{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:X4TVX2KZFUEWUAMDT2Y3AY72YE","short_pith_number":"pith:X4TVX2KZ","canonical_record":{"source":{"id":"2407.12707","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-07-17T16:30:27Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"f8bc0512143485ca6066323cbd516a93e018cc4840250c46cb1900dd1378b977","abstract_canon_sha256":"5345a3ceffd66ed74429e44142f04f99573f68e9fd04784376f7b3c56f0bd7e0"},"schema_version":"1.0"},"canonical_sha256":"bf275be9592d096a01839eb1b063fac128a25b2da6ca1a3bbd7167fb65cedd87","source":{"kind":"arxiv","id":"2407.12707","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12707","created_at":"2026-07-05T09:42:28Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12707v3","created_at":"2026-07-05T09:42:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12707","created_at":"2026-07-05T09:42:28Z"},{"alias_kind":"pith_short_12","alias_value":"X4TVX2KZFUEW","created_at":"2026-07-05T09:42:28Z"},{"alias_kind":"pith_short_16","alias_value":"X4TVX2KZFUEWUAMD","created_at":"2026-07-05T09:42:28Z"},{"alias_kind":"pith_short_8","alias_value":"X4TVX2KZ","created_at":"2026-07-05T09:42:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:X4TVX2KZFUEWUAMDT2Y3AY72YE","target":"record","payload":{"canonical_record":{"source":{"id":"2407.12707","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-07-17T16:30:27Z","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"title_canon_sha256":"f8bc0512143485ca6066323cbd516a93e018cc4840250c46cb1900dd1378b977","abstract_canon_sha256":"5345a3ceffd66ed74429e44142f04f99573f68e9fd04784376f7b3c56f0bd7e0"},"schema_version":"1.0"},"canonical_sha256":"bf275be9592d096a01839eb1b063fac128a25b2da6ca1a3bbd7167fb65cedd87","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:42:28.045991Z","signature_b64":"pYSU6yZKwlQC85x0bZBkxbb0S6ybEokUATOHEo11FWxCR1jWIEsGFgi12BW7sg2HE+QYSEQKkzW4zHQXmjqHCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf275be9592d096a01839eb1b063fac128a25b2da6ca1a3bbd7167fb65cedd87","last_reissued_at":"2026-07-05T09:42:28.045501Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:42:28.045501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.12707","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":"2026-07-05T09:42:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z/aUDSECgRBPaAZ8cFSnxvuZqO74KoJwXP1ywZyuaOvUGR9400vGeVPK6BC94q7C4Dyu0NnhBOnjSFONab9dAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:16:41.517306Z"},"content_sha256":"05e95e64a3712ff2645b3dec616cb0f04cb4daf1c407caa39dbc4825bc874499","schema_version":"1.0","event_id":"sha256:05e95e64a3712ff2645b3dec616cb0f04cb4daf1c407caa39dbc4825bc874499"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:X4TVX2KZFUEWUAMDT2Y3AY72YE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TTSDS -- Text-to-Speech Distribution Score","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.LG","cs.SD"],"primary_cat":"eess.AS","authors_text":"Christoph Minixhofer, Ond\\v{r}ej Klejch, Peter Bell","submitted_at":"2024-07-17T16:30:27Z","abstract_excerpt":"Many recently published Text-to-Speech (TTS) systems produce audio close to real speech. However, TTS evaluation needs to be revisited to make sense of the results obtained with the new architectures, approaches and datasets. We propose evaluating the quality of synthetic speech as a combination of multiple factors such as prosody, speaker identity, and intelligibility. Our approach assesses how well synthetic speech mirrors real speech by obtaining correlates of each factor and measuring their distance from both real speech datasets and noise datasets. We benchmark 35 TTS systems developed be"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12707","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/2407.12707/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":"2026-07-05T09:42:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MGgEKd+9iMWjpNVHgyxYV6ukpzuLXHHvZMaYtYcjlGV0wZ+5/qdR8ddmpzVyBijeHNGP/r6U5DGkd8BhJw5WAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T04:16:41.517933Z"},"content_sha256":"a7694bb4014d685b028305150aa0ae3606b3532b35d8769eb10733c973fa5296","schema_version":"1.0","event_id":"sha256:a7694bb4014d685b028305150aa0ae3606b3532b35d8769eb10733c973fa5296"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/X4TVX2KZFUEWUAMDT2Y3AY72YE/bundle.json","state_url":"https://