{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:UBUGDNCHD2PAFHA2XWQKSFF2GE","short_pith_number":"pith:UBUGDNCH","canonical_record":{"source":{"id":"2106.16038","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-30T13:06:00Z","cross_cats_sorted":[],"title_canon_sha256":"03963ed621b2b7c67372e26842b665201118a529028cf92373856261e1a3ae8e","abstract_canon_sha256":"9300b190fcbb386dc0664e587b8ae78e57971d75fdc5efb1a53af2ca33640b00"},"schema_version":"1.0"},"canonical_sha256":"a06861b4471e9e029c1abda0a914ba310bd9560358de0822ecf5ec8ddbfe786e","source":{"kind":"arxiv","id":"2106.16038","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.16038","created_at":"2026-07-05T02:54:02Z"},{"alias_kind":"arxiv_version","alias_value":"2106.16038v1","created_at":"2026-07-05T02:54:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.16038","created_at":"2026-07-05T02:54:02Z"},{"alias_kind":"pith_short_12","alias_value":"UBUGDNCHD2PA","created_at":"2026-07-05T02:54:02Z"},{"alias_kind":"pith_short_16","alias_value":"UBUGDNCHD2PAFHA2","created_at":"2026-07-05T02:54:02Z"},{"alias_kind":"pith_short_8","alias_value":"UBUGDNCH","created_at":"2026-07-05T02:54:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:UBUGDNCHD2PAFHA2XWQKSFF2GE","target":"record","payload":{"canonical_record":{"source":{"id":"2106.16038","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-30T13:06:00Z","cross_cats_sorted":[],"title_canon_sha256":"03963ed621b2b7c67372e26842b665201118a529028cf92373856261e1a3ae8e","abstract_canon_sha256":"9300b190fcbb386dc0664e587b8ae78e57971d75fdc5efb1a53af2ca33640b00"},"schema_version":"1.0"},"canonical_sha256":"a06861b4471e9e029c1abda0a914ba310bd9560358de0822ecf5ec8ddbfe786e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:54:02.599635Z","signature_b64":"fIlQXDhKNrnVvVXqo7PlRrYZVTXa153PjRfBwnZTLkBwGgrO3i7G3K0dJ+U8Z/jSfaGnOkEiuiuggizyX1H+Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a06861b4471e9e029c1abda0a914ba310bd9560358de0822ecf5ec8ddbfe786e","last_reissued_at":"2026-07-05T02:54:02.599164Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:54:02.599164Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.16038","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":"2026-07-05T02:54:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"122gWS6bP2EImdFIfxgECZ88WniSxfv5/0uMiF2hnnH8mAFC9cLB47IYzrpWd9ZDcGj4ygzP/Jy5SnEMic6eCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:40:23.567572Z"},"content_sha256":"8e8bbb56e9d80b00bb7350ccd7268a67896fec46255cc69422d143d594cf2be1","schema_version":"1.0","event_id":"sha256:8e8bbb56e9d80b00bb7350ccd7268a67896fec46255cc69422d143d594cf2be1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:UBUGDNCHD2PAFHA2XWQKSFF2GE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ChineseBERT: Chinese Pretraining Enhanced by Glyph and Pinyin Information","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fei Wu, Jiwei Li, Qing He, Xiang Ao, Xiaofei Sun, Xiaoya Li, Yuxian Meng, Zijun Sun","submitted_at":"2021-06-30T13:06:00Z","abstract_excerpt":"Recent pretraining models in Chinese neglect two important aspects specific to the Chinese language: glyph and pinyin, which carry significant syntax and semantic information for language understanding. In this work, we propose ChineseBERT, which incorporates both the {\\it glyph} and {\\it pinyin} information of Chinese characters into language model pretraining. The glyph embedding is obtained based on different fonts of a Chinese character, being able to capture character semantics from the visual features, and the pinyin embedding characterizes the pronunciation of Chinese characters, which "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.16038","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/2106.16038/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":"2026-07-05T02:54:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bOHKwV1Idj/u5TTy53g9L+eA5v8mqaRcwcQ/FA52mMIDc/aukDO73Bd48bbzbZyR+kEAr1o0Xd5vNT2ELfZsCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-09T06:40:23.568286Z"},"content_sha256":"a4872ff3bdf2b2dbd048d5914eb571b5961ec5935b6b306e226be5514d3dc339","schema_version":"1.0","event_id":"sha256:a4872ff3bdf2b2dbd048d5914eb571b5961ec5935b6b306e226be5514d3dc339"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UBUGDNCHD2PAFHA2XWQKSFF2GE/bundle.json","state_url":"https://pith.