{"as_of":"2026-08-08T02:28:00Z","caps":{"database_statements":6,"inbound":100,"outbound":100},"context_digest":"sha256:cd015c5f2df19233667f01b4a7f9ad0205e29b558fa27324d95b6fb572d75f96","coverage":[{"denominator":46,"lane":"reference_resolution","note":"Typed states for the displayed outbound observations.","records_observed":46,"source":"paper_references, paper_reference_links","source_observed_at":"2026-06-27T19:48:52.564810Z","state":"measured"},{"denominator":47,"lane":"standing_notices","note":"One-hop event checks from named stored sources.","records_observed":47,"source":"scholarly_work_events, retraction_status_cache","source_observed_at":"2026-08-07T06:34:17.273281+00:00","state":"measured"},{"denominator":1,"lane":"inbound_itemization","note":"Pith citing papers itemized under the disclosed page cap.","records_observed":1,"source":"paper_references, paper_reference_links","source_observed_at":"2026-08-01T12:58:45.908231Z","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":[{"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":"2026-08-06T19:16:17.352906Z","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":"sha256:8fa2bfb66258d3e06d73c4cb582be4bd57c9c4519e69d4a2eefa687732a931ee","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"}}],"links":{"evidence":"/evidence","html":"/paper/2606.08146/citation-record","integrity":"/paper/2606.08146/integrity","json":"/paper/2606.08146/citation-record.json","paper":"/paper/2606.08146"},"outbound":[{"citation":{"cited_paper":null,"cited_work":{"arxiv_id":null,"doi":null,"metadata_source":null,"pith_arxiv_id":null,"snapshot_observed_at":"2026-06-27T19:48:52.564810Z","title":"Qwen3-Max.https://qwen.ai/ research, 2025","venue":null,"work_id":null,"year":2025},"citing_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},"reference_index":1,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:5727d37ade3122087adf1f0bb9e7885d38a87f97c7bdb3b4f1082ae714e211be","observation_id":"1765eaca-741c-449f-a1e2-67a92eaf4c2c","resolution":{"observed_at":"2026-06-27T19:48:52.564810Z","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":"2026-06-27T19:48:52.564810Z","title":"Claude code.https://www.anthropic","venue":null,"work_id":null,"year":2025},"citing_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},"reference_index":2,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:55f4149565b30ad4a77577aba021a0aed98a92df19d29522515d3780fe056804","observation_id":"1a21a8d6-22f4-4f65-8b71-5ced4589eea6","resolution":{"observed_at":"2026-06-27T19:48:52.564810Z","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":"2026-06-27T19:48:52.564810Z","title":"Claude opus 4.7 system card.https://www","venue":null,"work_id":null,"year":2026},"citing_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},"reference_index":3,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:be0eca05876e5055664815185cfb038de21be2ee0b15fd6ba409411cb9487a26","observation_id":"7980fae2-8218-4cc5-855b-d37adee15d64","resolution":{"observed_at":"2026-06-27T19:48:52.564810Z","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":"2026-06-27T19:48:52.564810Z","title":"Data mining for credit card fraud: A comparative study.Decision support systems, pages 602–613, 2011","venue":null,"work_id":null,"year":2011},"citing_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},"reference_index":4,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:5ac6bbdd34cfdee124dc74d3e97e6b7c33773693b735020e454058db294f9eba","observation_id":"5c7aeb29-87bc-4876-aff4-a7618eeb0378","resolution":{"observed_at":"2026-06-27T19:48:52.564810Z","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":"2026-06-27T19:48:52.564810Z","title":"Smote: synthetic minority over- sampling technique.Journal of artificial intelligence re- search, pages 321–357, 2002","venue":null,"work_id":null,"year":2002},"citing_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},"reference_index":5,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:0f0537142219513ba863b6e57dfeedaa686a7bded29a72fa9605114aa9df628a","observation_id":"30bfcc89-7aa2-4dd9-8ef9-97569d443e9d","resolution":{"observed_at":"2026-06-27T19:48:52.564810Z","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":"2026-06-27T19:48:52.564810Z","title":"Xgboost: A scalable tree boosting