{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:QG2WVBYSHPAYE5YGYHVQ3WNUTM","short_pith_number":"pith:QG2WVBYS","canonical_record":{"source":{"id":"2203.13339","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-24T21:06:15Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"f46fd7ce8c9297ee4976e28548509398a4a7a771b3fe04cbae7efad220244096","abstract_canon_sha256":"e3c7761d60a9306e072018af8728218b899d4894533f4b201dbc65c1ab7c1ade"},"schema_version":"1.0"},"canonical_sha256":"81b56a87123bc1827706c1eb0dd9b49b346b64fddcfe20c56a2bb289fdbd3ffb","source":{"kind":"arxiv","id":"2203.13339","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.13339","created_at":"2026-07-05T04:35:20Z"},{"alias_kind":"arxiv_version","alias_value":"2203.13339v2","created_at":"2026-07-05T04:35:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.13339","created_at":"2026-07-05T04:35:20Z"},{"alias_kind":"pith_short_12","alias_value":"QG2WVBYSHPAY","created_at":"2026-07-05T04:35:20Z"},{"alias_kind":"pith_short_16","alias_value":"QG2WVBYSHPAYE5YG","created_at":"2026-07-05T04:35:20Z"},{"alias_kind":"pith_short_8","alias_value":"QG2WVBYS","created_at":"2026-07-05T04:35:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:QG2WVBYSHPAYE5YGYHVQ3WNUTM","target":"record","payload":{"canonical_record":{"source":{"id":"2203.13339","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-24T21:06:15Z","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"f46fd7ce8c9297ee4976e28548509398a4a7a771b3fe04cbae7efad220244096","abstract_canon_sha256":"e3c7761d60a9306e072018af8728218b899d4894533f4b201dbc65c1ab7c1ade"},"schema_version":"1.0"},"canonical_sha256":"81b56a87123bc1827706c1eb0dd9b49b346b64fddcfe20c56a2bb289fdbd3ffb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:35:20.826362Z","signature_b64":"j+mAgjQET7RRh6ofv/6Vvbnt5mEpvxPmSAQlH4Bwa6oeEjXY9xRlba4ZyarX11DM0qbTCcCC8TUEOZpwzOasDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"81b56a87123bc1827706c1eb0dd9b49b346b64fddcfe20c56a2bb289fdbd3ffb","last_reissued_at":"2026-07-05T04:35:20.825889Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:35:20.825889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2203.13339","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":"2026-07-05T04:35:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"glMTRBOKd28CXMAjXoLsJxO3sqakBGn6q8KhhhHW44eYiG49pyIm+DON39V0wXeqveY0O/QzMRZua0Ray1/SCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:53:28.931709Z"},"content_sha256":"4ab5deef9960774a86cd324cbfb866140e43c500b46bf90f9e2d57a780a47dc2","schema_version":"1.0","event_id":"sha256:4ab5deef9960774a86cd324cbfb866140e43c500b46bf90f9e2d57a780a47dc2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:QG2WVBYSHPAYE5YGYHVQ3WNUTM","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging unsupervised and weakly-supervised data to improve direct speech-to-speech translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Alexis Conneau, Ankur Bapna, Colin Cherry, Nobuyuki Morioka, Ye Jia, Yifan Ding, Yu Zhang","submitted_at":"2022-03-24T21:06:15Z","abstract_excerpt":"End-to-end speech-to-speech translation (S2ST) without relying on intermediate text representations is a rapidly emerging frontier of research. Recent works have demonstrated that the performance of such direct S2ST systems is approaching that of conventional cascade S2ST when trained on comparable datasets. However, in practice, the performance of direct S2ST is bounded by the availability of paired S2ST training data. In this work, we explore multiple approaches for leveraging much more widely available unsupervised and weakly-supervised speech and text data to improve the performance of dir"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.13339","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/2203.13339/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":"2026-07-05T04:35:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dXnyW4EPbRkAt93NbzREg+A+oOuEKzhlBktpwfAWMVPEyRAyChQscbRX9VuOrTFVXBvMwErtuCZ+SkzdYII/DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T19:53:28.932502Z"},"content_sha256":"9638a5a897bca69b8781222c7a0e60751d1eb006b81bb1445c548ee9105406a2","schema_version":"1.0","event_id":"sha256:9638a5a897bca69b8781222c7a0e60751d1eb006b81bb1445c548ee9105406a2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QG2WVBYSHPAYE5YGYHVQ3WNUTM/bundle.json","state_url":"https://pith.science/pith/QG2WVBYSHPAYE5YGYHVQ3WNUTM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QG2WVBYSHPAYE5YGYHVQ3WNUTM/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":"2026-08-06T19:53:28Z","links":{"resolver":"https://pith.science/pith/QG2WVBYSHPAYE5YGYHVQ3WNUTM","bundle":"https://pith.science/pith/QG2WVBYSHPAYE5YGYHVQ3WNUTM/bundle.json","state":"https://pith.science/pith/QG2WVBYSHPAYE5YGYHVQ3WNUTM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QG2WVBYSHPAYE5YGYHVQ3WNUTM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:QG2WVBYSHPAYE5YGYHVQ3WNUTM","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":"e3c7761d60a9306e072018af8728218b899d4894533f4b201dbc65c1ab7c1ade","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-24T21:06:15Z","title_canon_sha256":"f46fd7ce8c9297ee4976e28548509398a4a7a771b3fe04cbae7efad220244096"},"schema_version":"1.0","source":{"id":"2203.13339","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2203.13339","created_at":"2026-07-05T04:35:20Z"},{"alias_kind":"arxiv_version","alias_value":"2203.13339v2","created_at":"2026-07-05T04:35:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2203.13339","created_at":"2026-07-05T04:35:20Z"},{"alias_kind":"pith_short_12","alias_value":"QG2WVBYSHPAY","created_at":"2026-07-05T04:35:20Z"},{"alias_kind":"pith_short_16","alias_value":"QG2WVBYSHPAYE5YG","created_at":"2026-07-05T04:35:20Z"},{"alias_kind":"pith_short_8","alias_value":"QG2WVBYS","created_at":"2026-07-05T04:35:20Z"}],"graph_snapshots":[{"event_id":"sha256:9638a5a897bca69b8781222c7a0e60751d1eb006b81bb1445c548ee9105406a2","target":"graph","created_at":"2026-07-05T04:35:20Z","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/2203.13339/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"End-to-end speech-to-speech translation (S2ST) without relying on intermediate text representations is a rapidly emerging frontier of research. Recent works have demonstrated that the performance of such direct S2ST systems is approaching that of conventional cascade S2ST when trained on comparable datasets. However, in practice, the performance of direct S2ST is bounded by the availability of paired S2ST training data. In this work, we explore multiple approaches for leveraging much more widely available unsupervised and weakly-supervised speech and text data to improve the performance of dir","authors_text":"Alexis Conneau, Ankur Bapna, Colin Cherry, Nobuyuki Morioka, Ye Jia, Yifan Ding, Yu Zhang","cross_cats":["cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-24T21:06:15Z","title":"Leveraging unsupervised and weakly-supervised data to improve direct speech-to-speech translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2203.13339","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":"sha256:4ab5deef9960774a86cd324cbfb866140e43c500b46bf90f9e2d57a780a47dc2","target":"record","created_at":"2026-07-05T04:35:20Z","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":"e3c7761d60a9306e072018af8728218b899d4894533f4b201dbc65c1ab7c1ade","cross_cats_sorted":["cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-03-24T21:06:15Z","title_canon_sha256":"f46fd7ce8c9297ee4976e28548509398a4a7a771b3fe04cbae7efad220244096"},"schema_version":"1.0","source":{"id":"2203.13339","kind":"arxiv","version":2}},"canonical_sha256":"81b56a87123bc1827706c1eb0dd9b49b346b64fddcfe20c56a2bb289fdbd3ffb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"81b56a87123bc1827706c1eb0dd9b49b346b64fddcfe20c56a2bb289fdbd3ffb","first_computed_at":"2026-07-05T04:35:20.825889Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:35:20.825889Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"j+mAgjQET7RRh6ofv/6Vvbnt5mEpvxPmSAQlH4Bwa6oeEjXY9xRlba4ZyarX11DM0qbTCcCC8TUEOZpwzOasDw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:35:20.826362Z","signed_message":"canonical_sha256_bytes"},"source_id":"2203.13339","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4ab5deef9960774a86cd324cbfb866140e43c500b46bf90f9e2d57a780a47dc2","sha256:9638a5a897bca69b8781222c7a0e60751d1eb006b81bb1445c548ee9105406a2"],"state_sha256":"28e137bfee5a9926b994bcf6037b6e951a415c041673e55e93924238cfb5dd33"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"d5stMWX7EnZh16bJkBLZeyOUToeu2FkFMPmbbsrIYy80I1Ow0gDegf1o2/MW+JI9ls3FN3sW/+WhjXCg1X7VCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T19:53:28.938142Z","bundle_sha256":"c44d6f58d4e384bb1d7bc07db2ef1e840a0d4908edb0b18f1ecaf3137dacfb54"}}