{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:H3PRPCNSYJORLJZOYGHNUFRQVJ","short_pith_number":"pith:H3PRPCNS","schema_version":"1.0","canonical_sha256":"3edf1789b2c25d15a72ec18eda1630aa5a8c66d76556d9492bff18c34dd828f1","source":{"kind":"arxiv","id":"2412.08196","version":1},"attestation_state":"computed","paper":{"title":"DocSum: Domain-Adaptive Pre-training for Document Abstractive Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Antoine Doucet, Phan Phuong Mai Chau, Souhail Bakkali","submitted_at":"2024-12-11T08:36:50Z","abstract_excerpt":"Abstractive summarization has made significant strides in condensing and rephrasing large volumes of text into coherent summaries. However, summarizing administrative documents presents unique challenges due to domain-specific terminology, OCR-generated errors, and the scarcity of annotated datasets for model fine-tuning. Existing models often struggle to adapt to the intricate structure and specialized content of such documents. To address these limitations, we introduce DocSum, a domain-adaptive abstractive summarization framework tailored for administrative documents. Leveraging pre-trainin"},"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":"2412.08196","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-11T08:36:50Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"c799a95ca056ba210851aa841411e2a8e1aa9b7c17f477f304dc7ac5f1c0990e","abstract_canon_sha256":"ddf17f687f2f11be9338db3f86301c362265eed798f9ff54da2c0d7e911b52d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:45.876197Z","signature_b64":"bKm8ehUeA+uGRdAJwIUZEXZn7J1Q8xQDVWFCLa7/a2HjMFMWguB3cOV4GiaZV1ockd4FFuI/B4T8msy42F4SBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3edf1789b2c25d15a72ec18eda1630aa5a8c66d76556d9492bff18c34dd828f1","last_reissued_at":"2026-07-05T09:47:45.875785Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:45.875785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DocSum: Domain-Adaptive Pre-training for Document Abstractive Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Antoine Doucet, Phan Phuong Mai Chau, Souhail Bakkali","submitted_at":"2024-12-11T08:36:50Z","abstract_excerpt":"Abstractive summarization has made significant strides in condensing and rephrasing large volumes of text into coherent summaries. However, summarizing administrative documents presents unique challenges due to domain-specific terminology, OCR-generated errors, and the scarcity of annotated datasets for model fine-tuning. Existing models often struggle to adapt to the intricate structure and specialized content of such documents. To address these limitations, we introduce DocSum, a domain-adaptive abstractive summarization framework tailored for administrative documents. Leveraging pre-trainin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08196","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/2412.08196/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":"2412.08196","created_at":"2026-07-05T09:47:45.875845+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.08196v1","created_at":"2026-07-05T09:47:45.875845+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08196","created_at":"2026-07-05T09:47:45.875845+00:00"},{"alias_kind":"pith_short_12","alias_value":"H3PRPCNSYJOR","created_at":"2026-07-05T09:47:45.875845+00:00"},{"alias_kind":"pith_short_16","alias_value":"H3PRPCNSYJORLJZO","created_at":"2026-07-05T09:47:45.875845+00:00"},{"alias_kind":"pith_short_8","alias_value":"H3PRPCNS","created_at":"2026-07-05T09:47:45.875845+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/H3PRPCNSYJORLJZOYGHNUFRQVJ","json":"https://pith.science/pith/H3PRPCNSYJORLJZOYGHNUFRQVJ.json","graph_json":"https://pith.science/api/pith-number/H3PRPCNSYJORLJZOYGHNUFRQVJ/graph.json","events_json":"https://pith.science/api/pith-number/H3PRPCNSYJORLJZOYGHNUFRQVJ/events.json","paper":"https://pith.science/paper/H3PRPCNS"},"agent_actions":{"view_html":"https://pith.science/pith/H3PRPCNSYJORLJZOYGHNUFRQVJ","download_json":"https://pith.science/pith/H3PRPCNSYJORLJZOYGHNUFRQVJ.json","view_paper":"https://pith.science/paper/H3PRPCNS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.08196&json=true","fetch_graph":"https://pith.science/api/pith-number/H3PRPCNSYJORLJZOYGHNUFRQVJ/graph.json","fetch_events":"https://pith.science/api/pith-number/H3PRPCNSYJORLJZOYGHNUFRQVJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H3PRPCNSYJORLJZOYGHNUFRQVJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H3PRPCNSYJORLJZOYGHNUFRQVJ/action/storage_attestation","attest_author":"https://pith.science/pith/H3PRPCNSYJORLJZOYGHNUFRQVJ/action/author_attestation","sign_citation":"https://pith.science/pith/H3PRPCNSYJORLJZOYGHNUFRQVJ/action/citation_signature","submit_replication":"https://pith.science/pith/H3PRPCNSYJORLJZOYGHNUFRQVJ/action/replication_record"}},"created_at":"2026-07-05T09:47:45.875845+00:00","updated_at":"2026-07-05T09:47:45.875845+00:00"}