{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:U7GQATYIPRHM5TLP7GMIBFY4LA","short_pith_number":"pith:U7GQATYI","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"},"canonical_sha256":"a7cd004f087c4ececd6ff99880971c581a64f2f8ca77f618299de545f468ffb3","source":{"kind":"arxiv","id":"2110.05071","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.05071","created_at":"2026-07-05T03:21:24Z"},{"alias_kind":"arxiv_version","alias_value":"2110.05071v1","created_at":"2026-07-05T03:21:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.05071","created_at":"2026-07-05T03:21:24Z"},{"alias_kind":"pith_short_12","alias_value":"U7GQATYIPRHM","created_at":"2026-07-05T03:21:24Z"},{"alias_kind":"pith_short_16","alias_value":"U7GQATYIPRHM5TLP","created_at":"2026-07-05T03:21:24Z"},{"alias_kind":"pith_short_8","alias_value":"U7GQATYI","created_at":"2026-07-05T03:21:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:U7GQATYIPRHM5TLP7GMIBFY4LA","target":"record","payload":{"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"},"canonical_sha256":"a7cd004f087c4ececd6ff99880971c581a64f2f8ca77f618299de545f468ffb3","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"},"source_kind":"arxiv","source_id":"2110.05071","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:21:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Cf1ZswM8iA5i/9Cf05+zUubdkd3m0xV8NG06Cwwg0d8eawr6o7BXKPgnur1rceO6TdJ20x4a2C4JRHLfzaSFBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T19:55:14.616401Z"},"content_sha256":"5dd9e3099198b57865abeb638366feb4c39f3fb48678b3370691876107eb4dc4","schema_version":"1.0","event_id":"sha256:5dd9e3099198b57865abeb638366feb4c39f3fb48678b3370691876107eb4dc4"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:U7GQATYIPRHM5TLP7GMIBFY4LA","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:21:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NqpeFsq342JsXf+t7g/SMaYcFNB3GLKg3/42ZHnFWxDUYpXM7bplhqrHbwrqXBRI0bZF8esHDwU9Bxffa5psCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T19:55:14.617782Z"},"content_sha256":"962d4f95adac91f5404be1b50bee42799ac41bd2f057d3951784ee27f6cb0540","schema_version":"1.0","event_id":"sha256:962d4f95adac91f5404be1b50bee42799ac41bd2f057d3951784ee27f6cb0540"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/U7GQATYIPRHM5TLP7GMIBFY4LA/bundle.json","state_url":"https://pith.science/pith/U7GQATYIPRHM5TLP7GMIBFY4LA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/U7GQATYIPRHM5TLP7GMIBFY4LA/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-11T19:55:14Z","links":{"resolver":"https://pith.science/pith/U7GQATYIPRHM5TLP7GMIBFY4LA","bundle":"https://pith.science/pith/U7GQATYIPRHM5TLP7GMIBFY4LA/bundle.json","state":"https://pith.science/pith/U7GQATYIPRHM5TLP7GMIBFY4LA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/U7GQATYIPRHM5TLP7GMIBFY4LA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:U7GQATYIPRHM5TLP7GMIBFY4LA","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0a669096e0fae55cb2b391868335bb6b33b51071eaf20405246aa50b5b2a1c30","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-11T08:15:31Z","title_canon_sha256":"b84c2715f24f7c14ecb9407d12093c4c8437c21e09b209a13e44abe82adc21bc"},"schema_version":"1.0","source":{"id":"2110.05071","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.05071","created_at":"2026-07-05T03:21:24Z"},{"alias_kind":"arxiv_version","alias_value":"2110.05071v1","created_at":"2026-07-05T03:21:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.05071","created_at":"2026-07-05T03:21:24Z"},{"alias_kind":"pith_short_12","alias_value":"U7GQATYIPRHM","created_at":"2026-07-05T03:21:24Z"},{"alias_kind":"pith_short_16","alias_value":"U7GQATYIPRHM5TLP","created_at":"2026-07-05T03:21:24Z"},{"alias_kind":"pith_short_8","alias_value":"U7GQATYI","created_at":"2026-07-05T03:21:24Z"}],"graph_snapshots":[{"event_id":"sha256:962d4f95adac91f5404be1b50bee42799ac41bd2f057d3951784ee27f6cb0540","target":"graph","created_at":"2026-07-05T03:21:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2110.05071/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Hanqi Jin, Renliang Sun, Xiaojun Wan","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-11T08:15:31Z","title":"Document-Level Text Simplification: Dataset, Criteria and Baseline"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.05071","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:5dd9e3099198b57865abeb638366feb4c39f3fb48678b3370691876107eb4dc4","target":"record","created_at":"2026-07-05T03:21:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0a669096e0fae55cb2b391868335bb6b33b51071eaf20405246aa50b5b2a1c30","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-11T08:15:31Z","title_canon_sha256":"b84c2715f24f7c14ecb9407d12093c4c8437c21e09b209a13e44abe82adc21bc"},"schema_version":"1.0","source":{"id":"2110.05071","kind":"arxiv","version":1}},"canonical_sha256":"a7cd004f087c4ececd6ff99880971c581a64f2f8ca77f618299de545f468ffb3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a7cd004f087c4ececd6ff99880971c581a64f2f8ca77f618299de545f468ffb3","first_computed_at":"2026-07-05T03:21:24.312035Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:21:24.312035Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"KvzU6Ii7hBxmOLgGqs1DDyC4UtQjATLCcm7oVNCXJKoIgQ6RnQMH6q9yxqPrziKI99AwHb/mLLQKbo8YzFYDCA==","signature_status":"signed_v1","signed_at":"2026-07-05T03:21:24.312453Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.05071","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5dd9e3099198b57865abeb638366feb4c39f3fb48678b3370691876107eb4dc4","sha256:962d4f95adac91f5404be1b50bee42799ac41bd2f057d3951784ee27f6cb0540"],"state_sha256":"721916ea76d3ca8c041059dad3071c153ae7d9abe8e04fb947a5524b41aafb36"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y5VCGloqWcWZkF1/HDdTujST6PsJCRwOThwi4Ma6ByfTqCzYTYyvEkGVA0/bfyurV7WAish3JtLL/3W5FZk7DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T19:55:14.625229Z","bundle_sha256":"2b2ba2e9958e64c982fbcba8a5535e8d48faf84f16a51a6d5e21ae9366b2d5c9"}}