{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:57WD6E7YD7KARY76NDZOL77HU3","short_pith_number":"pith:57WD6E7Y","canonical_record":{"source":{"id":"2102.01757","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-02T21:16:25Z","cross_cats_sorted":[],"title_canon_sha256":"c8c1d18fec3cafae5577b84ecaf14cd4d1f9bc3967c5b5c0e6ab43d8f8f59418","abstract_canon_sha256":"317cd84525b2f2a4ca595c7813902a510093eec69b25218e5ddcc096ec7b65f5"},"schema_version":"1.0"},"canonical_sha256":"efec3f13f81fd408e3fe68f2e5ffe7a6e87d77da63209c778c30da8d968bc04d","source":{"kind":"arxiv","id":"2102.01757","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:57WD6E7YD7KARY76NDZOL77HU3","target":"record","payload":{"canonical_record":{"source":{"id":"2102.01757","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-02-02T21:16:25Z","cross_cats_sorted":[],"title_canon_sha256":"c8c1d18fec3cafae5577b84ecaf14cd4d1f9bc3967c5b5c0e6ab43d8f8f59418","abstract_canon_sha256":"317cd84525b2f2a4ca595c7813902a510093eec69b25218e5ddcc096ec7b65f5"},"schema_version":"1.0"},"canonical_sha256":"efec3f13f81fd408e3fe68f2e5ffe7a6e87d77da63209c778c30da8d968bc04d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:49:24.482572Z","signature_b64":"AH1vyjatswh5+QXiXsN6fs0K8CzMp9YAoWsPutzT6hv5FKFArzx208FvrQA/44AAIc6Vj3n27KRQsQznkyjbCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"efec3f13f81fd408e3fe68f2e5ffe7a6e87d77da63209c778c30da8d968bc04d","last_reissued_at":"2026-07-05T02:49:24.482160Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:49:24.482160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2102.01757","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:49:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"7m1+3nZwUpnNGS9gdUHi29dfgrjY2Mv6mTfxkqlKKRmkddRtawG8MxPf1GjbiAfiX/6ZRCwEQTz3OicHMGMSCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:45:58.626696Z"},"content_sha256":"04d9332f6be1517519695cfb354c4d7f1ecd71ee6163087acc08557ee777ab4a","schema_version":"1.0","event_id":"sha256:04d9332f6be1517519695cfb354c4d7f1ecd71ee6163087acc08557ee777ab4a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:57WD6E7YD7KARY76NDZOL77HU3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The Multilingual TEDx Corpus for Speech Recognition and Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Douglas W. Oard, Elizabeth Salesky, Jacob Bremerman, Marco Turchi, Matteo Negri, Matthew Wiesner, Matt Post, Roldano Cattoni","submitted_at":"2021-02-02T21:16:25Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2102.01757","kind":"arxiv","version":2},"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/2102.01757/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":"2026-07-05T02:49:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6cIyqS+kicXMG+6uq8CVzlSQTwkIQgY3wltJc0lzaNNlFv+pOwL1RytOIL/hUlgGzon+ErlOMlJtPMT96/EbCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T22:45:58.627198Z"},"content_sha256":"44995c9e492c7138fdfcb81544cd836338ad8a2dddf865264c995e38d0900c12","schema_version":"1.0","event_id":"sha256:44995c9e492c7138fdfcb81544cd836338ad8a2dddf865264c995e38d0900c12"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/57WD6E7YD7KARY76NDZOL77HU3/bundle.json","state_url":"https://pith.science/pith/57WD6E7YD7KARY76NDZOL77HU3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/57WD6E7YD7KARY76NDZOL77HU3/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":"2026-08-08T22:45:58Z","links":{"resolver":"https://pith.science/pith/57WD6E7YD7KARY76NDZOL77HU3","bundle":"https://pith.science/pith/57WD6E7YD7KARY76NDZOL77HU3/bundle.json","state":"https://pith.science/pith/57WD6E7YD7KARY76NDZOL77HU3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/57WD6E7YD7KARY76NDZOL77HU3/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HKzsctddUnORRwQU7BYIKc4LAWEV9clj7OHb/3BPpND3NckQ07cLtsGMuDBXcPpxM6vGC6rXXJ4HdsG9tnzjDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T22:45:58.631084Z","bundle_sha256":"6fabd1e3a79d0166971f27380d798c5b69ed583c04a917cb50f6a2da23af4be4"}}