{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:FFVLLEDMCNREIMWXUJ6E3ERIRS","short_pith_number":"pith:FFVLLEDM","canonical_record":{"source":{"id":"2204.03939","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-08T08:59:33Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"ff14160778ad73dd1f0d386a976ea73621e640a86f8cbe004c0b20e66a3391d2","abstract_canon_sha256":"66ebeded9a736316142317a3b838fb4dfb68e1c53c93cd6b7fbaf909a387c4e5"},"schema_version":"1.0"},"canonical_sha256":"296ab5906c13624432d7a27c4d92288c8f759f950b5634b957d710841f7a7417","source":{"kind":"arxiv","id":"2204.03939","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.03939","created_at":"2026-07-05T06:17:37Z"},{"alias_kind":"arxiv_version","alias_value":"2204.03939v2","created_at":"2026-07-05T06:17:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.03939","created_at":"2026-07-05T06:17:37Z"},{"alias_kind":"pith_short_12","alias_value":"FFVLLEDMCNRE","created_at":"2026-07-05T06:17:37Z"},{"alias_kind":"pith_short_16","alias_value":"FFVLLEDMCNREIMWX","created_at":"2026-07-05T06:17:37Z"},{"alias_kind":"pith_short_8","alias_value":"FFVLLEDM","created_at":"2026-07-05T06:17:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:FFVLLEDMCNREIMWXUJ6E3ERIRS","target":"record","payload":{"canonical_record":{"source":{"id":"2204.03939","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-08T08:59:33Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"ff14160778ad73dd1f0d386a976ea73621e640a86f8cbe004c0b20e66a3391d2","abstract_canon_sha256":"66ebeded9a736316142317a3b838fb4dfb68e1c53c93cd6b7fbaf909a387c4e5"},"schema_version":"1.0"},"canonical_sha256":"296ab5906c13624432d7a27c4d92288c8f759f950b5634b957d710841f7a7417","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:17:37.175196Z","signature_b64":"qm4nhq+DSKxDUwQv3mZzBBhy0rXPM8MC566JzcUTblHih0xL5LNriGlZP+QsQKqQZ7h7WZ/C6SLbKUpMxk7xDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"296ab5906c13624432d7a27c4d92288c8f759f950b5634b957d710841f7a7417","last_reissued_at":"2026-07-05T06:17:37.174789Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:17:37.174789Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2204.03939","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":"2026-07-05T06:17:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1wcM5JnRAvoQCcbLJKVpKvUybrZKW70IwL3ZOMBShIh2abxY3KEb5h3Bb1ugL9nUOxq6WMi08CfPxLgANmuABQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T15:09:21.440002Z"},"content_sha256":"2194cc43736bd2147ba105b0114420b16be62bc9105752242dcbb94673a26807","schema_version":"1.0","event_id":"sha256:2194cc43736bd2147ba105b0114420b16be62bc9105752242dcbb94673a26807"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:FFVLLEDMCNREIMWXUJ6E3ERIRS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"GigaST: A 10,000-hour Pseudo Speech Translation Corpus","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chengqi Zhao, Chutong Meng, Jun Cao, Mingxuan Wang, Rong Ye, Tao Wang, Tom Ko","submitted_at":"2022-04-08T08:59:33Z","abstract_excerpt":"This paper introduces GigaST, a large-scale pseudo speech translation (ST) corpus. We create the corpus by translating the text in GigaSpeech, an English ASR corpus, into German and Chinese. The training set is translated by a strong machine translation system and the test set is translated by human. ST models trained with an addition of our corpus obtain new state-of-the-art results on the MuST-C English-German benchmark test set. We provide a detailed description of the translation process and verify its quality. We make the translated text data public and hope to facilitate research in spee"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.03939","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/2204.03939/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":"2026-07-05T06:17:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5zvk+uxGyfHciW4Mz61RznN6sOQSVCEcHVruioDF/ayanmW90krrDGvjFb7SJ/5PP86ICLncP27oLQHvpSbFCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T15:09:21.440548Z"},"content_sha256":"4c9750563ad1e55b565191005baf54b70d7047fad8747fc50e80c01e9a252c74","schema_version":"1.0","event_id":"sha256:4c9750563ad1e55b565191005baf54b70d7047fad8747fc50e80c01e9a252c74"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FFVLLEDMCNREIMWXUJ6E3ERIRS/bundle.json","state_url":"https://pith.science/pith