{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:2CBBZWIIAPMUW774TT22Q65VCM","short_pith_number":"pith:2CBBZWII","canonical_record":{"source":{"id":"2005.02324","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-05T16:47:51Z","cross_cats_sorted":[],"title_canon_sha256":"d9f71faccb817bdd567d6ab704280aaffe867685f5d892b7dfdb8bf59151321b","abstract_canon_sha256":"486c2adf0039348e28fce2a49ce2eb39f659e24d3c736e8767fdd5f68140a5de"},"schema_version":"1.0"},"canonical_sha256":"d0821cd90803d94b7ffc9cf5a87bb5130e5023353f3ec7570909417e97c5ce45","source":{"kind":"arxiv","id":"2005.02324","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.02324","created_at":"2026-07-05T03:09:55Z"},{"alias_kind":"arxiv_version","alias_value":"2005.02324v4","created_at":"2026-07-05T03:09:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.02324","created_at":"2026-07-05T03:09:55Z"},{"alias_kind":"pith_short_12","alias_value":"2CBBZWIIAPMU","created_at":"2026-07-05T03:09:55Z"},{"alias_kind":"pith_short_16","alias_value":"2CBBZWIIAPMUW774","created_at":"2026-07-05T03:09:55Z"},{"alias_kind":"pith_short_8","alias_value":"2CBBZWII","created_at":"2026-07-05T03:09:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:2CBBZWIIAPMUW774TT22Q65VCM","target":"record","payload":{"canonical_record":{"source":{"id":"2005.02324","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-05T16:47:51Z","cross_cats_sorted":[],"title_canon_sha256":"d9f71faccb817bdd567d6ab704280aaffe867685f5d892b7dfdb8bf59151321b","abstract_canon_sha256":"486c2adf0039348e28fce2a49ce2eb39f659e24d3c736e8767fdd5f68140a5de"},"schema_version":"1.0"},"canonical_sha256":"d0821cd90803d94b7ffc9cf5a87bb5130e5023353f3ec7570909417e97c5ce45","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:09:55.473760Z","signature_b64":"hObsfn04wPPexov7KhNXQHnAm4zCUGs5WGpQe/a54UxJ8EsjTxVmrjVoflXICMfxr0oILv+xfqSE8k6vKwFDDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0821cd90803d94b7ffc9cf5a87bb5130e5023353f3ec7570909417e97c5ce45","last_reissued_at":"2026-07-05T03:09:55.473341Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:09:55.473341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2005.02324","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:09:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mBaWFp0X+NxwhYs7lmIVQvbrgyDn1L/y3JM9R127M8SwE7FOPbGiGVLOy00mb1SyFDEp5W5IpsEUVZWELYlwAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:35:27.638806Z"},"content_sha256":"c5e34a74669f2c294ebdfc7d3cd918a99d3e611e730b4e35d3ba9319a238ccd1","schema_version":"1.0","event_id":"sha256:c5e34a74669f2c294ebdfc7d3cd918a99d3e611e730b4e35d3ba9319a238ccd1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:2CBBZWIIAPMUW774TT22Q65VCM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Neural CRF Model for Sentence Alignment in Text Simplification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chao Jiang, Mounica Maddela, Wei Xu, Wuwei Lan, Yang Zhong","submitted_at":"2020-05-05T16:47:51Z","abstract_excerpt":"The success of a text simplification system heavily depends on the quality and quantity of complex-simple sentence pairs in the training corpus, which are extracted by aligning sentences between parallel articles. To evaluate and improve sentence alignment quality, we create two manually annotated sentence-aligned datasets from two commonly used text simplification corpora, Newsela and Wikipedia. We propose a novel neural CRF alignment model which not only leverages the sequential nature of sentences in parallel documents but also utilizes a neural sentence pair model to capture semantic simil"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.02324","kind":"arxiv","version":4},"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/2005.02324/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":"2026-07-05T03:09:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lX8YLhd1Cd1DDKk84Tg6aPunoSKhX/YNzmZ2V+AxpNjBy/feoQ/0cFwXjYwTerR4QD1nZYG5TqeyUfHMYzl6DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T22:35:27.639369Z"},"content_sha256":"8a9d544d74eaa376d2c2b443ec91270d978d58b0660adfa37afc5183c0f7b261","schema_version":"1.0","event_id":"sha256:8a9d544d74eaa376d2c2b443ec91270d978d58b0660adfa37afc5183c0f7b261"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2CBBZWIIAPMUW774TT22Q65VCM/bundle.json","state_url":"https://pith.science