{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:2KUCUBHFOM2NZKEU77Q4HFXBD5","short_pith_number":"pith:2KUCUBHF","canonical_record":{"source":{"id":"2203.00286","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-01T08:24:56Z","cross_cats_sorted":[],"title_canon_sha256":"461aa9a9908d885b4971e40b6c7901410a5a91a3ec02bcfd8769188b9c3a1551","abstract_canon_sha256":"4927018ac517f6e2e057cd801d26b8300cd08508aa5e5a34fc3665fa9037691c"},"schema_version":"1.0"},"canonical_sha256":"d2a82a04e57334dca894ffe1c396e11f772f2b78ab88d9f7ddb1e7ba72d5cd36","source":{"kind":"arxiv","id":"2203.00286","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.00286","created_at":"2026-07-05T04:01:34Z"},{"alias_kind":"arxiv_version","alias_value":"2203.00286v2","created_at":"2026-07-05T04:01:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.00286","created_at":"2026-07-05T04:01:34Z"},{"alias_kind":"pith_short_12","alias_value":"2KUCUBHFOM2N","created_at":"2026-07-05T04:01:34Z"},{"alias_kind":"pith_short_16","alias_value":"2KUCUBHFOM2NZKEU","created_at":"2026-07-05T04:01:34Z"},{"alias_kind":"pith_short_8","alias_value":"2KUCUBHF","created_at":"2026-07-05T04:01:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:2KUCUBHFOM2NZKEU77Q4HFXBD5","target":"record","payload":{"canonical_record":{"source":{"id":"2203.00286","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-01T08:24:56Z","cross_cats_sorted":[],"title_canon_sha256":"461aa9a9908d885b4971e40b6c7901410a5a91a3ec02bcfd8769188b9c3a1551","abstract_canon_sha256":"4927018ac517f6e2e057cd801d26b8300cd08508aa5e5a34fc3665fa9037691c"},"schema_version":"1.0"},"canonical_sha256":"d2a82a04e57334dca894ffe1c396e11f772f2b78ab88d9f7ddb1e7ba72d5cd36","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:01:34.893436Z","signature_b64":"RrePqslKizztXkVZNfWdgGdiB7yDUoK9HwKCmwNh0/pVkaVejWbRvzGktL/+GeLruFNiKO646tfUVWeoA+v2Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2a82a04e57334dca894ffe1c396e11f772f2b78ab88d9f7ddb1e7ba72d5cd36","last_reissued_at":"2026-07-05T04:01:34.892910Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:01:34.892910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.00286","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":"2026-07-05T04:01:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HmU5Mb2kqSxmM62hn1pw3lFKtcni75KN5eHFnhP9EEQ0qIEfLR3uMMgIdnruW1RgHVVpRsBUhmv9SgBHyZY4Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:12:55.745211Z"},"content_sha256":"d117fcb8f3f5f2abd2186e7ad8d23d8323a77dc5da0d2de0e2bdbe1fd58fae40","schema_version":"1.0","event_id":"sha256:d117fcb8f3f5f2abd2186e7ad8d23d8323a77dc5da0d2de0e2bdbe1fd58fae40"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:2KUCUBHFOM2NZKEU77Q4HFXBD5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"\"Is Whole Word Masking Always Better for Chinese BERT?\": Probing on Chinese Grammatical Error Correction","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cong Zhou, Duyu Tang, Enbo Zhao, Linyang Li, Piji Li, Xipeng Qiu, Yong Dai, Zhangyin Feng","submitted_at":"2022-03-01T08:24:56Z","abstract_excerpt":"Whole word masking (WWM), which masks all subwords corresponding to a word at once, makes a better English BERT model. For the Chinese language, however, there is no subword because each token is an atomic character. The meaning of a word in Chinese is different in that a word is a compositional unit consisting of multiple characters. Such difference motivates us to investigate whether WWM leads to better context understanding ability for Chinese BERT. To achieve this, we introduce two probing tasks related to grammatical error correction and ask pretrained models to revise or insert tokens in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.00286","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/2203.00286/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":"2026-07-05T04:01:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YuN3mrYIq7wDyU2VimuDnhwnw7wX8dF7kjexc6myrX0KfU6haU5JOa6SXoyOK5ReFzlSWkzkykCaREr6n5nwBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T04:12:55.759909Z"},"content_sha256":"bdf9c628f91f1ac1f5e81d793c041d26d567daa1d8be8b36217e6be3c07f5345","schema_version":"1.0","event_id":"sha256:bdf9c628f91f1ac1f5e81d793c041d26d567daa1d8be8b36217e6be3c07f5345"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2KUCUBHFOM2NZKEU77Q4HFXBD5/bundle.json","state_url":"https://