{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:PKAQTWUXY7D7NGHFRXI6RZPDXE","short_pith_number":"pith:PKAQTWUX","canonical_record":{"source":{"id":"2205.08993","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-18T15:24:02Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"637a9a2bba162d3653282f6e248738f7b5e8c568e6d3553b09e73312405ab2b0","abstract_canon_sha256":"89547ec91e35e2b6b1658e33bde783c234e02e2d72a2c27a4ae87955e2499a26"},"schema_version":"1.0"},"canonical_sha256":"7a8109da97c7c7f698e58dd1e8e5e3b9210d5c23b9b322408a57fd2e09361095","source":{"kind":"arxiv","id":"2205.08993","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.08993","created_at":"2026-07-05T04:24:31Z"},{"alias_kind":"arxiv_version","alias_value":"2205.08993v1","created_at":"2026-07-05T04:24:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.08993","created_at":"2026-07-05T04:24:31Z"},{"alias_kind":"pith_short_12","alias_value":"PKAQTWUXY7D7","created_at":"2026-07-05T04:24:31Z"},{"alias_kind":"pith_short_16","alias_value":"PKAQTWUXY7D7NGHF","created_at":"2026-07-05T04:24:31Z"},{"alias_kind":"pith_short_8","alias_value":"PKAQTWUX","created_at":"2026-07-05T04:24:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:PKAQTWUXY7D7NGHFRXI6RZPDXE","target":"record","payload":{"canonical_record":{"source":{"id":"2205.08993","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-18T15:24:02Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"637a9a2bba162d3653282f6e248738f7b5e8c568e6d3553b09e73312405ab2b0","abstract_canon_sha256":"89547ec91e35e2b6b1658e33bde783c234e02e2d72a2c27a4ae87955e2499a26"},"schema_version":"1.0"},"canonical_sha256":"7a8109da97c7c7f698e58dd1e8e5e3b9210d5c23b9b322408a57fd2e09361095","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:24:31.685103Z","signature_b64":"H2tezvLfrMgQTtC8jQSxLk7IpQeOK2SKHMBsFvlA/jLBNeELBXkf6tOMS+UNmN+FpvpnU8G4ocR7tlRb9Kr3AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7a8109da97c7c7f698e58dd1e8e5e3b9210d5c23b9b322408a57fd2e09361095","last_reissued_at":"2026-07-05T04:24:31.684673Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:24:31.684673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2205.08993","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:24:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OcLMlvWoSC7ESIGAfhHUXTfYrkiBGVNYTlfD4haPF8UVTw+/WlGmU/HFxutS6jESIrdiXERKWJHUEFTQ0QTYAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:25:29.571053Z"},"content_sha256":"d370eb01c52f791ee3941f7a94fbbc11b1f909b0e8bb5e7e98c184353cd92523","schema_version":"1.0","event_id":"sha256:d370eb01c52f791ee3941f7a94fbbc11b1f909b0e8bb5e7e98c184353cd92523"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:PKAQTWUXY7D7NGHFRXI6RZPDXE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Leveraging Pseudo-labeled Data to Improve Direct Speech-to-Speech Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Fengpeng Yue, Mingxuan Wang, Qianqian Dong, Qibing Bai, Tom Ko, Yu Zhang","submitted_at":"2022-05-18T15:24:02Z","abstract_excerpt":"Direct Speech-to-speech translation (S2ST) has drawn more and more attention recently. The task is very challenging due to data scarcity and complex speech-to-speech mapping. In this paper, we report our recent achievements in S2ST. Firstly, we build a S2ST Transformer baseline which outperforms the original Translatotron. Secondly, we utilize the external data by pseudo-labeling and obtain a new state-of-the-art result on the Fisher English-to-Spanish test set. Indeed, we exploit the pseudo data with a combination of popular techniques which are not trivial when applied to S2ST. Moreover, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.08993","kind":"arxiv","version":1},"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/2205.08993/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":"2026-07-05T04:24:31Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aiIo3Th6iQyv9G9kXxj+r3Yb5+OZFED/o++Wa2PGuTuIBqIgs5cuHgc8NybW2t5YDyDbsmvcNPQhYM7vwQeZCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:25:29.571461Z"},"content_sha256":"637617dbea864893007ec09ec39161cc5a0b58ad9aadb5916486de9d19e6be8f","schema_version":"1.0","event_id":"sha256:637617dbea864893007ec09ec39161cc5a0b58ad9aadb5916486de9d19e6be8f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PKAQTWUXY7D7NGHFRXI6RZPDXE/bundle.json","state_url":"https://pith.science/pith