/pith/2CBBZWIIAPMUW774TT22Q65VCM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2CBBZWIIAPMUW774TT22Q65VCM/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":"2026-08-09T22:35:27Z","links":{"resolver":"https://pith.science/pith/2CBBZWIIAPMUW774TT22Q65VCM","bundle":"https://pith.science/pith/2CBBZWIIAPMUW774TT22Q65VCM/bundle.json","state":"https://pith.science/pith/2CBBZWIIAPMUW774TT22Q65VCM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2CBBZWIIAPMUW774TT22Q65VCM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:2CBBZWIIAPMUW774TT22Q65VCM","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":"486c2adf0039348e28fce2a49ce2eb39f659e24d3c736e8767fdd5f68140a5de","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-05T16:47:51Z","title_canon_sha256":"d9f71faccb817bdd567d6ab704280aaffe867685f5d892b7dfdb8bf59151321b"},"schema_version":"1.0","source":{"id":"2005.02324","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.02324","created_at":"2026-07-05T03:09:55Z"},{"alias_kind":"arxiv_version","alias_value":"2005.02324v4","created_at":"2026-07-05T03:09:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.02324","created_at":"2026-07-05T03:09:55Z"},{"alias_kind":"pith_short_12","alias_value":"2CBBZWIIAPMU","created_at":"2026-07-05T03:09:55Z"},{"alias_kind":"pith_short_16","alias_value":"2CBBZWIIAPMUW774","created_at":"2026-07-05T03:09:55Z"},{"alias_kind":"pith_short_8","alias_value":"2CBBZWII","created_at":"2026-07-05T03:09:55Z"}],"graph_snapshots":[{"event_id":"sha256:8a9d544d74eaa376d2c2b443ec91270d978d58b0660adfa37afc5183c0f7b261","target":"graph","created_at":"2026-07-05T03:09:55Z","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/2005.02324/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The success of a text simplification system heavily depends on the quality and quantity of complex-simple sentence pairs in the training corpus, which are extracted by aligning sentences between parallel articles. To evaluate and improve sentence alignment quality, we create two manually annotated sentence-aligned datasets from two commonly used text simplification corpora, Newsela and Wikipedia. We propose a novel neural CRF alignment model which not only leverages the sequential nature of sentences in parallel documents but also utilizes a neural sentence pair model to capture semantic simil","authors_text":"Chao Jiang, Mounica Maddela, Wei Xu, Wuwei Lan, Yang Zhong","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-05T16:47:51Z","title":"Neural CRF Model for Sentence Alignment in Text Simplification"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.02324","kind":"arxiv","version":4},"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:c5e34a74669f2c294ebdfc7d3cd918a99d3e611e730b4e35d3ba9319a238ccd1","target":"record","created_at":"2026-07-05T03:09:55Z","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":"486c2adf0039348e28fce2a49ce2eb39f659e24d3c736e8767fdd5f68140a5de","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-05T16:47:51Z","title_canon_sha256":"d9f71faccb817bdd567d6ab704280aaffe867685f5d892b7dfdb8bf59151321b"},"schema_version":"1.0","source":{"id":"2005.02324","kind":"arxiv","version":4}},"canonical_sha256":"d0821cd90803d94b7ffc9cf5a87bb5130e5023353f3ec7570909417e97c5ce45","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d0821cd90803d94b7ffc9cf5a87bb5130e5023353f3ec7570909417e97c5ce45","first_computed_at":"2026-07-05T03:09:55.473341Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:09:55.473341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hObsfn04wPPexov7KhNXQHnAm4zCUGs5WGpQe/a54UxJ8EsjTxVmrjVoflXICMfxr0oILv+xfqSE8k6vKwFDDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:09:55.473760Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.02324","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c5e34a74669f2c294ebdfc7d3cd918a99d3e611e730b4e35d3ba9319a238ccd1","sha256:8a9d544d74eaa376d2c2b443ec91270d978d58b0660adfa37afc5183c0f7b261"],"state_sha256":"10e7cb1f132b84ddb52e482a6f33e8ca613caf5f17017c5a7c0db12a36ddbbd4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lEBAws7jLSENgruPo1OxLcp2V919lWRArxthaYKSnwedWyHXlkUcgx0vn0Nde7Wu8FEiEZnDwDqqqyNa0fALDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T22:35:27.643625Z","bundle_sha256":"e2147330585602c038ba568bf272cf84664e8a3428c27270bbe29d2122600e2a"}}