{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:FZZADBUAQAK5QXH723IYWUEC7O","short_pith_number":"pith:FZZADBUA","canonical_record":{"source":{"id":"2110.12199","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-23T11:42:01Z","cross_cats_sorted":[],"title_canon_sha256":"dddcaa6f04033d89583cea13319c780495e40df836be6fe6575af0340e14020a","abstract_canon_sha256":"4d1f0753ed280bfe8f2c2da3ac8481ced98a77eef53c20398505ae58daa4a478"},"schema_version":"1.0"},"canonical_sha256":"2e720186808015d85cffd6d18b5082fb852ff890ee3b058508a7ce0e8a67b17c","source":{"kind":"arxiv","id":"2110.12199","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.12199","created_at":"2026-07-05T03:25:01Z"},{"alias_kind":"arxiv_version","alias_value":"2110.12199v1","created_at":"2026-07-05T03:25:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.12199","created_at":"2026-07-05T03:25:01Z"},{"alias_kind":"pith_short_12","alias_value":"FZZADBUAQAK5","created_at":"2026-07-05T03:25:01Z"},{"alias_kind":"pith_short_16","alias_value":"FZZADBUAQAK5QXH7","created_at":"2026-07-05T03:25:01Z"},{"alias_kind":"pith_short_8","alias_value":"FZZADBUA","created_at":"2026-07-05T03:25:01Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:FZZADBUAQAK5QXH723IYWUEC7O","target":"record","payload":{"canonical_record":{"source":{"id":"2110.12199","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-23T11:42:01Z","cross_cats_sorted":[],"title_canon_sha256":"dddcaa6f04033d89583cea13319c780495e40df836be6fe6575af0340e14020a","abstract_canon_sha256":"4d1f0753ed280bfe8f2c2da3ac8481ced98a77eef53c20398505ae58daa4a478"},"schema_version":"1.0"},"canonical_sha256":"2e720186808015d85cffd6d18b5082fb852ff890ee3b058508a7ce0e8a67b17c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:25:01.403238Z","signature_b64":"AAqyic5xO+H2fWs2BDf8p4Duo3l/qHZIDrGb6pfrEfium+lwQE82RucKBDEjSGcI0reHzayIH8W0L3CsOQoaBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e720186808015d85cffd6d18b5082fb852ff890ee3b058508a7ce0e8a67b17c","last_reissued_at":"2026-07-05T03:25:01.402829Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:25:01.402829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.12199","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":"2026-07-05T03:25:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LeqcYQxuN+DYBrgRwOKDfQQS3A5PWxltd2GvOOJ6msHIUAnB2MO8tbfl9wQde3NUicv0GUzGC4gpvvtZy5czBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T23:00:15.756825Z"},"content_sha256":"efa7b6732e3e5e46a9c1a5728b7711333870ee841bbfbb7495f8eab6f6117bbf","schema_version":"1.0","event_id":"sha256:efa7b6732e3e5e46a9c1a5728b7711333870ee841bbfbb7495f8eab6f6117bbf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:FZZADBUAQAK5QXH723IYWUEC7O","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"PhoMT: A High-Quality and Large-Scale Benchmark Dataset for Vietnamese-English Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dat Quoc Nguyen, Linh The Nguyen, Long Doan, Nguyen Luong Tran, Thai Hoang","submitted_at":"2021-10-23T11:42:01Z","abstract_excerpt":"We introduce a high-quality and large-scale Vietnamese-English parallel dataset of 3.02M sentence pairs, which is 2.9M pairs larger than the benchmark Vietnamese-English machine translation corpus IWSLT15. We conduct experiments comparing strong neural baselines and well-known automatic translation engines on our dataset and find that in both automatic and human evaluations: the best performance is obtained by fine-tuning the pre-trained sequence-to-sequence denoising auto-encoder mBART. To our best knowledge, this is the first large-scale Vietnamese-English machine translation study. We hope "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.12199","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/2110.12199/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":"2026-07-05T03:25:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pnPSGV9VltES/hlnp6soXTUaoUHL3mPCcHAZVNEjCuA5GfQZ2Wr6iGV/oeh4ZIazY7jwf1ZDbM3DNHA/ixWIDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-22T23:00:15.757197Z"},"content_sha256":"23850ec38bd0b66ae0091440472ebe19f5c9f4c59db4dbc7a5b2c5406f04e723","schema_version":"1.0","event_id":"sha256:23850ec38bd0b66ae0091440472ebe19f5c9f4c59db4dbc7a5b2c5406f04e723"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FZZADBUAQAK5QXH723IYWUEC7O/bundle.json","state_url":"https