{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:Y7Y46QWLVE2EVO7MUUDANLKKQ7","short_pith_number":"pith:Y7Y46QWL","canonical_record":{"source":{"id":"2002.01320","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-04T14:35:28Z","cross_cats_sorted":[],"title_canon_sha256":"6ec1bdc269b557224a3335d086db4f3370b2423a17a4921a2371a8bf40989e2b","abstract_canon_sha256":"f8ed6e6163618aa772129b08ed73799c40b4856c00f8763ce5534131eb9e9b2f"},"schema_version":"1.0"},"canonical_sha256":"c7f1cf42cba9344abbeca50606ad4a87fbab7a6e8779ab76569636efeec43739","source":{"kind":"arxiv","id":"2002.01320","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.01320","created_at":"2026-07-05T01:09:03Z"},{"alias_kind":"arxiv_version","alias_value":"2002.01320v2","created_at":"2026-07-05T01:09:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.01320","created_at":"2026-07-05T01:09:03Z"},{"alias_kind":"pith_short_12","alias_value":"Y7Y46QWLVE2E","created_at":"2026-07-05T01:09:03Z"},{"alias_kind":"pith_short_16","alias_value":"Y7Y46QWLVE2EVO7M","created_at":"2026-07-05T01:09:03Z"},{"alias_kind":"pith_short_8","alias_value":"Y7Y46QWL","created_at":"2026-07-05T01:09:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:Y7Y46QWLVE2EVO7MUUDANLKKQ7","target":"record","payload":{"canonical_record":{"source":{"id":"2002.01320","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-04T14:35:28Z","cross_cats_sorted":[],"title_canon_sha256":"6ec1bdc269b557224a3335d086db4f3370b2423a17a4921a2371a8bf40989e2b","abstract_canon_sha256":"f8ed6e6163618aa772129b08ed73799c40b4856c00f8763ce5534131eb9e9b2f"},"schema_version":"1.0"},"canonical_sha256":"c7f1cf42cba9344abbeca50606ad4a87fbab7a6e8779ab76569636efeec43739","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:09:03.322621Z","signature_b64":"Wj6FJs/NCCAS0Xchr1cvhW7RnriXDFiHGsrsjAkVMk3FYw0bfRVUsRczlzhqxWGKcTocaB4KkW5ks5wI7LVeBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c7f1cf42cba9344abbeca50606ad4a87fbab7a6e8779ab76569636efeec43739","last_reissued_at":"2026-07-05T01:09:03.322148Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:09:03.322148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2002.01320","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":"2026-07-05T01:09:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WQlnWKlmLGFfy2L4E73ONbjZQiid7z0e6LO0sMuVhzqhD7pLOoaRC+QnldaIOdQUDFKsLxOEOrhHtmxj4xUsAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T20:15:49.037170Z"},"content_sha256":"178b01d7770caeb630ad9ed03897dec8b5aa5c75e3259fabe8d14af7eaded4bd","schema_version":"1.0","event_id":"sha256:178b01d7770caeb630ad9ed03897dec8b5aa5c75e3259fabe8d14af7eaded4bd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:Y7Y46QWLVE2EVO7MUUDANLKKQ7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CoVoST: A Diverse Multilingual Speech-To-Text Translation Corpus","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Anne Wu, Changhan Wang, Jiatao Gu, Juan Pino","submitted_at":"2020-02-04T14:35:28Z","abstract_excerpt":"Spoken language translation has recently witnessed a resurgence in popularity, thanks to the development of end-to-end models and the creation of new corpora, such as Augmented LibriSpeech and MuST-C. Existing datasets involve language pairs with English as a source language, involve very specific domains or are low resource. We introduce CoVoST, a multilingual speech-to-text translation corpus from 11 languages into English, diversified with over 11,000 speakers and over 60 accents. We describe the dataset creation methodology and provide empirical evidence of the quality of the data. We also"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.01320","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/2002.01320/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":"2026-07-05T01:09:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"f6NF04HJp2FZLf/qLewquXw3RmNl/6NSckYCnC/ulzxGzmCCQVLUEkcWr3Eyod/VZqGYi1fAVWFYOqHnAFApAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T20:15:49.038101Z"},"content_sha256":"a5ff7bdf33f77a3009828e4b25ae9971b034254e4b2b41dc50ce64673c0473be","schema_version":"1.0","event_id":"sha256:a5ff7bdf33f77a3009828e4b25ae9971b034254e4b2b41dc50ce64673c0473be"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Y7Y46QWLVE2EVO7MUUDANLKKQ7/bundle.json","state_url":"https://pith.science/pith/Y7Y46QWLVE2EVO7MUUDANLKKQ7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Y7Y46QWLVE2EVO7MUUDANLKKQ7/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":"2026-08-16T20:15:49Z","links":{"resolver":"https://pith.science/pith/Y7Y46QWLVE2EVO7MUUDANLKKQ7","bundle":"https://pith.science/pith/Y7Y46QWLVE2EVO7MUUDANLKKQ7/bundle.json","state":"https://pith.science/pith/Y7Y46QWLVE2EVO7MUUDANLKKQ7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Y7Y46QWLVE2EVO7MUUDANLKKQ7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:Y7Y46QWLVE2EVO7MUUDANLKKQ7","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":"f8ed6e6163618aa772129b08ed73799c40b4856c00f8763ce5534131eb9e9b2f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-04T14:35:28Z","title_canon_sha256":"6ec1bdc269b557224a3335d086db4f3370b2423a17a4921a2371a8bf40989e2b"},"schema_version":"1.0","source":{"id":"2002.01320","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2002.01320","created_at":"2026-07-05T01:09:03Z"},{"alias_kind":"arxiv_version","alias_value":"2002.01320v2","created_at":"2026-07-05T01:09:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2002.01320","created_at":"2026-07-05T01:09:03Z"},{"alias_kind":"pith_short_12","alias_value":"Y7Y46QWLVE2E","created_at":"2026-07-05T01:09:03Z"},{"alias_kind":"pith_short_16","alias_value":"Y7Y46QWLVE2EVO7M","created_at":"2026-07-05T01:09:03Z"},{"alias_kind":"pith_short_8","alias_value":"Y7Y46QWL","created_at":"2026-07-05T01:09:03Z"}],"graph_snapshots":[{"event_id":"sha256:a5ff7bdf33f77a3009828e4b25ae9971b034254e4b2b41dc50ce64673c0473be","target":"graph","created_at":"2026-07-05T01:09:03Z","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/2002.01320/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spoken language translation has recently witnessed a resurgence in popularity, thanks to the development of end-to-end models and the creation of new corpora, such as Augmented LibriSpeech and MuST-C. Existing datasets involve language pairs with English as a source language, involve very specific domains or are low resource. We introduce CoVoST, a multilingual speech-to-text translation corpus from 11 languages into English, diversified with over 11,000 speakers and over 60 accents. We describe the dataset creation methodology and provide empirical evidence of the quality of the data. We also","authors_text":"Anne Wu, Changhan Wang, Jiatao Gu, Juan Pino","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-04T14:35:28Z","title":"CoVoST: A Diverse Multilingual Speech-To-Text Translation Corpus"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2002.01320","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":"sha256:178b01d7770caeb630ad9ed03897dec8b5aa5c75e3259fabe8d14af7eaded4bd","target":"record","created_at":"2026-07-05T01:09:03Z","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":"f8ed6e6163618aa772129b08ed73799c40b4856c00f8763ce5534131eb9e9b2f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-02-04T14:35:28Z","title_canon_sha256":"6ec1bdc269b557224a3335d086db4f3370b2423a17a4921a2371a8bf40989e2b"},"schema_version":"1.0","source":{"id":"2002.01320","kind":"arxiv","version":2}},"canonical_sha256":"c7f1cf42cba9344abbeca50606ad4a87fbab7a6e8779ab76569636efeec43739","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c7f1cf42cba9344abbeca50606ad4a87fbab7a6e8779ab76569636efeec43739","first_computed_at":"2026-07-05T01:09:03.322148Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:09:03.322148Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Wj6FJs/NCCAS0Xchr1cvhW7RnriXDFiHGsrsjAkVMk3FYw0bfRVUsRczlzhqxWGKcTocaB4KkW5ks5wI7LVeBg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:09:03.322621Z","signed_message":"canonical_sha256_bytes"},"source_id":"2002.01320","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:178b01d7770caeb630ad9ed03897dec8b5aa5c75e3259fabe8d14af7eaded4bd","sha256:a5ff7bdf33f77a3009828e4b25ae9971b034254e4b2b41dc50ce64673c0473be"],"state_sha256":"0016c0605a6315682352289d2e93053ec108bfc97a1912efa86c063d7508b573"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8cSq4eSDfSTaj2JZVT945XnMUVmDUm/isW+gyMzUFOoWTC3MFcsGc7CciofpyhLOlPz94QC6RbGDrzjeO6lBCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T20:15:49.045327Z","bundle_sha256":"8ca0254766e0530ac6c5bf019ef764a5423e35b7738f04e1e6bafb79c577564f"}}