system","venue":null,"work_id":null,"year":2016},"citing_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},"reference_index":6,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:9f8bf898ea58359bd6afa1951dba8c2f7b2c730ecb00d96151427c9d87bb295d","observation_id":"551219ae-8914-4cee-a5d9-7461db0c7920","resolution":{"observed_at":"2026-06-27T19:48:52.564810Z","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":"2026-06-27T19:48:52.564810Z","title":"Tlk: An in- dustrial internet of things attack detection method based on transformer-lstm-kelm","venue":null,"work_id":null,"year":2025},"citing_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},"reference_index":7,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:59d235a5129acd720133c4c6ab46d0e73e69db89431a371583bc162904fd0729","observation_id":"8d088bfb-26e1-4c65-bbb0-d6c28898640d","resolution":{"observed_at":"2026-06-27T19:48:52.564810Z","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":"2026-06-27T19:48:52.564810Z","title":"Graph neural networks for financial fraud detection: a re- view.Frontiers of Computer Science, page 199609, 2025","venue":null,"work_id":null,"year":2025},"citing_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},"reference_index":8,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:7a796c65c2ce688da45c0df6fc1f4c411e4e593dd0f441f578976327227b2f77","observation_id":"809a6287-2121-4ed6-bfc7-0965bfd621e7","resolution":{"observed_at":"2026-06-27T19:48:52.564810Z","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":"2026-06-27T19:48:52.564810Z","title":"Learned lessons in credit card fraud detection from a practitioner perspective","venue":null,"work_id":null,"year":2014},"citing_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},"reference_index":9,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:94c5dd378691e430dade861f2591b0a807d327bf53b2f7fc993d305119743be8","observation_id":"537054d2-280e-417c-9547-4f9db003ba74","resolution":{"observed_at":"2026-06-27T19:48:52.564810Z","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":"2026-06-27T19:48:52.564810Z","title":"Credit card fraud de- tection: a realistic modeling and a novel learning strategy","venue":null,"work_id":null,"year":2017},"citing_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},"reference_index":10,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:6c045c648a66b51ae63faaf7ff70dd12d7f85814ae00f98b17c1fa0265a01799","observation_id":"2777a897-a1da-4373-b3fb-cff63958da7c","resolution":{"observed_at":"2026-06-27T19:48:52.564810Z","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":"2026-06-27T19:48:52.564810Z","title":"The relationship between precision-recall and roc curves","venue":null,"work_id":null,"year":null},"citing_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},"reference_index":11,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:9057aba51f9355310511d5904d9d9327c62edf93d526ceff295296e3cd624900","observation_id":"99c7f059-090e-4bfd-8b65-44e4e0079851","resolution":{"observed_at":"2026-06-27T19:48:52.564810Z","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":"2026-06-27T19:48:52.564810Z","title":"DeepSeek-V3.2.https : / / www","venue":null,"work_id":null,"year":2025},"citing_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},"reference_index":12,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:77e5b3b9d87163e1f0055c5b06d1a2e5b692f219764d8374a7ce47fb56d77841","observation_id":"8cbd7220-76f9-4c60-9d37-dd2d3c2018e7","resolution":{"observed_at":"2026-06-27T19:48:52.564810Z","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":"2026-06-27T19:48:52.564810Z","title":"Statistical comparisons of classifiers over multiple data sets.Journal of Machine learning research, pages 1–30, 2006","venue":null,"work_id":null,"year":2006},"citing_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},"reference_index":13,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:c86131960349bd55b43c28040ab784641c9e794ea2c595797f37185fe583d91d","observation_id":"13744eaa-566b-4111-ac93-ae282064c59f","resolution":{"observed_at":"2026-06-27T19:48:52.564810Z","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":"2026-06-27T19:48:52.564810Z","title":"Telecom fraud detection based on large language models: A multi-role, multi-layer prompting strategy.Applied Sciences, page 544, 