://pith.science/pith/FZZADBUAQAK5QXH723IYWUEC7O/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FZZADBUAQAK5QXH723IYWUEC7O/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":"2026-08-22T23:00:15Z","links":{"resolver":"https://pith.science/pith/FZZADBUAQAK5QXH723IYWUEC7O","bundle":"https://pith.science/pith/FZZADBUAQAK5QXH723IYWUEC7O/bundle.json","state":"https://pith.science/pith/FZZADBUAQAK5QXH723IYWUEC7O/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FZZADBUAQAK5QXH723IYWUEC7O/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:FZZADBUAQAK5QXH723IYWUEC7O","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":"4d1f0753ed280bfe8f2c2da3ac8481ced98a77eef53c20398505ae58daa4a478","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-23T11:42:01Z","title_canon_sha256":"dddcaa6f04033d89583cea13319c780495e40df836be6fe6575af0340e14020a"},"schema_version":"1.0","source":{"id":"2110.12199","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.12199","created_at":"2026-07-05T03:25:01Z"},{"alias_kind":"arxiv_version","alias_value":"2110.12199v1","created_at":"2026-07-05T03:25:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.12199","created_at":"2026-07-05T03:25:01Z"},{"alias_kind":"pith_short_12","alias_value":"FZZADBUAQAK5","created_at":"2026-07-05T03:25:01Z"},{"alias_kind":"pith_short_16","alias_value":"FZZADBUAQAK5QXH7","created_at":"2026-07-05T03:25:01Z"},{"alias_kind":"pith_short_8","alias_value":"FZZADBUA","created_at":"2026-07-05T03:25:01Z"}],"graph_snapshots":[{"event_id":"sha256:23850ec38bd0b66ae0091440472ebe19f5c9f4c59db4dbc7a5b2c5406f04e723","target":"graph","created_at":"2026-07-05T03:25:01Z","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/2110.12199/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce a high-quality and large-scale Vietnamese-English parallel dataset of 3.02M sentence pairs, which is 2.9M pairs larger than the benchmark Vietnamese-English machine translation corpus IWSLT15. We conduct experiments comparing strong neural baselines and well-known automatic translation engines on our dataset and find that in both automatic and human evaluations: the best performance is obtained by fine-tuning the pre-trained sequence-to-sequence denoising auto-encoder mBART. To our best knowledge, this is the first large-scale Vietnamese-English machine translation study. We hope ","authors_text":"Dat Quoc Nguyen, Linh The Nguyen, Long Doan, Nguyen Luong Tran, Thai Hoang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-23T11:42:01Z","title":"PhoMT: A High-Quality and Large-Scale Benchmark Dataset for Vietnamese-English Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.12199","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:efa7b6732e3e5e46a9c1a5728b7711333870ee841bbfbb7495f8eab6f6117bbf","target":"record","created_at":"2026-07-05T03:25:01Z","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":"4d1f0753ed280bfe8f2c2da3ac8481ced98a77eef53c20398505ae58daa4a478","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-23T11:42:01Z","title_canon_sha256":"dddcaa6f04033d89583cea13319c780495e40df836be6fe6575af0340e14020a"},"schema_version":"1.0","source":{"id":"2110.12199","kind":"arxiv","version":1}},"canonical_sha256":"2e720186808015d85cffd6d18b5082fb852ff890ee3b058508a7ce0e8a67b17c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2e720186808015d85cffd6d18b5082fb852ff890ee3b058508a7ce0e8a67b17c","first_computed_at":"2026-07-05T03:25:01.402829Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:25:01.402829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AAqyic5xO+H2fWs2BDf8p4Duo3l/qHZIDrGb6pfrEfium+lwQE82RucKBDEjSGcI0reHzayIH8W0L3CsOQoaBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:25:01.403238Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.12199","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:efa7b6732e3e5e46a9c1a5728b7711333870ee841bbfbb7495f8eab6f6117bbf","sha256:23850ec38bd0b66ae0091440472ebe19f5c9f4c59db4dbc7a5b2c5406f04e723"],"state_sha256":"cb40bcf4ba4693934ec0384885bbadde93c01dfe72d960f910b5d62fa47fd6a3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jmJDVed9UXr3OCdrx2YapFSAFLDCL+n3OTSawjo0TDoxSvH209ifjUzCtlJiy6eHIhtX5rOHxdggdOQlRg0gDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-22T23:00:15.759765Z","bundle_sha256":"06185ef083376929073716f57dd8ab0ccb551bb7eae8703b1932c9b429987518"}}