f6","observation_id":"4dd0879a-7b87-4b82-8bf3-a28aeff71ce8","resolution":{"observed_at":"2026-08-01T12:58:46.269543Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T12:58:46.529657Z","title":"Experian’s new fraud forecast warns agentic ai, deepfake job candidates and cyber break-ins are top threats for 2026, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.19266","last_updated":"2026-07-21T16:37:41Z","snapshot_observed_at":"2026-08-09T01:03:08.006963Z","submitted_at":"2026-07-21T16:37:41Z","title":"Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agentic Case Investigation","version":1},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-08-01T12:58:46.529657Z"},"links":{"citing_paper":"/paper/2607.19266"},"observation_digest":"sha256:998bf9d6c21e491e5420a1f0725f8fb6d27f7af933978cd5ac894fa4f1ac94a0","observation_id":"201fb4b9-db3c-422b-ab98-6f04385c3401","resolution":{"observed_at":"2026-08-01T12:58:46.529657Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T12:58:46.594760Z","title":"Friedman","venue":null,"work_id":null,"year":2001},"citing_paper":{"arxiv_id":"2607.19266","last_updated":"2026-07-21T16:37:41Z","snapshot_observed_at":"2026-08-09T01:03:08.006963Z","submitted_at":"2026-07-21T16:37:41Z","title":"Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agentic Case Investigation","version":1},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-08-01T12:58:46.594760Z"},"links":{"citing_paper":"/paper/2607.19266"},"observation_digest":"sha256:0e0900ab4fb767eab407c99a829802b313c076911aae3a0a1390c46fb715c1c9","observation_id":"fc0a0225-750a-4d2e-b59e-5f4245e2a9d9","resolution":{"observed_at":"2026-08-01T12:58:46.594760Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T12:58:46.667440Z","title":"node2vec: Scal- able feature learning for networks","venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.19266","last_updated":"2026-07-21T16:37:41Z","snapshot_observed_at":"2026-08-09T01:03:08.006963Z","submitted_at":"2026-07-21T16:37:41Z","title":"Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agentic Case Investigation","version":1},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-08-01T12:58:46.667440Z"},"links":{"citing_paper":"/paper/2607.19266"},"observation_digest":"sha256:635994ff5eec1bee72ce705c109464d501ccff40e6393dcb0ed400c1acda7f45","observation_id":"8f0650a9-48fa-4dd4-a1c6-b959bf938ec1","resolution":{"observed_at":"2026-08-01T12:58:46.667440Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T12:58:46.747245Z","title":"Can llms find fraudsters? multi- level llm enhanced graph fraud detection","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.19266","last_updated":"2026-07-21T16:37:41Z","snapshot_observed_at":"2026-08-09T01:03:08.006963Z","submitted_at":"2026-07-21T16:37:41Z","title":"Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agentic Case Investigation","version":1},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-08-01T12:58:46.747245Z"},"links":{"citing_paper":"/paper/2607.19266"},"observation_digest":"sha256:5b9eca35c38edeb0a004988276e1f1cf0a930a56010e25910edbc78d27d2764c","observation_id":"fc7208f0-0ddd-4695-8204-fd6f8691d71a","resolution":{"observed_at":"2026-08-01T12:58:46.747245Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T12:58:46.805242Z","title":"Kipf and Max Welling","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.19266","last_updated":"2026-07-21T16:37:41Z","snapshot_observed_at":"2026-08-09T01:03:08.006963Z","submitted_at":"2026-07-21T16:37:41Z","title":"Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agentic Case Investigation","version":1},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-08-01T12:58:46.805242Z"},"links":{"citing_paper":"/paper/2607.19266"},"observation_digest":"sha256:76439bccdcd0d616d01fbf4fe1c58635e6c7b01c9a0b68e901fedb85f904f308","observation_id":"e3e65cff-1556-4f86-ae3b-9a2b47668b46","resolution":{"observed_at":"2026-08-01T12:58:46.805242Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T12:58:46.867507Z","title":"Se- fraud: Graph-based self-explainable fraud detection via interpretative mask learning","venue":null,"work_id":null,"year":2024},"citing_paper":{"arxiv_id":"2607.19266","last_updated":"2026-07-21T16:37:41Z","snapshot_observed_at":"2026-08-09T01:03:08.006963Z","submitted_at":"2026-07-21T16:37:41Z","title":"Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agentic Case Investigation","version":1},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-08-01T12:58:46.867507Z"},"links":{"citing_paper":"/paper/2607.19266"},"observation_digest":"sha256:d063bdf890a5b77e0e7af2576af277c0fe2d8200d4857a4e2d266f44a78082e1","observation_id":"5e003f43-d194-49f2-9e01-d7f92b7ff776","resolution":{"observed_at":"2026-08-01T12:58:46.867507Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T12:58:46.959743Z","title":"Autonomous chain-of-thought distillation for graph-based fraud detection, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.19266","last_updated":"2026-07-21T16:37:41Z","snapshot_observed_at":"2026-08-09T01:03:08.006963Z","submitted_at":"2026-07-21T16:37:41Z","title":"Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agentic Case Investigation","version":1},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-08-01T12:58:46.959743Z"},"links":{"citing_paper":"/paper/2607.19266"},"observation_digest":"sha256:0e37129daab3a9fac4795bab2f20dd8f0ac6e3f7736b01f9d5a74e7e7114e574","observation_id":"889a7cda-67de-4c33-8ddf-dfaceee356a8","resolution":{"observed_at":"2026-08-01T12:58:46.959743Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2507.21407","last_updated":"2025-08-30T06:01:56Z","snapshot_observed_at":"2026-08-09T01:02:43.312508Z","submitted_at":"2025-07-29T00:27:12Z","title":"Graph-Augmented Large Language Model Agents: Current Progress and Future Prospects","version":2},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2507.21407","snapshot_observed_at":"2026-08-01T12:58:47.018570Z","title":"Graph-augmented large language model agents: Current progress and future prospects, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.19266","last_updated":"2026-07-21T16:37:41Z","snapshot_observed_at":"2026-08-09T01:03:08.006963Z","submitted_at":"2026-07-21T16:37:41Z","title":"Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agentic Case Investigation","version":1},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-08-01T12:58:47.018570Z"},"links":{"cited_paper":"/paper/2507.21407","citing_paper":"/paper/2607.19266"},"observation_digest":"sha256:fac41322ee572a1ed1e3d9254be105ae68edfda22ed3085aa5aad2bd7d3e1fc2","observation_id":"d8113428-f5e6-4150-a8bf-216ad5faf267","resolution":{"observed_at":"2026-08-01T12:58:47.018570Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T12:58:47.095272Z","title":"PaySim: A financial mobile money simulator for fraud detection","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.19266","last_updated":"2026-07-21T16:37:41Z","snapshot_observed_at":"2026-08-09T01:03:08.006963Z","submitted_at":"2026-07-21T16:37:41Z","title":"Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agentic Case Investigation","version":1},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-08-01T12:58:47.095272Z"},"links":{"citing_paper":"/paper/2607.19266"},"observation_digest":"sha256:ffa7b79299f0fb859ddd355f07604ec789a88e9ac4ee16164acabad35d61a6ed","observation_id":"b2b28912-91e4-43ed-ada5-23ce54c7ee5f","resolution":{"observed_at":"2026-08-01T12:58:47.095272Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T12:58:47.281707Z","title":"Lundberg and Su-In Lee","venue":null,"work_id":null,"year":2017},"citing_paper":{"arxiv_id":"2607.19266","last_updated":"2026-07-21T16:37:41Z","snapshot_observed_at":"2026-08-09T01:03:08.006963Z","submitted_at":"2026-07-21T16:37:41Z","title":"Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agentic Case