{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZJA54I5HIUDVRQPJL5J2FS5AEA","short_pith_number":"pith:ZJA54I5H","schema_version":"1.0","canonical_sha256":"ca41de23a7450758c1e95f53a2cba020088631b309fb08ad5c61ea6232fc35b9","source":{"kind":"arxiv","id":"2405.04294","version":1},"attestation_state":"computed","paper":{"title":"Enhancing the Efficiency and Accuracy of Underlying Asset Reviews in Structured Finance: The Application of Multi-agent Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Haicheng Deng, Kai Zou, Shiqi Xu, Xiangpeng Wan","submitted_at":"2024-05-07T13:09:49Z","abstract_excerpt":"Structured finance, which involves restructuring diverse assets into securities like MBS, ABS, and CDOs, enhances capital market efficiency but presents significant due diligence challenges. This study explores the integration of artificial intelligence (AI) with traditional asset review processes to improve efficiency and accuracy in structured finance. Using both open-sourced and close-sourced large language models (LLMs), we demonstrate that AI can automate the verification of information between loan applications and bank statements effectively. While close-sourced models such as GPT-4 sho"},"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":"2405.04294","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-05-07T13:09:49Z","cross_cats_sorted":[],"title_canon_sha256":"aad58a8f5c9186abafd0789932971e4bed3d87e1c807044cc95ae5b8311a0fcd","abstract_canon_sha256":"444e8ca900c2fff4035d8c44184f451dce0922f605faf9dabf12a60a83579da2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:16:34.756784Z","signature_b64":"hxucCZL/nzW1hO0iQHfZZ6kebajwfl0qVQeB2xLFEfDOnnosDS9Y3YzwqrcHwJdxefzbFHyqicIT6c7D45ohDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ca41de23a7450758c1e95f53a2cba020088631b309fb08ad5c61ea6232fc35b9","last_reissued_at":"2026-07-05T08:16:34.756304Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:16:34.756304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing the Efficiency and Accuracy of Underlying Asset Reviews in Structured Finance: The Application of Multi-agent Framework","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Haicheng Deng, Kai Zou, Shiqi Xu, Xiangpeng Wan","submitted_at":"2024-05-07T13:09:49Z","abstract_excerpt":"Structured finance, which involves restructuring diverse assets into securities like MBS, ABS, and CDOs, enhances capital market efficiency but presents significant due diligence challenges. This study explores the integration of artificial intelligence (AI) with traditional asset review processes to improve efficiency and accuracy in structured finance. Using both open-sourced and close-sourced large language models (LLMs), we demonstrate that AI can automate the verification of information between loan applications and bank statements effectively. While close-sourced models such as GPT-4 sho"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.04294","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/2405.04294/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":"2405.04294","created_at":"2026-07-05T08:16:34.756369+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.04294v1","created_at":"2026-07-05T08:16:34.756369+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.04294","created_at":"2026-07-05T08:16:34.756369+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZJA54I5HIUDV","created_at":"2026-07-05T08:16:34.756369+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZJA54I5HIUDVRQPJ","created_at":"2026-07-05T08:16:34.756369+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZJA54I5H","created_at":"2026-07-05T08:16:34.756369+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.19678","citing_title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","ref_index":190,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZJA54I5HIUDVRQPJL5J2FS5AEA","json":"https://pith.science/pith/ZJA54I5HIUDVRQPJL5J2FS5AEA.json","graph_json":"https://pith.science/api/pith-number/ZJA54I5HIUDVRQPJL5J2FS5AEA/graph.json","events_json":"https://pith.science/api/pith-number/ZJA54I5HIUDVRQPJL5J2FS5AEA/events.json","paper":"https://pith.science/paper/ZJA54I5H"},"agent_actions":{"view_html":"https://pith.science/pith/ZJA54I5HIUDVRQPJL5J2FS5AEA","download_json":"https://pith.science/pith/ZJA54I5HIUDVRQPJL5J2FS5AEA.json","view_paper":"https://pith.science/paper/ZJA54I5H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.04294&json=true","fetch_graph":"https://pith.science/api/pith-number/ZJA54I5HIUDVRQPJL5J2FS5AEA/graph.json","fetch_events":"https://pith.science/api/pith-number/ZJA54I5HIUDVRQPJL5J2FS5AEA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZJA54I5HIUDVRQPJL5J2FS5AEA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZJA54I5HIUDVRQPJL5J2FS5AEA/action/storage_attestation","attest_author":"https://pith.science/pith/ZJA54I5HIUDVRQPJL5J2FS5AEA/action/author_attestation","sign_citation":"https://pith.science/pith/ZJA54I5HIUDVRQPJL5J2FS5AEA/action/citation_signature","submit_replication":"https://pith.science/pith/ZJA54I5HIUDVRQPJL5J2FS5AEA/action/replication_record"}},"created_at":"2026-07-05T08:16:34.756369+00:00","updated_at":"2026-07-05T08:16:34.756369+00:00"}