{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:U7GQATYIPRHM5TLP7GMIBFY4LA","short_pith_number":"pith:U7GQATYI","schema_version":"1.0","canonical_sha256":"a7cd004f087c4ececd6ff99880971c581a64f2f8ca77f618299de545f468ffb3","source":{"kind":"arxiv","id":"2110.05071","version":1},"attestation_state":"computed","paper":{"title":"Document-Level Text Simplification: Dataset, Criteria and Baseline","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hanqi Jin, Renliang Sun, Xiaojun Wan","submitted_at":"2021-10-11T08:15:31Z","abstract_excerpt":"Text simplification is a valuable technique. However, current research is limited to sentence simplification. In this paper, we define and investigate a new task of document-level text simplification, which aims to simplify a document consisting of multiple sentences. Based on Wikipedia dumps, we first construct a large-scale dataset named D-Wikipedia and perform analysis and human evaluation on it to show that the dataset is reliable. Then, we propose a new automatic evaluation metric called D-SARI that is more suitable for the document-level simplification task. Finally, we select several re"},"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":"2110.05071","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-11T08:15:31Z","cross_cats_sorted":[],"title_canon_sha256":"b84c2715f24f7c14ecb9407d12093c4c8437c21e09b209a13e44abe82adc21bc","abstract_canon_sha256":"0a669096e0fae55cb2b391868335bb6b33b51071eaf20405246aa50b5b2a1c30"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:21:24.312453Z","signature_b64":"KvzU6Ii7hBxmOLgGqs1DDyC4UtQjATLCcm7oVNCXJKoIgQ6RnQMH6q9yxqPrziKI99AwHb/mLLQKbo8YzFYDCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7cd004f087c4ececd6ff99880971c581a64f2f8ca77f618299de545f468ffb3","last_reissued_at":"2026-07-05T03:21:24.312035Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:21:24.312035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Document-Level Text Simplification: Dataset, Criteria and Baseline","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hanqi Jin, Renliang Sun, Xiaojun Wan","submitted_at":"2021-10-11T08:15:31Z","abstract_excerpt":"Text simplification is a valuable technique. However, current research is limited to sentence simplification. In this paper, we define and investigate a new task of document-level text simplification, which aims to simplify a document consisting of multiple sentences. Based on Wikipedia dumps, we first construct a large-scale dataset named D-Wikipedia and perform analysis and human evaluation on it to show that the dataset is reliable. Then, we propose a new automatic evaluation metric called D-SARI that is more suitable for the document-level simplification task. Finally, we select several re"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.05071","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/2110.05071/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":"2110.05071","created_at":"2026-07-05T03:21:24.312093+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.05071v1","created_at":"2026-07-05T03:21:24.312093+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.05071","created_at":"2026-07-05T03:21:24.312093+00:00"},{"alias_kind":"pith_short_12","alias_value":"U7GQATYIPRHM","created_at":"2026-07-05T03:21:24.312093+00:00"},{"alias_kind":"pith_short_16","alias_value":"U7GQATYIPRHM5TLP","created_at":"2026-07-05T03:21:24.312093+00:00"},{"alias_kind":"pith_short_8","alias_value":"U7GQATYI","created_at":"2026-07-05T03:21:24.312093+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.03857","citing_title":"Progressive Document-level Text Simplification via Large Language Models","ref_index":36,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/U7GQATYIPRHM5TLP7GMIBFY4LA","json":"https://pith.science/pith/U7GQATYIPRHM5TLP7GMIBFY4LA.json","graph_json":"https://pith.science/api/pith-number/U7GQATYIPRHM5TLP7GMIBFY4LA/graph.json","events_json":"https://pith.science/api/pith-number/U7GQATYIPRHM5TLP7GMIBFY4LA/events.json","paper":"https://pith.science/paper/U7GQATYI"},"agent_actions":{"view_html":"https://pith.science/pith/U7GQATYIPRHM5TLP7GMIBFY4LA","download_json":"https://pith.science/pith/U7GQATYIPRHM5TLP7GMIBFY4LA.json","view_paper":"https://pith.science/paper/U7GQATYI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.05071&json=true","fetch_graph":"https://pith.science/api/pith-number/U7GQATYIPRHM5TLP7GMIBFY4LA/graph.json","fetch_events":"https://pith.science/api/pith-number/U7GQATYIPRHM5TLP7GMIBFY4LA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U7GQATYIPRHM5TLP7GMIBFY4LA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U7GQATYIPRHM5TLP7GMIBFY4LA/action/storage_attestation","attest_author":"https://pith.science/pith/U7GQATYIPRHM5TLP7GMIBFY4LA/action/author_attestation","sign_citation":"https://pith.science/pith/U7GQATYIPRHM5TLP7GMIBFY4LA/action/citation_signature","submit_replication":"https://pith.science/pith/U7GQATYIPRHM5TLP7GMIBFY4LA/action/replication_record"}},"created_at":"2026-07-05T03:21:24.312093+00:00","updated_at":"2026-07-05T03:21:24.312093+00:00"}