{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:WANURUME7IJNKYYZZ7NN6G475A","short_pith_number":"pith:WANURUME","canonical_record":{"source":{"id":"2003.00744","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-03-02T10:21:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"342dddb41ca7818d4e75b204d87baa3e1dd0cd2a73b3fb4fde5bcdf55f37aae8","abstract_canon_sha256":"9917a28aa1b6a4888b10394f20d2a6cfbf25614b7971792f47556c4aecd17f69"},"schema_version":"1.0"},"canonical_sha256":"b01b48d184fa12d56319cfdadf1b9fe807cfc9c827d49e4cd28561481b5f25c2","source":{"kind":"arxiv","id":"2003.00744","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.00744","created_at":"2026-07-05T01:39:56Z"},{"alias_kind":"arxiv_version","alias_value":"2003.00744v3","created_at":"2026-07-05T01:39:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.00744","created_at":"2026-07-05T01:39:56Z"},{"alias_kind":"pith_short_12","alias_value":"WANURUME7IJN","created_at":"2026-07-05T01:39:56Z"},{"alias_kind":"pith_short_16","alias_value":"WANURUME7IJNKYYZ","created_at":"2026-07-05T01:39:56Z"},{"alias_kind":"pith_short_8","alias_value":"WANURUME","created_at":"2026-07-05T01:39:56Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:WANURUME7IJNKYYZZ7NN6G475A","target":"record","payload":{"canonical_record":{"source":{"id":"2003.00744","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-03-02T10:21:17Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"342dddb41ca7818d4e75b204d87baa3e1dd0cd2a73b3fb4fde5bcdf55f37aae8","abstract_canon_sha256":"9917a28aa1b6a4888b10394f20d2a6cfbf25614b7971792f47556c4aecd17f69"},"schema_version":"1.0"},"canonical_sha256":"b01b48d184fa12d56319cfdadf1b9fe807cfc9c827d49e4cd28561481b5f25c2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:39:56.416101Z","signature_b64":"Wtq3FAcH3U+6udkMDrCwIoEcH0QL9/UmlgqKx0B/2S8+EWtlkPk9wF2CttHrQtn20baVL+qdQfHYUOnRd4ohCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b01b48d184fa12d56319cfdadf1b9fe807cfc9c827d49e4cd28561481b5f25c2","last_reissued_at":"2026-07-05T01:39:56.415646Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:39:56.415646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2003.00744","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":"2026-07-05T01:39:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZnfoG0Xa4aoiFaNLFjBX9CIpB8qqat98y5BY/FaXyKXusZgWBsxVADfLW0gPyvyF61t+uaYtYt8qiBuUnCqvBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T11:13:00.627436Z"},"content_sha256":"277b6e378324644edfe69ae11e2ac32d1e7b1a43bec01151c761ff438d769a55","schema_version":"1.0","event_id":"sha256:277b6e378324644edfe69ae11e2ac32d1e7b1a43bec01151c761ff438d769a55"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:WANURUME7IJNKYYZZ7NN6G475A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PhoBERT: Pre-trained language models for Vietnamese","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Anh Tuan Nguyen, Dat Quoc Nguyen","submitted_at":"2020-03-02T10:21:17Z","abstract_excerpt":"We present PhoBERT with two versions, PhoBERT-base and PhoBERT-large, the first public large-scale monolingual language models pre-trained for Vietnamese. Experimental results show that PhoBERT consistently outperforms the recent best pre-trained multilingual model XLM-R (Conneau et al., 2020) and improves the state-of-the-art in multiple Vietnamese-specific NLP tasks including Part-of-speech tagging, Dependency parsing, Named-entity recognition and Natural language inference. We release PhoBERT to facilitate future research and downstream applications for Vietnamese NLP. Our PhoBERT models ar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.00744","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/2003.00744/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":"2026-07-05T01:39:56Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kc6ZvCWplpTg9tZcmCyOLQTRr4+7mAZC7YmbQwbBTdROgfJDjdYKqH4tD6Fqu/09Kgca1K+mScgXsWjrV9IaAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T11:13:00.628553Z"},"content_sha256":"24437bf3d3572b4d34bf570ff44a9cf2893d5c3c8c60298253ff7a9511261596","schema_version":"1.0","event_id":"sha256:24437bf3d3572b4d34bf570ff44a9cf2893d5c3c8c60298253ff7a9511261596"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WANURUME7IJNKYYZZ7NN6G475A/bundle.json","state_url":"https://