{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:67RYPFMJU5FIK3DGNXT5XC4GR4","short_pith_number":"pith:67RYPFMJ","canonical_record":{"source":{"id":"2305.15405","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T17:59:05Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"79a4687c4c5221e4f09e5bc648e14db2a2937e0359fe24e141d0f7e10a97d8b3","abstract_canon_sha256":"cb60ffe886cfc918f4f95c007225a1cefa861441cb6df17178f3978ca816a07b"},"schema_version":"1.0"},"canonical_sha256":"f7e3879589a74a856c666de7db8b868f1d522865ab02783b6475b99dcd67bc51","source":{"kind":"arxiv","id":"2305.15405","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.15405","created_at":"2026-07-05T09:32:02Z"},{"alias_kind":"arxiv_version","alias_value":"2305.15405v3","created_at":"2026-07-05T09:32:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15405","created_at":"2026-07-05T09:32:02Z"},{"alias_kind":"pith_short_12","alias_value":"67RYPFMJU5FI","created_at":"2026-07-05T09:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"67RYPFMJU5FIK3DG","created_at":"2026-07-05T09:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"67RYPFMJ","created_at":"2026-07-05T09:32:02Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:67RYPFMJU5FIK3DGNXT5XC4GR4","target":"record","payload":{"canonical_record":{"source":{"id":"2305.15405","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T17:59:05Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"79a4687c4c5221e4f09e5bc648e14db2a2937e0359fe24e141d0f7e10a97d8b3","abstract_canon_sha256":"cb60ffe886cfc918f4f95c007225a1cefa861441cb6df17178f3978ca816a07b"},"schema_version":"1.0"},"canonical_sha256":"f7e3879589a74a856c666de7db8b868f1d522865ab02783b6475b99dcd67bc51","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:32:02.805641Z","signature_b64":"12yceHJBycgjhtdT/P+2+T1hRHYSt8/oD8bKa27RJSl/T0BBvkxpSdK3nXzcztfhbV6sCASKDL/q6H4g+X9UBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f7e3879589a74a856c666de7db8b868f1d522865ab02783b6475b99dcd67bc51","last_reissued_at":"2026-07-05T09:32:02.805228Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:32:02.805228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.15405","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T09:32:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4hU4p8KvW7rRHR0J6uqjIEgCmG2mp9ssNCL6UfYLs0b/NMiPQiEFcW2GyYQY/R4h7BK9N1ERII/5zOHQDxYbBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:26:51.131563Z"},"content_sha256":"691ddf508fa23cc4a7b208f98a0fc88d14d10f8fbbe3f6e030d16aac5011177f","schema_version":"1.0","event_id":"sha256:691ddf508fa23cc4a7b208f98a0fc88d14d10f8fbbe3f6e030d16aac5011177f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:67RYPFMJU5FIK3DGNXT5XC4GR4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Textless Speech-to-Speech Translation With Limited Parallel Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.CL","authors_text":"Anirudh Srinivasan, Anuj Diwan, David Harwath, Eunsol Choi","submitted_at":"2023-05-24T17:59:05Z","abstract_excerpt":"Existing speech-to-speech translation (S2ST) models fall into two camps: they either leverage text as an intermediate step or require hundreds of hours of parallel speech data. Both approaches are incompatible with textless languages or language pairs with limited parallel data. We present PFB, a framework for training textless S2ST models that require just dozens of hours of parallel speech data. We first pretrain a model on large-scale monolingual speech data, finetune it with a small amount of parallel speech data (20-60 hours), and lastly train with an unsupervised backtranslation objectiv"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15405","kind":"arxiv","version":3},"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/2305.15405/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":"2026-07-05T09:32:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N/WJDLwakvmN/o4uh8T8GkAeNcyv9XD31XSeqtzJ9AMExt8mwWcspsDR5qFDeJWgbNmgjShgIkioMYElvzxnDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:26:51.132077Z"},"content_sha256":"2f0ec6625e84b54becb0e018cb5db0a29ef4c5302dd2376d7c6cc9c5889f256e","schema_version":"1.0","event_id":"sha256:2f0ec6625e84b54becb0e018cb5db0a29ef4c5302dd2376d7c6cc9c5889f256e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/67RYPFMJU5FIK3DGNXT5XC4GR4/bundle.json","state_url":"https://pith.science/pith/67RYPFMJU5FIK3DGNXT5XC4GR4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/67RYPFMJU5FIK3DGNXT5XC4GR4/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":"2026-08-03T18:26:51Z","links":{"resolver":"https://pith.science/pith/67RYPFMJU5FIK3DGNXT5XC4GR4","bundle":"https://pith.science/pith/67RYPFMJU5FIK3DGNXT5XC4GR4/bundle.json","state":"https://pith.science/pith/67RYPFMJU5FIK3DGNXT5XC4GR4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/67RYPFMJU5FIK3DGNXT5XC4GR4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:67RYPFMJU5FIK3DGNXT5XC4GR4","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":"cb60ffe886cfc918f4f95c007225a1cefa861441cb6df17178f3978ca816a07b","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T17:59:05Z","title_canon_sha256":"79a4687c4c5221e4f09e5bc648e14db2a2937e0359fe24e141d0f7e10a97d8b3"},"schema_version":"1.0","source":{"id":"2305.15405","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.15405","created_at":"2026-07-05T09:32:02Z"},{"alias_kind":"arxiv_version","alias_value":"2305.15405v3","created_at":"2026-07-05T09:32:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.15405","created_at":"2026-07-05T09:32:02Z"},{"alias_kind":"pith_short_12","alias_value":"67RYPFMJU5FI","created_at":"2026-07-05T09:32:02Z"},{"alias_kind":"pith_short_16","alias_value":"67RYPFMJU5FIK3DG","created_at":"2026-07-05T09:32:02Z"},{"alias_kind":"pith_short_8","alias_value":"67RYPFMJ","created_at":"2026-07-05T09:32:02Z"}],"graph_snapshots":[{"event_id":"sha256:2f0ec6625e84b54becb0e018cb5db0a29ef4c5302dd2376d7c6cc9c5889f256e","target":"graph","created_at":"2026-07-05T09:32:02Z","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/2305.15405/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Existing speech-to-speech translation (S2ST) models fall into two camps: they either leverage text as an intermediate step or require hundreds of hours of parallel speech data. Both approaches are incompatible with textless languages or language pairs with limited parallel data. We present PFB, a framework for training textless S2ST models that require just dozens of hours of parallel speech data. We first pretrain a model on large-scale monolingual speech data, finetune it with a small amount of parallel speech data (20-60 hours), and lastly train with an unsupervised backtranslation objectiv","authors_text":"Anirudh Srinivasan, Anuj Diwan, David Harwath, Eunsol Choi","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T17:59:05Z","title":"Textless Speech-to-Speech Translation With Limited Parallel Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.15405","kind":"arxiv","version":3},"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":"sha256:691ddf508fa23cc4a7b208f98a0fc88d14d10f8fbbe3f6e030d16aac5011177f","target":"record","created_at":"2026-07-05T09:32:02Z","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":"cb60ffe886cfc918f4f95c007225a1cefa861441cb6df17178f3978ca816a07b","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-24T17:59:05Z","title_canon_sha256":"79a4687c4c5221e4f09e5bc648e14db2a2937e0359fe24e141d0f7e10a97d8b3"},"schema_version":"1.0","source":{"id":"2305.15405","kind":"arxiv","version":3}},"canonical_sha256":"f7e3879589a74a856c666de7db8b868f1d522865ab02783b6475b99dcd67bc51","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f7e3879589a74a856c666de7db8b868f1d522865ab02783b6475b99dcd67bc51","first_computed_at":"2026-07-05T09:32:02.805228Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:32:02.805228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"12yceHJBycgjhtdT/P+2+T1hRHYSt8/oD8bKa27RJSl/T0BBvkxpSdK3nXzcztfhbV6sCASKDL/q6H4g+X9UBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:32:02.805641Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.15405","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:691ddf508fa23cc4a7b208f98a0fc88d14d10f8fbbe3f6e030d16aac5011177f","sha256:2f0ec6625e84b54becb0e018cb5db0a29ef4c5302dd2376d7c6cc9c5889f256e"],"state_sha256":"3109a72b46d5050780db96e0f27d0a5ab39b6189d64ae2fbd144117e0df60c1a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9/f1WyGoGS3tKxsIaI27v461EzEIsVPy2idOo08Y8BjdBHgfqwq88g7Qfk1kQhxyVGpgjSZ+zNGzhzkRAbwLDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T18:26:51.139210Z","bundle_sha256":"468c9b0baa3a7b6cba0b4a9dcdd15059973a9401b5b30715561a092f6f6b7ea8"}}