{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:42THY3DUTDHWCSKRT7P6X7EIDR","short_pith_number":"pith:42THY3DU","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"},"canonical_sha256":"e6a67c6c7498cf6149519fdfebfc881c72eb7691b4a47f407623b3c34df56355","source":{"kind":"arxiv","id":"2203.06378","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.06378","created_at":"2026-07-05T05:04:28Z"},{"alias_kind":"arxiv_version","alias_value":"2203.06378v2","created_at":"2026-07-05T05:04:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.06378","created_at":"2026-07-05T05:04:28Z"},{"alias_kind":"pith_short_12","alias_value":"42THY3DUTDHW","created_at":"2026-07-05T05:04:28Z"},{"alias_kind":"pith_short_16","alias_value":"42THY3DUTDHWCSKR","created_at":"2026-07-05T05:04:28Z"},{"alias_kind":"pith_short_8","alias_value":"42THY3DU","created_at":"2026-07-05T05:04:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:42THY3DUTDHWCSKRT7P6X7EIDR","target":"record","payload":{"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"},"canonical_sha256":"e6a67c6c7498cf6149519fdfebfc881c72eb7691b4a47f407623b3c34df56355","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"},"source_kind":"arxiv","source_id":"2203.06378","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:04:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QJqJjR4wmV2woktB02CyPJAJPfQxmm2WHuoqaa93N0uBu90gr8pdPT0wraNsSlBH0kBL0OKhX86/TeB6tt4AAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T23:54:10.419592Z"},"content_sha256":"5d40efde5a546603fb7e6cbb99cbe105a9f2a4dff212324bb9bf852cacd79269","schema_version":"1.0","event_id":"sha256:5d40efde5a546603fb7e6cbb99cbe105a9f2a4dff212324bb9bf852cacd79269"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:42THY3DUTDHWCSKRT7P6X7EIDR","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:04:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dHg4pnOHy94O8vuw+52QSiR72GSzc/rQ36+eNaeIpRtN4JSmdhKCVK8niPZFRlUDL9OhYltVbwqvPG0MsiovBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T23:54:10.420509Z"},"content_sha256":"505391f28f99f275a36061c062918dbc2004042ea84eda8da5880944df324e2b","schema_version":"1.0","event_id":"sha256:505391f28f99f275a36061c062918dbc2004042ea84eda8da5880944df324e2b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/42THY3DUTDHWCSKRT7P6X7EIDR/bundle.json","state_url":"https://pith.science/pith/42THY3DUTDHWCSKRT7P6X7EIDR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/42THY3DUTDHWCSKRT7P6X7EIDR/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":"2026-08-05T23:54:10Z","links":{"resolver":"https://pith.science/pith/42THY3DUTDHWCSKRT7P6X7EIDR","bundle":"https://pith.science/pith/42THY3DUTDHWCSKRT7P6X7EIDR/bundle.json","state":"https://pith.science/pith/42THY3DUTDHWCSKRT7P6X7EIDR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/42THY3DUTDHWCSKRT7P6X7EIDR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:42THY3DUTDHWCSKRT7P6X7EIDR","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":"57f08fc6fee0756aedd75b2f3f04b75f85deb9b4a4af8d94f5d69516115b6175","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-12T08:43:06Z","title_canon_sha256":"266a56904a023c990cbdce286327ecf581960c245422485dd5df439225b24e32"},"schema_version":"1.0","source":{"id":"2203.06378","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.06378","created_at":"2026-07-05T05:04:28Z"},{"alias_kind":"arxiv_version","alias_value":"2203.06378v2","created_at":"2026-07-05T05:04:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.06378","created_at":"2026-07-05T05:04:28Z"},{"alias_kind":"pith_short_12","alias_value":"42THY3DUTDHW","created_at":"2026-07-05T05:04:28Z"},{"alias_kind":"pith_short_16","alias_value":"42THY3DUTDHWCSKR","created_at":"2026-07-05T05:04:28Z"},{"alias_kind":"pith_short_8","alias_value":"42THY3DU","created_at":"2026-07-05T05:04:28Z"}],"graph_snapshots":[{"event_id":"sha256:505391f28f99f275a36061c062918dbc2004042ea84eda8da5880944df324e2b","target":"graph","created_at":"2026-07-05T05:04:28Z","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/2203.06378/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Duyu Tang, Linyang Li, Shuming Shi, Xipeng Qiu, Yong Dai, Zenglin Xu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-12T08:43:06Z","title":"MarkBERT: Marking Word Boundaries Improves Chinese BERT"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.06378","kind":"arxiv","version":2},"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":"sha256:5d40efde5a546603fb7e6cbb99cbe105a9f2a4dff212324bb9bf852cacd79269","target":"record","created_at":"2026-07-05T05:04:28Z","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":"57f08fc6fee0756aedd75b2f3f04b75f85deb9b4a4af8d94f5d69516115b6175","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-12T08:43:06Z","title_canon_sha256":"266a56904a023c990cbdce286327ecf581960c245422485dd5df439225b24e32"},"schema_version":"1.0","source":{"id":"2203.06378","kind":"arxiv","version":2}},"canonical_sha256":"e6a67c6c7498cf6149519fdfebfc881c72eb7691b4a47f407623b3c34df56355","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e6a67c6c7498cf6149519fdfebfc881c72eb7691b4a47f407623b3c34df56355","first_computed_at":"2026-07-05T05:04:28.207808Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:04:28.207808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uDkGvJUzeuW8GRBAbOngpy3VZW9BXDAehwEvrGty7ZWL5yckzOrt6DAuRWXFM8iM+KzMLfMy74whE6oFa52aDw==","signature_status":"signed_v1","signed_at":"2026-07-05T05:04:28.208228Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.06378","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5d40efde5a546603fb7e6cbb99cbe105a9f2a4dff212324bb9bf852cacd79269","sha256:505391f28f99f275a36061c062918dbc2004042ea84eda8da5880944df324e2b"],"state_sha256":"027370696a3c3f70f5cc6a9c31f7262d153cb71a46532f2eeb92ab1b56219134"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f5f14gIuS1FkPNW0Ee1uuKohW2iHrTBkWYrj3ZttN/fwtrE6561efAMXCfeiyFk5E8ey+R++gQtRfuTlQpv9DA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T23:54:10.429966Z","bundle_sha256":"4e0a204bbc676cfa727c974e91c70df802d2d0198de85787b440dafb96a078e6"}}