/FFVLLEDMCNREIMWXUJ6E3ERIRS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FFVLLEDMCNREIMWXUJ6E3ERIRS/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":"2026-07-06T15:09:21Z","links":{"resolver":"https://pith.science/pith/FFVLLEDMCNREIMWXUJ6E3ERIRS","bundle":"https://pith.science/pith/FFVLLEDMCNREIMWXUJ6E3ERIRS/bundle.json","state":"https://pith.science/pith/FFVLLEDMCNREIMWXUJ6E3ERIRS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FFVLLEDMCNREIMWXUJ6E3ERIRS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:FFVLLEDMCNREIMWXUJ6E3ERIRS","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":"66ebeded9a736316142317a3b838fb4dfb68e1c53c93cd6b7fbaf909a387c4e5","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-08T08:59:33Z","title_canon_sha256":"ff14160778ad73dd1f0d386a976ea73621e640a86f8cbe004c0b20e66a3391d2"},"schema_version":"1.0","source":{"id":"2204.03939","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2204.03939","created_at":"2026-07-05T06:17:37Z"},{"alias_kind":"arxiv_version","alias_value":"2204.03939v2","created_at":"2026-07-05T06:17:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2204.03939","created_at":"2026-07-05T06:17:37Z"},{"alias_kind":"pith_short_12","alias_value":"FFVLLEDMCNRE","created_at":"2026-07-05T06:17:37Z"},{"alias_kind":"pith_short_16","alias_value":"FFVLLEDMCNREIMWX","created_at":"2026-07-05T06:17:37Z"},{"alias_kind":"pith_short_8","alias_value":"FFVLLEDM","created_at":"2026-07-05T06:17:37Z"}],"graph_snapshots":[{"event_id":"sha256:4c9750563ad1e55b565191005baf54b70d7047fad8747fc50e80c01e9a252c74","target":"graph","created_at":"2026-07-05T06:17:37Z","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/2204.03939/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"This paper introduces GigaST, a large-scale pseudo speech translation (ST) corpus. We create the corpus by translating the text in GigaSpeech, an English ASR corpus, into German and Chinese. The training set is translated by a strong machine translation system and the test set is translated by human. ST models trained with an addition of our corpus obtain new state-of-the-art results on the MuST-C English-German benchmark test set. We provide a detailed description of the translation process and verify its quality. We make the translated text data public and hope to facilitate research in spee","authors_text":"Chengqi Zhao, Chutong Meng, Jun Cao, Mingxuan Wang, Rong Ye, Tao Wang, Tom Ko","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-08T08:59:33Z","title":"GigaST: A 10,000-hour Pseudo Speech Translation Corpus"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2204.03939","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":"sha256:2194cc43736bd2147ba105b0114420b16be62bc9105752242dcbb94673a26807","target":"record","created_at":"2026-07-05T06:17:37Z","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":"66ebeded9a736316142317a3b838fb4dfb68e1c53c93cd6b7fbaf909a387c4e5","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-04-08T08:59:33Z","title_canon_sha256":"ff14160778ad73dd1f0d386a976ea73621e640a86f8cbe004c0b20e66a3391d2"},"schema_version":"1.0","source":{"id":"2204.03939","kind":"arxiv","version":2}},"canonical_sha256":"296ab5906c13624432d7a27c4d92288c8f759f950b5634b957d710841f7a7417","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"296ab5906c13624432d7a27c4d92288c8f759f950b5634b957d710841f7a7417","first_computed_at":"2026-07-05T06:17:37.174789Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:17:37.174789Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qm4nhq+DSKxDUwQv3mZzBBhy0rXPM8MC566JzcUTblHih0xL5LNriGlZP+QsQKqQZ7h7WZ/C6SLbKUpMxk7xDg==","signature_status":"signed_v1","signed_at":"2026-07-05T06:17:37.175196Z","signed_message":"canonical_sha256_bytes"},"source_id":"2204.03939","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2194cc43736bd2147ba105b0114420b16be62bc9105752242dcbb94673a26807","sha256:4c9750563ad1e55b565191005baf54b70d7047fad8747fc50e80c01e9a252c74"],"state_sha256":"31032743685bc7fea8036e93e6abfc07c4ee1928d01d7975c27b37c0a58dc212"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"WeWli7zb+qou3Z3XjgRz1kuonTRT3BNXgm+Y6xbeMwlQOURF66m0ufVN/MJ2BU6PUMQME6FBjDYVSa65OPSuCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T15:09:21.442528Z","bundle_sha256":"d1647c9c30721a8f00e8b670cef04ba1e81ba1e245d82b7ee2a4129b2472b218"}}