{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:VM3PATYP6CQEA7QIR25G7MSWC4","short_pith_number":"pith:VM3PATYP","canonical_record":{"source":{"id":"2206.13756","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-28T05:01:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1a9a423e90f841c75b2b691a9556dc7b68e2f8c41bebacdc128e55bb38248604","abstract_canon_sha256":"97b23d22f97ccd688eee3a569eb9f4d110121f6e3be03eb330b19a5848cd8727"},"schema_version":"1.0"},"canonical_sha256":"ab36f04f0ff0a0407e088eba6fb25617209818469bb0051a36c90d99a70d673c","source":{"kind":"arxiv","id":"2206.13756","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.13756","created_at":"2026-07-05T04:36:37Z"},{"alias_kind":"arxiv_version","alias_value":"2206.13756v2","created_at":"2026-07-05T04:36:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.13756","created_at":"2026-07-05T04:36:37Z"},{"alias_kind":"pith_short_12","alias_value":"VM3PATYP6CQE","created_at":"2026-07-05T04:36:37Z"},{"alias_kind":"pith_short_16","alias_value":"VM3PATYP6CQEA7QI","created_at":"2026-07-05T04:36:37Z"},{"alias_kind":"pith_short_8","alias_value":"VM3PATYP","created_at":"2026-07-05T04:36:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:VM3PATYP6CQEA7QIR25G7MSWC4","target":"record","payload":{"canonical_record":{"source":{"id":"2206.13756","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-28T05:01:06Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"1a9a423e90f841c75b2b691a9556dc7b68e2f8c41bebacdc128e55bb38248604","abstract_canon_sha256":"97b23d22f97ccd688eee3a569eb9f4d110121f6e3be03eb330b19a5848cd8727"},"schema_version":"1.0"},"canonical_sha256":"ab36f04f0ff0a0407e088eba6fb25617209818469bb0051a36c90d99a70d673c","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:36:37.447845Z","signature_b64":"FnwEwtxRMUMvk058OHzVr2i6pTGO8VTU/gBe6gj4TCkLGcfYTbR2m7nE10gLCmZHyjzmnqJVQtLmwItjfajbAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab36f04f0ff0a0407e088eba6fb25617209818469bb0051a36c90d99a70d673c","last_reissued_at":"2026-07-05T04:36:37.447409Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:36:37.447409Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2206.13756","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":"2026-07-05T04:36:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ChIDt4ICxA8POqoqF+CRk3FKlhSN9PGtYyrLd+/6QL/dPdLW30Im81WOYrLferi81mxguqjdVI9eVLZPh/8QDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:01:30.686971Z"},"content_sha256":"bbd14640609b09e304005be69f9d199454a763585851014a3a48ec185e97acb8","schema_version":"1.0","event_id":"sha256:bbd14640609b09e304005be69f9d199454a763585851014a3a48ec185e97acb8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:VM3PATYP6CQEA7QIR25G7MSWC4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Impact of Noises in Crowd-Sourced Data for Speech Translation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Lei Li, Rong Ye, Siqi Ouyang","submitted_at":"2022-06-28T05:01:06Z","abstract_excerpt":"Training speech translation (ST) models requires large and high-quality datasets. MuST-C is one of the most widely used ST benchmark datasets. It contains around 400 hours of speech-transcript-translation data for each of the eight translation directions. This dataset passes several quality-control filters during creation. However, we find that MuST-C still suffers from three major quality issues: audio-text misalignment, inaccurate translation, and unnecessary speaker's name. What are the impacts of these data quality issues for model development and evaluation? In this paper, we propose an a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.13756","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/2206.13756/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":"2026-07-05T04:36:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ypmNXth3QZWtOGlc7qwYh6wfaj8J56rYrZJCsoPYaDZMoR2RBr3v/sbAs8xfBSl5XoJ2DUFhHbTq5AnFtSLdDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T17:01:30.687358Z"},"content_sha256":"76b5fcc8870612dd38d0f1e6286be6fe10247d2a76242c6beae8af7b63c16fc0","schema_version":"1.0","event_id":"sha256:76b5fcc8870612dd38d0f1e6286be6fe10247d2a76242c6beae8af7b63c16fc0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/VM3PATYP6CQEA7QIR25G7MSWC4/bundle.json","state_url":"https