2026","venue":null,"work_id":null,"year":2026},"citing_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},"reference_index":14,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:e76b47d2aea9f76a798b56e5bf9bce1e8384309cc6741088823b31ec22194475","observation_id":"f060fdce-c5bc-4720-a81f-98aa73b51e2e","resolution":{"observed_at":"2026-06-27T19:48:52.564810Z","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":"2026-06-27T19:48:52.564810Z","title":"Enhancing graph neural network-based 15 fraud detectors against camouflaged fraudsters","venue":null,"work_id":null,"year":2020},"citing_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},"reference_index":15,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:5563d0222ccf9f17b2bd5ee17e2080eaac8a7b4b4b8fc515ef8a6c2f275f5df9","observation_id":"3269db11-515a-4e0f-b3ee-c7b7241defa8","resolution":{"observed_at":"2026-06-27T19:48:52.564810Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2003.06505","last_updated":"2020-03-13T23:10:39Z","snapshot_observed_at":"2026-07-06T09:04:37.917150Z","submitted_at":"2020-03-13T23:10:39Z","title":"AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data","version":1},"cited_work":{"arxiv_id":"2003.06505","doi":"10.48550/arxiv.2003.06505","metadata_source":"pith","pith_arxiv_id":"2003.06505","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"AutoGluon-Tabular: Robust and Accurate AutoML for Structured Data","venue":"stat.ML","work_id":"32ca4e6c-bd72-4586-8594-40eb6bcb6582","year":2020},"citing_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},"reference_index":16,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"cited_paper":"/paper/2003.06505","citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:9511e02c67ae7d3b6ec1e9b0cc3ff46231a49c54f6734dd184d2a582e84a44a4","observation_id":"5b7e3d6a-373c-4072-8f08-d1a2f5b29821","resolution":{"observed_at":"2026-07-02T21:17:25.049143Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-05-23T01:54:03.658463+00:00","source":"crossref_status_cache"},{"observed_at":"2026-05-23T01:54:03.658463+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-27T19:48:52.564810Z","title":"Efficient and robust automated machine learning","venue":null,"work_id":null,"year":2015},"citing_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},"reference_index":17,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:069278b5aa680a99299a358421576cf9b089376e5b4b8343f1a59b9de30164c0","observation_id":"65b50180-8e6d-4e13-8fde-9ec6302c8002","resolution":{"observed_at":"2026-06-27T19:48:52.564810Z","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":"2026-06-27T19:48:52.564810Z","title":"The global state of scams 2025 report.https://www.gasa.org/, 2025","venue":null,"work_id":null,"year":2025},"citing_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},"reference_index":18,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:7e551b4b2fc0dc8ce3edd41b3d08aa106e63e35afc7e3ef456fa466e090de1dd","observation_id":"feef9485-a51e-47f6-bf61-db27563b02ad","resolution":{"observed_at":"2026-06-27T19:48:52.564810Z","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":"2026-06-27T19:48:52.564810Z","title":"Why do tree-based models still outperform deep learning on typi- cal tabular data? InNeurIPS, pages 507–520, 2022","venue":null,"work_id":null,"year":2022},"citing_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},"reference_index":19,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:2b2da0e13b6843ec9d2a4b8700a229d0e1373ffb37454231514c2736c6273346","observation_id":"6090a72f-31bc-48b4-aff5-0a2740c635ae","resolution":{"observed_at":"2026-06-27T19:48:52.564810Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2208.14417","last_updated":"2023-09-22T14:50:22Z","snapshot_observed_at":"2026-07-06T13:47:00.653824Z","submitted_at":"2022-08-30T17:35:39Z","title":"Fraud Dataset Benchmark and Applications","version":3},"cited_work":{"arxiv_id":"2208.14417","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2208.14417","snapshot_observed_at":"2026-07-02T21:17:25.056594Z","title":"Fraud dataset benchmark and applications.arXiv preprint arXiv:2208.14417, 2022","venue":null,"work_id":"2b12f0ca-fc0b-470b-a88b-a93fdb1e00e8","year":2022},"citing_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},"reference_index":20,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"cited_paper":"/paper/2208.14417","citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:f93d342395889fe0c48bf5fa84df25a3a1cfcac023c8896e08d057d190e6b900","observation_id":"7ab9fce2-24ce-46ac-b988-91f22b178c80","resolution":{"observed_at":"2026-07-02T21:17:25.058728Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-27T19:48:52.564810Z","title":"Learning