{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:5Q473OV3JD535KU6T4P3VAK27Q","short_pith_number":"pith:5Q473OV3","canonical_record":{"source":{"id":"2305.18893","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-30T09:49:42Z","cross_cats_sorted":[],"title_canon_sha256":"7397744d78b8c8965b1a7d0b5108c3a54f59b0f9bec948c7579a34a653cd4154","abstract_canon_sha256":"daefdef9acee8c292f5042e0b1bc68ec16dc94eff8ea0bdbe3adfee85e56a7c5"},"schema_version":"1.0"},"canonical_sha256":"ec39fdbabb48fbbeaa9e9f1fba815afc17d27ccf3bb2dbbac0a9a3648971d563","source":{"kind":"arxiv","id":"2305.18893","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.18893","created_at":"2026-07-05T06:15:34Z"},{"alias_kind":"arxiv_version","alias_value":"2305.18893v1","created_at":"2026-07-05T06:15:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18893","created_at":"2026-07-05T06:15:34Z"},{"alias_kind":"pith_short_12","alias_value":"5Q473OV3JD53","created_at":"2026-07-05T06:15:34Z"},{"alias_kind":"pith_short_16","alias_value":"5Q473OV3JD535KU6","created_at":"2026-07-05T06:15:34Z"},{"alias_kind":"pith_short_8","alias_value":"5Q473OV3","created_at":"2026-07-05T06:15:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:5Q473OV3JD535KU6T4P3VAK27Q","target":"record","payload":{"canonical_record":{"source":{"id":"2305.18893","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-30T09:49:42Z","cross_cats_sorted":[],"title_canon_sha256":"7397744d78b8c8965b1a7d0b5108c3a54f59b0f9bec948c7579a34a653cd4154","abstract_canon_sha256":"daefdef9acee8c292f5042e0b1bc68ec16dc94eff8ea0bdbe3adfee85e56a7c5"},"schema_version":"1.0"},"canonical_sha256":"ec39fdbabb48fbbeaa9e9f1fba815afc17d27ccf3bb2dbbac0a9a3648971d563","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:15:34.599414Z","signature_b64":"DKNGGbAabbTbnNuH77b/5g59FzgYRDSAYGpArM2WOoTxqICRKcqq1E9angjCme9nHPA7EgJQE7etTmN9r6KdCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec39fdbabb48fbbeaa9e9f1fba815afc17d27ccf3bb2dbbac0a9a3648971d563","last_reissued_at":"2026-07-05T06:15:34.598933Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:15:34.598933Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.18893","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":"2026-07-05T06:15:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G5l/+v5aEev6DAwpAFiydZUqMSR3mvyhu9c2aYENuS0gbCSJC8N2zDbzXZmwo6XLg1F9+mLivTcvfr7ekeVrAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:09:26.397181Z"},"content_sha256":"7f4d35af1d9b16743197f9ae4d072b61a7ce7199ac5d375f88ce5a2ffad03a8c","schema_version":"1.0","event_id":"sha256:7f4d35af1d9b16743197f9ae4d072b61a7ce7199ac5d375f88ce5a2ffad03a8c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:5Q473OV3JD535KU6T4P3VAK27Q","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Where's the Point? Self-Supervised Multilingual Punctuation-Agnostic Sentence Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Benjamin Minixhofer, Ivan Vuli\\'c, Jonas Pfeiffer","submitted_at":"2023-05-30T09:49:42Z","abstract_excerpt":"Many NLP pipelines split text into sentences as one of the crucial preprocessing steps. Prior sentence segmentation tools either rely on punctuation or require a considerable amount of sentence-segmented training data: both central assumptions might fail when porting sentence segmenters to diverse languages on a massive scale. In this work, we thus introduce a multilingual punctuation-agnostic sentence segmentation method, currently covering 85 languages, trained in a self-supervised fashion on unsegmented text, by making use of newline characters which implicitly perform segmentation into par"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18893","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/2305.18893/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":"2026-07-05T06:15:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aU6p+cvSairLp/aOaZ/a7EdIwe5Q4KBMv5NHWuUqlfcphC7jRCSKPC/yffRPGVSf5XosxsG9WL+e5Tk5f+87CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T10:09:26.397561Z"},"content_sha256":"e186d9b8cbf5637c0fb6ee0775a466d5d4088e3ea32b8f016d259ea75e315f41","schema_version":"1.0","event_id":"sha256:e186d9b8cbf5637c0fb6ee0775a466d5d4088e3ea32b8f016d259ea75e315f41"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5Q473OV3JD535KU6T4P3VAK27Q/bundle.json","state_url":"https://pith.science