{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:5LRZSGJOVZECWO57SQPM67PXSI","short_pith_number":"pith:5LRZSGJO","canonical_record":{"source":{"id":"2011.01513","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-03T07:13:06Z","cross_cats_sorted":[],"title_canon_sha256":"37b7b7d3c112bf61f257a4afb90bc7f101af2b0b5cb3f7f645d753f1931ff41d","abstract_canon_sha256":"15f200eca56e3c902a19716479ccae36d87c7430f515a5eba64a8c96f17875ba"},"schema_version":"1.0"},"canonical_sha256":"eae399192eae482b3bbf941ecf7df79224d747a5b63a5fee25ef9a5369fa813d","source":{"kind":"arxiv","id":"2011.01513","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.01513","created_at":"2026-07-05T02:40:09Z"},{"alias_kind":"arxiv_version","alias_value":"2011.01513v1","created_at":"2026-07-05T02:40:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.01513","created_at":"2026-07-05T02:40:09Z"},{"alias_kind":"pith_short_12","alias_value":"5LRZSGJOVZEC","created_at":"2026-07-05T02:40:09Z"},{"alias_kind":"pith_short_16","alias_value":"5LRZSGJOVZECWO57","created_at":"2026-07-05T02:40:09Z"},{"alias_kind":"pith_short_8","alias_value":"5LRZSGJO","created_at":"2026-07-05T02:40:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:5LRZSGJOVZECWO57SQPM67PXSI","target":"record","payload":{"canonical_record":{"source":{"id":"2011.01513","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-03T07:13:06Z","cross_cats_sorted":[],"title_canon_sha256":"37b7b7d3c112bf61f257a4afb90bc7f101af2b0b5cb3f7f645d753f1931ff41d","abstract_canon_sha256":"15f200eca56e3c902a19716479ccae36d87c7430f515a5eba64a8c96f17875ba"},"schema_version":"1.0"},"canonical_sha256":"eae399192eae482b3bbf941ecf7df79224d747a5b63a5fee25ef9a5369fa813d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:40:09.414866Z","signature_b64":"0MD3Ze6MrzSmz1mt9+P12VIdGmAPLEylOiYxSR6CRTyq2mc393W17CkjHOhYmdPjbZARAkLCByZ/R9ECg9LXBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eae399192eae482b3bbf941ecf7df79224d747a5b63a5fee25ef9a5369fa813d","last_reissued_at":"2026-07-05T02:40:09.414473Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:40:09.414473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.01513","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":"2026-07-05T02:40:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I6X0vOEoGYLeFSM+n3bNlrchbEMBgAiPbmSccuJBLWTJWiEg/GEZ1iHo2D2mLTcDxQjjJ0yRhFdsufB1LuWuBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:11:02.441871Z"},"content_sha256":"fe2f87ccdb6489a1602e54d5856d084f0e2a592923e5653249c889223111fefa","schema_version":"1.0","event_id":"sha256:fe2f87ccdb6489a1602e54d5856d084f0e2a592923e5653249c889223111fefa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:5LRZSGJOVZECWO57SQPM67PXSI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CharBERT: Character-aware Pre-trained Language Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chenglei Si, Guoping Hu, Shijin Wang, Ting Liu, Wentao Ma, Yiming Cui","submitted_at":"2020-11-03T07:13:06Z","abstract_excerpt":"Most pre-trained language models (PLMs) construct word representations at subword level with Byte-Pair Encoding (BPE) or its variations, by which OOV (out-of-vocab) words are almost avoidable. However, those methods split a word into subword units and make the representation incomplete and fragile. In this paper, we propose a character-aware pre-trained language model named CharBERT improving on the previous methods (such as BERT, RoBERTa) to tackle these problems. We first construct the contextual word embedding for each token from the sequential character representations, then fuse the repre"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.01513","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/2011.01513/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":"2026-07-05T02:40:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"i1lBUgrRDoG6RN9MKfetvuOx03syb5A3k1KQicOk/ptLkYPFhBYUVcYdUMZMykbWshSlnBzBvRO+HWcEY39dCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T09:11:02.442717Z"},"content_sha256":"c3a6d147cfc235c912dca3db4a42bbed696538e43040b0840f49312a15fdf22c","schema_version":"1.0","event_id":"sha256:c3a6d147cfc235c912dca3db4a42bbed696538e43040b0840f49312a15fdf22c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5LRZSGJOVZECWO57SQPM67PXSI/bundle.json","state_url":"https://