from imbalanced data.IEEE Transactions on knowledge and data engineer- ing, pages 1263–1284, 2009","venue":null,"work_id":null,"year":2009},"citing_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},"reference_index":21,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:729709df20b075a9bfc3ecc499d21cfa8af45147be8e9e9bbec03381455f589c","observation_id":"80547a67-cce4-4521-95a4-0d59e70cce40","resolution":{"observed_at":"2026-06-27T19:48:52.564810Z","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":"2026-06-27T19:48:52.564810Z","title":"FACTGUARD: event-centric and commonsense-guided fake news detection","venue":null,"work_id":null,"year":2026},"citing_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},"reference_index":22,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:b8dd5a956ae4e96805b30d9ef66a274d1788de489bdf6c05120d1a4b4f5dcf04","observation_id":"cb91dd31-f62b-4f7a-aca8-70b2e36f4a92","resolution":{"observed_at":"2026-06-27T19:48:52.564810Z","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":"2026-06-27T19:48:52.564810Z","title":"Data interpreter: An llm agent for data sci- ence","venue":null,"work_id":null,"year":2025},"citing_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},"reference_index":23,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:24f1e2f056a6eb76e14114e138823412c805ee2acdad5658bce3dd29e85654a3","observation_id":"983c0702-2d7a-4383-a6fb-17e596a04eb2","resolution":{"observed_at":"2026-06-27T19:48:52.564810Z","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":"2026-06-27T19:48:52.564810Z","title":"Sequence classification for credit-card fraud detection.Expert systems with applica- tions, pages 234–245, 2018","venue":null,"work_id":null,"year":2018},"citing_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},"reference_index":24,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:2bf8a31a26113b1de943f0606c33981a3667a088fe4e6a354c49c06d06fb2e90","observation_id":"705cbb46-13a5-42f8-9b47-46bc1d395b62","resolution":{"observed_at":"2026-06-27T19:48:52.564810Z","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":"2026-06-27T19:48:52.564810Z","title":"Pick and choose: A gnn-based imbalanced learning approach for fraud detection","venue":null,"work_id":null,"year":2021},"citing_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},"reference_index":25,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:913198d2a15874966c3a1c5174083fdd394b951349f4bd7d318ebbeae1f42c88","observation_id":"f6953e09-2af9-43cd-ae7a-b3eed96dd27f","resolution":{"observed_at":"2026-06-27T19:48:52.564810Z","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":"2026-06-27T19:48:52.564810Z","title":"Paysim: A financial mobile money simulator for fraud de- tection","venue":null,"work_id":null,"year":2016},"citing_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},"reference_index":26,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:c35a4e2d38e4f71d09d0f3193f2b534c8cc121ae525b0e9bd22ad6f9824f7288","observation_id":"5f39f296-96b8-407b-9f22-adbc8b75c118","resolution":{"observed_at":"2026-06-27T19:48:52.564810Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"2010.06479","last_updated":"2020-10-13T15:35:32Z","snapshot_observed_at":"2026-07-06T10:04:02.247851Z","submitted_at":"2020-10-13T15:35:32Z","title":"Credit card fraud detection using machine learning: A survey","version":1},"cited_work":{"arxiv_id":"2010.06479","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"2010.06479","snapshot_observed_at":"2026-07-02T21:17:25.045112Z","title":"Credit card fraud de- tection using machine learning: A survey.arXiv preprint arXiv:2010.06479, 2020","venue":null,"work_id":"8faea344-5c0b-4eb5-8844-1cf49698e112","year":2010},"citing_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},"reference_index":27,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"cited_paper":"/paper/2010.06479","citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:20321004b8e32d3b4653aeb4655e514857e017ee7a3b50f4f2b6625cefe2646f","observation_id":"58df24be-260f-403b-97d3-fe8b62d0af38","resolution":{"observed_at":"2026-07-02T21:17:25.046810Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-27T19:48:52.564810Z","title":"Comparison