{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:SU46RERG3P2XK2BU7C2BAMVNRG","short_pith_number":"pith:SU46RERG","canonical_record":{"source":{"id":"2606.20266","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-18T14:14:14Z","cross_cats_sorted":[],"title_canon_sha256":"d0cc2f5c8a41c099c968917e38063c0231f2f54a9491fc6f51ab63cd4f408c0e","abstract_canon_sha256":"c085c1fef3f982a8cf2c83f8cfcfac6dd584aa8ce7dfe7dbb6299786a05718fe"},"schema_version":"1.0"},"canonical_sha256":"9539e89226dbf5756834f8b41032ad89881009a5be2cd403681ef827ce59ec76","source":{"kind":"arxiv","id":"2606.20266","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.20266","created_at":"2026-06-19T16:13:07Z"},{"alias_kind":"arxiv_version","alias_value":"2606.20266v1","created_at":"2026-06-19T16:13:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20266","created_at":"2026-06-19T16:13:07Z"},{"alias_kind":"pith_short_12","alias_value":"SU46RERG3P2X","created_at":"2026-06-19T16:13:07Z"},{"alias_kind":"pith_short_16","alias_value":"SU46RERG3P2XK2BU","created_at":"2026-06-19T16:13:07Z"},{"alias_kind":"pith_short_8","alias_value":"SU46RERG","created_at":"2026-06-19T16:13:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:SU46RERG3P2XK2BU7C2BAMVNRG","target":"record","payload":{"canonical_record":{"source":{"id":"2606.20266","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-18T14:14:14Z","cross_cats_sorted":[],"title_canon_sha256":"d0cc2f5c8a41c099c968917e38063c0231f2f54a9491fc6f51ab63cd4f408c0e","abstract_canon_sha256":"c085c1fef3f982a8cf2c83f8cfcfac6dd584aa8ce7dfe7dbb6299786a05718fe"},"schema_version":"1.0"},"canonical_sha256":"9539e89226dbf5756834f8b41032ad89881009a5be2cd403681ef827ce59ec76","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:13:07.306130Z","signature_b64":"FufvHFFK5oC57tQ03R72m4+liuk8aawuqLoHvx+BFToseUxlb5sA/1J3z6S5kHZCsVI1U5KrgoGgfS2kpe/sCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9539e89226dbf5756834f8b41032ad89881009a5be2cd403681ef827ce59ec76","last_reissued_at":"2026-06-19T16:13:07.305783Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:13:07.305783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.20266","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":"2026-06-19T16:13:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g8kOH7VJ9s/+8qN18a/gH7Yn93TCcsTIjJCfPnv+QQvZd1DHgCa+TvqpR1d0wiJweXTpzeQrW7CJCi5TzyFdAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T05:26:27.560372Z"},"content_sha256":"ccec46da0c9e97bdf66fbcc39a3bc4d94675fe83063275a1d102c4dcd7a36fed","schema_version":"1.0","event_id":"sha256:ccec46da0c9e97bdf66fbcc39a3bc4d94675fe83063275a1d102c4dcd7a36fed"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:SU46RERG3P2XK2BU7C2BAMVNRG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Transcript-Free Flow-Matching Text-to-Speech via Speech Feature Conditioning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Chang D. Yoo, Eunseop Yoon, Hee Suk Yoon, Mark Hasegawa-Johnson, SooHwan Eom","submitted_at":"2026-06-18T14:14:14Z","abstract_excerpt":"Recent flow-matching text-to-speech (TTS) models, such as F5-TTS, rely on a reference transcript at inference time, obtained from an external ASR system. This dependency makes zero-shot TTS brittle for accented or dysarthric speakers, precisely the scenarios where it is most needed. Moreover, we find that text-based reference conditioning can propagate atypical acoustic patterns from atypical speech into synthesis, even when ground-truth transcripts are available. To address this, we propose RTFree-F5, which replaces the reference transcript with continuous self-supervised speech representatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20266","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/2606.20266/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":"2026-06-19T16:13:07Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"YKQI9UuWWWQb3doCrzpBY51VtaRP5u8FfGYWLQ1vpw1R9p4KL9G4o1BmMJyrKudacvBhH/jxRs9RaT7hcHslAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-29T05:26:27.560984Z"},"content_sha256":"a992e926d0a567721ff820e2ae2493d9dc6487623f291f7e787262fff8cf4359","schema_version":"1.0","event_id":"sha256:a992e926d0a567721ff820e2ae2493d9dc6487623f291f7e787262fff8cf4359"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SU46RERG3P2XK2BU7C2BAMVNRG/bundle.json","state_url":"https://pith.science