Investigation","version":1},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-08-01T12:58:47.281707Z"},"links":{"citing_paper":"/paper/2607.19266"},"observation_digest":"sha256:bcda55b26c449ee24d1a56da2c3552dfdfa248bedb21b410999c76cd245d04db","observation_id":"3c677561-7c20-4ecc-a69a-9969bf20b0aa","resolution":{"observed_at":"2026-08-01T12:58:47.281707Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T12:58:47.364733Z","title":"Lundberg, Gabriel Erion, Hugh Chen, Alex DeGrave, Jordan M","venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.19266","last_updated":"2026-07-21T16:37:41Z","snapshot_observed_at":"2026-08-09T01:03:08.006963Z","submitted_at":"2026-07-21T16:37:41Z","title":"Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agentic Case Investigation","version":1},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-08-01T12:58:47.364733Z"},"links":{"citing_paper":"/paper/2607.19266"},"observation_digest":"sha256:bdbd8016ae0323b38fa92c91c7f709c910087b1fd19a3d29a5928dd60b4c54d9","observation_id":"324993a9-dbc6-41ca-a18f-8c94ade5c895","resolution":{"observed_at":"2026-08-01T12:58:47.364733Z","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":"10.1016/j.procs.2020.03.219","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":null,"venue":"Procedia Computer Science","work_id":"30c9dcd8-92ed-4196-9a57-b4c9d9cedec5","year":2020},"citing_paper":{"arxiv_id":"2607.19266","last_updated":"2026-07-21T16:37:41Z","snapshot_observed_at":"2026-08-09T01:03:08.006963Z","submitted_at":"2026-07-21T16:37:41Z","title":"Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agentic Case Investigation","version":1},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-08-01T12:58:47.552252Z"},"links":{"citing_paper":"/paper/2607.19266"},"observation_digest":"sha256:a2665245c857f548a39fa6f125f796099e6564ae508338f708b34e238cd7414f","observation_id":"c56ccc04-b120-41f9-b5af-ab7d9d2ee147","resolution":{"observed_at":"2026-08-01T13:04:35.450407Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T12:58:47.664757Z","title":"Agentic ai: Streamlining the future of ach fraud detection, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.19266","last_updated":"2026-07-21T16:37:41Z","snapshot_observed_at":"2026-08-09T01:03:08.006963Z","submitted_at":"2026-07-21T16:37:41Z","title":"Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agentic Case Investigation","version":1},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-08-01T12:58:47.664757Z"},"links":{"citing_paper":"/paper/2607.19266"},"observation_digest":"sha256:bc77e162cb7c917f7d081dbf663ce4988f1790ef28d865ffee8159ea963e0013","observation_id":"4a97dd3e-aaa4-4c17-9456-52f7f26c698f","resolution":{"observed_at":"2026-08-01T12:58:47.664757Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1904.10604","last_updated":"2019-04-24T01:59:27Z","snapshot_observed_at":"2026-07-06T07:47:56.409052Z","submitted_at":"2019-04-24T01:59:27Z","title":"A Comparison Study of Credit Card Fraud Detection: Supervised versus Unsupervised","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"1904.10604","snapshot_observed_at":"2026-08-01T12:58:47.744545Z","title":"A comparison study of credit card fraud detection: Supervised versus unsupervised, 2019","venue":null,"work_id":null,"year":2019},"citing_paper":{"arxiv_id":"2607.19266","last_updated":"2026-07-21T16:37:41Z","snapshot_observed_at":"2026-08-09T01:03:08.006963Z","submitted_at":"2026-07-21T16:37:41Z","title":"Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agentic Case Investigation","version":1},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-08-01T12:58:47.744545Z"},"links":{"cited_paper":"/paper/1904.10604","citing_paper":"/paper/2607.19266"},"observation_digest":"sha256:2988022de17948c3e838a807287bb8fddf42f70a7fb90420a370710aa127c293","observation_id":"c3faf681-cadb-4ae3-8fe6-bedbae1e6af1","resolution":{"observed_at":"2026-08-01T12:58:47.744545Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T12:58:47.894755Z","title":"A label-free heterophily-guided