{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:B3DVKELNVCUETC3AQBHW6ZOTOZ","short_pith_number":"pith:B3DVKELN","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"},"canonical_sha256":"0ec755116da8a8498b60804f6f65d3766a6e97a4a12c7657f1b6177a2616c6b5","source":{"kind":"arxiv","id":"2004.05808","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.05808","created_at":"2026-07-05T00:54:41Z"},{"alias_kind":"arxiv_version","alias_value":"2004.05808v1","created_at":"2026-07-05T00:54:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.05808","created_at":"2026-07-05T00:54:41Z"},{"alias_kind":"pith_short_12","alias_value":"B3DVKELNVCUE","created_at":"2026-07-05T00:54:41Z"},{"alias_kind":"pith_short_16","alias_value":"B3DVKELNVCUETC3A","created_at":"2026-07-05T00:54:41Z"},{"alias_kind":"pith_short_8","alias_value":"B3DVKELN","created_at":"2026-07-05T00:54:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:B3DVKELNVCUETC3AQBHW6ZOTOZ","target":"record","payload":{"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"},"canonical_sha256":"0ec755116da8a8498b60804f6f65d3766a6e97a4a12c7657f1b6177a2616c6b5","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"},"source_kind":"arxiv","source_id":"2004.05808","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":"2026-07-05T00:54:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"V/JuNIH8y3Of5wW8Br15fw13DyA2lzv8vMaRwqCb5++14ijEvD2t9DmiEl7B89l/7qGC42qn8EwQHr0pne1pBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T19:48:33.846487Z"},"content_sha256":"448a1d23a5c3d244e92af26a491fad23a72302df2da2bd9f5ded4c691315d1ff","schema_version":"1.0","event_id":"sha256:448a1d23a5c3d244e92af26a491fad23a72302df2da2bd9f5ded4c691315d1ff"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:B3DVKELNVCUETC3AQBHW6ZOTOZ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:54:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5v1c87QXe7ATLj31OCoX12SJjA5ECWEgULVK3XeKJfII6hicIh5UcHkHWCGHca/EFgBiZC3d9j1RA4DEx67hDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T19:48:33.848456Z"},"content_sha256":"98df389878956a406566029960ce7cd4a9a537d79300abfd300a2933eb7b8dbb","schema_version":"1.0","event_id":"sha256:98df389878956a406566029960ce7cd4a9a537d79300abfd300a2933eb7b8dbb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B3DVKELNVCUETC3AQBHW6ZOTOZ/bundle.json","state_url":"https://pith.science/pith/B3DVKELNVCUETC3AQBHW6ZOTOZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B3DVKELNVCUETC3AQBHW6ZOTOZ/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":"2026-08-05T19:48:33Z","links":{"resolver":"https://pith.science/pith/B3DVKELNVCUETC3AQBHW6ZOTOZ","bundle":"https://pith.science/pith/B3DVKELNVCUETC3AQBHW6ZOTOZ/bundle.json","state":"https://pith.science/pith/B3DVKELNVCUETC3AQBHW6ZOTOZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B3DVKELNVCUETC3AQBHW6ZOTOZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:B3DVKELNVCUETC3AQBHW6ZOTOZ","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":"d881e94bb0f5a7bd6462a3882548690886c19557cacf893e2f70be31657d6bda","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-13T07:50:04Z","title_canon_sha256":"2c43e7311def2c3244cbf13d545b6766d202100c6e4d8e1df3ca7e5c03f9d5a0"},"schema_version":"1.0","source":{"id":"2004.05808","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.05808","created_at":"2026-07-05T00:54:41Z"},{"alias_kind":"arxiv_version","alias_value":"2004.05808v1","created_at":"2026-07-05T00:54:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.05808","created_at":"2026-07-05T00:54:41Z"},{"alias_kind":"pith_short_12","alias_value":"B3DVKELNVCUE","created_at":"2026-07-05T00:54:41Z"},{"alias_kind":"pith_short_16","alias_value":"B3DVKELNVCUETC3A","created_at":"2026-07-05T00:54:41Z"},{"alias_kind":"pith_short_8","alias_value":"B3DVKELN","created_at":"2026-07-05T00:54:41Z"}],"graph_snapshots":[{"event_id":"sha256:98df389878956a406566029960ce7cd4a9a537d79300abfd300a2933eb7b8dbb","target":"graph","created_at":"2026-07-05T00:54:41Z","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/2004.05808/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Bin Wang, Erli Meng, Liang Shi, Xipeng Qiu, Xuanjing Huang, Zhen Ke","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-13T07:50:04Z","title":"Unified Multi-Criteria Chinese Word Segmentation with BERT"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.05808","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":"sha256:448a1d23a5c3d244e92af26a491fad23a72302df2da2bd9f5ded4c691315d1ff","target":"record","created_at":"2026-07-05T00:54:41Z","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":"d881e94bb0f5a7bd6462a3882548690886c19557cacf893e2f70be31657d6bda","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-13T07:50:04Z","title_canon_sha256":"2c43e7311def2c3244cbf13d545b6766d202100c6e4d8e1df3ca7e5c03f9d5a0"},"schema_version":"1.0","source":{"id":"2004.05808","kind":"arxiv","version":1}},"canonical_sha256":"0ec755116da8a8498b60804f6f65d3766a6e97a4a12c7657f1b6177a2616c6b5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0ec755116da8a8498b60804f6f65d3766a6e97a4a12c7657f1b6177a2616c6b5","first_computed_at":"2026-07-05T00:54:41.079320Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:54:41.079320Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Hcn3omhHkezph+YGE6MNglzcNKpJks9vJld5fBPcWDV6izamxCC13FVNXi+redaR6p80f20qaH7UXdPor4csBw==","signature_status":"signed_v1","signed_at":"2026-07-05T00:54:41.079813Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.05808","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:448a1d23a5c3d244e92af26a491fad23a72302df2da2bd9f5ded4c691315d1ff","sha256:98df389878956a406566029960ce7cd4a9a537d79300abfd300a2933eb7b8dbb"],"state_sha256":"a80f0e8a01847a2ef7eab0879fd8857e32499351bf9acf012624b8d870d9cedb"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uWoW4FAKzmcifvysf3/22uLXnHNd/mOcPRfOS+8+j8X57cIY436kMxApbvXqELVbb7YzrNJNw/6oIXCko58dAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T19:48:33.856412Z","bundle_sha256":"d1b33b75de1661c2a55be944490348d7984659aa5a404a786f329700bcf9a9eb"}}