{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:42THY3DUTDHWCSKRT7P6X7EIDR","short_pith_number":"pith:42THY3DU","schema_version":"1.0","canonical_sha256":"e6a67c6c7498cf6149519fdfebfc881c72eb7691b4a47f407623b3c34df56355","source":{"kind":"arxiv","id":"2203.06378","version":2},"attestation_state":"computed","paper":{"title":"MarkBERT: Marking Word Boundaries Improves Chinese BERT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Duyu Tang, Linyang Li, Shuming Shi, Xipeng Qiu, Yong Dai, Zenglin Xu","submitted_at":"2022-03-12T08:43:06Z","abstract_excerpt":"We present a Chinese BERT model dubbed MarkBERT that uses word information in this work. Existing word-based BERT models regard words as basic units, however, due to the vocabulary limit of BERT, they only cover high-frequency words and fall back to character level when encountering out-of-vocabulary (OOV) words. Different from existing works, MarkBERT keeps the vocabulary being Chinese characters and inserts boundary markers between contiguous words. Such design enables the model to handle any words in the same way, no matter they are OOV words or not. Besides, our model has two additional be"},"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":"2203.06378","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-12T08:43:06Z","cross_cats_sorted":[],"title_canon_sha256":"266a56904a023c990cbdce286327ecf581960c245422485dd5df439225b24e32","abstract_canon_sha256":"57f08fc6fee0756aedd75b2f3f04b75f85deb9b4a4af8d94f5d69516115b6175"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:04:28.208228Z","signature_b64":"uDkGvJUzeuW8GRBAbOngpy3VZW9BXDAehwEvrGty7ZWL5yckzOrt6DAuRWXFM8iM+KzMLfMy74whE6oFa52aDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6a67c6c7498cf6149519fdfebfc881c72eb7691b4a47f407623b3c34df56355","last_reissued_at":"2026-07-05T05:04:28.207808Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:04:28.207808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MarkBERT: Marking Word Boundaries Improves Chinese BERT","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Duyu Tang, Linyang Li, Shuming Shi, Xipeng Qiu, Yong Dai, Zenglin Xu","submitted_at":"2022-03-12T08:43:06Z","abstract_excerpt":"We present a Chinese BERT model dubbed MarkBERT that uses word information in this work. Existing word-based BERT models regard words as basic units, however, due to the vocabulary limit of BERT, they only cover high-frequency words and fall back to character level when encountering out-of-vocabulary (OOV) words. Different from existing works, MarkBERT keeps the vocabulary being Chinese characters and inserts boundary markers between contiguous words. Such design enables the model to handle any words in the same way, no matter they are OOV words or not. Besides, our model has two additional be"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.06378","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/2203.06378/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":"2203.06378","created_at":"2026-07-05T05:04:28.207865+00:00"},{"alias_kind":"arxiv_version","alias_value":"2203.06378v2","created_at":"2026-07-05T05:04:28.207865+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.06378","created_at":"2026-07-05T05:04:28.207865+00:00"},{"alias_kind":"pith_short_12","alias_value":"42THY3DUTDHW","created_at":"2026-07-05T05:04:28.207865+00:00"},{"alias_kind":"pith_short_16","alias_value":"42THY3DUTDHWCSKR","created_at":"2026-07-05T05:04:28.207865+00:00"},{"alias_kind":"pith_short_8","alias_value":"42THY3DU","created_at":"2026-07-05T05:04:28.207865+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/42THY3DUTDHWCSKRT7P6X7EIDR","json":"https://pith.science/pith/42THY3DUTDHWCSKRT7P6X7EIDR.json","graph_json":"https://pith.science/api/pith-number/42THY3DUTDHWCSKRT7P6X7EIDR/graph.json","events_json":"https://pith.science/api/pith-number/42THY3DUTDHWCSKRT7P6X7EIDR/events.json","paper":"https://pith.science/paper/42THY3DU"},"agent_actions":{"view_html":"https://pith.science/pith/42THY3DUTDHWCSKRT7P6X7EIDR","download_json":"https://pith.science/pith/42THY3DUTDHWCSKRT7P6X7EIDR.json","view_paper":"https://pith.science/paper/42THY3DU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2203.06378&json=true","fetch_graph":"https://pith.science/api/pith-number/42THY3DUTDHWCSKRT7P6X7EIDR/graph.json","fetch_events":"https://pith.science/api/pith-number/42THY3DUTDHWCSKRT7P6X7EIDR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/42THY3DUTDHWCSKRT7P6X7EIDR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/42THY3DUTDHWCSKRT7P6X7EIDR/action/storage_attestation","attest_author":"https://pith.science/pith/42THY3DUTDHWCSKRT7P6X7EIDR/action/author_attestation","sign_citation":"https://pith.science/pith/42THY3DUTDHWCSKRT7P6X7EIDR/action/citation_signature","submit_replication":"https://pith.science/pith/42THY3DUTDHWCSKRT7P6X7EIDR/action/replication_record"}},"created_at":"2026-07-05T05:04:28.207865+00:00","updated_at":"2026-07-05T05:04:28.207865+00:00"}