of the predicted and ob- served secondary structure of t4 phage lysozyme.Biochim- ica et Biophysica Acta (BBA)-Protein Structure, pages 442– 451, 1975","venue":null,"work_id":null,"year":1975},"citing_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},"reference_index":28,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:c5ea29f34589868cb85bb6716290c740a04c361af31855a886a706e80a61b45d","observation_id":"d3572872-c7b4-4b90-98ac-52ae8dd1c492","resolution":{"observed_at":"2026-06-27T19:48:52.564810Z","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":"2026-06-27T19:48:52.564810Z","title":"LLaMA-3.3-70B.https://www.llama.com,","venue":null,"work_id":null,"year":null},"citing_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},"reference_index":29,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:d9491f05d0a9a2a8a870fb372618a1cd9a960eaccb751dd1e38db9554e4ecdaa","observation_id":"3c633ee8-891c-42ab-95cc-b2f868cd0f56","resolution":{"observed_at":"2026-06-27T19:48:52.564810Z","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":"2026-06-27T19:48:52.564810Z","title":"GPT-5.4.https://openai.com, 2026","venue":null,"work_id":null,"year":2026},"citing_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},"reference_index":30,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:7b9e2675df3215a4730db628fb4c74f4e4bb53dadd2867aaf38bdd78945d47b0","observation_id":"85f63baa-4b75-4438-bb77-9996c739d56d","resolution":{"observed_at":"2026-06-27T19:48:52.564810Z","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":"2026-06-27T19:48:52.564810Z","title":"Johnson, and Gianluca Bontempi","venue":null,"work_id":null,"year":null},"citing_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},"reference_index":31,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:a67a87ef434645647f9a016069b83c7722d8bf86a4e37b413d904b59c680e0d8","observation_id":"1f003d1f-3032-4d09-aace-1a9449b040c3","resolution":{"observed_at":"2026-06-27T19:48:52.564810Z","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":"2026-06-27T19:48:52.564810Z","title":"Automatic prompt optimization with ”gradient descent” and beam search","venue":null,"work_id":null,"year":2023},"citing_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},"reference_index":32,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:c97944f18e974ed3033c1bd7fa0be8ebb26817f3f1ec41cc48959b8c923257d2","observation_id":"7672e079-54a1-4d07-bc2d-67ff4d80d0b7","resolution":{"observed_at":"2026-06-27T19:48:52.564810Z","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":"2026-06-27T19:48:52.564810Z","title":"Sequential fraud de- tection for prepaid cards using hidden markov model diver- gence.Expert Systems with Applications, pages 235–251,","venue":null,"work_id":null,"year":null},"citing_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},"reference_index":33,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:491be3c3043a4eea37429b4d4013994b503c7236af055734f63a8d4dc63f0e95","observation_id":"e83a4329-1b18-4f8e-a394-46ab3ede734d","resolution":{"observed_at":"2026-06-27T19:48:52.564810Z","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":"2026-06-27T19:48:52.564810Z","title":"Digital deception: Genera- tive artificial intelligence in social engineering and phishing","venue":null,"work_id":null,"year":2024},"citing_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},"reference_index":34,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:51960b2bc193010b976875f9da0ef560c245510098f19430075b85b3c3a85cb2","observation_id":"5dd3b263-be64-4487-9c88-45661ab59a14","resolution":{"observed_at":"2026-06-27T19:48:52.564810Z","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":"2026-06-27T19:48:52.564810Z","title":"Reflexion: language agents with verbal reinforcement learning","venue":null,"work_id":null,"year":2023},"citing_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},"reference_index":35,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:02ea26995fd337e4532fd553336449b3004d9916d8303a62d1bddec28368d8f2","observation_id":"b4a33e06-84b6-472e-8f7b-442dd66883dc","resolution":{"observed_at":"2026-06-27T19:48:52.564810Z","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":"2026-06-27T19:48:52.564810Z","title":"Tabular