{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:GUV2TJZMMDQCIRHCIIBQBUWJ2N","short_pith_number":"pith:GUV2TJZM","schema_version":"1.0","canonical_sha256":"352ba9a72c60e02444e2420300d2c9d35a1d8cd9805c6bdba68a00c15d65fbdd","source":{"kind":"arxiv","id":"1906.12035","version":2},"attestation_state":"computed","paper":{"title":"A Concise Model for Multi-Criteria Chinese Word Segmentation with Transformer Encoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hang Yan, Hengzhi Pei, Xipeng Qiu, Xuanjing Huang","submitted_at":"2019-06-28T04:08:15Z","abstract_excerpt":"Multi-criteria Chinese word segmentation (MCCWS) aims to exploit the relations among the multiple heterogeneous segmentation criteria and further improve the performance of each single criterion. Previous work usually regards MCCWS as different tasks, which are learned together under the multi-task learning framework. In this paper, we propose a concise but effective unified model for MCCWS, which is fully-shared for all the criteria. By leveraging the powerful ability of the Transformer encoder, the proposed unified model can segment Chinese text according to a unique criterion-token indicati"},"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":"1906.12035","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-06-28T04:08:15Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"b8ee1f1421fc6afed2c5c81b933c52826dd0f165db4dbbe98fb6b37c74e49aa7","abstract_canon_sha256":"d3a8232a64b613f24eafc562d19782e471aed8fe23aea561a888e74a486e0868"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:39:54.094472Z","signature_b64":"90rVJM8nmIVwhjjoQdwJmtT3pZhOPRnPX9tq/xSP8tZaFdxgb4EJM92/leuogAlnuhq9Za/E6LamETop9KrzCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"352ba9a72c60e02444e2420300d2c9d35a1d8cd9805c6bdba68a00c15d65fbdd","last_reissued_at":"2026-07-05T01:39:54.094107Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:39:54.094107Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Concise Model for Multi-Criteria Chinese Word Segmentation with Transformer Encoder","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hang Yan, Hengzhi Pei, Xipeng Qiu, Xuanjing Huang","submitted_at":"2019-06-28T04:08:15Z","abstract_excerpt":"Multi-criteria Chinese word segmentation (MCCWS) aims to exploit the relations among the multiple heterogeneous segmentation criteria and further improve the performance of each single criterion. Previous work usually regards MCCWS as different tasks, which are learned together under the multi-task learning framework. In this paper, we propose a concise but effective unified model for MCCWS, which is fully-shared for all the criteria. By leveraging the powerful ability of the Transformer encoder, the proposed unified model can segment Chinese text according to a unique criterion-token indicati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1906.12035","kind":"arxiv","version":2},"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/1906.12035/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":"1906.12035","created_at":"2026-07-05T01:39:54.094169+00:00"},{"alias_kind":"arxiv_version","alias_value":"1906.12035v2","created_at":"2026-07-05T01:39:54.094169+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1906.12035","created_at":"2026-07-05T01:39:54.094169+00:00"},{"alias_kind":"pith_short_12","alias_value":"GUV2TJZMMDQC","created_at":"2026-07-05T01:39:54.094169+00:00"},{"alias_kind":"pith_short_16","alias_value":"GUV2TJZMMDQCIRHC","created_at":"2026-07-05T01:39:54.094169+00:00"},{"alias_kind":"pith_short_8","alias_value":"GUV2TJZM","created_at":"2026-07-05T01:39:54.094169+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/GUV2TJZMMDQCIRHCIIBQBUWJ2N","json":"https://pith.science/pith/GUV2TJZMMDQCIRHCIIBQBUWJ2N.json","graph_json":"https://pith.science/api/pith-number/GUV2TJZMMDQCIRHCIIBQBUWJ2N/graph.json","events_json":"https://pith.science/api/pith-number/GUV2TJZMMDQCIRHCIIBQBUWJ2N/events.json","paper":"https://pith.science/paper/GUV2TJZM"},"agent_actions":{"view_html":"https://pith.science/pith/GUV2TJZMMDQCIRHCIIBQBUWJ2N","download_json":"https://pith.science/pith/GUV2TJZMMDQCIRHCIIBQBUWJ2N.json","view_paper":"https://pith.science/paper/GUV2TJZM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1906.12035&json=true","fetch_graph":"https://pith.science/api/pith-number/GUV2TJZMMDQCIRHCIIBQBUWJ2N/graph.json","fetch_events":"https://pith.science/api/pith-number/GUV2TJZMMDQCIRHCIIBQBUWJ2N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GUV2TJZMMDQCIRHCIIBQBUWJ2N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GUV2TJZMMDQCIRHCIIBQBUWJ2N/action/storage_attestation","attest_author":"https://pith.science/pith/GUV2TJZMMDQCIRHCIIBQBUWJ2N/action/author_attestation","sign_citation":"https://pith.science/pith/GUV2TJZMMDQCIRHCIIBQBUWJ2N/action/citation_signature","submit_replication":"https://pith.science/pith/GUV2TJZMMDQCIRHCIIBQBUWJ2N/action/replication_record"}},"created_at":"2026-07-05T01:39:54.094169+00:00","updated_at":"2026-07-05T01:39:54.094169+00:00"}