{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OA24EFOJ3UIDJL3OK3SW2AGE4K","short_pith_number":"pith:OA24EFOJ","schema_version":"1.0","canonical_sha256":"7035c215c9dd1034af6e56e56d00c4e2be835e472d39d03bc9940fcfb7ddfdf6","source":{"kind":"arxiv","id":"2507.10448","version":1},"attestation_state":"computed","paper":{"title":"FinTeam: A Multi-Agent Collaborative Intelligence System for Comprehensive Financial Scenarios","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CE","authors_text":"Bingxuan Li, Liwen Zhang, Qiushi Wang, Rong Ye, Wei Chen, Xianyin Zhang, Yingqian Wu, Zefei Long, Zhongtian Lu, Zhongyu Wei","submitted_at":"2025-07-05T10:12:25Z","abstract_excerpt":"Financial report generation tasks range from macro- to micro-economics analysis, also requiring extensive data analysis. Existing LLM models are usually fine-tuned on simple QA tasks and cannot comprehensively analyze real financial scenarios. Given the complexity, financial companies often distribute tasks among departments. Inspired by this, we propose FinTeam, a financial multi-agent collaborative system, with a workflow with four LLM agents: document analyzer, analyst, accountant, and consultant. We train these agents with specific financial expertise using constructed datasets. We evaluat"},"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":"2507.10448","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CE","submitted_at":"2025-07-05T10:12:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"9d560702d8278bdd78f833182be73b9f2847ebd17157bfdc910835cf187974a2","abstract_canon_sha256":"2a36fe36f95d5abbaab0e7051adc1cd8d44ae64d8d1decb4f459a6b7da02ac4e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:36:51.561478Z","signature_b64":"JjXi4Sb03/d13WSwBGrx0LBIF2LVJfil+YmsFhmyRbzWqN2zETc6QVuuWHbJAl6ei2WW0X0RoaY5N583f2W3DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7035c215c9dd1034af6e56e56d00c4e2be835e472d39d03bc9940fcfb7ddfdf6","last_reissued_at":"2026-07-05T11:36:51.560935Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:36:51.560935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FinTeam: A Multi-Agent Collaborative Intelligence System for Comprehensive Financial Scenarios","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CE","authors_text":"Bingxuan Li, Liwen Zhang, Qiushi Wang, Rong Ye, Wei Chen, Xianyin Zhang, Yingqian Wu, Zefei Long, Zhongtian Lu, Zhongyu Wei","submitted_at":"2025-07-05T10:12:25Z","abstract_excerpt":"Financial report generation tasks range from macro- to micro-economics analysis, also requiring extensive data analysis. Existing LLM models are usually fine-tuned on simple QA tasks and cannot comprehensively analyze real financial scenarios. Given the complexity, financial companies often distribute tasks among departments. Inspired by this, we propose FinTeam, a financial multi-agent collaborative system, with a workflow with four LLM agents: document analyzer, analyst, accountant, and consultant. We train these agents with specific financial expertise using constructed datasets. We evaluat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.10448","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/2507.10448/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":"2507.10448","created_at":"2026-07-05T11:36:51.560997+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.10448v1","created_at":"2026-07-05T11:36:51.560997+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.10448","created_at":"2026-07-05T11:36:51.560997+00:00"},{"alias_kind":"pith_short_12","alias_value":"OA24EFOJ3UID","created_at":"2026-07-05T11:36:51.560997+00:00"},{"alias_kind":"pith_short_16","alias_value":"OA24EFOJ3UIDJL3O","created_at":"2026-07-05T11:36:51.560997+00:00"},{"alias_kind":"pith_short_8","alias_value":"OA24EFOJ","created_at":"2026-07-05T11:36:51.560997+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.13942","citing_title":"AI Agents in Financial Markets: Architecture, Applications, and Systemic Implications","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OA24EFOJ3UIDJL3OK3SW2AGE4K","json":"https://pith.science/pith/OA24EFOJ3UIDJL3OK3SW2AGE4K.json","graph_json":"https://pith.science/api/pith-number/OA24EFOJ3UIDJL3OK3SW2AGE4K/graph.json","events_json":"https://pith.science/api/pith-number/OA24EFOJ3UIDJL3OK3SW2AGE4K/events.json","paper":"https://pith.science/paper/OA24EFOJ"},"agent_actions":{"view_html":"https://pith.science/pith/OA24EFOJ3UIDJL3OK3SW2AGE4K","download_json":"https://pith.science/pith/OA24EFOJ3UIDJL3OK3SW2AGE4K.json","view_paper":"https://pith.science/paper/OA24EFOJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.10448&json=true","fetch_graph":"https://pith.science/api/pith-number/OA24EFOJ3UIDJL3OK3SW2AGE4K/graph.json","fetch_events":"https://pith.science/api/pith-number/OA24EFOJ3UIDJL3OK3SW2AGE4K/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OA24EFOJ3UIDJL3OK3SW2AGE4K/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OA24EFOJ3UIDJL3OK3SW2AGE4K/action/storage_attestation","attest_author":"https://pith.science/pith/OA24EFOJ3UIDJL3OK3SW2AGE4K/action/author_attestation","sign_citation":"https://pith.science/pith/OA24EFOJ3UIDJL3OK3SW2AGE4K/action/citation_signature","submit_replication":"https://pith.science/pith/OA24EFOJ3UIDJL3OK3SW2AGE4K/action/replication_record"}},"created_at":"2026-07-05T11:36:51.560997+00:00","updated_at":"2026-07-05T11:36:51.560997+00:00"}