science/pith/UBUGDNCHD2PAFHA2XWQKSFF2GE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UBUGDNCHD2PAFHA2XWQKSFF2GE/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":"2026-07-09T06:40:23Z","links":{"resolver":"https://pith.science/pith/UBUGDNCHD2PAFHA2XWQKSFF2GE","bundle":"https://pith.science/pith/UBUGDNCHD2PAFHA2XWQKSFF2GE/bundle.json","state":"https://pith.science/pith/UBUGDNCHD2PAFHA2XWQKSFF2GE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UBUGDNCHD2PAFHA2XWQKSFF2GE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:UBUGDNCHD2PAFHA2XWQKSFF2GE","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":"9300b190fcbb386dc0664e587b8ae78e57971d75fdc5efb1a53af2ca33640b00","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-30T13:06:00Z","title_canon_sha256":"03963ed621b2b7c67372e26842b665201118a529028cf92373856261e1a3ae8e"},"schema_version":"1.0","source":{"id":"2106.16038","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.16038","created_at":"2026-07-05T02:54:02Z"},{"alias_kind":"arxiv_version","alias_value":"2106.16038v1","created_at":"2026-07-05T02:54:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.16038","created_at":"2026-07-05T02:54:02Z"},{"alias_kind":"pith_short_12","alias_value":"UBUGDNCHD2PA","created_at":"2026-07-05T02:54:02Z"},{"alias_kind":"pith_short_16","alias_value":"UBUGDNCHD2PAFHA2","created_at":"2026-07-05T02:54:02Z"},{"alias_kind":"pith_short_8","alias_value":"UBUGDNCH","created_at":"2026-07-05T02:54:02Z"}],"graph_snapshots":[{"event_id":"sha256:a4872ff3bdf2b2dbd048d5914eb571b5961ec5935b6b306e226be5514d3dc339","target":"graph","created_at":"2026-07-05T02:54:02Z","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/2106.16038/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent pretraining models in Chinese neglect two important aspects specific to the Chinese language: glyph and pinyin, which carry significant syntax and semantic information for language understanding. In this work, we propose ChineseBERT, which incorporates both the {\\it glyph} and {\\it pinyin} information of Chinese characters into language model pretraining. The glyph embedding is obtained based on different fonts of a Chinese character, being able to capture character semantics from the visual features, and the pinyin embedding characterizes the pronunciation of Chinese characters, which ","authors_text":"Fei Wu, Jiwei Li, Qing He, Xiang Ao, Xiaofei Sun, Xiaoya Li, Yuxian Meng, Zijun Sun","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-30T13:06:00Z","title":"ChineseBERT: Chinese Pretraining Enhanced by Glyph and Pinyin Information"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.16038","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":"sha256:8e8bbb56e9d80b00bb7350ccd7268a67896fec46255cc69422d143d594cf2be1","target":"record","created_at":"2026-07-05T02:54:02Z","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":"9300b190fcbb386dc0664e587b8ae78e57971d75fdc5efb1a53af2ca33640b00","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-30T13:06:00Z","title_canon_sha256":"03963ed621b2b7c67372e26842b665201118a529028cf92373856261e1a3ae8e"},"schema_version":"1.0","source":{"id":"2106.16038","kind":"arxiv","version":1}},"canonical_sha256":"a06861b4471e9e029c1abda0a914ba310bd9560358de0822ecf5ec8ddbfe786e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a06861b4471e9e029c1abda0a914ba310bd9560358de0822ecf5ec8ddbfe786e","first_computed_at":"2026-07-05T02:54:02.599164Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:54:02.599164Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"fIlQXDhKNrnVvVXqo7PlRrYZVTXa153PjRfBwnZTLkBwGgrO3i7G3K0dJ+U8Z/jSfaGnOkEiuiuggizyX1H+Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:54:02.599635Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.16038","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e8bbb56e9d80b00bb7350ccd7268a67896fec46255cc69422d143d594cf2be1","sha256:a4872ff3bdf2b2dbd048d5914eb571b5961ec5935b6b306e226be5514d3dc339"],"state_sha256":"6b147eabe7d3bd54497f81a38578e4ceac7990c34172b69ff3ad56e1f27d49fd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8eSb/lcCghIBChGahhp3B8B3pRtzJlJham+YzDP0RHdsDggXOwyPK6zeJ0VmROeD1Xm9U2qQ2x1jcggcg4MCDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-09T06:40:23.572022Z","bundle_sha256":"bc1380460a33cce3392aa1e2c61d44a2e83fdbdfa81b5522f7ea2d996d413a58"}}