{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:AGDVBHVEHY7NOGFVEJVWC5R7LY","short_pith_number":"pith:AGDVBHVE","schema_version":"1.0","canonical_sha256":"0187509ea43e3ed718b5226b61763f5e302885afc2fa21158254de93f3b1da6f","source":{"kind":"arxiv","id":"2507.17186","version":2},"attestation_state":"computed","paper":{"title":"FinGAIA: A Chinese Benchmark for AI Agents in Real-World Financial Domain","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dongpo Cheng, Fangqi Lou, Jiajie Xu, Jinyi Niu, Jun Han, Lejie Zhang, Lingfeng Zeng, Liwen Zhang, Mengping Li, Qi Qi, Ruilun Feng, Ruiqi Hu, Weige Cai, Wei Zhang, Xin Guo, Yicheng Ren, Yifan Dong, Zhaowei Liu, Zhengbo Feng, Ziwei Yang, Zixuan Wang","submitted_at":"2025-07-23T04:19:16Z","abstract_excerpt":"The booming development of AI agents presents unprecedented opportunities for automating complex tasks across various domains. However, their multi-step, multi-tool collaboration capabilities in the financial sector remain underexplored. This paper introduces FinGAIA, an end-to-end benchmark designed to evaluate the practical abilities of AI agents in the financial domain. FinGAIA comprises 407 meticulously crafted tasks, spanning seven major financial sub-domains: securities, funds, banking, insurance, futures, trusts, and asset management. These tasks are organized into three hierarchical le"},"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":"2507.17186","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-23T04:19:16Z","cross_cats_sorted":[],"title_canon_sha256":"57162e0cf99c61cde2e8c808c5213daaa8957e19de2109804e1fce863064e2f0","abstract_canon_sha256":"d2b898a2c6ac9129ed63d5d4fbfbf522dde3556239319bbb71d57e8bd5ca20a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:59.785424Z","signature_b64":"djNx58LqTU6ZVG4p9Jo5O+7ef20PNjtGTC9hjUspEZyBR+rFnk5jI8GjpbhJ+awnEYke1moYuzz4x/ufFYGZDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0187509ea43e3ed718b5226b61763f5e302885afc2fa21158254de93f3b1da6f","last_reissued_at":"2026-07-05T11:45:59.784903Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:59.784903Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FinGAIA: A Chinese Benchmark for AI Agents in Real-World Financial Domain","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dongpo Cheng, Fangqi Lou, Jiajie Xu, Jinyi Niu, Jun Han, Lejie Zhang, Lingfeng Zeng, Liwen Zhang, Mengping Li, Qi Qi, Ruilun Feng, Ruiqi Hu, Weige Cai, Wei Zhang, Xin Guo, Yicheng Ren, Yifan Dong, Zhaowei Liu, Zhengbo Feng, Ziwei Yang, Zixuan Wang","submitted_at":"2025-07-23T04:19:16Z","abstract_excerpt":"The booming development of AI agents presents unprecedented opportunities for automating complex tasks across various domains. However, their multi-step, multi-tool collaboration capabilities in the financial sector remain underexplored. This paper introduces FinGAIA, an end-to-end benchmark designed to evaluate the practical abilities of AI agents in the financial domain. FinGAIA comprises 407 meticulously crafted tasks, spanning seven major financial sub-domains: securities, funds, banking, insurance, futures, trusts, and asset management. These tasks are organized into three hierarchical le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.17186","kind":"arxiv","version":2},"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/2507.17186/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":"2507.17186","created_at":"2026-07-05T11:45:59.784964+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.17186v2","created_at":"2026-07-05T11:45:59.784964+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.17186","created_at":"2026-07-05T11:45:59.784964+00:00"},{"alias_kind":"pith_short_12","alias_value":"AGDVBHVEHY7N","created_at":"2026-07-05T11:45:59.784964+00:00"},{"alias_kind":"pith_short_16","alias_value":"AGDVBHVEHY7NOGFV","created_at":"2026-07-05T11:45:59.784964+00:00"},{"alias_kind":"pith_short_8","alias_value":"AGDVBHVE","created_at":"2026-07-05T11:45:59.784964+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17458","citing_title":"ICBCBench: An Industry Consortium Benchmark for Financial Deep Research","ref_index":45,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AGDVBHVEHY7NOGFVEJVWC5R7LY","json":"https://pith.science/pith/AGDVBHVEHY7NOGFVEJVWC5R7LY.json","graph_json":"https://pith.science/api/pith-number/AGDVBHVEHY7NOGFVEJVWC5R7LY/graph.json","events_json":"https://pith.science/api/pith-number/AGDVBHVEHY7NOGFVEJVWC5R7LY/events.json","paper":"https://pith.science/paper/AGDVBHVE"},"agent_actions":{"view_html":"https://pith.science/pith/AGDVBHVEHY7NOGFVEJVWC5R7LY","download_json":"https://pith.science/pith/AGDVBHVEHY7NOGFVEJVWC5R7LY.json","view_paper":"https://pith.science/paper/AGDVBHVE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.17186&json=true","fetch_graph":"https://pith.science/api/pith-number/AGDVBHVEHY7NOGFVEJVWC5R7LY/graph.json","fetch_events":"https://pith.science/api/pith-number/AGDVBHVEHY7NOGFVEJVWC5R7LY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AGDVBHVEHY7NOGFVEJVWC5R7LY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AGDVBHVEHY7NOGFVEJVWC5R7LY/action/storage_attestation","attest_author":"https://pith.science/pith/AGDVBHVEHY7NOGFVEJVWC5R7LY/action/author_attestation","sign_citation":"https://pith.science/pith/AGDVBHVEHY7NOGFVEJVWC5R7LY/action/citation_signature","submit_replication":"https://pith.science/pith/AGDVBHVEHY7NOGFVEJVWC5R7LY/action/replication_record"}},"created_at":"2026-07-05T11:45:59.784964+00:00","updated_at":"2026-07-05T11:45:59.784964+00:00"}