pith.science/pith/WANURUME7IJNKYYZZ7NN6G475A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WANURUME7IJNKYYZZ7NN6G475A/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":"2026-08-18T11:13:00Z","links":{"resolver":"https://pith.science/pith/WANURUME7IJNKYYZZ7NN6G475A","bundle":"https://pith.science/pith/WANURUME7IJNKYYZZ7NN6G475A/bundle.json","state":"https://pith.science/pith/WANURUME7IJNKYYZZ7NN6G475A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WANURUME7IJNKYYZZ7NN6G475A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:WANURUME7IJNKYYZZ7NN6G475A","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":"9917a28aa1b6a4888b10394f20d2a6cfbf25614b7971792f47556c4aecd17f69","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-03-02T10:21:17Z","title_canon_sha256":"342dddb41ca7818d4e75b204d87baa3e1dd0cd2a73b3fb4fde5bcdf55f37aae8"},"schema_version":"1.0","source":{"id":"2003.00744","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.00744","created_at":"2026-07-05T01:39:56Z"},{"alias_kind":"arxiv_version","alias_value":"2003.00744v3","created_at":"2026-07-05T01:39:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.00744","created_at":"2026-07-05T01:39:56Z"},{"alias_kind":"pith_short_12","alias_value":"WANURUME7IJN","created_at":"2026-07-05T01:39:56Z"},{"alias_kind":"pith_short_16","alias_value":"WANURUME7IJNKYYZ","created_at":"2026-07-05T01:39:56Z"},{"alias_kind":"pith_short_8","alias_value":"WANURUME","created_at":"2026-07-05T01:39:56Z"}],"graph_snapshots":[{"event_id":"sha256:24437bf3d3572b4d34bf570ff44a9cf2893d5c3c8c60298253ff7a9511261596","target":"graph","created_at":"2026-07-05T01:39:56Z","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/2003.00744/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present PhoBERT with two versions, PhoBERT-base and PhoBERT-large, the first public large-scale monolingual language models pre-trained for Vietnamese. Experimental results show that PhoBERT consistently outperforms the recent best pre-trained multilingual model XLM-R (Conneau et al., 2020) and improves the state-of-the-art in multiple Vietnamese-specific NLP tasks including Part-of-speech tagging, Dependency parsing, Named-entity recognition and Natural language inference. We release PhoBERT to facilitate future research and downstream applications for Vietnamese NLP. Our PhoBERT models ar","authors_text":"Anh Tuan Nguyen, Dat Quoc Nguyen","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-03-02T10:21:17Z","title":"PhoBERT: Pre-trained language models for Vietnamese"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.00744","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":"sha256:277b6e378324644edfe69ae11e2ac32d1e7b1a43bec01151c761ff438d769a55","target":"record","created_at":"2026-07-05T01:39:56Z","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":"9917a28aa1b6a4888b10394f20d2a6cfbf25614b7971792f47556c4aecd17f69","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-03-02T10:21:17Z","title_canon_sha256":"342dddb41ca7818d4e75b204d87baa3e1dd0cd2a73b3fb4fde5bcdf55f37aae8"},"schema_version":"1.0","source":{"id":"2003.00744","kind":"arxiv","version":3}},"canonical_sha256":"b01b48d184fa12d56319cfdadf1b9fe807cfc9c827d49e4cd28561481b5f25c2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b01b48d184fa12d56319cfdadf1b9fe807cfc9c827d49e4cd28561481b5f25c2","first_computed_at":"2026-07-05T01:39:56.415646Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:39:56.415646Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Wtq3FAcH3U+6udkMDrCwIoEcH0QL9/UmlgqKx0B/2S8+EWtlkPk9wF2CttHrQtn20baVL+qdQfHYUOnRd4ohCg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:39:56.416101Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.00744","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:277b6e378324644edfe69ae11e2ac32d1e7b1a43bec01151c761ff438d769a55","sha256:24437bf3d3572b4d34bf570ff44a9cf2893d5c3c8c60298253ff7a9511261596"],"state_sha256":"2d6a86d2953cc39d51b11cdd3bd91905c4af7bc819ff30a40c72218aeb8de884"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PjtEyrq3kprd9sGM1dLmVWBlmSjZz1qhoAl8tantjFrCodERGQno7POeoOZykNoB75JHPoNmnH/grPCWcHkLCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T11:13:00.636255Z","bundle_sha256":"4c9e3165ea4a091f36de529a31e24d5b39c861cb284427e70ba6258af4fd5a91"}}