{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YYY4FODZSFEXFOHCONHHXD7NS3","short_pith_number":"pith:YYY4FODZ","canonical_record":{"source":{"id":"2407.02243","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T13:04:04Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"bc43a8725cc1fee3e1a6df9c91a0d5232617faef537939ece09af0a1caddac5b","abstract_canon_sha256":"5afb94daaafb405c7916cc77e2892fc3d8f1c3e79e8b30205669033a2f394072"},"schema_version":"1.0"},"canonical_sha256":"c631c2b879914972b8e2734e7b8fed96f61668042ec896e3863fb3f38f71e55e","source":{"kind":"arxiv","id":"2407.02243","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.02243","created_at":"2026-07-05T08:39:11Z"},{"alias_kind":"arxiv_version","alias_value":"2407.02243v1","created_at":"2026-07-05T08:39:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02243","created_at":"2026-07-05T08:39:11Z"},{"alias_kind":"pith_short_12","alias_value":"YYY4FODZSFEX","created_at":"2026-07-05T08:39:11Z"},{"alias_kind":"pith_short_16","alias_value":"YYY4FODZSFEXFOHC","created_at":"2026-07-05T08:39:11Z"},{"alias_kind":"pith_short_8","alias_value":"YYY4FODZ","created_at":"2026-07-05T08:39:11Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YYY4FODZSFEXFOHCONHHXD7NS3","target":"record","payload":{"canonical_record":{"source":{"id":"2407.02243","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T13:04:04Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"bc43a8725cc1fee3e1a6df9c91a0d5232617faef537939ece09af0a1caddac5b","abstract_canon_sha256":"5afb94daaafb405c7916cc77e2892fc3d8f1c3e79e8b30205669033a2f394072"},"schema_version":"1.0"},"canonical_sha256":"c631c2b879914972b8e2734e7b8fed96f61668042ec896e3863fb3f38f71e55e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:11.990990Z","signature_b64":"iIds6BMIOKZ8H22g9ROSroEZ9QtegLFjwxEGrhN2yDy0AIeCmDYvt3oQzrg6zmF593cQOMgnS5zdjOasIiglBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c631c2b879914972b8e2734e7b8fed96f61668042ec896e3863fb3f38f71e55e","last_reissued_at":"2026-07-05T08:39:11.990617Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:11.990617Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.02243","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":"2026-07-05T08:39:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"BJENzwdneXuK5GF3P3GnoIkaqorYEPJ4dXyDkBEL31sxKN03LPhtRtbv9Vp3dpHvHOEOr0/eyoLDFo4qhntZCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:34:16.182244Z"},"content_sha256":"013ba0f44ab9f6c48a3eb4777681272016dff14d7c8d5c5fad49d1eb30a6ee49","schema_version":"1.0","event_id":"sha256:013ba0f44ab9f6c48a3eb4777681272016dff14d7c8d5c5fad49d1eb30a6ee49"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YYY4FODZSFEXFOHCONHHXD7NS3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Robust Zero-Shot Text-to-Speech Synthesis with Reverse Inference Optimization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chao Zhang, Chen Chen, Eng Siong Chng, Siyin Wang, Yuchen Hu","submitted_at":"2024-07-02T13:04:04Z","abstract_excerpt":"In this paper, we propose reverse inference optimization (RIO), a simple and effective method designed to enhance the robustness of autoregressive-model-based zero-shot text-to-speech (TTS) systems using reinforcement learning from human feedback (RLHF). To assess the quality of speech produced by the TTS system without human annotations, RIO introduces a novel concept termed as reverse inference based on the Bayesian principle, which suggests that a high-quality generated speech should be able to be used as a prompt for subsequent generation using the same TTS model. By leveraging reverse inf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02243","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/2407.02243/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":"2026-07-05T08:39:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fSFqahWIrxFyK1dzIOsw/KjVrxxvo9RckM7jOtVwP2O2o4XiSVprXSXsKwKfaRzn7Rp2aZYobUJ/MTQ24HPyCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:34:16.182754Z"},"content_sha256":"c7abd770d987019d129fb932d29bd96b40fcbb2879b240ed8f2f09427f0062d0","schema_version":"1.0","event_id":"sha256:c7abd770d987019d129fb932d29bd96b40fcbb2879b240ed8f2f09427f0062d0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YYY4FODZSFEXFOHCONHHXD7NS3/bundle.json","state_url":"https://pith