pith.science/pith/5LRZSGJOVZECWO57SQPM67PXSI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5LRZSGJOVZECWO57SQPM67PXSI/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":"2026-08-06T09:11:02Z","links":{"resolver":"https://pith.science/pith/5LRZSGJOVZECWO57SQPM67PXSI","bundle":"https://pith.science/pith/5LRZSGJOVZECWO57SQPM67PXSI/bundle.json","state":"https://pith.science/pith/5LRZSGJOVZECWO57SQPM67PXSI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5LRZSGJOVZECWO57SQPM67PXSI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:5LRZSGJOVZECWO57SQPM67PXSI","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":"15f200eca56e3c902a19716479ccae36d87c7430f515a5eba64a8c96f17875ba","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-03T07:13:06Z","title_canon_sha256":"37b7b7d3c112bf61f257a4afb90bc7f101af2b0b5cb3f7f645d753f1931ff41d"},"schema_version":"1.0","source":{"id":"2011.01513","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.01513","created_at":"2026-07-05T02:40:09Z"},{"alias_kind":"arxiv_version","alias_value":"2011.01513v1","created_at":"2026-07-05T02:40:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.01513","created_at":"2026-07-05T02:40:09Z"},{"alias_kind":"pith_short_12","alias_value":"5LRZSGJOVZEC","created_at":"2026-07-05T02:40:09Z"},{"alias_kind":"pith_short_16","alias_value":"5LRZSGJOVZECWO57","created_at":"2026-07-05T02:40:09Z"},{"alias_kind":"pith_short_8","alias_value":"5LRZSGJO","created_at":"2026-07-05T02:40:09Z"}],"graph_snapshots":[{"event_id":"sha256:c3a6d147cfc235c912dca3db4a42bbed696538e43040b0840f49312a15fdf22c","target":"graph","created_at":"2026-07-05T02:40:09Z","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/2011.01513/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most pre-trained language models (PLMs) construct word representations at subword level with Byte-Pair Encoding (BPE) or its variations, by which OOV (out-of-vocab) words are almost avoidable. However, those methods split a word into subword units and make the representation incomplete and fragile. In this paper, we propose a character-aware pre-trained language model named CharBERT improving on the previous methods (such as BERT, RoBERTa) to tackle these problems. We first construct the contextual word embedding for each token from the sequential character representations, then fuse the repre","authors_text":"Chenglei Si, Guoping Hu, Shijin Wang, Ting Liu, Wentao Ma, Yiming Cui","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-03T07:13:06Z","title":"CharBERT: Character-aware Pre-trained Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.01513","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:fe2f87ccdb6489a1602e54d5856d084f0e2a592923e5653249c889223111fefa","target":"record","created_at":"2026-07-05T02:40:09Z","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":"15f200eca56e3c902a19716479ccae36d87c7430f515a5eba64a8c96f17875ba","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-11-03T07:13:06Z","title_canon_sha256":"37b7b7d3c112bf61f257a4afb90bc7f101af2b0b5cb3f7f645d753f1931ff41d"},"schema_version":"1.0","source":{"id":"2011.01513","kind":"arxiv","version":1}},"canonical_sha256":"eae399192eae482b3bbf941ecf7df79224d747a5b63a5fee25ef9a5369fa813d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eae399192eae482b3bbf941ecf7df79224d747a5b63a5fee25ef9a5369fa813d","first_computed_at":"2026-07-05T02:40:09.414473Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:40:09.414473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0MD3Ze6MrzSmz1mt9+P12VIdGmAPLEylOiYxSR6CRTyq2mc393W17CkjHOhYmdPjbZARAkLCByZ/R9ECg9LXBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:40:09.414866Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.01513","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fe2f87ccdb6489a1602e54d5856d084f0e2a592923e5653249c889223111fefa","sha256:c3a6d147cfc235c912dca3db4a42bbed696538e43040b0840f49312a15fdf22c"],"state_sha256":"e00fbdd1018650a5437227902b0062d3e4a2ec894d19da6abb605fa9a5f765f8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AVpDwzpdOz3zEpUUc4mrvL0PJOyV476IQwY2QZR5VatMqDqqwSGbphi5Kro7zqXt61F9XLhHl/TTkQvDxr7pDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T09:11:02.450205Z","bundle_sha256":"4761304a48f8e536ae3844fb76966752e6708ddcdf7c7d75a1f938a5a2f48c4c"}}