{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:CQIT7WBQDOFUVIX5XIC6YWU4O7","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":"f301179ad029c2e1adcf044ddac9810e2d73146007e408678c2554d451383895","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-20T17:14:22Z","title_canon_sha256":"05c963561a6f0331761a3179e51c63d9fae5b98390430a33120c87075b4fa400"},"schema_version":"1.0","source":{"id":"2109.09701","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2109.09701","created_at":"2026-07-05T04:34:47Z"},{"alias_kind":"arxiv_version","alias_value":"2109.09701v3","created_at":"2026-07-05T04:34:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2109.09701","created_at":"2026-07-05T04:34:47Z"},{"alias_kind":"pith_short_12","alias_value":"CQIT7WBQDOFU","created_at":"2026-07-05T04:34:47Z"},{"alias_kind":"pith_short_16","alias_value":"CQIT7WBQDOFUVIX5","created_at":"2026-07-05T04:34:47Z"},{"alias_kind":"pith_short_8","alias_value":"CQIT7WBQ","created_at":"2026-07-05T04:34:47Z"}],"graph_snapshots":[{"event_id":"sha256:c6f3e3a415ce2f2d431a50a77d994668ec7aefea26e95763c7897f9b64275420","target":"graph","created_at":"2026-07-05T04:34:47Z","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/2109.09701/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present BARTpho with two versions, BARTpho-syllable and BARTpho-word, which are the first public large-scale monolingual sequence-to-sequence models pre-trained for Vietnamese. BARTpho uses the \"large\" architecture and the pre-training scheme of the sequence-to-sequence denoising autoencoder BART, thus it is especially suitable for generative NLP tasks. We conduct experiments to compare our BARTpho with its competitor mBART on a downstream task of Vietnamese text summarization and show that: in both automatic and human evaluations, BARTpho outperforms the strong baseline mBART and improves ","authors_text":"Dat Quoc Nguyen, Duong Minh Le, Nguyen Luong Tran","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-20T17:14:22Z","title":"BARTpho: Pre-trained Sequence-to-Sequence Models for Vietnamese"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2109.09701","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":"sha256:751670c46fe4c424b308ab2951eee4abd14f93b6a7123b2077f5b62341fe3ec9","target":"record","created_at":"2026-07-05T04:34:47Z","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":"f301179ad029c2e1adcf044ddac9810e2d73146007e408678c2554d451383895","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-09-20T17:14:22Z","title_canon_sha256":"05c963561a6f0331761a3179e51c63d9fae5b98390430a33120c87075b4fa400"},"schema_version":"1.0","source":{"id":"2109.09701","kind":"arxiv","version":3}},"canonical_sha256":"14113fd8301b8b4aa2fdba05ec5a9c77fa81ac2a8ed6424a3035ba1704565b7b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"14113fd8301b8b4aa2fdba05ec5a9c77fa81ac2a8ed6424a3035ba1704565b7b","first_computed_at":"2026-07-05T04:34:47.232461Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:34:47.232461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"525PLz0YRGWSAJKADuATyjeBkixJmyYtTXkjcoJnd39MNBx4a5ee5ku2pgaOr17IxU/6ar87Ntq6kz6R0cqaDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:34:47.232868Z","signed_message":"canonical_sha256_bytes"},"source_id":"2109.09701","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:751670c46fe4c424b308ab2951eee4abd14f93b6a7123b2077f5b62341fe3ec9","sha256:c6f3e3a415ce2f2d431a50a77d994668ec7aefea26e95763c7897f9b64275420"],"state_sha256":"07cf3d0d979ff2219d301b777a684e1aa631acfcb9e6e0bb6c91619a8818f34a"}