pith.science/pith/2KUCUBHFOM2NZKEU77Q4HFXBD5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2KUCUBHFOM2NZKEU77Q4HFXBD5/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":"2026-08-06T04:12:55Z","links":{"resolver":"https://pith.science/pith/2KUCUBHFOM2NZKEU77Q4HFXBD5","bundle":"https://pith.science/pith/2KUCUBHFOM2NZKEU77Q4HFXBD5/bundle.json","state":"https://pith.science/pith/2KUCUBHFOM2NZKEU77Q4HFXBD5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2KUCUBHFOM2NZKEU77Q4HFXBD5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:2KUCUBHFOM2NZKEU77Q4HFXBD5","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":"4927018ac517f6e2e057cd801d26b8300cd08508aa5e5a34fc3665fa9037691c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-01T08:24:56Z","title_canon_sha256":"461aa9a9908d885b4971e40b6c7901410a5a91a3ec02bcfd8769188b9c3a1551"},"schema_version":"1.0","source":{"id":"2203.00286","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.00286","created_at":"2026-07-05T04:01:34Z"},{"alias_kind":"arxiv_version","alias_value":"2203.00286v2","created_at":"2026-07-05T04:01:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.00286","created_at":"2026-07-05T04:01:34Z"},{"alias_kind":"pith_short_12","alias_value":"2KUCUBHFOM2N","created_at":"2026-07-05T04:01:34Z"},{"alias_kind":"pith_short_16","alias_value":"2KUCUBHFOM2NZKEU","created_at":"2026-07-05T04:01:34Z"},{"alias_kind":"pith_short_8","alias_value":"2KUCUBHF","created_at":"2026-07-05T04:01:34Z"}],"graph_snapshots":[{"event_id":"sha256:bdf9c628f91f1ac1f5e81d793c041d26d567daa1d8be8b36217e6be3c07f5345","target":"graph","created_at":"2026-07-05T04:01:34Z","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/2203.00286/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Whole word masking (WWM), which masks all subwords corresponding to a word at once, makes a better English BERT model. For the Chinese language, however, there is no subword because each token is an atomic character. The meaning of a word in Chinese is different in that a word is a compositional unit consisting of multiple characters. Such difference motivates us to investigate whether WWM leads to better context understanding ability for Chinese BERT. To achieve this, we introduce two probing tasks related to grammatical error correction and ask pretrained models to revise or insert tokens in","authors_text":"Cong Zhou, Duyu Tang, Enbo Zhao, Linyang Li, Piji Li, Xipeng Qiu, Yong Dai, Zhangyin Feng","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-01T08:24:56Z","title":"\"Is Whole Word Masking Always Better for Chinese BERT?\": Probing on Chinese Grammatical Error Correction"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.00286","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:d117fcb8f3f5f2abd2186e7ad8d23d8323a77dc5da0d2de0e2bdbe1fd58fae40","target":"record","created_at":"2026-07-05T04:01:34Z","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":"4927018ac517f6e2e057cd801d26b8300cd08508aa5e5a34fc3665fa9037691c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-01T08:24:56Z","title_canon_sha256":"461aa9a9908d885b4971e40b6c7901410a5a91a3ec02bcfd8769188b9c3a1551"},"schema_version":"1.0","source":{"id":"2203.00286","kind":"arxiv","version":2}},"canonical_sha256":"d2a82a04e57334dca894ffe1c396e11f772f2b78ab88d9f7ddb1e7ba72d5cd36","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d2a82a04e57334dca894ffe1c396e11f772f2b78ab88d9f7ddb1e7ba72d5cd36","first_computed_at":"2026-07-05T04:01:34.892910Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:01:34.892910Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RrePqslKizztXkVZNfWdgGdiB7yDUoK9HwKCmwNh0/pVkaVejWbRvzGktL/+GeLruFNiKO646tfUVWeoA+v2Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:01:34.893436Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.00286","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d117fcb8f3f5f2abd2186e7ad8d23d8323a77dc5da0d2de0e2bdbe1fd58fae40","sha256:bdf9c628f91f1ac1f5e81d793c041d26d567daa1d8be8b36217e6be3c07f5345"],"state_sha256":"dd5473f4355a7b758ce1eee3c348f93f8131acfd4d617c2fd787ab4cd421b8e5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"70XgiPDVRzp5B49DQ39XGTSe6rJo8SN5pTem68vL2ki3AgjbKHIn9jcAQJA2g0yduBFvkagj7X8+Xq4YP+b9DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T04:12:55.824939Z","bundle_sha256":"367227a6f53607e226c9317ff85d960e17ed3a191b012f70dbc415590ef07b93"}}