{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:B3DVKELNVCUETC3AQBHW6ZOTOZ","short_pith_number":"pith:B3DVKELN","schema_version":"1.0","canonical_sha256":"0ec755116da8a8498b60804f6f65d3766a6e97a4a12c7657f1b6177a2616c6b5","source":{"kind":"arxiv","id":"2004.05808","version":1},"attestation_state":"computed","paper":{"title":"Unified Multi-Criteria Chinese Word Segmentation with BERT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bin Wang, Erli Meng, Liang Shi, Xipeng Qiu, Xuanjing Huang, Zhen Ke","submitted_at":"2020-04-13T07:50:04Z","abstract_excerpt":"Multi-Criteria Chinese Word Segmentation (MCCWS) aims at finding word boundaries in a Chinese sentence composed of continuous characters while multiple segmentation criteria exist. The unified framework has been widely used in MCCWS and shows its effectiveness. Besides, the pre-trained BERT language model has been also introduced into the MCCWS task in a multi-task learning framework. In this paper, we combine the superiority of the unified framework and pretrained language model, and propose a unified MCCWS model based on BERT. Moreover, we augment the unified BERT-based MCCWS model with the "},"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":"2004.05808","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-13T07:50:04Z","cross_cats_sorted":[],"title_canon_sha256":"2c43e7311def2c3244cbf13d545b6766d202100c6e4d8e1df3ca7e5c03f9d5a0","abstract_canon_sha256":"d881e94bb0f5a7bd6462a3882548690886c19557cacf893e2f70be31657d6bda"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:54:41.079813Z","signature_b64":"Hcn3omhHkezph+YGE6MNglzcNKpJks9vJld5fBPcWDV6izamxCC13FVNXi+redaR6p80f20qaH7UXdPor4csBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ec755116da8a8498b60804f6f65d3766a6e97a4a12c7657f1b6177a2616c6b5","last_reissued_at":"2026-07-05T00:54:41.079320Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:54:41.079320Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Unified Multi-Criteria Chinese Word Segmentation with BERT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bin Wang, Erli Meng, Liang Shi, Xipeng Qiu, Xuanjing Huang, Zhen Ke","submitted_at":"2020-04-13T07:50:04Z","abstract_excerpt":"Multi-Criteria Chinese Word Segmentation (MCCWS) aims at finding word boundaries in a Chinese sentence composed of continuous characters while multiple segmentation criteria exist. The unified framework has been widely used in MCCWS and shows its effectiveness. Besides, the pre-trained BERT language model has been also introduced into the MCCWS task in a multi-task learning framework. In this paper, we combine the superiority of the unified framework and pretrained language model, and propose a unified MCCWS model based on BERT. Moreover, we augment the unified BERT-based MCCWS model with the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.05808","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/2004.05808/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2004.05808","created_at":"2026-07-05T00:54:41.079396+00:00"},{"alias_kind":"arxiv_version","alias_value":"2004.05808v1","created_at":"2026-07-05T00:54:41.079396+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.05808","created_at":"2026-07-05T00:54:41.079396+00:00"},{"alias_kind":"pith_short_12","alias_value":"B3DVKELNVCUE","created_at":"2026-07-05T00:54:41.079396+00:00"},{"alias_kind":"pith_short_16","alias_value":"B3DVKELNVCUETC3A","created_at":"2026-07-05T00:54:41.079396+00:00"},{"alias_kind":"pith_short_8","alias_value":"B3DVKELN","created_at":"2026-07-05T00:54:41.079396+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/B3DVKELNVCUETC3AQBHW6ZOTOZ","json":"https://pith.science/pith/B3DVKELNVCUETC3AQBHW6ZOTOZ.json","graph_json":"https://pith.science/api/pith-number/B3DVKELNVCUETC3AQBHW6ZOTOZ/graph.json","events_json":"https://pith.science/api/pith-number/B3DVKELNVCUETC3AQBHW6ZOTOZ/events.json","paper":"https://pith.science/paper/B3DVKELN"},"agent_actions":{"view_html":"https://pith.science/pith/B3DVKELNVCUETC3AQBHW6ZOTOZ","download_json":"https://pith.science/pith/B3DVKELNVCUETC3AQBHW6ZOTOZ.json","view_paper":"https://pith.science/paper/B3DVKELN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2004.05808&json=true","fetch_graph":"https://pith.science/api/pith-number/B3DVKELNVCUETC3AQBHW6ZOTOZ/graph.json","fetch_events":"https://pith.science/api/pith-number/B3DVKELNVCUETC3AQBHW6ZOTOZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B3DVKELNVCUETC3AQBHW6ZOTOZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B3DVKELNVCUETC3AQBHW6ZOTOZ/action/storage_attestation","attest_author":"https://pith.science/pith/B3DVKELNVCUETC3AQBHW6ZOTOZ/action/author_attestation","sign_citation":"https://pith.science/pith/B3DVKELNVCUETC3AQBHW6ZOTOZ/action/citation_signature","submit_replication":"https://pith.science/pith/B3DVKELNVCUETC3AQBHW6ZOTOZ/action/replication_record"}},"created_at":"2026-07-05T00:54:41.079396+00:00","updated_at":"2026-07-05T00:54:41.079396+00:00"}