{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:2QRRNWV3LQQ3FZ2UUXG6ZJRV35","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":"d2afb16f9f435f891a0efbb569eeabe0f8b45e1473d28a992dbc622882d7588f","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-01T16:31:01Z","title_canon_sha256":"bc30bb878453577c3072dbe052d16ebf51febd04e9e5d4e13c03f7da18404b12"},"schema_version":"1.0","source":{"id":"2303.00628","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.00628","created_at":"2026-07-05T05:48:53Z"},{"alias_kind":"arxiv_version","alias_value":"2303.00628v2","created_at":"2026-07-05T05:48:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.00628","created_at":"2026-07-05T05:48:53Z"},{"alias_kind":"pith_short_12","alias_value":"2QRRNWV3LQQ3","created_at":"2026-07-05T05:48:53Z"},{"alias_kind":"pith_short_16","alias_value":"2QRRNWV3LQQ3FZ2U","created_at":"2026-07-05T05:48:53Z"},{"alias_kind":"pith_short_8","alias_value":"2QRRNWV3","created_at":"2026-07-05T05:48:53Z"}],"graph_snapshots":[{"event_id":"sha256:61e0a7924909adf988e0aa823b3180cce579590da2b821685190864dd2dab590","target":"graph","created_at":"2026-07-05T05:48:53Z","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/2303.00628/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce MuAViC, a multilingual audio-visual corpus for robust speech recognition and robust speech-to-text translation providing 1200 hours of audio-visual speech in 9 languages. It is fully transcribed and covers 6 English-to-X translation as well as 6 X-to-English translation directions. To the best of our knowledge, this is the first open benchmark for audio-visual speech-to-text translation and the largest open benchmark for multilingual audio-visual speech recognition. Our baseline results show that MuAViC is effective for building noise-robust speech recognition and translation mode","authors_text":"Bowen Shi, Changhan Wang, Juan Pino, Mohamed Anwar, Vedanuj Goswami, Wei-Ning Hsu","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-01T16:31:01Z","title":"MuAViC: A Multilingual Audio-Visual Corpus for Robust Speech Recognition and Robust Speech-to-Text Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.00628","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":"sha256:7409dd72f0862a49a92f4292b26f8cfbb2ab21c9024a8233c9499ae584b91b67","target":"record","created_at":"2026-07-05T05:48:53Z","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":"d2afb16f9f435f891a0efbb569eeabe0f8b45e1473d28a992dbc622882d7588f","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-03-01T16:31:01Z","title_canon_sha256":"bc30bb878453577c3072dbe052d16ebf51febd04e9e5d4e13c03f7da18404b12"},"schema_version":"1.0","source":{"id":"2303.00628","kind":"arxiv","version":2}},"canonical_sha256":"d42316dabb5c21b2e754a5cdeca635df6357699890efe6c5ef75bb170f411d32","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d42316dabb5c21b2e754a5cdeca635df6357699890efe6c5ef75bb170f411d32","first_computed_at":"2026-07-05T05:48:53.629116Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:48:53.629116Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"mYIBXeanqWtCM9N+qfH1hOjt9D6w0dSmRvMaT4tIhP6uieSbba9wIKvQICoxaLkVWfacVUE7ESvGo8c2CYSWAg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:48:53.629560Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.00628","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7409dd72f0862a49a92f4292b26f8cfbb2ab21c9024a8233c9499ae584b91b67","sha256:61e0a7924909adf988e0aa823b3180cce579590da2b821685190864dd2dab590"],"state_sha256":"5cbe5c18089b2c42beddaca8e8b8dabd4715b5c1cf448f6edb6339504f78af96"}