{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7QCQHGJP27X3CJVAWDGG5ZVYTS","short_pith_number":"pith:7QCQHGJP","schema_version":"1.0","canonical_sha256":"fc0503992fd7efb126a0b0cc6ee6b89cb7f55a2a8053ce16c26905f3d0f1471e","source":{"kind":"arxiv","id":"2403.19735","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Anomaly Detection in Financial Markets with an LLM-based Multi-Agent Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"q-fin.RM","authors_text":"Taejin Park","submitted_at":"2024-03-28T14:43:49Z","abstract_excerpt":"This paper introduces a Large Language Model (LLM)-based multi-agent framework designed to enhance anomaly detection within financial market data, tackling the longstanding challenge of manually verifying system-generated anomaly alerts. The framework harnesses a collaborative network of AI agents, each specialised in distinct functions including data conversion, expert analysis via web research, institutional knowledge utilization or cross-checking and report consolidation and management roles. By coordinating these agents towards a common objective, the framework provides a comprehensive and"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2403.19735","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"q-fin.RM","submitted_at":"2024-03-28T14:43:49Z","cross_cats_sorted":[],"title_canon_sha256":"4ab5c6b6d41c7c0ebccd01a0fbaf9ab5a7f1cfe0d10c9aeb69f525fde217e58b","abstract_canon_sha256":"23fed6a89f4383c20925ea2b4809c78467e4f2f3902390c8a52a8efbe5e8b1de"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:02:07.977033Z","signature_b64":"KFlPbEAlSS2jlTUatlVtwGD/cRH9PRx/E1SC+Cdc0jAgOfzPH0Yp1tXlgkA84UFdVI6lILmhgZ2YDTLH/LZ6Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fc0503992fd7efb126a0b0cc6ee6b89cb7f55a2a8053ce16c26905f3d0f1471e","last_reissued_at":"2026-07-05T08:02:07.976491Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:02:07.976491Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Anomaly Detection in Financial Markets with an LLM-based Multi-Agent Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"q-fin.RM","authors_text":"Taejin Park","submitted_at":"2024-03-28T14:43:49Z","abstract_excerpt":"This paper introduces a Large Language Model (LLM)-based multi-agent framework designed to enhance anomaly detection within financial market data, tackling the longstanding challenge of manually verifying system-generated anomaly alerts. The framework harnesses a collaborative network of AI agents, each specialised in distinct functions including data conversion, expert analysis via web research, institutional knowledge utilization or cross-checking and report consolidation and management roles. By coordinating these agents towards a common objective, the framework provides a comprehensive and"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.19735","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2403.19735/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2403.19735","created_at":"2026-07-05T08:02:07.976554+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.19735v1","created_at":"2026-07-05T08:02:07.976554+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.19735","created_at":"2026-07-05T08:02:07.976554+00:00"},{"alias_kind":"pith_short_12","alias_value":"7QCQHGJP27X3","created_at":"2026-07-05T08:02:07.976554+00:00"},{"alias_kind":"pith_short_16","alias_value":"7QCQHGJP27X3CJVA","created_at":"2026-07-05T08:02:07.976554+00:00"},{"alias_kind":"pith_short_8","alias_value":"7QCQHGJP","created_at":"2026-07-05T08:02:07.976554+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.19538","citing_title":"Integrating Anomaly Detection into Agentic AI for Proactive Risk Management in Human Activity","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18266","citing_title":"Enhancing Tabular Anomaly Detection via Pseudo-Label-Guided Generation","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7QCQHGJP27X3CJVAWDGG5ZVYTS","json":"https://pith.science/pith/7QCQHGJP27X3CJVAWDGG5ZVYTS.json","graph_json":"https://pith.science/api/pith-number/7QCQHGJP27X3CJVAWDGG5ZVYTS/graph.json","events_json":"https://pith.science/api/pith-number/7QCQHGJP27X3CJVAWDGG5ZVYTS/events.json","paper":"https://pith.science/paper/7QCQHGJP"},"agent_actions":{"view_html":"https://pith.science/pith/7QCQHGJP27X3CJVAWDGG5ZVYTS","download_json":"https://pith.science/pith/7QCQHGJP27X3CJVAWDGG5ZVYTS.json","view_paper":"https://pith.science/paper/7QCQHGJP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.19735&json=true","fetch_graph":"https://pith.science/api/pith-number/7QCQHGJP27X3CJVAWDGG5ZVYTS/graph.json","fetch_events":"https://pith.science/api/pith-number/7QCQHGJP27X3CJVAWDGG5ZVYTS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7QCQHGJP27X3CJVAWDGG5ZVYTS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7QCQHGJP27X3CJVAWDGG5ZVYTS/action/storage_attestation","attest_author":"https://pith.science/pith/7QCQHGJP27X3CJVAWDGG5ZVYTS/action/author_attestation","sign_citation":"https://pith.science/pith/7QCQHGJP27X3CJVAWDGG5ZVYTS/action/citation_signature","submit_replication":"https://pith.science/pith/7QCQHGJP27X3CJVAWDGG5ZVYTS/action/replication_record"}},"created_at":"2026-07-05T08:02:07.976554+00:00","updated_at":"2026-07-05T08:02:07.976554+00:00"}