://pith.science/pith/VM3PATYP6CQEA7QIR25G7MSWC4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/VM3PATYP6CQEA7QIR25G7MSWC4/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":"2026-07-06T17:01:30Z","links":{"resolver":"https://pith.science/pith/VM3PATYP6CQEA7QIR25G7MSWC4","bundle":"https://pith.science/pith/VM3PATYP6CQEA7QIR25G7MSWC4/bundle.json","state":"https://pith.science/pith/VM3PATYP6CQEA7QIR25G7MSWC4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/VM3PATYP6CQEA7QIR25G7MSWC4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:VM3PATYP6CQEA7QIR25G7MSWC4","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":"97b23d22f97ccd688eee3a569eb9f4d110121f6e3be03eb330b19a5848cd8727","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-28T05:01:06Z","title_canon_sha256":"1a9a423e90f841c75b2b691a9556dc7b68e2f8c41bebacdc128e55bb38248604"},"schema_version":"1.0","source":{"id":"2206.13756","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.13756","created_at":"2026-07-05T04:36:37Z"},{"alias_kind":"arxiv_version","alias_value":"2206.13756v2","created_at":"2026-07-05T04:36:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.13756","created_at":"2026-07-05T04:36:37Z"},{"alias_kind":"pith_short_12","alias_value":"VM3PATYP6CQE","created_at":"2026-07-05T04:36:37Z"},{"alias_kind":"pith_short_16","alias_value":"VM3PATYP6CQEA7QI","created_at":"2026-07-05T04:36:37Z"},{"alias_kind":"pith_short_8","alias_value":"VM3PATYP","created_at":"2026-07-05T04:36:37Z"}],"graph_snapshots":[{"event_id":"sha256:76b5fcc8870612dd38d0f1e6286be6fe10247d2a76242c6beae8af7b63c16fc0","target":"graph","created_at":"2026-07-05T04:36:37Z","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/2206.13756/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Training speech translation (ST) models requires large and high-quality datasets. MuST-C is one of the most widely used ST benchmark datasets. It contains around 400 hours of speech-transcript-translation data for each of the eight translation directions. This dataset passes several quality-control filters during creation. However, we find that MuST-C still suffers from three major quality issues: audio-text misalignment, inaccurate translation, and unnecessary speaker's name. What are the impacts of these data quality issues for model development and evaluation? In this paper, we propose an a","authors_text":"Lei Li, Rong Ye, Siqi Ouyang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-28T05:01:06Z","title":"On the Impact of Noises in Crowd-Sourced Data for Speech Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.13756","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:bbd14640609b09e304005be69f9d199454a763585851014a3a48ec185e97acb8","target":"record","created_at":"2026-07-05T04:36:37Z","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":"97b23d22f97ccd688eee3a569eb9f4d110121f6e3be03eb330b19a5848cd8727","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-28T05:01:06Z","title_canon_sha256":"1a9a423e90f841c75b2b691a9556dc7b68e2f8c41bebacdc128e55bb38248604"},"schema_version":"1.0","source":{"id":"2206.13756","kind":"arxiv","version":2}},"canonical_sha256":"ab36f04f0ff0a0407e088eba6fb25617209818469bb0051a36c90d99a70d673c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ab36f04f0ff0a0407e088eba6fb25617209818469bb0051a36c90d99a70d673c","first_computed_at":"2026-07-05T04:36:37.447409Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:36:37.447409Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FnwEwtxRMUMvk058OHzVr2i6pTGO8VTU/gBe6gj4TCkLGcfYTbR2m7nE10gLCmZHyjzmnqJVQtLmwItjfajbAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:36:37.447845Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.13756","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bbd14640609b09e304005be69f9d199454a763585851014a3a48ec185e97acb8","sha256:76b5fcc8870612dd38d0f1e6286be6fe10247d2a76242c6beae8af7b63c16fc0"],"state_sha256":"c92b7eb2e60875a62ba0003117148454fad510ea69e70a93573df108ec413581"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"oEDcMejAiyXGZv0vSUlVXRql6saN6K7o6BwpeZ+Ksrw9pHGYoqzcvek1zrMQkFKocwVd6lyn6upbSscssZ6/DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T17:01:30.689442Z","bundle_sha256":"6319fd95ec0ee4ac49858638ada77c31dbdedae7704f8ff6cda83f7f9978ee4e"}}