{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:M5WNUHHNXAH7KPRSU2JQBQTERD","short_pith_number":"pith:M5WNUHHN","schema_version":"1.0","canonical_sha256":"676cda1cedb80ff53e32a69300c26488fc0989516492fca76275fc8e2fbd77e1","source":{"kind":"arxiv","id":"2504.15800","version":3},"attestation_state":"computed","paper":{"title":"FinDER: Financial Dataset for Question Answering and Evaluating Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Alejandro Lopez-Lira, Chaewoon Kim, Chanyeol Choi, Hojun Choi, Jaeseon Ha, Jihoon Kwon, Jy-yong Sohn, Yongjae Lee","submitted_at":"2025-04-22T11:30:13Z","abstract_excerpt":"In the fast-paced financial domain, accurate and up-to-date information is critical to addressing ever-evolving market conditions. Retrieving this information correctly is essential in financial Question-Answering (QA), since many language models struggle with factual accuracy in this domain. We present FinDER, an expert-generated dataset tailored for Retrieval-Augmented Generation (RAG) in finance. Unlike existing QA datasets that provide predefined contexts and rely on relatively clear and straightforward queries, FinDER focuses on annotating search-relevant evidence by domain experts, offer"},"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":"2504.15800","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-04-22T11:30:13Z","cross_cats_sorted":[],"title_canon_sha256":"cba252d23d7d8777434f922ff393157798004d9770f360d64433a73c40c28c57","abstract_canon_sha256":"4f013b3c29b35a745275cafc53caefdc2ac51246075b7301e9004cd17f81e276"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:03:47.823709Z","signature_b64":"9SbsdE0XWPzlrQNV1iQvb2V5pSJEMGMPECrvDmVw09wJ6pCUgQpNkQ/+Ebi1yb+oWImPozB2Fh8EXNrQQ6ReBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"676cda1cedb80ff53e32a69300c26488fc0989516492fca76275fc8e2fbd77e1","last_reissued_at":"2026-07-05T12:03:47.823155Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:03:47.823155Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FinDER: Financial Dataset for Question Answering and Evaluating Retrieval-Augmented Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Alejandro Lopez-Lira, Chaewoon Kim, Chanyeol Choi, Hojun Choi, Jaeseon Ha, Jihoon Kwon, Jy-yong Sohn, Yongjae Lee","submitted_at":"2025-04-22T11:30:13Z","abstract_excerpt":"In the fast-paced financial domain, accurate and up-to-date information is critical to addressing ever-evolving market conditions. Retrieving this information correctly is essential in financial Question-Answering (QA), since many language models struggle with factual accuracy in this domain. We present FinDER, an expert-generated dataset tailored for Retrieval-Augmented Generation (RAG) in finance. Unlike existing QA datasets that provide predefined contexts and rely on relatively clear and straightforward queries, FinDER focuses on annotating search-relevant evidence by domain experts, offer"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.15800","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/2504.15800/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":"2504.15800","created_at":"2026-07-05T12:03:47.823217+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.15800v3","created_at":"2026-07-05T12:03:47.823217+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15800","created_at":"2026-07-05T12:03:47.823217+00:00"},{"alias_kind":"pith_short_12","alias_value":"M5WNUHHNXAH7","created_at":"2026-07-05T12:03:47.823217+00:00"},{"alias_kind":"pith_short_16","alias_value":"M5WNUHHNXAH7KPRS","created_at":"2026-07-05T12:03:47.823217+00:00"},{"alias_kind":"pith_short_8","alias_value":"M5WNUHHN","created_at":"2026-07-05T12:03:47.823217+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25030","citing_title":"MimirRAG: A Multi-Agent RAG Framework for Financial Data Retrieval with Metadata Integration","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2603.16877","citing_title":"Enhancing Financial Report Question-Answering: A Retrieval-Augmented Generation System with Reranking Analysis","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2603.26815","citing_title":"Sustainable Hybrid Document-Routed Retrieval for Financial RAG: Resolving the Robustness-Precision Trade-off","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14488","citing_title":"Controlling Authority Retrieval: A Missing Retrieval Objective for Authority-Governed Knowledge","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M5WNUHHNXAH7KPRSU2JQBQTERD","json":"https://pith.science/pith/M5WNUHHNXAH7KPRSU2JQBQTERD.json","graph_json":"https://pith.science/api/pith-number/M5WNUHHNXAH7KPRSU2JQBQTERD/graph.json","events_json":"https://pith.science/api/pith-number/M5WNUHHNXAH7KPRSU2JQBQTERD/events.json","paper":"https://pith.science/paper/M5WNUHHN"},"agent_actions":{"view_html":"https://pith.science/pith/M5WNUHHNXAH7KPRSU2JQBQTERD","download_json":"https://pith.science/pith/M5WNUHHNXAH7KPRSU2JQBQTERD.json","view_paper":"https://pith.science/paper/M5WNUHHN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.15800&json=true","fetch_graph":"https://pith.science/api/pith-number/M5WNUHHNXAH7KPRSU2JQBQTERD/graph.json","fetch_events":"https://pith.science/api/pith-number/M5WNUHHNXAH7KPRSU2JQBQTERD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M5WNUHHNXAH7KPRSU2JQBQTERD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M5WNUHHNXAH7KPRSU2JQBQTERD/action/storage_attestation","attest_author":"https://pith.science/pith/M5WNUHHNXAH7KPRSU2JQBQTERD/action/author_attestation","sign_citation":"https://pith.science/pith/M5WNUHHNXAH7KPRSU2JQBQTERD/action/citation_signature","submit_replication":"https://pith.science/pith/M5WNUHHNXAH7KPRSU2JQBQTERD/action/replication_record"}},"created_at":"2026-07-05T12:03:47.823217+00:00","updated_at":"2026-07-05T12:03:47.823217+00:00"}