{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:2N7WNZ3BN2YESWH32IPHLQEGSF","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":"8307874df1854bd43cd5b82bc0f9f916fa68182c3e0d83949d85ba6c44c52e30","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-31T01:03:07Z","title_canon_sha256":"0642725f4ae5e7f5e9f2788f183a7aa207e406bf974d497043af0e057334ca54"},"schema_version":"1.0","source":{"id":"2301.13352","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2301.13352","created_at":"2026-07-05T05:37:13Z"},{"alias_kind":"arxiv_version","alias_value":"2301.13352v1","created_at":"2026-07-05T05:37:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2301.13352","created_at":"2026-07-05T05:37:13Z"},{"alias_kind":"pith_short_12","alias_value":"2N7WNZ3BN2YE","created_at":"2026-07-05T05:37:13Z"},{"alias_kind":"pith_short_16","alias_value":"2N7WNZ3BN2YESWH3","created_at":"2026-07-05T05:37:13Z"},{"alias_kind":"pith_short_8","alias_value":"2N7WNZ3B","created_at":"2026-07-05T05:37:13Z"}],"graph_snapshots":[{"event_id":"sha256:7dad9e7c027020db85bb5089267d8c17e103f89b6145697b7d3ff013a801dfd3","target":"graph","created_at":"2026-07-05T05:37:13Z","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/2301.13352/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The sentence is a fundamental unit in many NLP applications. Sentence segmentation is widely used as the first preprocessing task, where an input text is split into consecutive sentences considering the end of the sentence (EOS) as their boundaries. This task formulation relies on a strong assumption that the input text consists only of sentences, or what we call the sentential units (SUs). However, real-world texts often contain non-sentential units (NSUs) such as metadata, sentence fragments, nonlinguistic markers, etc. which are unreasonable or undesirable to be treated as a part of an SU. ","authors_text":"Hiroshi Kanayama, Issei Yoshida, Takuma Udagawa","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-31T01:03:07Z","title":"Sentence Identification with BOS and EOS Label Combinations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.13352","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":"sha256:5e3bc507bbf4c20fd194d02a131f35552f38656336025492684171e59aab5a33","target":"record","created_at":"2026-07-05T05:37:13Z","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":"8307874df1854bd43cd5b82bc0f9f916fa68182c3e0d83949d85ba6c44c52e30","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-31T01:03:07Z","title_canon_sha256":"0642725f4ae5e7f5e9f2788f183a7aa207e406bf974d497043af0e057334ca54"},"schema_version":"1.0","source":{"id":"2301.13352","kind":"arxiv","version":1}},"canonical_sha256":"d37f66e7616eb04958fbd21e75c0869155dca9b57dac9191dc531ea1dcd6c603","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d37f66e7616eb04958fbd21e75c0869155dca9b57dac9191dc531ea1dcd6c603","first_computed_at":"2026-07-05T05:37:13.831005Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:37:13.831005Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xOvpdFfMe//Z5dWqoBjoXXB0jwjPQRObNu5tbsMFEsXndUsNn0RUvxEfbZTWlHVWzoWSX6cTZIXciBCYqNWYDA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:37:13.831418Z","signed_message":"canonical_sha256_bytes"},"source_id":"2301.13352","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5e3bc507bbf4c20fd194d02a131f35552f38656336025492684171e59aab5a33","sha256:7dad9e7c027020db85bb5089267d8c17e103f89b6145697b7d3ff013a801dfd3"],"state_sha256":"f3189703d377930d10692adfc23005fdab5c6689a5e9432709267e00b68ed1ae"}