{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:XNYX6DAZ4R2IJ7Q2ZSURVELDFG","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":"086fe5f04b20e9f03a0a0d0e4b8a8f5d78ebdbae2c4bed7e79aa8054201ed552","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-12-13T12:03:39Z","title_canon_sha256":"f97f2f27c2c0428883e05d66444010f378a2b2e669132f341a74b6ed87cecc4b"},"schema_version":"1.0","source":{"id":"1612.04113","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1612.04113","created_at":"2026-05-18T00:55:05Z"},{"alias_kind":"arxiv_version","alias_value":"1612.04113v1","created_at":"2026-05-18T00:55:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1612.04113","created_at":"2026-05-18T00:55:05Z"},{"alias_kind":"pith_short_12","alias_value":"XNYX6DAZ4R2I","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_16","alias_value":"XNYX6DAZ4R2IJ7Q2","created_at":"2026-05-18T12:30:51Z"},{"alias_kind":"pith_short_8","alias_value":"XNYX6DAZ","created_at":"2026-05-18T12:30:51Z"}],"graph_snapshots":[{"event_id":"sha256:c0cd0545238975747b91a31163416193edc71105e6d102791ae91d1db2dc35aa","target":"graph","created_at":"2026-05-18T00:55:05Z","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"},"paper":{"abstract_excerpt":"Parallel corpora have driven great progress in the field of Text Simplification. However, most sentence alignment algorithms either offer a limited range of alignment types supported, or simply ignore valuable clues present in comparable documents. We address this problem by introducing a new set of flexible vicinity-driven paragraph and sentence alignment algorithms that 1-N, N-1, N-N and long distance null alignments without the need for hard-to-replicate supervised models.","authors_text":"Gustavo Henrique Paetzold, Lucia Specia","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-12-13T12:03:39Z","title":"Vicinity-Driven Paragraph and Sentence Alignment for Comparable Corpora"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1612.04113","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":"sha256:008706eb5a949bf5973c1be09a196677f02c8fd52e761661a9f99b5163aae4b1","target":"record","created_at":"2026-05-18T00:55:05Z","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":"086fe5f04b20e9f03a0a0d0e4b8a8f5d78ebdbae2c4bed7e79aa8054201ed552","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-12-13T12:03:39Z","title_canon_sha256":"f97f2f27c2c0428883e05d66444010f378a2b2e669132f341a74b6ed87cecc4b"},"schema_version":"1.0","source":{"id":"1612.04113","kind":"arxiv","version":1}},"canonical_sha256":"bb717f0c19e47484fe1acca91a916329839cde176d16c7656799e941813ff5f9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bb717f0c19e47484fe1acca91a916329839cde176d16c7656799e941813ff5f9","first_computed_at":"2026-05-18T00:55:05.503126Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:55:05.503126Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5sBJCybxknWSBKz7LMM0wfVforF2BO03XzPE7nVuvr9DKsPhKTs743HdWLPK2m7KtrQNBu6T3XIx288lybqdBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:55:05.503803Z","signed_message":"canonical_sha256_bytes"},"source_id":"1612.04113","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:008706eb5a949bf5973c1be09a196677f02c8fd52e761661a9f99b5163aae4b1","sha256:c0cd0545238975747b91a31163416193edc71105e6d102791ae91d1db2dc35aa"],"state_sha256":"066cc5d6f241509d176216462ed4fb8db23a475923b24e8881d99ccd9a63c4fc"}