.science/pith/YYY4FODZSFEXFOHCONHHXD7NS3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YYY4FODZSFEXFOHCONHHXD7NS3/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":"2026-08-09T20:34:16Z","links":{"resolver":"https://pith.science/pith/YYY4FODZSFEXFOHCONHHXD7NS3","bundle":"https://pith.science/pith/YYY4FODZSFEXFOHCONHHXD7NS3/bundle.json","state":"https://pith.science/pith/YYY4FODZSFEXFOHCONHHXD7NS3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YYY4FODZSFEXFOHCONHHXD7NS3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YYY4FODZSFEXFOHCONHHXD7NS3","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":"5afb94daaafb405c7916cc77e2892fc3d8f1c3e79e8b30205669033a2f394072","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T13:04:04Z","title_canon_sha256":"bc43a8725cc1fee3e1a6df9c91a0d5232617faef537939ece09af0a1caddac5b"},"schema_version":"1.0","source":{"id":"2407.02243","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.02243","created_at":"2026-07-05T08:39:11Z"},{"alias_kind":"arxiv_version","alias_value":"2407.02243v1","created_at":"2026-07-05T08:39:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02243","created_at":"2026-07-05T08:39:11Z"},{"alias_kind":"pith_short_12","alias_value":"YYY4FODZSFEX","created_at":"2026-07-05T08:39:11Z"},{"alias_kind":"pith_short_16","alias_value":"YYY4FODZSFEXFOHC","created_at":"2026-07-05T08:39:11Z"},{"alias_kind":"pith_short_8","alias_value":"YYY4FODZ","created_at":"2026-07-05T08:39:11Z"}],"graph_snapshots":[{"event_id":"sha256:c7abd770d987019d129fb932d29bd96b40fcbb2879b240ed8f2f09427f0062d0","target":"graph","created_at":"2026-07-05T08:39:11Z","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/2407.02243/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we propose reverse inference optimization (RIO), a simple and effective method designed to enhance the robustness of autoregressive-model-based zero-shot text-to-speech (TTS) systems using reinforcement learning from human feedback (RLHF). To assess the quality of speech produced by the TTS system without human annotations, RIO introduces a novel concept termed as reverse inference based on the Bayesian principle, which suggests that a high-quality generated speech should be able to be used as a prompt for subsequent generation using the same TTS model. By leveraging reverse inf","authors_text":"Chao Zhang, Chen Chen, Eng Siong Chng, Siyin Wang, Yuchen Hu","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T13:04:04Z","title":"Robust Zero-Shot Text-to-Speech Synthesis with Reverse Inference Optimization"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02243","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":"sha256:013ba0f44ab9f6c48a3eb4777681272016dff14d7c8d5c5fad49d1eb30a6ee49","target":"record","created_at":"2026-07-05T08:39:11Z","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":"5afb94daaafb405c7916cc77e2892fc3d8f1c3e79e8b30205669033a2f394072","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-07-02T13:04:04Z","title_canon_sha256":"bc43a8725cc1fee3e1a6df9c91a0d5232617faef537939ece09af0a1caddac5b"},"schema_version":"1.0","source":{"id":"2407.02243","kind":"arxiv","version":1}},"canonical_sha256":"c631c2b879914972b8e2734e7b8fed96f61668042ec896e3863fb3f38f71e55e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c631c2b879914972b8e2734e7b8fed96f61668042ec896e3863fb3f38f71e55e","first_computed_at":"2026-07-05T08:39:11.990617Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:39:11.990617Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iIds6BMIOKZ8H22g9ROSroEZ9QtegLFjwxEGrhN2yDy0AIeCmDYvt3oQzrg6zmF593cQOMgnS5zdjOasIiglBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:39:11.990990Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.02243","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:013ba0f44ab9f6c48a3eb4777681272016dff14d7c8d5c5fad49d1eb30a6ee49","sha256:c7abd770d987019d129fb932d29bd96b40fcbb2879b240ed8f2f09427f0062d0"],"state_sha256":"68ced33864603fb6f8598c7b83f8e7f798a0f47dc088d776ad7aee0ff9741e20"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j6FXZBnJcUZEYbvb4AMgM8F98HL2lBc84x0sWtcmAq7Ut7TDxQeO6h/UmBGCWGrjWgZ/y+WJfz0t0d5+e8PlAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T20:34:16.186316Z","bundle_sha256":"3f74126e11ded679b179765a75d544bce23185325ee83ae7b71a0cd7880ed0e8"}}