{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:CTCDNTCAWJWQAAE5INDCIXP7XC","short_pith_number":"pith:CTCDNTCA","canonical_record":{"source":{"id":"2106.00400","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-01T11:20:02Z","cross_cats_sorted":[],"title_canon_sha256":"52d11f4d36a46ed9233e898a42d350045d8116d9d7aa321a8932503d6701f565","abstract_canon_sha256":"38688b5df7e12acb6d0a765c94d7430189ca0aa419192f77e64c0a9886818977"},"schema_version":"1.0"},"canonical_sha256":"14c436cc40b26d00009d4346245dffb8a8bafe55a3732edee46d9efa31ad2e1d","source":{"kind":"arxiv","id":"2106.00400","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.00400","created_at":"2026-07-05T05:41:49Z"},{"alias_kind":"arxiv_version","alias_value":"2106.00400v3","created_at":"2026-07-05T05:41:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.00400","created_at":"2026-07-05T05:41:49Z"},{"alias_kind":"pith_short_12","alias_value":"CTCDNTCAWJWQ","created_at":"2026-07-05T05:41:49Z"},{"alias_kind":"pith_short_16","alias_value":"CTCDNTCAWJWQAAE5","created_at":"2026-07-05T05:41:49Z"},{"alias_kind":"pith_short_8","alias_value":"CTCDNTCA","created_at":"2026-07-05T05:41:49Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:CTCDNTCAWJWQAAE5INDCIXP7XC","target":"record","payload":{"canonical_record":{"source":{"id":"2106.00400","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-01T11:20:02Z","cross_cats_sorted":[],"title_canon_sha256":"52d11f4d36a46ed9233e898a42d350045d8116d9d7aa321a8932503d6701f565","abstract_canon_sha256":"38688b5df7e12acb6d0a765c94d7430189ca0aa419192f77e64c0a9886818977"},"schema_version":"1.0"},"canonical_sha256":"14c436cc40b26d00009d4346245dffb8a8bafe55a3732edee46d9efa31ad2e1d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:41:49.292329Z","signature_b64":"bb4IURQiVoqMf12dMWpjNlbp9J3R+nhv1hnMmwmczML1ZhaGP2c60shgsdE1h33g1iwdQcxyYMrfocvrEdgiBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14c436cc40b26d00009d4346245dffb8a8bafe55a3732edee46d9efa31ad2e1d","last_reissued_at":"2026-07-05T05:41:49.291849Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:41:49.291849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.00400","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:41:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ELTsREmiw8b8Mqm/ED7SQPON4ryw4Tyv3sjlJQ+kDX7P8tGvVi7YD5bcnTfIoqN3iiz6tiJ7YGset+8abtLyAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T23:30:28.446180Z"},"content_sha256":"aa1ab1916c23a42552e941b7ba8b8c9d0594a00caf239d6d079a76ddcdac8f47","schema_version":"1.0","event_id":"sha256:aa1ab1916c23a42552e941b7ba8b8c9d0594a00caf239d6d079a76ddcdac8f47"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:CTCDNTCAWJWQAAE5INDCIXP7XC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Sub-Character Tokenization for Chinese Pretrained Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenglei Si, Fanchao Qi, Maosong Sun, Qun Liu, Xiaozhi Wang, Yasheng Wang, Yingfa Chen, Zhengyan Zhang, Zhiyuan Liu","submitted_at":"2021-06-01T11:20:02Z","abstract_excerpt":"Tokenization is fundamental to pretrained language models (PLMs). Existing tokenization methods for Chinese PLMs typically treat each character as an indivisible token. However, they ignore the unique feature of the Chinese writing system where additional linguistic information exists below the character level, i.e., at the sub-character level. To utilize such information, we propose sub-character (SubChar for short) tokenization. Specifically, we first encode the input text by converting each Chinese character into a short sequence based on its glyph or pronunciation, and then construct the v"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.00400","kind":"arxiv","version":3},"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/2106.00400/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":"2026-07-05T05:41:49Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BtV0lC8kD7NRlYPcdXyGreRd0ldHZKdy2besgeeBMzKCDUsVLKHzL5cMCeDFAQeGI/hpQpPzguxWiyx7YccyBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T23:30:28.446588Z"},"content_sha256":"b333f8e5b156309f89a9d9e4a14235bb951e05abfae8ddf522293d04bbad4dc0","schema_version":"1.0","event_id":"sha256:b333f8e5b156309f89a9d9e4a14235bb951e05abfae8ddf522293d04bbad4dc0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CTCDNTCAWJWQAAE5INDCIXP7XC/bundle.json","state_url":"https://pith.science