{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:S77DQWE3L5GLG5B3RLT2DDNTCT","short_pith_number":"pith:S77DQWE3","canonical_record":{"source":{"id":"2004.13922","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-29T02:08:30Z","cross_cats_sorted":[],"title_canon_sha256":"66cfaeffd30c5d206f148ae0a95988858016af1b4f2f05945a72ff7d3a519070","abstract_canon_sha256":"3f3f0dec07cf6c874429942f82207782a0bb54f1afa03329235c79f915758eb7"},"schema_version":"1.0"},"canonical_sha256":"97fe38589b5f4cb3743b8ae7a18db314cb4f7e21edf263456db363e973be9c09","source":{"kind":"arxiv","id":"2004.13922","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.13922","created_at":"2026-07-05T01:58:40Z"},{"alias_kind":"arxiv_version","alias_value":"2004.13922v2","created_at":"2026-07-05T01:58:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.13922","created_at":"2026-07-05T01:58:40Z"},{"alias_kind":"pith_short_12","alias_value":"S77DQWE3L5GL","created_at":"2026-07-05T01:58:40Z"},{"alias_kind":"pith_short_16","alias_value":"S77DQWE3L5GLG5B3","created_at":"2026-07-05T01:58:40Z"},{"alias_kind":"pith_short_8","alias_value":"S77DQWE3","created_at":"2026-07-05T01:58:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:S77DQWE3L5GLG5B3RLT2DDNTCT","target":"record","payload":{"canonical_record":{"source":{"id":"2004.13922","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-29T02:08:30Z","cross_cats_sorted":[],"title_canon_sha256":"66cfaeffd30c5d206f148ae0a95988858016af1b4f2f05945a72ff7d3a519070","abstract_canon_sha256":"3f3f0dec07cf6c874429942f82207782a0bb54f1afa03329235c79f915758eb7"},"schema_version":"1.0"},"canonical_sha256":"97fe38589b5f4cb3743b8ae7a18db314cb4f7e21edf263456db363e973be9c09","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:58:40.920914Z","signature_b64":"AAVpBHPoG/FL+o32KXIktakZE43JMsPxYkHdwMbvFMyoZwBJDkqlY0nyzAbT4U/DrSOH7NePJ4JSnAqCrRU+DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"97fe38589b5f4cb3743b8ae7a18db314cb4f7e21edf263456db363e973be9c09","last_reissued_at":"2026-07-05T01:58:40.920415Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:58:40.920415Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2004.13922","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":"2026-07-05T01:58:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"I/8NX1hxBYVP5ZhFdIQUBM7qvJ5pK+4Sm73seCmYA7C4FC4kw2e5Tl7BcqAdI0vUIbA7gM136BT4tAOCEiKKAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T14:22:19.762542Z"},"content_sha256":"a3d4c33cdda590abbee5161fd0def5bf7c4e8e533cf91716194f98b10671afe1","schema_version":"1.0","event_id":"sha256:a3d4c33cdda590abbee5161fd0def5bf7c4e8e533cf91716194f98b10671afe1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:S77DQWE3L5GLG5B3RLT2DDNTCT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Revisiting Pre-Trained Models for Chinese Natural Language Processing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bing Qin, Guoping Hu, Shijin Wang, Ting Liu, Wanxiang Che, Yiming Cui","submitted_at":"2020-04-29T02:08:30Z","abstract_excerpt":"Bidirectional Encoder Representations from Transformers (BERT) has shown marvelous improvements across various NLP tasks, and consecutive variants have been proposed to further improve the performance of the pre-trained language models. In this paper, we target on revisiting Chinese pre-trained language models to examine their effectiveness in a non-English language and release the Chinese pre-trained language model series to the community. We also propose a simple but effective model called MacBERT, which improves upon RoBERTa in several ways, especially the masking strategy that adopts MLM a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.13922","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/2004.13922/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":"2026-07-05T01:58:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/RLuW7oUgneqzd8ftqQgSI85eIfocQL3VEpoAE07/TM8crhIoJ7hNBWCdA5ddFjDs+vrj3jJ8wNQyclcA1aHBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T14:22:19.763156Z"},"content_sha256":"68418fe72e20f41b5e45deb4af2ecfedc05bcf723659a507f2cc37a1677254e6","schema_version":"1.0","event_id":"sha256:68418fe72e20f41b5e45deb4af2ecfedc05bcf723659a507f2cc37a1677254e6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/S77DQWE3L5GLG5B3RLT2DDNTCT/bundle.json","state_url":"https://pith.science