{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:OVWLEG6M62RPJ6BHCW55LZP3UE","short_pith_number":"pith:OVWLEG6M","canonical_record":{"source":{"id":"2005.10200","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-20T17:05:57Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"97f821d156cb73dc14d468cea44865003e42e83f5b4b8158dd297bf9cdf5fac4","abstract_canon_sha256":"2ccb5e882b30034ef85bac1bc22a72e7999a4ae27bf3c3967eda9d6917dd19af"},"schema_version":"1.0"},"canonical_sha256":"756cb21bccf6a2f4f82715bbd5e5fba10f325cf668c220b014227cfd98aef912","source":{"kind":"arxiv","id":"2005.10200","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.10200","created_at":"2026-07-05T01:39:58Z"},{"alias_kind":"arxiv_version","alias_value":"2005.10200v2","created_at":"2026-07-05T01:39:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.10200","created_at":"2026-07-05T01:39:58Z"},{"alias_kind":"pith_short_12","alias_value":"OVWLEG6M62RP","created_at":"2026-07-05T01:39:58Z"},{"alias_kind":"pith_short_16","alias_value":"OVWLEG6M62RPJ6BH","created_at":"2026-07-05T01:39:58Z"},{"alias_kind":"pith_short_8","alias_value":"OVWLEG6M","created_at":"2026-07-05T01:39:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:OVWLEG6M62RPJ6BHCW55LZP3UE","target":"record","payload":{"canonical_record":{"source":{"id":"2005.10200","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-20T17:05:57Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"97f821d156cb73dc14d468cea44865003e42e83f5b4b8158dd297bf9cdf5fac4","abstract_canon_sha256":"2ccb5e882b30034ef85bac1bc22a72e7999a4ae27bf3c3967eda9d6917dd19af"},"schema_version":"1.0"},"canonical_sha256":"756cb21bccf6a2f4f82715bbd5e5fba10f325cf668c220b014227cfd98aef912","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:39:58.490329Z","signature_b64":"7myi0ZJghMKn30mategpNaLtHP3wN2vZXO4QXiRvG8vJ6fotBnV31nDf/9ehWOt2yMcMvqH7QHcJpuKSLmGqAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"756cb21bccf6a2f4f82715bbd5e5fba10f325cf668c220b014227cfd98aef912","last_reissued_at":"2026-07-05T01:39:58.489874Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:39:58.489874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2005.10200","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":"2026-07-05T01:39:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KwekVQemg2QiM/7LrrXIS1npWnTTiNftqYIzCYMRZiv4Vg+8s3lwSDoMGgxFAZGehcRzpwMpqWwW2D7NJb5iDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T08:12:20.654182Z"},"content_sha256":"ededcfcb4dc7525597173dafbb7fe29cadaffdd598f3a80eebb76c5ce258419c","schema_version":"1.0","event_id":"sha256:ededcfcb4dc7525597173dafbb7fe29cadaffdd598f3a80eebb76c5ce258419c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:OVWLEG6M62RPJ6BHCW55LZP3UE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"BERTweet: A pre-trained language model for English Tweets","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Anh Tuan Nguyen, Dat Quoc Nguyen, Thanh Vu","submitted_at":"2020-05-20T17:05:57Z","abstract_excerpt":"We present BERTweet, the first public large-scale pre-trained language model for English Tweets. Our BERTweet, having the same architecture as BERT-base (Devlin et al., 2019), is trained using the RoBERTa pre-training procedure (Liu et al., 2019). Experiments show that BERTweet outperforms strong baselines RoBERTa-base and XLM-R-base (Conneau et al., 2020), producing better performance results than the previous state-of-the-art models on three Tweet NLP tasks: Part-of-speech tagging, Named-entity recognition and text classification. We release BERTweet under the MIT License to facilitate futur"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.10200","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/2005.10200/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":"2026-07-05T01:39:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4ofWHO5/6tLbwJnbJrYBsbL179rUKdUqeuEupGjA23K/lV50VdfL4GEgJuAgWZ4qMXX/rIrJr1gzKQ/g3qPFBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T08:12:20.654690Z"},"content_sha256":"870ab33b4c0dcad6ea64d0613055fa33b9b14427b3960e18f929bdaef7c256ae","schema_version":"1.0","event_id":"sha256:870ab33b4c0dcad6ea64d0613055fa33b9b14427b3960e18f929bdaef7c256ae"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OVWLEG6M62RPJ6BHCW55LZP3UE/bundle.json","state_url":"https://