{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OMO5QVJJHSXBZAE7H2FJVWVZUM","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":"7d2c266434d9524ba47043a519bc0b09d177439fbffa6f92335b0d8cda879aa3","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-19T03:48:16Z","title_canon_sha256":"3002bd140616115b1c7562fce184f376b637a47b1e81e35a199954c5a3cf59e3"},"schema_version":"1.0","source":{"id":"2305.11411","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.11411","created_at":"2026-07-05T06:11:46Z"},{"alias_kind":"arxiv_version","alias_value":"2305.11411v1","created_at":"2026-07-05T06:11:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.11411","created_at":"2026-07-05T06:11:46Z"},{"alias_kind":"pith_short_12","alias_value":"OMO5QVJJHSXB","created_at":"2026-07-05T06:11:46Z"},{"alias_kind":"pith_short_16","alias_value":"OMO5QVJJHSXBZAE7","created_at":"2026-07-05T06:11:46Z"},{"alias_kind":"pith_short_8","alias_value":"OMO5QVJJ","created_at":"2026-07-05T06:11:46Z"}],"graph_snapshots":[{"event_id":"sha256:6abe2121a45a4f8598820360781a799586ba1949968e9b15398bd5b1b20f6126","target":"graph","created_at":"2026-07-05T06:11:46Z","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/2305.11411/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"How can speech-to-text translation (ST) perform as well as machine translation (MT)? The key point is to bridge the modality gap between speech and text so that useful MT techniques can be applied to ST. Recently, the approach of representing speech with unsupervised discrete units yields a new way to ease the modality problem. This motivates us to propose Discrete Unit Back-translation (DUB) to answer two questions: (1) Is it better to represent speech with discrete units than with continuous features in direct ST? (2) How much benefit can useful MT techniques bring to ST? With DUB, the back-","authors_text":"Dong Zhang, Mingxuan Wang, Rong Ye, Tom Ko, Yaqian Zhou","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-19T03:48:16Z","title":"DUB: Discrete Unit Back-translation for Speech Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.11411","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":"sha256:04393223b60b6f9648723658455c5e24077b60c5c34bb4fd1531cac1ec058bdf","target":"record","created_at":"2026-07-05T06:11:46Z","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":"7d2c266434d9524ba47043a519bc0b09d177439fbffa6f92335b0d8cda879aa3","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2023-05-19T03:48:16Z","title_canon_sha256":"3002bd140616115b1c7562fce184f376b637a47b1e81e35a199954c5a3cf59e3"},"schema_version":"1.0","source":{"id":"2305.11411","kind":"arxiv","version":1}},"canonical_sha256":"731dd855293cae1c809f3e8a9adab9a3081b1f112f96169d6bad8bafc46fb284","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"731dd855293cae1c809f3e8a9adab9a3081b1f112f96169d6bad8bafc46fb284","first_computed_at":"2026-07-05T06:11:46.754908Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:11:46.754908Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1Ko8tggRjSqG2+wmbggmfAibKyY/lXyaGNqu0pK8tAEaJTDOw9NvlrJnZ14rGHQf0fiTSuUh9GauFBLksCFhBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:11:46.755410Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.11411","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:04393223b60b6f9648723658455c5e24077b60c5c34bb4fd1531cac1ec058bdf","sha256:6abe2121a45a4f8598820360781a799586ba1949968e9b15398bd5b1b20f6126"],"state_sha256":"3765c7aa999ce6725907ff24818070d25597b2017d86326199b22df8e8b231d2"}