/pith/CTCDNTCAWJWQAAE5INDCIXP7XC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CTCDNTCAWJWQAAE5INDCIXP7XC/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":"2026-08-05T23:30:28Z","links":{"resolver":"https://pith.science/pith/CTCDNTCAWJWQAAE5INDCIXP7XC","bundle":"https://pith.science/pith/CTCDNTCAWJWQAAE5INDCIXP7XC/bundle.json","state":"https://pith.science/pith/CTCDNTCAWJWQAAE5INDCIXP7XC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CTCDNTCAWJWQAAE5INDCIXP7XC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:CTCDNTCAWJWQAAE5INDCIXP7XC","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":"38688b5df7e12acb6d0a765c94d7430189ca0aa419192f77e64c0a9886818977","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-01T11:20:02Z","title_canon_sha256":"52d11f4d36a46ed9233e898a42d350045d8116d9d7aa321a8932503d6701f565"},"schema_version":"1.0","source":{"id":"2106.00400","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.00400","created_at":"2026-07-05T05:41:49Z"},{"alias_kind":"arxiv_version","alias_value":"2106.00400v3","created_at":"2026-07-05T05:41:49Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.00400","created_at":"2026-07-05T05:41:49Z"},{"alias_kind":"pith_short_12","alias_value":"CTCDNTCAWJWQ","created_at":"2026-07-05T05:41:49Z"},{"alias_kind":"pith_short_16","alias_value":"CTCDNTCAWJWQAAE5","created_at":"2026-07-05T05:41:49Z"},{"alias_kind":"pith_short_8","alias_value":"CTCDNTCA","created_at":"2026-07-05T05:41:49Z"}],"graph_snapshots":[{"event_id":"sha256:b333f8e5b156309f89a9d9e4a14235bb951e05abfae8ddf522293d04bbad4dc0","target":"graph","created_at":"2026-07-05T05:41:49Z","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/2106.00400/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tokenization is fundamental to pretrained language models (PLMs). Existing tokenization methods for Chinese PLMs typically treat each character as an indivisible token. However, they ignore the unique feature of the Chinese writing system where additional linguistic information exists below the character level, i.e., at the sub-character level. To utilize such information, we propose sub-character (SubChar for short) tokenization. Specifically, we first encode the input text by converting each Chinese character into a short sequence based on its glyph or pronunciation, and then construct the v","authors_text":"Chenglei Si, Fanchao Qi, Maosong Sun, Qun Liu, Xiaozhi Wang, Yasheng Wang, Yingfa Chen, Zhengyan Zhang, Zhiyuan Liu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-01T11:20:02Z","title":"Sub-Character Tokenization for Chinese Pretrained Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.00400","kind":"arxiv","version":3},"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:aa1ab1916c23a42552e941b7ba8b8c9d0594a00caf239d6d079a76ddcdac8f47","target":"record","created_at":"2026-07-05T05:41:49Z","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":"38688b5df7e12acb6d0a765c94d7430189ca0aa419192f77e64c0a9886818977","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-06-01T11:20:02Z","title_canon_sha256":"52d11f4d36a46ed9233e898a42d350045d8116d9d7aa321a8932503d6701f565"},"schema_version":"1.0","source":{"id":"2106.00400","kind":"arxiv","version":3}},"canonical_sha256":"14c436cc40b26d00009d4346245dffb8a8bafe55a3732edee46d9efa31ad2e1d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"14c436cc40b26d00009d4346245dffb8a8bafe55a3732edee46d9efa31ad2e1d","first_computed_at":"2026-07-05T05:41:49.291849Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:41:49.291849Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"bb4IURQiVoqMf12dMWpjNlbp9J3R+nhv1hnMmwmczML1ZhaGP2c60shgsdE1h33g1iwdQcxyYMrfocvrEdgiBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:41:49.292329Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.00400","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:aa1ab1916c23a42552e941b7ba8b8c9d0594a00caf239d6d079a76ddcdac8f47","sha256:b333f8e5b156309f89a9d9e4a14235bb951e05abfae8ddf522293d04bbad4dc0"],"state_sha256":"170ba3f1538214074bd4b5a6dbca06f47ba6074089368f3e04aad0f9436430cf"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nq9zQHIRIyRhbmsB1EEW/Piza8OiW7R3Dfo5ebtwJ5oxd4IW6kE32jJRmllmJxZC6DFEPWck7o6QOPrAZ+U2Cg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T23:30:28.449606Z","bundle_sha256":"62f672924065a3dfad4888689c5f22850ef3ef616b14ab0911f2b8118ac554cd"}}