{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YGFCTXEBUQ4K5PYNOPMJLZTBBM","short_pith_number":"pith:YGFCTXEB","schema_version":"1.0","canonical_sha256":"c18a29dc81a438aebf0d73d895e6610b1d7da057899a40c211acf913a3cc19d5","source":{"kind":"arxiv","id":"2503.23671","version":2},"attestation_state":"computed","paper":{"title":"CrossFormer: Cross-Segment Semantic Fusion for Document Segmentation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Junru Zhou, Qingcai Chen, Tongke Ni, Xiangping Wu, Yang Fan","submitted_at":"2025-03-31T02:27:49Z","abstract_excerpt":"Text semantic segmentation involves partitioning a document into multiple paragraphs with continuous semantics based on the subject matter, contextual information, and document structure. Traditional approaches have typically relied on preprocessing documents into segments to address input length constraints, resulting in the loss of critical semantic information across segments. To address this, we present CrossFormer, a transformer-based model featuring a novel cross-segment fusion module that dynamically models latent semantic dependencies across document segments, substantially elevating s"},"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":"2503.23671","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2025-03-31T02:27:49Z","cross_cats_sorted":[],"title_canon_sha256":"9eb946c959e92cccc37e606566d7fe6d6f166ab3c53d703769292b27ada6b37e","abstract_canon_sha256":"6965e4fb502c0c42bdb1c218c596ad500670d15db264cffafe4c3364d6d28546"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:43:07.293647Z","signature_b64":"lfVbKEdAWCl5dZ5M/+ie8CcU0GueUveFsMUtYb0cHn3/Sa26/Cu8hhYBUhwAW/NcxAQGP0IeflVqAKHnmJgrAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c18a29dc81a438aebf0d73d895e6610b1d7da057899a40c211acf913a3cc19d5","last_reissued_at":"2026-07-05T10:43:07.293142Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:43:07.293142Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CrossFormer: Cross-Segment Semantic Fusion for Document Segmentation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Junru Zhou, Qingcai Chen, Tongke Ni, Xiangping Wu, Yang Fan","submitted_at":"2025-03-31T02:27:49Z","abstract_excerpt":"Text semantic segmentation involves partitioning a document into multiple paragraphs with continuous semantics based on the subject matter, contextual information, and document structure. Traditional approaches have typically relied on preprocessing documents into segments to address input length constraints, resulting in the loss of critical semantic information across segments. To address this, we present CrossFormer, a transformer-based model featuring a novel cross-segment fusion module that dynamically models latent semantic dependencies across document segments, substantially elevating s"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.23671","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/2503.23671/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":"2503.23671","created_at":"2026-07-05T10:43:07.293200+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.23671v2","created_at":"2026-07-05T10:43:07.293200+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.23671","created_at":"2026-07-05T10:43:07.293200+00:00"},{"alias_kind":"pith_short_12","alias_value":"YGFCTXEBUQ4K","created_at":"2026-07-05T10:43:07.293200+00:00"},{"alias_kind":"pith_short_16","alias_value":"YGFCTXEBUQ4K5PYN","created_at":"2026-07-05T10:43:07.293200+00:00"},{"alias_kind":"pith_short_8","alias_value":"YGFCTXEB","created_at":"2026-07-05T10:43:07.293200+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.00449","citing_title":"GOSU: Retrieval-Augmented Generation with Global-Level Optimized Semantic Unit-Centric Framework","ref_index":45,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YGFCTXEBUQ4K5PYNOPMJLZTBBM","json":"https://pith.science/pith/YGFCTXEBUQ4K5PYNOPMJLZTBBM.json","graph_json":"https://pith.science/api/pith-number/YGFCTXEBUQ4K5PYNOPMJLZTBBM/graph.json","events_json":"https://pith.science/api/pith-number/YGFCTXEBUQ4K5PYNOPMJLZTBBM/events.json","paper":"https://pith.science/paper/YGFCTXEB"},"agent_actions":{"view_html":"https://pith.science/pith/YGFCTXEBUQ4K5PYNOPMJLZTBBM","download_json":"https://pith.science/pith/YGFCTXEBUQ4K5PYNOPMJLZTBBM.json","view_paper":"https://pith.science/paper/YGFCTXEB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.23671&json=true","fetch_graph":"https://pith.science/api/pith-number/YGFCTXEBUQ4K5PYNOPMJLZTBBM/graph.json","fetch_events":"https://pith.science/api/pith-number/YGFCTXEBUQ4K5PYNOPMJLZTBBM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YGFCTXEBUQ4K5PYNOPMJLZTBBM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YGFCTXEBUQ4K5PYNOPMJLZTBBM/action/storage_attestation","attest_author":"https://pith.science/pith/YGFCTXEBUQ4K5PYNOPMJLZTBBM/action/author_attestation","sign_citation":"https://pith.science/pith/YGFCTXEBUQ4K5PYNOPMJLZTBBM/action/citation_signature","submit_replication":"https://pith.science/pith/YGFCTXEBUQ4K5PYNOPMJLZTBBM/action/replication_record"}},"created_at":"2026-07-05T10:43:07.293200+00:00","updated_at":"2026-07-05T10:43:07.293200+00:00"}