/pith/S77DQWE3L5GLG5B3RLT2DDNTCT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/S77DQWE3L5GLG5B3RLT2DDNTCT/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":"2026-08-10T14:22:19Z","links":{"resolver":"https://pith.science/pith/S77DQWE3L5GLG5B3RLT2DDNTCT","bundle":"https://pith.science/pith/S77DQWE3L5GLG5B3RLT2DDNTCT/bundle.json","state":"https://pith.science/pith/S77DQWE3L5GLG5B3RLT2DDNTCT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/S77DQWE3L5GLG5B3RLT2DDNTCT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:S77DQWE3L5GLG5B3RLT2DDNTCT","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":"3f3f0dec07cf6c874429942f82207782a0bb54f1afa03329235c79f915758eb7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-29T02:08:30Z","title_canon_sha256":"66cfaeffd30c5d206f148ae0a95988858016af1b4f2f05945a72ff7d3a519070"},"schema_version":"1.0","source":{"id":"2004.13922","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2004.13922","created_at":"2026-07-05T01:58:40Z"},{"alias_kind":"arxiv_version","alias_value":"2004.13922v2","created_at":"2026-07-05T01:58:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2004.13922","created_at":"2026-07-05T01:58:40Z"},{"alias_kind":"pith_short_12","alias_value":"S77DQWE3L5GL","created_at":"2026-07-05T01:58:40Z"},{"alias_kind":"pith_short_16","alias_value":"S77DQWE3L5GLG5B3","created_at":"2026-07-05T01:58:40Z"},{"alias_kind":"pith_short_8","alias_value":"S77DQWE3","created_at":"2026-07-05T01:58:40Z"}],"graph_snapshots":[{"event_id":"sha256:68418fe72e20f41b5e45deb4af2ecfedc05bcf723659a507f2cc37a1677254e6","target":"graph","created_at":"2026-07-05T01:58:40Z","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/2004.13922/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Bidirectional Encoder Representations from Transformers (BERT) has shown marvelous improvements across various NLP tasks, and consecutive variants have been proposed to further improve the performance of the pre-trained language models. In this paper, we target on revisiting Chinese pre-trained language models to examine their effectiveness in a non-English language and release the Chinese pre-trained language model series to the community. We also propose a simple but effective model called MacBERT, which improves upon RoBERTa in several ways, especially the masking strategy that adopts MLM a","authors_text":"Bing Qin, Guoping Hu, Shijin Wang, Ting Liu, Wanxiang Che, Yiming Cui","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-29T02:08:30Z","title":"Revisiting Pre-Trained Models for Chinese Natural Language Processing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2004.13922","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:a3d4c33cdda590abbee5161fd0def5bf7c4e8e533cf91716194f98b10671afe1","target":"record","created_at":"2026-07-05T01:58:40Z","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":"3f3f0dec07cf6c874429942f82207782a0bb54f1afa03329235c79f915758eb7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-04-29T02:08:30Z","title_canon_sha256":"66cfaeffd30c5d206f148ae0a95988858016af1b4f2f05945a72ff7d3a519070"},"schema_version":"1.0","source":{"id":"2004.13922","kind":"arxiv","version":2}},"canonical_sha256":"97fe38589b5f4cb3743b8ae7a18db314cb4f7e21edf263456db363e973be9c09","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"97fe38589b5f4cb3743b8ae7a18db314cb4f7e21edf263456db363e973be9c09","first_computed_at":"2026-07-05T01:58:40.920415Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:58:40.920415Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AAVpBHPoG/FL+o32KXIktakZE43JMsPxYkHdwMbvFMyoZwBJDkqlY0nyzAbT4U/DrSOH7NePJ4JSnAqCrRU+DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T01:58:40.920914Z","signed_message":"canonical_sha256_bytes"},"source_id":"2004.13922","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a3d4c33cdda590abbee5161fd0def5bf7c4e8e533cf91716194f98b10671afe1","sha256:68418fe72e20f41b5e45deb4af2ecfedc05bcf723659a507f2cc37a1677254e6"],"state_sha256":"c67ce2518fe7fb32ef99c16b70d12bb6de206d6b18b28bf40aa7d95c1ce16e7d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"draFwe8agTYHTvCuG4itBQItgQbcQiJ/pRunrRR+TQjzKOsW6qZ9NiK78qGGcboWQu/Kk0vGV/aiI+5kRCnyAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T14:22:19.768596Z","bundle_sha256":"62b12abbe4d28eaf9ef4174fad4b6bd787e48bc4b4ebff99583dd25abed02892"}}