{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:WIDG2KLUX4SA4EBOGIGQOCLGXD","short_pith_number":"pith:WIDG2KLU","canonical_record":{"source":{"id":"2406.00654","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-02T07:54:33Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"aa3f20e87e5d4f3aa7269035a74634544cf5aefecd4c25edbfb9a2edcf76b328","abstract_canon_sha256":"1c427e55309e19bd7fe12e9d6f452fbf31ec8ea0f9ae32e463054d83640ed40d"},"schema_version":"1.0"},"canonical_sha256":"b2066d2974bf240e102e320d070966b8ddeb617f801c4758d70718fbee264af7","source":{"kind":"arxiv","id":"2406.00654","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.00654","created_at":"2026-07-05T08:26:28Z"},{"alias_kind":"arxiv_version","alias_value":"2406.00654v1","created_at":"2026-07-05T08:26:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00654","created_at":"2026-07-05T08:26:28Z"},{"alias_kind":"pith_short_12","alias_value":"WIDG2KLUX4SA","created_at":"2026-07-05T08:26:28Z"},{"alias_kind":"pith_short_16","alias_value":"WIDG2KLUX4SA4EBO","created_at":"2026-07-05T08:26:28Z"},{"alias_kind":"pith_short_8","alias_value":"WIDG2KLU","created_at":"2026-07-05T08:26:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:WIDG2KLUX4SA4EBOGIGQOCLGXD","target":"record","payload":{"canonical_record":{"source":{"id":"2406.00654","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-02T07:54:33Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"aa3f20e87e5d4f3aa7269035a74634544cf5aefecd4c25edbfb9a2edcf76b328","abstract_canon_sha256":"1c427e55309e19bd7fe12e9d6f452fbf31ec8ea0f9ae32e463054d83640ed40d"},"schema_version":"1.0"},"canonical_sha256":"b2066d2974bf240e102e320d070966b8ddeb617f801c4758d70718fbee264af7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:28.727053Z","signature_b64":"qduxxoazGlOzJg4/ZLlJ7UK4fLF1/yyRwIH/oseeYnQH4poMyucl4vnsgdtZgALUC1yI/Epqh77HggQJI5Y6AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b2066d2974bf240e102e320d070966b8ddeb617f801c4758d70718fbee264af7","last_reissued_at":"2026-07-05T08:26:28.726617Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:28.726617Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.00654","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":"2026-07-05T08:26:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9b8nI18pi670yom0/2AGpXfLIDBMlkFU28oMcH4GTcBP/AkXp44nwvUgZ775DoklaBdjrTqIM6sgIVpXW5M7BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:46:53.116146Z"},"content_sha256":"db406c58ade8e6b2590a17b87cb50facab25033c25bb3f2e5dacbe9587dd1ec7","schema_version":"1.0","event_id":"sha256:db406c58ade8e6b2590a17b87cb50facab25033c25bb3f2e5dacbe9587dd1ec7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:WIDG2KLUX4SA4EBOGIGQOCLGXD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Enhancing Zero-shot Text-to-Speech Synthesis with Human Feedback","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, Helin Wang, Wen Wu, Yuchen Hu","submitted_at":"2024-06-02T07:54:33Z","abstract_excerpt":"In recent years, text-to-speech (TTS) technology has witnessed impressive advancements, particularly with large-scale training datasets, showcasing human-level speech quality and impressive zero-shot capabilities on unseen speakers. However, despite human subjective evaluations, such as the mean opinion score (MOS), remaining the gold standard for assessing the quality of synthetic speech, even state-of-the-art TTS approaches have kept human feedback isolated from training that resulted in mismatched training objectives and evaluation metrics. In this work, we investigate a novel topic of inte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00654","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/2406.00654/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":"2026-07-05T08:26:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mc0yVRd9rlUn4SO1HuqrzIVemiz1YhaY+1+1tkFVV1zY0OaDITaYIV+SlGTB9juDxR5RzG3Wxzip8WzLLalTDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T18:46:53.116698Z"},"content_sha256":"d7a43d03bf1a34cf0d6bff2277170eeb6c0596967c681f364caa24cfa4585fc8","schema_version":"1.0","event_id":"sha256:d7a43d03bf1a34cf0d6bff2277170eeb6c0596967c681f364caa24cfa4585fc8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/WIDG2KLUX4SA4EBOGIGQOCLGXD/bundle.json","state_url":"https://pith.science