{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:O4Q6LTHVFXC4BSGNOTSBIHOVYQ","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":"cc70df8dcb31755fdcd43dec773a1296b6fe1ecf16a00377c136161a046d7546","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-10-19T16:56:03Z","title_canon_sha256":"74ca44b0b1b265aa530726243bd4f00c9fcc9c4868fa009114894c961995c725"},"schema_version":"1.0","source":{"id":"2010.09657","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.09657","created_at":"2026-07-05T01:44:06Z"},{"alias_kind":"arxiv_version","alias_value":"2010.09657v1","created_at":"2026-07-05T01:44:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.09657","created_at":"2026-07-05T01:44:06Z"},{"alias_kind":"pith_short_12","alias_value":"O4Q6LTHVFXC4","created_at":"2026-07-05T01:44:06Z"},{"alias_kind":"pith_short_16","alias_value":"O4Q6LTHVFXC4BSGN","created_at":"2026-07-05T01:44:06Z"},{"alias_kind":"pith_short_8","alias_value":"O4Q6LTHV","created_at":"2026-07-05T01:44:06Z"}],"graph_snapshots":[{"event_id":"sha256:289dc1ee610c723e49f1b238a1f8613da455bdb6cdee23e1514f1d57493223e8","target":"graph","created_at":"2026-07-05T01:44:06Z","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/2010.09657/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we present a rule-based sentence boundary disambiguation Python package that works out-of-the-box for 22 languages. We aim to provide a realistic segmenter which can provide logical sentences even when the format and domain of the input text is unknown. In our work, we adapt the Golden Rules Set (a language-specific set of sentence boundary exemplars) originally implemented as a ruby gem - pragmatic_segmenter - which we ported to Python with additional improvements and functionality. PySBD passes 97.92% of the Golden Rule Set exemplars for English, an improvement of 25% over the","authors_text":"Mark Neumann, Nipun Sadvilkar","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-10-19T16:56:03Z","title":"PySBD: Pragmatic Sentence Boundary Disambiguation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.09657","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:f7d85717c8444e54977a9a652b39b7a8ece8ffc11155bba4dfebc53b12c45e82","target":"record","created_at":"2026-07-05T01:44:06Z","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":"cc70df8dcb31755fdcd43dec773a1296b6fe1ecf16a00377c136161a046d7546","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-10-19T16:56:03Z","title_canon_sha256":"74ca44b0b1b265aa530726243bd4f00c9fcc9c4868fa009114894c961995c725"},"schema_version":"1.0","source":{"id":"2010.09657","kind":"arxiv","version":1}},"canonical_sha256":"7721e5ccf52dc5c0c8cd74e4141dd5c41a135ec21cb6beb39eff7e1c9bb39028","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7721e5ccf52dc5c0c8cd74e4141dd5c41a135ec21cb6beb39eff7e1c9bb39028","first_computed_at":"2026-07-05T01:44:06.373296Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:44:06.373296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+9vx/vBeEiUwaGfcSFtwAjppouS3fDsnnPUq5vayAHq9UdxWhkRCobYh3mzhoWt3JQSnceEM+NQMDoPtkFx2BA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:44:06.373794Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.09657","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f7d85717c8444e54977a9a652b39b7a8ece8ffc11155bba4dfebc53b12c45e82","sha256:289dc1ee610c723e49f1b238a1f8613da455bdb6cdee23e1514f1d57493223e8"],"state_sha256":"94279370f82ee531838e9d449c247b56e838328e75a2d0a8226d734a46300f0f"}