pith.science/pith/X4TVX2KZFUEWUAMDT2Y3AY72YE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/X4TVX2KZFUEWUAMDT2Y3AY72YE/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":"2026-08-09T04:16:41Z","links":{"resolver":"https://pith.science/pith/X4TVX2KZFUEWUAMDT2Y3AY72YE","bundle":"https://pith.science/pith/X4TVX2KZFUEWUAMDT2Y3AY72YE/bundle.json","state":"https://pith.science/pith/X4TVX2KZFUEWUAMDT2Y3AY72YE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/X4TVX2KZFUEWUAMDT2Y3AY72YE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:X4TVX2KZFUEWUAMDT2Y3AY72YE","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":"5345a3ceffd66ed74429e44142f04f99573f68e9fd04784376f7b3c56f0bd7e0","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-07-17T16:30:27Z","title_canon_sha256":"f8bc0512143485ca6066323cbd516a93e018cc4840250c46cb1900dd1378b977"},"schema_version":"1.0","source":{"id":"2407.12707","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.12707","created_at":"2026-07-05T09:42:28Z"},{"alias_kind":"arxiv_version","alias_value":"2407.12707v3","created_at":"2026-07-05T09:42:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12707","created_at":"2026-07-05T09:42:28Z"},{"alias_kind":"pith_short_12","alias_value":"X4TVX2KZFUEW","created_at":"2026-07-05T09:42:28Z"},{"alias_kind":"pith_short_16","alias_value":"X4TVX2KZFUEWUAMD","created_at":"2026-07-05T09:42:28Z"},{"alias_kind":"pith_short_8","alias_value":"X4TVX2KZ","created_at":"2026-07-05T09:42:28Z"}],"graph_snapshots":[{"event_id":"sha256:a7694bb4014d685b028305150aa0ae3606b3532b35d8769eb10733c973fa5296","target":"graph","created_at":"2026-07-05T09:42:28Z","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/2407.12707/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Many recently published Text-to-Speech (TTS) systems produce audio close to real speech. However, TTS evaluation needs to be revisited to make sense of the results obtained with the new architectures, approaches and datasets. We propose evaluating the quality of synthetic speech as a combination of multiple factors such as prosody, speaker identity, and intelligibility. Our approach assesses how well synthetic speech mirrors real speech by obtaining correlates of each factor and measuring their distance from both real speech datasets and noise datasets. We benchmark 35 TTS systems developed be","authors_text":"Christoph Minixhofer, Ond\\v{r}ej Klejch, Peter Bell","cross_cats":["cs.CL","cs.LG","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-07-17T16:30:27Z","title":"TTSDS -- Text-to-Speech Distribution Score"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12707","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":"sha256:05e95e64a3712ff2645b3dec616cb0f04cb4daf1c407caa39dbc4825bc874499","target":"record","created_at":"2026-07-05T09:42:28Z","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":"5345a3ceffd66ed74429e44142f04f99573f68e9fd04784376f7b3c56f0bd7e0","cross_cats_sorted":["cs.CL","cs.LG","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-07-17T16:30:27Z","title_canon_sha256":"f8bc0512143485ca6066323cbd516a93e018cc4840250c46cb1900dd1378b977"},"schema_version":"1.0","source":{"id":"2407.12707","kind":"arxiv","version":3}},"canonical_sha256":"bf275be9592d096a01839eb1b063fac128a25b2da6ca1a3bbd7167fb65cedd87","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bf275be9592d096a01839eb1b063fac128a25b2da6ca1a3bbd7167fb65cedd87","first_computed_at":"2026-07-05T09:42:28.045501Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:42:28.045501Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"pYSU6yZKwlQC85x0bZBkxbb0S6ybEokUATOHEo11FWxCR1jWIEsGFgi12BW7sg2HE+QYSEQKkzW4zHQXmjqHCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:42:28.045991Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.12707","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:05e95e64a3712ff2645b3dec616cb0f04cb4daf1c407caa39dbc4825bc874499","sha256:a7694bb4014d685b028305150aa0ae3606b3532b35d8769eb10733c973fa5296"],"state_sha256":"c824f8ad9e59199931c54f2d92a7348ce3fa2f339d81df23f67d64f89e992da3"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yPQ1vWpXc38xGFb3qhl6vgOTtSKaN9u+qKkg+iy0/qQyDcuRGeovK6dZpdsVKoIU4MWkQdjfb2SiOEG0WZ6nDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T04:16:41.522296Z","bundle_sha256":"0f80751a4c44e1a71de0f9b62ecaef3d02e0c0f545e6c4ad38e122d22741d09f"}}