/pith/WIDG2KLUX4SA4EBOGIGQOCLGXD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/WIDG2KLUX4SA4EBOGIGQOCLGXD/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":"2026-08-07T18:46:53Z","links":{"resolver":"https://pith.science/pith/WIDG2KLUX4SA4EBOGIGQOCLGXD","bundle":"https://pith.science/pith/WIDG2KLUX4SA4EBOGIGQOCLGXD/bundle.json","state":"https://pith.science/pith/WIDG2KLUX4SA4EBOGIGQOCLGXD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/WIDG2KLUX4SA4EBOGIGQOCLGXD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:WIDG2KLUX4SA4EBOGIGQOCLGXD","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":"1c427e55309e19bd7fe12e9d6f452fbf31ec8ea0f9ae32e463054d83640ed40d","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-02T07:54:33Z","title_canon_sha256":"aa3f20e87e5d4f3aa7269035a74634544cf5aefecd4c25edbfb9a2edcf76b328"},"schema_version":"1.0","source":{"id":"2406.00654","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.00654","created_at":"2026-07-05T08:26:28Z"},{"alias_kind":"arxiv_version","alias_value":"2406.00654v1","created_at":"2026-07-05T08:26:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.00654","created_at":"2026-07-05T08:26:28Z"},{"alias_kind":"pith_short_12","alias_value":"WIDG2KLUX4SA","created_at":"2026-07-05T08:26:28Z"},{"alias_kind":"pith_short_16","alias_value":"WIDG2KLUX4SA4EBO","created_at":"2026-07-05T08:26:28Z"},{"alias_kind":"pith_short_8","alias_value":"WIDG2KLU","created_at":"2026-07-05T08:26:28Z"}],"graph_snapshots":[{"event_id":"sha256:d7a43d03bf1a34cf0d6bff2277170eeb6c0596967c681f364caa24cfa4585fc8","target":"graph","created_at":"2026-07-05T08:26:28Z","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/2406.00654/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, text-to-speech (TTS) technology has witnessed impressive advancements, particularly with large-scale training datasets, showcasing human-level speech quality and impressive zero-shot capabilities on unseen speakers. However, despite human subjective evaluations, such as the mean opinion score (MOS), remaining the gold standard for assessing the quality of synthetic speech, even state-of-the-art TTS approaches have kept human feedback isolated from training that resulted in mismatched training objectives and evaluation metrics. In this work, we investigate a novel topic of inte","authors_text":"Chao Zhang, Chen Chen, Eng Siong Chng, Helin Wang, Wen Wu, Yuchen Hu","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-02T07:54:33Z","title":"Enhancing Zero-shot Text-to-Speech Synthesis with Human Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.00654","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:db406c58ade8e6b2590a17b87cb50facab25033c25bb3f2e5dacbe9587dd1ec7","target":"record","created_at":"2026-07-05T08:26:28Z","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":"1c427e55309e19bd7fe12e9d6f452fbf31ec8ea0f9ae32e463054d83640ed40d","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-02T07:54:33Z","title_canon_sha256":"aa3f20e87e5d4f3aa7269035a74634544cf5aefecd4c25edbfb9a2edcf76b328"},"schema_version":"1.0","source":{"id":"2406.00654","kind":"arxiv","version":1}},"canonical_sha256":"b2066d2974bf240e102e320d070966b8ddeb617f801c4758d70718fbee264af7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b2066d2974bf240e102e320d070966b8ddeb617f801c4758d70718fbee264af7","first_computed_at":"2026-07-05T08:26:28.726617Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:26:28.726617Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qduxxoazGlOzJg4/ZLlJ7UK4fLF1/yyRwIH/oseeYnQH4poMyucl4vnsgdtZgALUC1yI/Epqh77HggQJI5Y6AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:26:28.727053Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.00654","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db406c58ade8e6b2590a17b87cb50facab25033c25bb3f2e5dacbe9587dd1ec7","sha256:d7a43d03bf1a34cf0d6bff2277170eeb6c0596967c681f364caa24cfa4585fc8"],"state_sha256":"3a714605299921b84f5a2786dfd8b3c013a1d107617752de28e0637301362a13"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GgKJRLI69MZwHTDTGSgqBYZhR15B5Gx09Wj9eLDny5nvLgkoqkLZbJGpPgOWzxTxzE8EOO+FWZtv+8JwGL7jAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T18:46:53.121821Z","bundle_sha256":"d6ebfb939b1676b0bb89d98c4847a937c2674b45ae2323c124ba78887f3418b5"}}