/pith/5Q473OV3JD535KU6T4P3VAK27Q/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5Q473OV3JD535KU6T4P3VAK27Q/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":"2026-07-07T10:09:26Z","links":{"resolver":"https://pith.science/pith/5Q473OV3JD535KU6T4P3VAK27Q","bundle":"https://pith.science/pith/5Q473OV3JD535KU6T4P3VAK27Q/bundle.json","state":"https://pith.science/pith/5Q473OV3JD535KU6T4P3VAK27Q/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5Q473OV3JD535KU6T4P3VAK27Q/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:5Q473OV3JD535KU6T4P3VAK27Q","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":"daefdef9acee8c292f5042e0b1bc68ec16dc94eff8ea0bdbe3adfee85e56a7c5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-30T09:49:42Z","title_canon_sha256":"7397744d78b8c8965b1a7d0b5108c3a54f59b0f9bec948c7579a34a653cd4154"},"schema_version":"1.0","source":{"id":"2305.18893","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.18893","created_at":"2026-07-05T06:15:34Z"},{"alias_kind":"arxiv_version","alias_value":"2305.18893v1","created_at":"2026-07-05T06:15:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18893","created_at":"2026-07-05T06:15:34Z"},{"alias_kind":"pith_short_12","alias_value":"5Q473OV3JD53","created_at":"2026-07-05T06:15:34Z"},{"alias_kind":"pith_short_16","alias_value":"5Q473OV3JD535KU6","created_at":"2026-07-05T06:15:34Z"},{"alias_kind":"pith_short_8","alias_value":"5Q473OV3","created_at":"2026-07-05T06:15:34Z"}],"graph_snapshots":[{"event_id":"sha256:e186d9b8cbf5637c0fb6ee0775a466d5d4088e3ea32b8f016d259ea75e315f41","target":"graph","created_at":"2026-07-05T06:15:34Z","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/2305.18893/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many NLP pipelines split text into sentences as one of the crucial preprocessing steps. Prior sentence segmentation tools either rely on punctuation or require a considerable amount of sentence-segmented training data: both central assumptions might fail when porting sentence segmenters to diverse languages on a massive scale. In this work, we thus introduce a multilingual punctuation-agnostic sentence segmentation method, currently covering 85 languages, trained in a self-supervised fashion on unsegmented text, by making use of newline characters which implicitly perform segmentation into par","authors_text":"Benjamin Minixhofer, Ivan Vuli\\'c, Jonas Pfeiffer","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-30T09:49:42Z","title":"Where's the Point? Self-Supervised Multilingual Punctuation-Agnostic Sentence Segmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18893","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":"sha256:7f4d35af1d9b16743197f9ae4d072b61a7ce7199ac5d375f88ce5a2ffad03a8c","target":"record","created_at":"2026-07-05T06:15:34Z","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":"daefdef9acee8c292f5042e0b1bc68ec16dc94eff8ea0bdbe3adfee85e56a7c5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-30T09:49:42Z","title_canon_sha256":"7397744d78b8c8965b1a7d0b5108c3a54f59b0f9bec948c7579a34a653cd4154"},"schema_version":"1.0","source":{"id":"2305.18893","kind":"arxiv","version":1}},"canonical_sha256":"ec39fdbabb48fbbeaa9e9f1fba815afc17d27ccf3bb2dbbac0a9a3648971d563","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ec39fdbabb48fbbeaa9e9f1fba815afc17d27ccf3bb2dbbac0a9a3648971d563","first_computed_at":"2026-07-05T06:15:34.598933Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:15:34.598933Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DKNGGbAabbTbnNuH77b/5g59FzgYRDSAYGpArM2WOoTxqICRKcqq1E9angjCme9nHPA7EgJQE7etTmN9r6KdCg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:15:34.599414Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.18893","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7f4d35af1d9b16743197f9ae4d072b61a7ce7199ac5d375f88ce5a2ffad03a8c","sha256:e186d9b8cbf5637c0fb6ee0775a466d5d4088e3ea32b8f016d259ea75e315f41"],"state_sha256":"d8d84c31ddcd350a2eff6a59b392cab484961c8c29473ca92da25a9e7557eff7"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mc8jjbX4zOZLXB9W0uwqlBoZS+aAHZtUsZ/dHrSKASdYtHX8KGZr7A7bZ+GwGKk+BvvcQnzQqt4qM4BnnK5wCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T10:09:26.399505Z","bundle_sha256":"6e2644d926d99e95cc9845ed8f788c1530a24d41d25f200c25aeed1d6d5761c0"}}