{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:2N7WNZ3BN2YESWH32IPHLQEGSF","short_pith_number":"pith:2N7WNZ3B","canonical_record":{"source":{"id":"2301.13352","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-31T01:03:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0642725f4ae5e7f5e9f2788f183a7aa207e406bf974d497043af0e057334ca54","abstract_canon_sha256":"8307874df1854bd43cd5b82bc0f9f916fa68182c3e0d83949d85ba6c44c52e30"},"schema_version":"1.0"},"canonical_sha256":"d37f66e7616eb04958fbd21e75c0869155dca9b57dac9191dc531ea1dcd6c603","source":{"kind":"arxiv","id":"2301.13352","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:2N7WNZ3BN2YESWH32IPHLQEGSF","target":"record","payload":{"canonical_record":{"source":{"id":"2301.13352","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-01-31T01:03:07Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0642725f4ae5e7f5e9f2788f183a7aa207e406bf974d497043af0e057334ca54","abstract_canon_sha256":"8307874df1854bd43cd5b82bc0f9f916fa68182c3e0d83949d85ba6c44c52e30"},"schema_version":"1.0"},"canonical_sha256":"d37f66e7616eb04958fbd21e75c0869155dca9b57dac9191dc531ea1dcd6c603","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:37:13.831418Z","signature_b64":"xOvpdFfMe//Z5dWqoBjoXXB0jwjPQRObNu5tbsMFEsXndUsNn0RUvxEfbZTWlHVWzoWSX6cTZIXciBCYqNWYDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d37f66e7616eb04958fbd21e75c0869155dca9b57dac9191dc531ea1dcd6c603","last_reissued_at":"2026-07-05T05:37:13.831005Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:37:13.831005Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2301.13352","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":"2026-07-05T05:37:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"orxFIdOL34adtGScaO8rJ7H8d7Lnwtbitihb41AkrTeOTCXbmZPuNQJqr9bBCDR0+y74K9doQDdzxyxLBK38DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T23:08:16.948851Z"},"content_sha256":"5e3bc507bbf4c20fd194d02a131f35552f38656336025492684171e59aab5a33","schema_version":"1.0","event_id":"sha256:5e3bc507bbf4c20fd194d02a131f35552f38656336025492684171e59aab5a33"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:2N7WNZ3BN2YESWH32IPHLQEGSF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sentence Identification with BOS and EOS Label Combinations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hiroshi Kanayama, Issei Yoshida, Takuma Udagawa","submitted_at":"2023-01-31T01:03:07Z","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. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2301.13352","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/2301.13352/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":"2026-07-05T05:37:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bPEoIeTqP8UzyURHu1AnZn0Zld01eZ4nf8iO6POjHN8uF8S1taWCzTcu/ouyBp9PWALwoFyxKcXBvusx+PmwBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T23:08:16.949231Z"},"content_sha256":"7dad9e7c027020db85bb5089267d8c17e103f89b6145697b7d3ff013a801dfd3","schema_version":"1.0","event_id":"sha256:7dad9e7c027020db85bb5089267d8c17e103f89b6145697b7d3ff013a801dfd3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2N7WNZ3BN2YESWH32IPHLQEGSF/bundle.json","state_url":"https://pith.science/pith/2N7WNZ3BN2YESWH32IPHLQEGSF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2N7WNZ3BN2YESWH32IPHLQEGSF/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":"2026-07-09T23:08:16Z","links":{"resolver":"https://pith.science/pith/2N7WNZ3BN2YESWH32IPHLQEGSF","bundle":"https://pith.science/pith/2N7WNZ3BN2YESWH32IPHLQEGSF/bundle.json","state":"https://pith.science/pith/2N7WNZ3BN2YESWH32IPHLQEGSF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2N7WNZ3BN2YESWH32IPHLQEGSF/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g2YEwK1i2deSCjAJPd4WEi/DIj64npcS7t/c22NLmi1POESJwr3ULhEYRs+oNLahgFvukKvxBKhAbHOnu+L/AQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T23:08:16.951162Z","bundle_sha256":"35b054bd9cd0c145d8088b452eef1ee57690f6f6ed893d38f54c6601bb285ee9"}}