{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:Q6TK4WN4KLT4MWSETF5APYWY7M","short_pith_number":"pith:Q6TK4WN4","schema_version":"1.0","canonical_sha256":"87a6ae59bc52e7c65a44997a07e2d8fb049d0b5b6bf0b7124dd961a916bdcc2a","source":{"kind":"arxiv","id":"1905.08732","version":1},"attestation_state":"computed","paper":{"title":"A realistic and robust model for Chinese word segmentation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chu-Ren Huang, Petr Simon, Shu-Kai Hsieh, Ting-Shuo Yo","submitted_at":"2019-05-21T16:22:47Z","abstract_excerpt":"A realistic Chinese word segmentation tool must adapt to textual variations with minimal training input and yet robust enough to yield reliable segmentation result for all variants. Various lexicon-driven approaches to Chinese segmentation, e.g. [1,16], achieve high f-scores yet require massive training for any variation. Text-driven approach, e.g. [12], can be easily adapted for domain and genre changes yet has difficulty matching the high f-scores of the lexicon-driven approaches. In this paper, we refine and implement an innovative text-driven word boundary decision (WBD) segmentation model"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1905.08732","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2019-05-21T16:22:47Z","cross_cats_sorted":["cs.IR","cs.LG"],"title_canon_sha256":"1b4a533e98e7830132b5fd2a7aff33fa290b9c400c7a552c3321213c94e87fca","abstract_canon_sha256":"83b425b391cb276285d94d87c89f6410f4287121782ed45da4a6e78b6727ccb7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:42.237677Z","signature_b64":"k8kUUdJAL3noZuwJCrHy2zK4W/imxp14OlG4i9c8l55A5e6t+hxtfr1HPWF40hWRB6FFJRb15BOkw2Ww8UtHAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"87a6ae59bc52e7c65a44997a07e2d8fb049d0b5b6bf0b7124dd961a916bdcc2a","last_reissued_at":"2026-05-17T23:45:42.236989Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:42.236989Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A realistic and robust model for Chinese word segmentation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.IR","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chu-Ren Huang, Petr Simon, Shu-Kai Hsieh, Ting-Shuo Yo","submitted_at":"2019-05-21T16:22:47Z","abstract_excerpt":"A realistic Chinese word segmentation tool must adapt to textual variations with minimal training input and yet robust enough to yield reliable segmentation result for all variants. Various lexicon-driven approaches to Chinese segmentation, e.g. [1,16], achieve high f-scores yet require massive training for any variation. Text-driven approach, e.g. [12], can be easily adapted for domain and genre changes yet has difficulty matching the high f-scores of the lexicon-driven approaches. In this paper, we refine and implement an innovative text-driven word boundary decision (WBD) segmentation model"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.08732","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":""},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1905.08732","created_at":"2026-05-17T23:45:42.237089+00:00"},{"alias_kind":"arxiv_version","alias_value":"1905.08732v1","created_at":"2026-05-17T23:45:42.237089+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.08732","created_at":"2026-05-17T23:45:42.237089+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q6TK4WN4KLT4","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q6TK4WN4KLT4MWSE","created_at":"2026-05-18T12:33:27.125529+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q6TK4WN4","created_at":"2026-05-18T12:33:27.125529+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q6TK4WN4KLT4MWSETF5APYWY7M","json":"https://pith.science/pith/Q6TK4WN4KLT4MWSETF5APYWY7M.json","graph_json":"https://pith.science/api/pith-number/Q6TK4WN4KLT4MWSETF5APYWY7M/graph.json","events_json":"https://pith.science/api/pith-number/Q6TK4WN4KLT4MWSETF5APYWY7M/events.json","paper":"https://pith.science/paper/Q6TK4WN4"},"agent_actions":{"view_html":"https://pith.science/pith/Q6TK4WN4KLT4MWSETF5APYWY7M","download_json":"https://pith.science/pith/Q6TK4WN4KLT4MWSETF5APYWY7M.json","view_paper":"https://pith.science/paper/Q6TK4WN4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1905.08732&json=true","fetch_graph":"https://pith.science/api/pith-number/Q6TK4WN4KLT4MWSETF5APYWY7M/graph.json","fetch_events":"https://pith.science/api/pith-number/Q6TK4WN4KLT4MWSETF5APYWY7M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q6TK4WN4KLT4MWSETF5APYWY7M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q6TK4WN4KLT4MWSETF5APYWY7M/action/storage_attestation","attest_author":"https://pith.science/pith/Q6TK4WN4KLT4MWSETF5APYWY7M/action/author_attestation","sign_citation":"https://pith.science/pith/Q6TK4WN4KLT4MWSETF5APYWY7M/action/citation_signature","submit_replication":"https://pith.science/pith/Q6TK4WN4KLT4MWSETF5APYWY7M/action/replication_record"}},"created_at":"2026-05-17T23:45:42.237089+00:00","updated_at":"2026-05-17T23:45:42.237089+00:00"}