/pith/SU46RERG3P2XK2BU7C2BAMVNRG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SU46RERG3P2XK2BU7C2BAMVNRG/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":"2026-06-29T05:26:27Z","links":{"resolver":"https://pith.science/pith/SU46RERG3P2XK2BU7C2BAMVNRG","bundle":"https://pith.science/pith/SU46RERG3P2XK2BU7C2BAMVNRG/bundle.json","state":"https://pith.science/pith/SU46RERG3P2XK2BU7C2BAMVNRG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SU46RERG3P2XK2BU7C2BAMVNRG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:SU46RERG3P2XK2BU7C2BAMVNRG","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":"c085c1fef3f982a8cf2c83f8cfcfac6dd584aa8ce7dfe7dbb6299786a05718fe","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-18T14:14:14Z","title_canon_sha256":"d0cc2f5c8a41c099c968917e38063c0231f2f54a9491fc6f51ab63cd4f408c0e"},"schema_version":"1.0","source":{"id":"2606.20266","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.20266","created_at":"2026-06-19T16:13:07Z"},{"alias_kind":"arxiv_version","alias_value":"2606.20266v1","created_at":"2026-06-19T16:13:07Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20266","created_at":"2026-06-19T16:13:07Z"},{"alias_kind":"pith_short_12","alias_value":"SU46RERG3P2X","created_at":"2026-06-19T16:13:07Z"},{"alias_kind":"pith_short_16","alias_value":"SU46RERG3P2XK2BU","created_at":"2026-06-19T16:13:07Z"},{"alias_kind":"pith_short_8","alias_value":"SU46RERG","created_at":"2026-06-19T16:13:07Z"}],"graph_snapshots":[{"event_id":"sha256:a992e926d0a567721ff820e2ae2493d9dc6487623f291f7e787262fff8cf4359","target":"graph","created_at":"2026-06-19T16:13:07Z","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/2606.20266/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent flow-matching text-to-speech (TTS) models, such as F5-TTS, rely on a reference transcript at inference time, obtained from an external ASR system. This dependency makes zero-shot TTS brittle for accented or dysarthric speakers, precisely the scenarios where it is most needed. Moreover, we find that text-based reference conditioning can propagate atypical acoustic patterns from atypical speech into synthesis, even when ground-truth transcripts are available. To address this, we propose RTFree-F5, which replaces the reference transcript with continuous self-supervised speech representatio","authors_text":"Chang D. Yoo, Eunseop Yoon, Hee Suk Yoon, Mark Hasegawa-Johnson, SooHwan Eom","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-18T14:14:14Z","title":"Transcript-Free Flow-Matching Text-to-Speech via Speech Feature Conditioning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20266","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:ccec46da0c9e97bdf66fbcc39a3bc4d94675fe83063275a1d102c4dcd7a36fed","target":"record","created_at":"2026-06-19T16:13:07Z","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":"c085c1fef3f982a8cf2c83f8cfcfac6dd584aa8ce7dfe7dbb6299786a05718fe","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2026-06-18T14:14:14Z","title_canon_sha256":"d0cc2f5c8a41c099c968917e38063c0231f2f54a9491fc6f51ab63cd4f408c0e"},"schema_version":"1.0","source":{"id":"2606.20266","kind":"arxiv","version":1}},"canonical_sha256":"9539e89226dbf5756834f8b41032ad89881009a5be2cd403681ef827ce59ec76","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9539e89226dbf5756834f8b41032ad89881009a5be2cd403681ef827ce59ec76","first_computed_at":"2026-06-19T16:13:07.305783Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:13:07.305783Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"FufvHFFK5oC57tQ03R72m4+liuk8aawuqLoHvx+BFToseUxlb5sA/1J3z6S5kHZCsVI1U5KrgoGgfS2kpe/sCg==","signature_status":"signed_v1","signed_at":"2026-06-19T16:13:07.306130Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.20266","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ccec46da0c9e97bdf66fbcc39a3bc4d94675fe83063275a1d102c4dcd7a36fed","sha256:a992e926d0a567721ff820e2ae2493d9dc6487623f291f7e787262fff8cf4359"],"state_sha256":"16fd7f8b382635c0fd508b5f8aca249f83d2b506af21b21b58ce0f071ed1ddf0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"deKMXdSyE1HEnjD0Vhvt/dy8iy7943pMxnq+Rdm54pgriQrfZsQ92P+UkXNyEGBi1iQarxRpHUrRwjpRBTQFAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-29T05:26:27.563415Z","bundle_sha256":"3f3b334544028a6c62e6c93c706bee6aac7fe0641be4a308a33ba36529433e5a"}}