{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:57WD6E7YD7KARY76NDZOL77HU3","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":"317cd84525b2f2a4ca595c7813902a510093eec69b25218e5ddcc096ec7b65f5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-02T21:16:25Z","title_canon_sha256":"c8c1d18fec3cafae5577b84ecaf14cd4d1f9bc3967c5b5c0e6ab43d8f8f59418"},"schema_version":"1.0","source":{"id":"2102.01757","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2102.01757","created_at":"2026-07-05T02:49:24Z"},{"alias_kind":"arxiv_version","alias_value":"2102.01757v2","created_at":"2026-07-05T02:49:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2102.01757","created_at":"2026-07-05T02:49:24Z"},{"alias_kind":"pith_short_12","alias_value":"57WD6E7YD7KA","created_at":"2026-07-05T02:49:24Z"},{"alias_kind":"pith_short_16","alias_value":"57WD6E7YD7KARY76","created_at":"2026-07-05T02:49:24Z"},{"alias_kind":"pith_short_8","alias_value":"57WD6E7Y","created_at":"2026-07-05T02:49:24Z"}],"graph_snapshots":[{"event_id":"sha256:44995c9e492c7138fdfcb81544cd836338ad8a2dddf865264c995e38d0900c12","target":"graph","created_at":"2026-07-05T02:49:24Z","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/2102.01757/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present the Multilingual TEDx corpus, built to support speech recognition (ASR) and speech translation (ST) research across many non-English source languages. The corpus is a collection of audio recordings from TEDx talks in 8 source languages. We segment transcripts into sentences and align them to the source-language audio and target-language translations. The corpus is released along with open-sourced code enabling extension to new talks and languages as they become available. Our corpus creation methodology can be applied to more languages than previous work, and creates multi-way paral","authors_text":"Douglas W. Oard, Elizabeth Salesky, Jacob Bremerman, Marco Turchi, Matteo Negri, Matthew Wiesner, Matt Post, Roldano Cattoni","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-02T21:16:25Z","title":"The Multilingual TEDx Corpus for Speech Recognition and Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.01757","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":"sha256:04d9332f6be1517519695cfb354c4d7f1ecd71ee6163087acc08557ee777ab4a","target":"record","created_at":"2026-07-05T02:49:24Z","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":"317cd84525b2f2a4ca595c7813902a510093eec69b25218e5ddcc096ec7b65f5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-02T21:16:25Z","title_canon_sha256":"c8c1d18fec3cafae5577b84ecaf14cd4d1f9bc3967c5b5c0e6ab43d8f8f59418"},"schema_version":"1.0","source":{"id":"2102.01757","kind":"arxiv","version":2}},"canonical_sha256":"efec3f13f81fd408e3fe68f2e5ffe7a6e87d77da63209c778c30da8d968bc04d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"efec3f13f81fd408e3fe68f2e5ffe7a6e87d77da63209c778c30da8d968bc04d","first_computed_at":"2026-07-05T02:49:24.482160Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:49:24.482160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AH1vyjatswh5+QXiXsN6fs0K8CzMp9YAoWsPutzT6hv5FKFArzx208FvrQA/44AAIc6Vj3n27KRQsQznkyjbCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:49:24.482572Z","signed_message":"canonical_sha256_bytes"},"source_id":"2102.01757","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:04d9332f6be1517519695cfb354c4d7f1ecd71ee6163087acc08557ee777ab4a","sha256:44995c9e492c7138fdfcb81544cd836338ad8a2dddf865264c995e38d0900c12"],"state_sha256":"c8bba4748cd2f497347f4a12b057d65d64e1ac3ccb463acebf0b253d9a72f40c"}