{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:3RQRZZ326EOOK2IC5VMT4HQDUW","short_pith_number":"pith:3RQRZZ32","schema_version":"1.0","canonical_sha256":"dc611ce77af11ce56902ed593e1e03a595667deb640bd87590c95bce7c1cee89","source":{"kind":"arxiv","id":"2508.20778","version":2},"attestation_state":"computed","paper":{"title":"SEAL: Structure and Element Aware Learning to Improve Long Structured Document Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Xinhao Huang, Ying Zhou, Yipeng Yu, Zeyi Wen, Zhibo Ren, Zulong Chen","submitted_at":"2025-08-28T13:34:42Z","abstract_excerpt":"In long structured document retrieval, existing methods typically fine-tune pre-trained language models (PLMs) using contrastive learning on datasets lacking explicit structural information. This practice suffers from two critical issues: 1) current methods fail to leverage structural features and element-level semantics effectively, and 2) the lack of datasets containing structural metadata. To bridge these gaps, we propose \\our, a novel contrastive learning framework. It leverages structure-aware learning to preserve semantic hierarchies and masked element alignment for fine-grained semantic"},"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":"2508.20778","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-08-28T13:34:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"0813e113cc6dbd2c552c197cbb8d4bca24b7bd3f6defb4efad799058d4dfe034","abstract_canon_sha256":"295b174a4b0f0b3330e76eaa2910e39180dd8516a6f8c6fcdb9639ab32e9beae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:02:07.546252Z","signature_b64":"FKo2wZBWQyeLrPuCoRAQYwY/ckk2Uea8VTKgecSMpmtLyKCG2ll6Kdosnwk7DBK9WxBOaiRrDMEKRxIKMIPUCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"dc611ce77af11ce56902ed593e1e03a595667deb640bd87590c95bce7c1cee89","last_reissued_at":"2026-07-05T12:02:07.545670Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:02:07.545670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SEAL: Structure and Element Aware Learning to Improve Long Structured Document Retrieval","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.IR","authors_text":"Xinhao Huang, Ying Zhou, Yipeng Yu, Zeyi Wen, Zhibo Ren, Zulong Chen","submitted_at":"2025-08-28T13:34:42Z","abstract_excerpt":"In long structured document retrieval, existing methods typically fine-tune pre-trained language models (PLMs) using contrastive learning on datasets lacking explicit structural information. This practice suffers from two critical issues: 1) current methods fail to leverage structural features and element-level semantics effectively, and 2) the lack of datasets containing structural metadata. To bridge these gaps, we propose \\our, a novel contrastive learning framework. It leverages structure-aware learning to preserve semantic hierarchies and masked element alignment for fine-grained semantic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.20778","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/2508.20778/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":"2508.20778","created_at":"2026-07-05T12:02:07.545738+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.20778v2","created_at":"2026-07-05T12:02:07.545738+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.20778","created_at":"2026-07-05T12:02:07.545738+00:00"},{"alias_kind":"pith_short_12","alias_value":"3RQRZZ326EOO","created_at":"2026-07-05T12:02:07.545738+00:00"},{"alias_kind":"pith_short_16","alias_value":"3RQRZZ326EOOK2IC","created_at":"2026-07-05T12:02:07.545738+00:00"},{"alias_kind":"pith_short_8","alias_value":"3RQRZZ32","created_at":"2026-07-05T12:02:07.545738+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/3RQRZZ326EOOK2IC5VMT4HQDUW","json":"https://pith.science/pith/3RQRZZ326EOOK2IC5VMT4HQDUW.json","graph_json":"https://pith.science/api/pith-number/3RQRZZ326EOOK2IC5VMT4HQDUW/graph.json","events_json":"https://pith.science/api/pith-number/3RQRZZ326EOOK2IC5VMT4HQDUW/events.json","paper":"https://pith.science/paper/3RQRZZ32"},"agent_actions":{"view_html":"https://pith.science/pith/3RQRZZ326EOOK2IC5VMT4HQDUW","download_json":"https://pith.science/pith/3RQRZZ326EOOK2IC5VMT4HQDUW.json","view_paper":"https://pith.science/paper/3RQRZZ32","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.20778&json=true","fetch_graph":"https://pith.science/api/pith-number/3RQRZZ326EOOK2IC5VMT4HQDUW/graph.json","fetch_events":"https://pith.science/api/pith-number/3RQRZZ326EOOK2IC5VMT4HQDUW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3RQRZZ326EOOK2IC5VMT4HQDUW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3RQRZZ326EOOK2IC5VMT4HQDUW/action/storage_attestation","attest_author":"https://pith.science/pith/3RQRZZ326EOOK2IC5VMT4HQDUW/action/author_attestation","sign_citation":"https://pith.science/pith/3RQRZZ326EOOK2IC5VMT4HQDUW/action/citation_signature","submit_replication":"https://pith.science/pith/3RQRZZ326EOOK2IC5VMT4HQDUW/action/replication_record"}},"created_at":"2026-07-05T12:02:07.545738+00:00","updated_at":"2026-07-05T12:02:07.545738+00:00"}