approach for unsupervised graph fraud detection","venue":null,"work_id":null,"year":2025},"citing_paper":{"arxiv_id":"2607.19266","last_updated":"2026-07-21T16:37:41Z","snapshot_observed_at":"2026-08-09T01:03:08.006963Z","submitted_at":"2026-07-21T16:37:41Z","title":"Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agentic Case Investigation","version":1},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-08-01T12:58:47.894755Z"},"links":{"citing_paper":"/paper/2607.19266"},"observation_digest":"sha256:2ac157f1e17be8da4b937b1a5377063322ecbb1e51627a09b977987fbf6b51cb","observation_id":"b4e877d9-2107-4865-ae48-1363ca0496a1","resolution":{"observed_at":"2026-08-01T12:58:47.894755Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T12:58:47.994753Z","title":"Correcting false alarms from unseen: Adapting graph anomaly detectors at test time","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.19266","last_updated":"2026-07-21T16:37:41Z","snapshot_observed_at":"2026-08-09T01:03:08.006963Z","submitted_at":"2026-07-21T16:37:41Z","title":"Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agentic Case Investigation","version":1},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-08-01T12:58:47.994753Z"},"links":{"citing_paper":"/paper/2607.19266"},"observation_digest":"sha256:65a3b3b2aa04dd755b4fca90cbde224168ceb8dfa0244d2d3e7e3ebbe8a470ea","observation_id":"d7eab0d5-36da-4f91-adb1-f7bd5f79a68e","resolution":{"observed_at":"2026-08-01T12:58:47.994753Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T12:58:48.194747Z","title":"How paypal uses real-time graph database and graph analysis to fight fraud, 2021","venue":null,"work_id":null,"year":2021},"citing_paper":{"arxiv_id":"2607.19266","last_updated":"2026-07-21T16:37:41Z","snapshot_observed_at":"2026-08-09T01:03:08.006963Z","submitted_at":"2026-07-21T16:37:41Z","title":"Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agentic Case Investigation","version":1},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-08-01T12:58:48.194747Z"},"links":{"citing_paper":"/paper/2607.19266"},"observation_digest":"sha256:a4530490a50434a18495ae7854fc14e804ddca50f4e742dbf24e7303fef550b0","observation_id":"ac1ba197-400d-4fe7-b52a-0a76fdbc8e5b","resolution":{"observed_at":"2026-08-01T12:58:48.194747Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T12:58:48.276108Z","title":"Kam, and Yee Ling Boo","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.19266","last_updated":"2026-07-21T16:37:41Z","snapshot_observed_at":"2026-08-09T01:03:08.006963Z","submitted_at":"2026-07-21T16:37:41Z","title":"Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agentic Case Investigation","version":1},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-08-01T12:58:48.276108Z"},"links":{"citing_paper":"/paper/2607.19266"},"observation_digest":"sha256:c05684e8416f7cbe4f3f10c98617e6cd6c430adfa1abef3707059ecb7be00cfb","observation_id":"4b8d65b2-ef9a-4150-bbe9-3d1d98c219f5","resolution":{"observed_at":"2026-08-01T12:58:48.276108Z","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":"10.1609/aaai.v40i29.39654","metadata_source":"openalex","pith_arxiv_id":null,"snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":null,"venue":"Proceedings of the AAAI Conference on Artificial Intelligence","work_id":"55baa174-893b-4740-ae21-1a2e22ace865","year":null},"citing_paper":{"arxiv_id":"2607.19266","last_updated":"2026-07-21T16:37:41Z","snapshot_observed_at":"2026-08-09T01:03:08.006963Z","submitted_at":"2026-07-21T16:37:41Z","title":"Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agentic Case Investigation","version":1},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-08-01T12:58:48.085387Z"},"links":{"citing_paper":"/paper/2607.19266"},"observation_digest":"sha256:320bb3f069f265301e847247207961638e3462cf8d3d84b59f605626eb1c4b8b","observation_id":"03278012-5744-4631-878d-92fafb93b9e0","resolution":{"observed_at":"2026-08-01T13:04:35.360251Z","resolver_source":"doi","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-09T06:31:02.800959+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T12:58:48.674748Z","title":"Stripe