{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BBG5J4MRABHIYMTVC2MVLXQJQG","short_pith_number":"pith:BBG5J4MR","schema_version":"1.0","canonical_sha256":"084dd4f191004e8c3275169955de09819cfb976f223d3f0c34e1f9b4428942ed","source":{"kind":"arxiv","id":"2511.07322","version":3},"attestation_state":"computed","paper":{"title":"FinRpt: Dataset, Evaluation System and LLM-based Multi-agent Framework for Equity Research Report Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Rui Yan, Shukun Zhang, Shuqi Li, Song Jin","submitted_at":"2025-11-10T17:22:32Z","abstract_excerpt":"While LLMs have shown great success in financial tasks like stock prediction and question answering, their application in fully automating Equity Research Report generation remains uncharted territory. In this paper, we formulate the Equity Research Report (ERR) Generation task for the first time. To address the data scarcity and the evaluation metrics absence, we present an open-source evaluation benchmark for ERR generation - FinRpt. We frame a Dataset Construction Pipeline that integrates 7 financial data types and produces a high-quality ERR dataset automatically, which could be used for m"},"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":"2511.07322","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-11-10T17:22:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"da52acf5abf8e3ad9d243b94299a0ad944cae52d5cb3a32576d9cbf62e8479e9","abstract_canon_sha256":"fd3abbb52cc29789ae3d19d9328798a54f35811ad0b239474de8d1623bf40a7c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-06T01:37:24.116455Z","signature_b64":"0nBlGGBaW7eQoGfqiahiw2gYDMCkCTFYsZRgzIBDhEsUiOz4zBAGa3BriQ+phpgFVY8mqLFzfQl87Lehm5dlDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"084dd4f191004e8c3275169955de09819cfb976f223d3f0c34e1f9b4428942ed","last_reissued_at":"2026-08-06T01:37:24.114770Z","signature_status":"signed_v1","first_computed_at":"2026-08-06T01:37:24.114770Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FinRpt: Dataset, Evaluation System and LLM-based Multi-agent Framework for Equity Research Report Generation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Rui Yan, Shukun Zhang, Shuqi Li, Song Jin","submitted_at":"2025-11-10T17:22:32Z","abstract_excerpt":"While LLMs have shown great success in financial tasks like stock prediction and question answering, their application in fully automating Equity Research Report generation remains uncharted territory. In this paper, we formulate the Equity Research Report (ERR) Generation task for the first time. To address the data scarcity and the evaluation metrics absence, we present an open-source evaluation benchmark for ERR generation - FinRpt. We frame a Dataset Construction Pipeline that integrates 7 financial data types and produces a high-quality ERR dataset automatically, which could be used for m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.07322","kind":"arxiv","version":3},"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/2511.07322/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":"2511.07322","created_at":"2026-08-06T01:37:24.116647+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.07322v3","created_at":"2026-08-06T01:37:24.116647+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.07322","created_at":"2026-08-06T01:37:24.116647+00:00"},{"alias_kind":"pith_short_12","alias_value":"BBG5J4MRABHI","created_at":"2026-08-06T01:37:24.116647+00:00"},{"alias_kind":"pith_short_16","alias_value":"BBG5J4MRABHIYMTV","created_at":"2026-08-06T01:37:24.116647+00:00"},{"alias_kind":"pith_short_8","alias_value":"BBG5J4MR","created_at":"2026-08-06T01:37:24.116647+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2606.17458","citing_title":"ICBCBench: An Industry Consortium Benchmark for Financial Deep Research","ref_index":17,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BBG5J4MRABHIYMTVC2MVLXQJQG","json":"https://pith.science/pith/BBG5J4MRABHIYMTVC2MVLXQJQG.json","graph_json":"https://pith.science/api/pith-number/BBG5J4MRABHIYMTVC2MVLXQJQG/graph.json","events_json":"https://pith.science/api/pith-number/BBG5J4MRABHIYMTVC2MVLXQJQG/events.json","paper":"https://pith.science/paper/BBG5J4MR"},"agent_actions":{"view_html":"https://pith.science/pith/BBG5J4MRABHIYMTVC2MVLXQJQG","download_json":"https://pith.science/pith/BBG5J4MRABHIYMTVC2MVLXQJQG.json","view_paper":"https://pith.science/paper/BBG5J4MR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.07322&json=true","fetch_graph":"https://pith.science/api/pith-number/BBG5J4MRABHIYMTVC2MVLXQJQG/graph.json","fetch_events":"https://pith.science/api/pith-number/BBG5J4MRABHIYMTVC2MVLXQJQG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BBG5J4MRABHIYMTVC2MVLXQJQG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BBG5J4MRABHIYMTVC2MVLXQJQG/action/storage_attestation","attest_author":"https://pith.science/pith/BBG5J4MRABHIYMTVC2MVLXQJQG/action/author_attestation","sign_citation":"https://pith.science/pith/BBG5J4MRABHIYMTVC2MVLXQJQG/action/citation_signature","submit_replication":"https://pith.science/pith/BBG5J4MRABHIYMTVC2MVLXQJQG/action/replication_record"}},"created_at":"2026-08-06T01:37:24.116647+00:00","updated_at":"2026-08-06T01:37:24.116647+00:00"}