pith.science/pith/OVWLEG6M62RPJ6BHCW55LZP3UE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OVWLEG6M62RPJ6BHCW55LZP3UE/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":"2026-08-09T08:12:20Z","links":{"resolver":"https://pith.science/pith/OVWLEG6M62RPJ6BHCW55LZP3UE","bundle":"https://pith.science/pith/OVWLEG6M62RPJ6BHCW55LZP3UE/bundle.json","state":"https://pith.science/pith/OVWLEG6M62RPJ6BHCW55LZP3UE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OVWLEG6M62RPJ6BHCW55LZP3UE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:OVWLEG6M62RPJ6BHCW55LZP3UE","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":"2ccb5e882b30034ef85bac1bc22a72e7999a4ae27bf3c3967eda9d6917dd19af","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-20T17:05:57Z","title_canon_sha256":"97f821d156cb73dc14d468cea44865003e42e83f5b4b8158dd297bf9cdf5fac4"},"schema_version":"1.0","source":{"id":"2005.10200","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2005.10200","created_at":"2026-07-05T01:39:58Z"},{"alias_kind":"arxiv_version","alias_value":"2005.10200v2","created_at":"2026-07-05T01:39:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.10200","created_at":"2026-07-05T01:39:58Z"},{"alias_kind":"pith_short_12","alias_value":"OVWLEG6M62RP","created_at":"2026-07-05T01:39:58Z"},{"alias_kind":"pith_short_16","alias_value":"OVWLEG6M62RPJ6BH","created_at":"2026-07-05T01:39:58Z"},{"alias_kind":"pith_short_8","alias_value":"OVWLEG6M","created_at":"2026-07-05T01:39:58Z"}],"graph_snapshots":[{"event_id":"sha256:870ab33b4c0dcad6ea64d0613055fa33b9b14427b3960e18f929bdaef7c256ae","target":"graph","created_at":"2026-07-05T01:39:58Z","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/2005.10200/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present BERTweet, the first public large-scale pre-trained language model for English Tweets. Our BERTweet, having the same architecture as BERT-base (Devlin et al., 2019), is trained using the RoBERTa pre-training procedure (Liu et al., 2019). Experiments show that BERTweet outperforms strong baselines RoBERTa-base and XLM-R-base (Conneau et al., 2020), producing better performance results than the previous state-of-the-art models on three Tweet NLP tasks: Part-of-speech tagging, Named-entity recognition and text classification. We release BERTweet under the MIT License to facilitate futur","authors_text":"Anh Tuan Nguyen, Dat Quoc Nguyen, Thanh Vu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-20T17:05:57Z","title":"BERTweet: A pre-trained language model for English Tweets"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.10200","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:ededcfcb4dc7525597173dafbb7fe29cadaffdd598f3a80eebb76c5ce258419c","target":"record","created_at":"2026-07-05T01:39:58Z","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":"2ccb5e882b30034ef85bac1bc22a72e7999a4ae27bf3c3967eda9d6917dd19af","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-05-20T17:05:57Z","title_canon_sha256":"97f821d156cb73dc14d468cea44865003e42e83f5b4b8158dd297bf9cdf5fac4"},"schema_version":"1.0","source":{"id":"2005.10200","kind":"arxiv","version":2}},"canonical_sha256":"756cb21bccf6a2f4f82715bbd5e5fba10f325cf668c220b014227cfd98aef912","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"756cb21bccf6a2f4f82715bbd5e5fba10f325cf668c220b014227cfd98aef912","first_computed_at":"2026-07-05T01:39:58.489874Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:39:58.489874Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7myi0ZJghMKn30mategpNaLtHP3wN2vZXO4QXiRvG8vJ6fotBnV31nDf/9ehWOt2yMcMvqH7QHcJpuKSLmGqAw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:39:58.490329Z","signed_message":"canonical_sha256_bytes"},"source_id":"2005.10200","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ededcfcb4dc7525597173dafbb7fe29cadaffdd598f3a80eebb76c5ce258419c","sha256:870ab33b4c0dcad6ea64d0613055fa33b9b14427b3960e18f929bdaef7c256ae"],"state_sha256":"630bc096f4e41db95efab2716b2d808a738619ac0eb8618de514ad9722607b27"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wm6dOmMp6Of3z1z4MQqoaO9jbtqRhVdZeZx33Aba6GaG6N3GqpMYYUpcj9diX3gEi4M+7Mkb0wdS8wcfb7ApCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T08:12:20.658485Z","bundle_sha256":"8562f6c1f4e7de401a9634cb892718bc1e4dd6a0a6dd778c5dc5bfa134598bb6"}}