radar: fraud detection architecture and model choices","venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.19266","last_updated":"2026-07-21T16:37:41Z","snapshot_observed_at":"2026-08-09T01:03:08.006963Z","submitted_at":"2026-07-21T16:37:41Z","title":"Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agentic Case Investigation","version":1},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-08-01T12:58:48.674748Z"},"links":{"citing_paper":"/paper/2607.19266"},"observation_digest":"sha256:e5d0e3313319a7ed4636275f853502d7849c4f0ba7b59d12657c904fabd530e5","observation_id":"d9d44ea5-00bb-448b-958e-9560d2d499b3","resolution":{"observed_at":"2026-08-01T12:58:48.674748Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T12:58:48.834750Z","title":"Explainability in graph neural networks: A taxonomic survey.IEEE Transactions on Pattern Analysis and Machine Intelligence, 45(5):5782–5799, 2023","venue":null,"work_id":null,"year":2023},"citing_paper":{"arxiv_id":"2607.19266","last_updated":"2026-07-21T16:37:41Z","snapshot_observed_at":"2026-08-09T01:03:08.006963Z","submitted_at":"2026-07-21T16:37:41Z","title":"Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agentic Case Investigation","version":1},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-08-01T12:58:48.834750Z"},"links":{"citing_paper":"/paper/2607.19266"},"observation_digest":"sha256:6a10249427325a7f5d843948962f5b1f4fed76fd040b9ea6c7f88a2c0b380296","observation_id":"fe1ecee2-98c5-4244-9c6d-17b6a1e511a6","resolution":{"observed_at":"2026-08-01T12:58:48.834750Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T12:58:48.934750Z","title":"Agentic ai in payments in 2026: What’s real, what’s pilot and what’s still hype","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.19266","last_updated":"2026-07-21T16:37:41Z","snapshot_observed_at":"2026-08-09T01:03:08.006963Z","submitted_at":"2026-07-21T16:37:41Z","title":"Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agentic Case Investigation","version":1},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-08-01T12:58:48.934750Z"},"links":{"citing_paper":"/paper/2607.19266"},"observation_digest":"sha256:4394290a8a69933271b511ea19145b4b420e0ae9466a07a82500356dc4299fa6","observation_id":"540e4d91-24d1-4d77-9a08-e3d7792a59cb","resolution":{"observed_at":"2026-08-01T12:58:48.934750Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T12:58:48.525001Z","title":"The precision– recall plot is more informative than the ROC plot when evaluating binary classifiers on imbalanced datasets","venue":null,"work_id":null,"year":2015},"citing_paper":{"arxiv_id":"2607.19266","last_updated":"2026-07-21T16:37:41Z","snapshot_observed_at":"2026-08-09T01:03:08.006963Z","submitted_at":"2026-07-21T16:37:41Z","title":"Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agentic Case Investigation","version":1},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-08-01T12:58:48.525001Z"},"links":{"citing_paper":"/paper/2607.19266"},"observation_digest":"sha256:5dcb5e7fa2cb09e0f686725455ab969812024172496c3c42c1adf5f7eb1c27e4","observation_id":"e74629e3-9718-49db-9d68-b962b0574cf2","resolution":{"observed_at":"2026-08-01T12:58:48.525001Z","resolver_source":null,"status":"malformed_identifier"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2605.28524","last_updated":"2026-05-27T14:21:47Z","snapshot_observed_at":"2026-08-01T17:31:25.013558Z","submitted_at":"2026-05-27T14:21:47Z","title":"Let Relations Speak: An End-to-End LLM-GNN Soft Prompt Framework for Fraud Detection","version":1},"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":"2605.28524","snapshot_observed_at":"2026-08-01T12:58:49.057313Z","title":"Let relations speak: An end-to-end llm-gnn soft prompt framework for fraud detection, 