{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:YLOIW6RO3PT7EC4SFE6VQXHIIQ","short_pith_number":"pith:YLOIW6RO","schema_version":"1.0","canonical_sha256":"c2dc8b7a2edbe7f20b92293d585ce84425d856d8a567a5971a1a6f35b6d2d1de","source":{"kind":"arxiv","id":"1910.14142","version":2},"attestation_state":"computed","paper":{"title":"Discourse-Aware Neural Extractive Text Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiacheng Xu, Jingjing Liu, Yu Cheng, Zhe Gan","submitted_at":"2019-10-30T21:17:26Z","abstract_excerpt":"Recently BERT has been adopted for document encoding in state-of-the-art text summarization models. However, sentence-based extractive models often result in redundant or uninformative phrases in the extracted summaries. Also, long-range dependencies throughout a document are not well captured by BERT, which is pre-trained on sentence pairs instead of documents. To address these issues, we present a discourse-aware neural summarization model - DiscoBert. DiscoBert extracts sub-sentential discourse units (instead of sentences) as candidates for extractive selection on a finer granularity. To ca"},"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":"1910.14142","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-10-30T21:17:26Z","cross_cats_sorted":[],"title_canon_sha256":"27584f3ece3ab5c275db76c5404d846240134f0b99ad48d440d08cce5986c9c3","abstract_canon_sha256":"7fe6addf94710b865256599c9f7921e0a638affee33be874d99967e41039d40e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:58:05.683112Z","signature_b64":"KMTGFagqEaoauDX45t2P+Z8vTkKyyADsmgkKOqW71nE/GwRu0WCpdenrhYslakxQrRqeVPCZ4JBfv2zC3nNOCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c2dc8b7a2edbe7f20b92293d585ce84425d856d8a567a5971a1a6f35b6d2d1de","last_reissued_at":"2026-07-05T00:58:05.682754Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:58:05.682754Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Discourse-Aware Neural Extractive Text Summarization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jiacheng Xu, Jingjing Liu, Yu Cheng, Zhe Gan","submitted_at":"2019-10-30T21:17:26Z","abstract_excerpt":"Recently BERT has been adopted for document encoding in state-of-the-art text summarization models. However, sentence-based extractive models often result in redundant or uninformative phrases in the extracted summaries. Also, long-range dependencies throughout a document are not well captured by BERT, which is pre-trained on sentence pairs instead of documents. To address these issues, we present a discourse-aware neural summarization model - DiscoBert. DiscoBert extracts sub-sentential discourse units (instead of sentences) as candidates for extractive selection on a finer granularity. To ca"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.14142","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/1910.14142/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":"1910.14142","created_at":"2026-07-05T00:58:05.682810+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.14142v2","created_at":"2026-07-05T00:58:05.682810+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.14142","created_at":"2026-07-05T00:58:05.682810+00:00"},{"alias_kind":"pith_short_12","alias_value":"YLOIW6RO3PT7","created_at":"2026-07-05T00:58:05.682810+00:00"},{"alias_kind":"pith_short_16","alias_value":"YLOIW6RO3PT7EC4S","created_at":"2026-07-05T00:58:05.682810+00:00"},{"alias_kind":"pith_short_8","alias_value":"YLOIW6RO","created_at":"2026-07-05T00:58:05.682810+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.15190","citing_title":"SemToken: Semantic-Aware Tokenization for Efficient Long-Context Language Modeling","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YLOIW6RO3PT7EC4SFE6VQXHIIQ","json":"https://pith.science/pith/YLOIW6RO3PT7EC4SFE6VQXHIIQ.json","graph_json":"https://pith.science/api/pith-number/YLOIW6RO3PT7EC4SFE6VQXHIIQ/graph.json","events_json":"https://pith.science/api/pith-number/YLOIW6RO3PT7EC4SFE6VQXHIIQ/events.json","paper":"https://pith.science/paper/YLOIW6RO"},"agent_actions":{"view_html":"https://pith.science/pith/YLOIW6RO3PT7EC4SFE6VQXHIIQ","download_json":"https://pith.science/pith/YLOIW6RO3PT7EC4SFE6VQXHIIQ.json","view_paper":"https://pith.science/paper/YLOIW6RO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.14142&json=true","fetch_graph":"https://pith.science/api/pith-number/YLOIW6RO3PT7EC4SFE6VQXHIIQ/graph.json","fetch_events":"https://pith.science/api/pith-number/YLOIW6RO3PT7EC4SFE6VQXHIIQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YLOIW6RO3PT7EC4SFE6VQXHIIQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YLOIW6RO3PT7EC4SFE6VQXHIIQ/action/storage_attestation","attest_author":"https://pith.science/pith/YLOIW6RO3PT7EC4SFE6VQXHIIQ/action/author_attestation","sign_citation":"https://pith.science/pith/YLOIW6RO3PT7EC4SFE6VQXHIIQ/action/citation_signature","submit_replication":"https://pith.science/pith/YLOIW6RO3PT7EC4SFE6VQXHIIQ/action/replication_record"}},"created_at":"2026-07-05T00:58:05.682810+00:00","updated_at":"2026-07-05T00:58:05.682810+00:00"}