{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZW25QCZ42UACXJUSTM6XQGLYK5","short_pith_number":"pith:ZW25QCZ4","schema_version":"1.0","canonical_sha256":"cdb5d80b3cd5002ba6929b3d781978575b87ee75529c330e4e772a605e714f43","source":{"kind":"arxiv","id":"2608.00183","version":1},"attestation_state":"computed","paper":{"title":"Evidence-Unit Fairness and the Limits of Query-Adaptive Sparse-Dense Fusion in Financial Document Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CE","authors_text":"Chenyu Wu, You Lin","submitted_at":"2026-07-31T18:06:58Z","abstract_excerpt":"Retrieval over financial filings is difficult because queries are short and acronym-heavy while the answer-bearing evidence sits inside long, table-dense documents. We study sparse-dense hybrid retrieval on FinDER, a benchmark of expert-annotated questions over corporate 10-K filings. Our first finding is methodological: if the retrieval unit is larger than the dense encoder's input window, the dense model never sees a large share of the labeled evidence, confounding comparison against a full-text sparse baseline. We measure this directly and remove it by segmenting the corpus into encoder-siz"},"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":"2608.00183","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CE","submitted_at":"2026-07-31T18:06:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"28a0b5742f94247be2f85d4566fcb22530ba7332549729f6099d4c759b5a5c63","abstract_canon_sha256":"11816189c16fe6ff00c8e99ff9f2f940d15cc9931589807c7ec6b5ae7be48510"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T00:33:17.131336Z","signature_b64":"n5FyhdsqK9UWVHtWjHIM7hMAc5MdH13mF7HljH35wJaTzjDt96wD5nOSvCSXconB/jnAmPi2T9p+rhOuk+XSDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cdb5d80b3cd5002ba6929b3d781978575b87ee75529c330e4e772a605e714f43","last_reissued_at":"2026-08-04T00:33:17.129641Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T00:33:17.129641Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Evidence-Unit Fairness and the Limits of Query-Adaptive Sparse-Dense Fusion in Financial Document Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CE","authors_text":"Chenyu Wu, You Lin","submitted_at":"2026-07-31T18:06:58Z","abstract_excerpt":"Retrieval over financial filings is difficult because queries are short and acronym-heavy while the answer-bearing evidence sits inside long, table-dense documents. We study sparse-dense hybrid retrieval on FinDER, a benchmark of expert-annotated questions over corporate 10-K filings. Our first finding is methodological: if the retrieval unit is larger than the dense encoder's input window, the dense model never sees a large share of the labeled evidence, confounding comparison against a full-text sparse baseline. We measure this directly and remove it by segmenting the corpus into encoder-siz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.00183","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/2608.00183/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":"2608.00183","created_at":"2026-08-04T00:33:17.130776+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.00183v1","created_at":"2026-08-04T00:33:17.130776+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.00183","created_at":"2026-08-04T00:33:17.130776+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZW25QCZ42UAC","created_at":"2026-08-04T00:33:17.130776+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZW25QCZ42UACXJUS","created_at":"2026-08-04T00:33:17.130776+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZW25QCZ4","created_at":"2026-08-04T00:33:17.130776+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZW25QCZ42UACXJUSTM6XQGLYK5","json":"https://pith.science/pith/ZW25QCZ42UACXJUSTM6XQGLYK5.json","graph_json":"https://pith.science/api/pith-number/ZW25QCZ42UACXJUSTM6XQGLYK5/graph.json","events_json":"https://pith.science/api/pith-number/ZW25QCZ42UACXJUSTM6XQGLYK5/events.json","paper":"https://pith.science/paper/ZW25QCZ4"},"agent_actions":{"view_html":"https://pith.science/pith/ZW25QCZ42UACXJUSTM6XQGLYK5","download_json":"https://pith.science/pith/ZW25QCZ42UACXJUSTM6XQGLYK5.json","view_paper":"https://pith.science/paper/ZW25QCZ4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.00183&json=true","fetch_graph":"https://pith.science/api/pith-number/ZW25QCZ42UACXJUSTM6XQGLYK5/graph.json","fetch_events":"https://pith.science/api/pith-number/ZW25QCZ42UACXJUSTM6XQGLYK5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZW25QCZ42UACXJUSTM6XQGLYK5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZW25QCZ42UACXJUSTM6XQGLYK5/action/storage_attestation","attest_author":"https://pith.science/pith/ZW25QCZ42UACXJUSTM6XQGLYK5/action/author_attestation","sign_citation":"https://pith.science/pith/ZW25QCZ42UACXJUSTM6XQGLYK5/action/citation_signature","submit_replication":"https://pith.science/pith/ZW25QCZ42UACXJUSTM6XQGLYK5/action/replication_record"}},"created_at":"2026-08-04T00:33:17.130776+00:00","updated_at":"2026-08-04T00:33:17.130776+00:00"}