2026","venue":null,"work_id":null,"year":2026},"citing_paper":{"arxiv_id":"2607.19266","last_updated":"2026-07-21T16:37:41Z","snapshot_observed_at":"2026-08-09T01:03:08.006963Z","submitted_at":"2026-07-21T16:37:41Z","title":"Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agentic Case Investigation","version":1},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-08-01T12:58:49.057313Z"},"links":{"cited_paper":"/paper/2605.28524","citing_paper":"/paper/2607.19266"},"observation_digest":"sha256:4281c431b0e335730941b4893443e853601ff8abb6d6ab0fe00ff7b9945556ca","observation_id":"8f1df6cd-f6fe-4baf-86d0-94168741c309","resolution":{"observed_at":"2026-08-01T12:58:49.057313Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T12:58:47.146250Z","title":null,"venue":null,"work_id":null,"year":2016},"citing_paper":{"arxiv_id":"2607.19266","last_updated":"2026-07-21T16:37:41Z","snapshot_observed_at":"2026-08-09T01:03:08.006963Z","submitted_at":"2026-07-21T16:37:41Z","title":"Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agentic Case Investigation","version":1},"reference_index":2016,"source":"pdf_text","source_observed_at":"2026-08-01T12:58:47.146250Z"},"links":{"citing_paper":"/paper/2607.19266"},"observation_digest":"sha256:9ba372cbd6d32ac9065ce17cfddd158852deaafea0c76ded30a1ddbd96b5f475","observation_id":"f82b92a2-daef-4f4b-ba51-832dc9afbdf1","resolution":{"observed_at":"2026-08-01T12:58:47.146250Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T12:58:48.440491Z","title":null,"venue":null,"work_id":null,"year":2020},"citing_paper":{"arxiv_id":"2607.19266","last_updated":"2026-07-21T16:37:41Z","snapshot_observed_at":"2026-08-09T01:03:08.006963Z","submitted_at":"2026-07-21T16:37:41Z","title":"Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agentic Case Investigation","version":1},"reference_index":2020,"source":"pdf_text","source_observed_at":"2026-08-01T12:58:48.440491Z"},"links":{"citing_paper":"/paper/2607.19266"},"observation_digest":"sha256:6267c620d5fe9f5ded76736df37c50ee9d9febdd17634a298926d6ed75503e24","observation_id":"6e9ef00c-dd64-40f4-8fda-4ef3e14686ff","resolution":{"observed_at":"2026-08-01T12:58:48.440491Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-08-01T12:58:46.370297Z","title":null,"venue":null,"work_id":null,"year":null},"citing_paper":{"arxiv_id":"2607.19266","last_updated":"2026-07-21T16:37:41Z","snapshot_observed_at":"2026-08-09T01:03:08.006963Z","submitted_at":"2026-07-21T16:37:41Z","title":"Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agentic Case Investigation","version":1},"reference_index":2026,"source":"pdf_text","source_observed_at":"2026-08-01T12:58:46.370297Z"},"links":{"citing_paper":"/paper/2607.19266"},"observation_digest":"sha256:05b897bdece831a20583ee0471b42dd6db10aa0527f8aa55a96d410fd3dc2e93","observation_id":"f6c72af0-e4a3-4b0e-9403-518cfc68a68c","resolution":{"observed_at":"2026-08-01T12:58:46.370297Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}}],"paper":{"arxiv_id":"2607.19266","last_updated":"2026-07-21T16:37:41Z","latest_version":1,"primary_category":"cs.LG","snapshot_observed_at":"2026-08-09T01:03:08.006963Z","submitted_at":"2026-07-21T16:37:41Z","title":"Toward Auditable Fraud Detection: Combining Graph Features, Model Explanations, and Agentic Case Investigation"},"reference_resolution":{"displayed":32,"state_counts":{"malformed_identifier":2,"metadata_mismatch":0,"parse_uncertain":0,"unresolved":27,"verified_exact":3,"verified_fuzzy":0},"total_outbound_references":32},"refusal":"A citation records a reference. It does not transfer a finding from one paper to another.","schema":"pith.paper-citation-record.v1","standing_sources":[{"observed_at":"2026-08-09T06:31:02.800959+00:00","source":"crossref"},{"observed_at":"2026-08-09T06:30:57.326959+00:00","source":"retraction_watch"}],"thesis":"As of 9 August 2026, this Paper Citation Record lists 32 of 32 outbound references and 0 inbound Pith citation observations for arXiv:2607.19266."}