/PKAQTWUXY7D7NGHFRXI6RZPDXE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PKAQTWUXY7D7NGHFRXI6RZPDXE/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":"2026-07-07T12:25:29Z","links":{"resolver":"https://pith.science/pith/PKAQTWUXY7D7NGHFRXI6RZPDXE","bundle":"https://pith.science/pith/PKAQTWUXY7D7NGHFRXI6RZPDXE/bundle.json","state":"https://pith.science/pith/PKAQTWUXY7D7NGHFRXI6RZPDXE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PKAQTWUXY7D7NGHFRXI6RZPDXE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:PKAQTWUXY7D7NGHFRXI6RZPDXE","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":"89547ec91e35e2b6b1658e33bde783c234e02e2d72a2c27a4ae87955e2499a26","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-18T15:24:02Z","title_canon_sha256":"637a9a2bba162d3653282f6e248738f7b5e8c568e6d3553b09e73312405ab2b0"},"schema_version":"1.0","source":{"id":"2205.08993","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2205.08993","created_at":"2026-07-05T04:24:31Z"},{"alias_kind":"arxiv_version","alias_value":"2205.08993v1","created_at":"2026-07-05T04:24:31Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.08993","created_at":"2026-07-05T04:24:31Z"},{"alias_kind":"pith_short_12","alias_value":"PKAQTWUXY7D7","created_at":"2026-07-05T04:24:31Z"},{"alias_kind":"pith_short_16","alias_value":"PKAQTWUXY7D7NGHF","created_at":"2026-07-05T04:24:31Z"},{"alias_kind":"pith_short_8","alias_value":"PKAQTWUX","created_at":"2026-07-05T04:24:31Z"}],"graph_snapshots":[{"event_id":"sha256:637617dbea864893007ec09ec39161cc5a0b58ad9aadb5916486de9d19e6be8f","target":"graph","created_at":"2026-07-05T04:24:31Z","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/2205.08993/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Direct Speech-to-speech translation (S2ST) has drawn more and more attention recently. The task is very challenging due to data scarcity and complex speech-to-speech mapping. In this paper, we report our recent achievements in S2ST. Firstly, we build a S2ST Transformer baseline which outperforms the original Translatotron. Secondly, we utilize the external data by pseudo-labeling and obtain a new state-of-the-art result on the Fisher English-to-Spanish test set. Indeed, we exploit the pseudo data with a combination of popular techniques which are not trivial when applied to S2ST. Moreover, we ","authors_text":"Fengpeng Yue, Mingxuan Wang, Qianqian Dong, Qibing Bai, Tom Ko, Yu Zhang","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-18T15:24:02Z","title":"Leveraging Pseudo-labeled Data to Improve Direct Speech-to-Speech Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.08993","kind":"arxiv","version":1},"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:d370eb01c52f791ee3941f7a94fbbc11b1f909b0e8bb5e7e98c184353cd92523","target":"record","created_at":"2026-07-05T04:24:31Z","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":"89547ec91e35e2b6b1658e33bde783c234e02e2d72a2c27a4ae87955e2499a26","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-18T15:24:02Z","title_canon_sha256":"637a9a2bba162d3653282f6e248738f7b5e8c568e6d3553b09e73312405ab2b0"},"schema_version":"1.0","source":{"id":"2205.08993","kind":"arxiv","version":1}},"canonical_sha256":"7a8109da97c7c7f698e58dd1e8e5e3b9210d5c23b9b322408a57fd2e09361095","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7a8109da97c7c7f698e58dd1e8e5e3b9210d5c23b9b322408a57fd2e09361095","first_computed_at":"2026-07-05T04:24:31.684673Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:24:31.684673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"H2tezvLfrMgQTtC8jQSxLk7IpQeOK2SKHMBsFvlA/jLBNeELBXkf6tOMS+UNmN+FpvpnU8G4ocR7tlRb9Kr3AA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:24:31.685103Z","signed_message":"canonical_sha256_bytes"},"source_id":"2205.08993","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d370eb01c52f791ee3941f7a94fbbc11b1f909b0e8bb5e7e98c184353cd92523","sha256:637617dbea864893007ec09ec39161cc5a0b58ad9aadb5916486de9d19e6be8f"],"state_sha256":"b9432c353e138cd65615e9cc3ebcea44f9c748435473acabe480cb2c24690e19"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LBr8TMubN/idBPoshczwswM6iYeyjaPdwymMt7sigIO/hKlrQFI3MmXalbHsixlMbJzW11yzbG2e+Kl8nPp5BQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T12:25:29.573423Z","bundle_sha256":"e434ebd6ac9dcb2604c6ea51e8dcd2d9c26d5e15c13793a7dc434cf1f0a36fc3"}}