data: Deep learning is not all you need.Information fusion, pages 84– 90, 2022","venue":null,"work_id":null,"year":2022},"citing_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},"reference_index":36,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:8f0afc2b3165b56a396fab7b7ec0bd000d8e5760c1265d6620e1ac27ce6e637a","observation_id":"5bd3ffb2-2c8c-434e-9992-8adf3d17d041","resolution":{"observed_at":"2026-06-27T19:48:52.564810Z","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":"2026-06-27T19:48:52.564810Z","title":"MIT press Cambridge, 1998","venue":null,"work_id":null,"year":1998},"citing_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},"reference_index":37,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:0af08599f61d52db3725ed6153100a1a84d6f8458d5fcce45faa7e4666e3122b","observation_id":"6c5187dd-8b3a-46a9-a1bc-e3261b177746","resolution":{"observed_at":"2026-06-27T19:48:52.564810Z","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":"2026-06-27T19:48:52.564810Z","title":"FLAML: A fast and lightweight automl library","venue":null,"work_id":null,"year":null},"citing_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},"reference_index":38,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:ea88d6cac6ca2f5c1e8ac67bf8f0f70b10dbb400e0bf96acb72a79c056714ea6","observation_id":"cdb44926-7f47-4e02-a8e2-9659fd6ef971","resolution":{"observed_at":"2026-06-27T19:48:52.564810Z","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":"2026-06-27T19:48:52.564810Z","title":"A semi-supervised graph attentive network for financial fraud detection","venue":null,"work_id":null,"year":2019},"citing_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},"reference_index":39,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:0c427684790df5cdc805b9edf33e66543ae92c5e12f831567e39e5aa32a6485f","observation_id":"6b29d6c3-a4fe-460b-ba82-ce81c15b3fd4","resolution":{"observed_at":"2026-06-27T19:48:52.564810Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1908.02591","last_updated":"2019-07-31T22:10:01Z","snapshot_observed_at":"2026-08-07T09:37:01.633122Z","submitted_at":"2019-07-31T22:10:01Z","title":"Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensics","version":1},"cited_work":{"arxiv_id":"1908.02591","doi":null,"metadata_source":"pith","pith_arxiv_id":"1908.02591","snapshot_observed_at":"2026-07-09T11:46:12.885720Z","title":"Anti-money laundering in bitcoin: Experimenting with graph convolutional networks for financial forensics","venue":"cs.SI","work_id":"19e55ccd-457d-400e-b663-c70469ccb117","year":2019},"citing_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},"reference_index":40,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"cited_paper":"/paper/1908.02591","citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:5e6c3c4b862a4c779d1a892a2c1ba756ae2bbeef4258c81688e6cb57da67b010","observation_id":"8bfcc596-d4cf-46d7-aed0-92b2c67db0bc","resolution":{"observed_at":"2026-07-02T21:17:25.043924Z","resolver_source":"arxiv_id","status":"metadata_mismatch"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}},{"citation":{"cited_paper":{"arxiv_id":"2308.08155","last_updated":"2023-10-03T20:47:10Z","snapshot_observed_at":"2026-07-31T19:03:03.494918Z","submitted_at":"2023-08-16T05:57:52Z","title":"AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation","version":2},"cited_work":{"arxiv_id":"2308.08155","doi":"10.48550/arxiv.2308.08155","metadata_source":"pith","pith_arxiv_id":"2308.08155","snapshot_observed_at":"2026-08-05T02:28:24.338817Z","title":"AutoGen: Enabling Next-Gen LLM Applications via Multi-Agent Conversation","venue":"cs.AI","work_id":"92b7eb9c-c3d8-4518-a376-06fa15dd895b","year":2023},"citing_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},"reference_index":41,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"cited_paper":"/paper/2308.08155","citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:5c04bd5cceb44ab5191b931260f027fecc43827526502bb5e885d13d1ed2374a","observation_id":"2eee3e8d-1405-4ccd-8d45-8f404fb70094","resolution":{"observed_at":"2026-07-02T21:17:25.051794Z","resolver_source":"local_arxiv","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-07-14T18:20:20.607676+00:00","source":"crossref_status_cache"},{"observed_at":"2026-07-14T18:20:20.607676+00:00","source":"openalex_status_cache"},{"observed_at":"2026-08-07T06:34:11.927384+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":"2026-06-27T19:48:52.564810Z","title":"Semi- supervised credit card fraud detection via attribute-driven graph representation","venue":null,"work_id":null,"year":2023},"citing_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},"reference_index":42,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:87da766477db06b484b4508517ee1eca22f56addac27d10f6db83a524a5c4a0d","observation_id":"369b533b-9de1-46be-8c48-dbbe47801734","resolution":{"observed_at":"2026-06-27T19:48:52.564810Z","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":"2026-06-27T19:48:52.564810Z","title":null,"venue":null,"work_id":null,"year":2024},"citing_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},"reference_index":43,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:091ae9d37a7609899a1007e14d9530b7fabcb7ebbe7478033a7f3aeac8ea8436","observation_id":"b9200d79-2405-4884-a496-de2ccb9c44ec","resolution":{"observed_at":"2026-06-27T19:48:52.564810Z","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":"2026-06-27T19:48:52.564810Z","title":"Random forest for credit card fraud detection","venue":null,"work_id":null,"year":2018},"citing_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},"reference_index":44,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:887b76b524087f3412fcbab757dbf5efab35f448b3a3e20e234fbd9094b2003d","observation_id":"352ffc70-7154-4c8b-a173-143ca7227144","resolution":{"observed_at":"2026-06-27T19:48:52.564810Z","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":"2026-06-27T19:48:52.564810Z","title":"Narasimhan, and Yuan Cao","venue":null,"work_id":null,"year":2023},"citing_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},"reference_index":45,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:595607a095b275565f30ea98bfce421cd73b2287d98b9ddf61f53811a388844b","observation_id":"1edcc6dd-ed75-4a8b-8c29-717b4ee4de57","resolution":{"observed_at":"2026-06-27T19:48:52.564810Z","resolver_source":null,"status":"unresolved"},"standing_notice":{"events":[],"reason":"canonical_work_link_unavailable","source_receipts":[],"state":"unavailable"}},{"citation":{"cited_paper":{"arxiv_id":"1912.02629","last_updated":"2019-12-02T21:40:39Z","snapshot_observed_at":"2026-08-04T21:00:10.716718Z","submitted_at":"2019-12-02T21:40:39Z","title":"A Comprehensive Survey on Machine Learning Techniques and User Authentication Approaches for Credit Card Fraud Detection","version":1},"cited_work":{"arxiv_id":"1912.02629","doi":null,"metadata_source":"arxiv_reference","pith_arxiv_id":"1912.02629","snapshot_observed_at":"2026-07-02T21:17:25.053505Z","title":"A comprehensive survey on machine learning techniques and user authentication approaches for credit card fraud detection","venue":null,"work_id":"02a8c85e-dbc7-4c98-9349-d224c14abbc7","year":1912},"citing_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},"reference_index":46,"source":"pdf_text","source_observed_at":"2026-06-27T19:48:52.564810Z"},"links":{"cited_paper":"/paper/1912.02629","citing_paper":"/paper/2606.08146"},"observation_digest":"sha256:60d659416e48e269d458c3f550a3cfe107a82976b7b8ef8d3719d863b58e353f","observation_id":"76f7da30-0c1b-47d8-a3b2-ca1b90382c2c","resolution":{"observed_at":"2026-07-02T21:17:25.055343Z","resolver_source":"arxiv_id","status":"verified_exact"},"standing_notice":{"events":[],"observation":"No event found in the named queried sources as of 2026-08-07T06:34:17.273281+00:00.","reason":null,"source_receipts":[{"observed_at":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"state":"measured"}}],"paper":{"arxiv_id":"2606.08146","last_updated":"2026-06-06T12:48:45Z","latest_version":1,"primary_category":"cs.AI","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"},"reference_resolution":{"displayed":46,"state_counts":{"malformed_identifier":0,"metadata_mismatch":1,"parse_uncertain":0,"unresolved":40,"verified_exact":5,"verified_fuzzy":0},"total_outbound_references":46},"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":"2026-08-07T06:34:17.273281+00:00","source":"crossref"},{"observed_at":"2026-08-07T06:34:11.927384+00:00","source":"retraction_watch"}],"thesis":"As of 8 August 2026, this Paper Citation Record lists 46 of 46 outbound references and 1 inbound Pith citation observation for arXiv:2606.08146."}