{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:KF3QR6E7PCISI5DB53QBVV2W6U","short_pith_number":"pith:KF3QR6E7","canonical_record":{"source":{"id":"2506.16381","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-19T15:08:01Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"3db0eb5b6ec43e419f4398a89e8acc4aa1121e7a3a7054d09c398d258392edd3","abstract_canon_sha256":"82169052f331a48a9c2d7f90eabf0739d3ceb0e1e325135fc39b79909058f0a6"},"schema_version":"1.0"},"canonical_sha256":"517708f89f7891247461eee01ad756f51dd06b7c3f0f455109cacccbefa097a3","source":{"kind":"arxiv","id":"2506.16381","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.16381","created_at":"2026-07-05T11:24:35Z"},{"alias_kind":"arxiv_version","alias_value":"2506.16381v1","created_at":"2026-07-05T11:24:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16381","created_at":"2026-07-05T11:24:35Z"},{"alias_kind":"pith_short_12","alias_value":"KF3QR6E7PCIS","created_at":"2026-07-05T11:24:35Z"},{"alias_kind":"pith_short_16","alias_value":"KF3QR6E7PCISI5DB","created_at":"2026-07-05T11:24:35Z"},{"alias_kind":"pith_short_8","alias_value":"KF3QR6E7","created_at":"2026-07-05T11:24:35Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:KF3QR6E7PCISI5DB53QBVV2W6U","target":"record","payload":{"canonical_record":{"source":{"id":"2506.16381","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-19T15:08:01Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"3db0eb5b6ec43e419f4398a89e8acc4aa1121e7a3a7054d09c398d258392edd3","abstract_canon_sha256":"82169052f331a48a9c2d7f90eabf0739d3ceb0e1e325135fc39b79909058f0a6"},"schema_version":"1.0"},"canonical_sha256":"517708f89f7891247461eee01ad756f51dd06b7c3f0f455109cacccbefa097a3","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:24:35.532611Z","signature_b64":"ZwHTqi+6novCWDd9XXRNksNJ3n89kuzQP4KeNnCTcOjP/shJ9ksQdGdTLW2f9oNdUif+1hzJk+nMLytx5frNBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"517708f89f7891247461eee01ad756f51dd06b7c3f0f455109cacccbefa097a3","last_reissued_at":"2026-07-05T11:24:35.532068Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:24:35.532068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2506.16381","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":"2026-07-05T11:24:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GwKg2yF7PAgRrQ0zCafyUJFWC4+BciVjAl7G5yJ+s0W7xE+QzCJeavL1qJ0DherL4+wfODw3bkThn1vwXDjUCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:11:12.409192Z"},"content_sha256":"8476e634b75a39b9e64fe37f7577339620f1f64fa2c9b32a3476517b98cba7fa","schema_version":"1.0","event_id":"sha256:8476e634b75a39b9e64fe37f7577339620f1f64fa2c9b32a3476517b98cba7fa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:KF3QR6E7PCISI5DB53QBVV2W6U","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"InstructTTSEval: Benchmarking Complex Natural-Language Instruction Following in Text-to-Speech Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CL","authors_text":"Chenchen Yang, Dong Zhang, Kexin Huang, Liwei Fan, Qian Tu, Qinyuan Cheng, Shimin Li, Xipeng Qiu, Zhaoye Fei","submitted_at":"2025-06-19T15:08:01Z","abstract_excerpt":"In modern speech synthesis, paralinguistic information--such as a speaker's vocal timbre, emotional state, and dynamic prosody--plays a critical role in conveying nuance beyond mere semantics. Traditional Text-to-Speech (TTS) systems rely on fixed style labels or inserting a speech prompt to control these cues, which severely limits flexibility. Recent attempts seek to employ natural-language instructions to modulate paralinguistic features, substantially improving the generalization of instruction-driven TTS models. Although many TTS systems now support customized synthesis via textual descri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16381","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/2506.16381/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":"2026-07-05T11:24:35Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"krPah5/74ObQTLo4BCBSXItXJU7d9ufsskhMfYhLl5X0MCD7lBS1TtWfXSgL4i6kP3Pue108VwDdPT1km4StDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T07:11:12.409683Z"},"content_sha256":"aa1ff36e2a8f8d50317ec99a58d85c003adff2abcea134d7a0199f17ec857df1","schema_version":"1.0","event_id":"sha256:aa1ff36e2a8f8d50317ec99a58d85c003adff2abcea134d7a0199f17ec857df1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/KF3QR6E7PCISI5DB53QBVV2W6U/bundle.json","state_url":"https://pith.science/pith/KF3QR6E7PCISI5DB53QBVV2W6U/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/KF3QR6E7PCISI5DB53QBVV2W6U/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":"2026-08-05T07:11:12Z","links":{"resolver":"https://pith.science/pith/KF3QR6E7PCISI5DB53QBVV2W6U","bundle":"https://pith.science/pith/KF3QR6E7PCISI5DB53QBVV2W6U/bundle.json","state":"https://pith.science/pith/KF3QR6E7PCISI5DB53QBVV2W6U/state.json","well_known_bundle":"https://pith.science/.well-known/pith/KF3QR6E7PCISI5DB53QBVV2W6U/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KF3QR6E7PCISI5DB53QBVV2W6U","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":"82169052f331a48a9c2d7f90eabf0739d3ceb0e1e325135fc39b79909058f0a6","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-19T15:08:01Z","title_canon_sha256":"3db0eb5b6ec43e419f4398a89e8acc4aa1121e7a3a7054d09c398d258392edd3"},"schema_version":"1.0","source":{"id":"2506.16381","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.16381","created_at":"2026-07-05T11:24:35Z"},{"alias_kind":"arxiv_version","alias_value":"2506.16381v1","created_at":"2026-07-05T11:24:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.16381","created_at":"2026-07-05T11:24:35Z"},{"alias_kind":"pith_short_12","alias_value":"KF3QR6E7PCIS","created_at":"2026-07-05T11:24:35Z"},{"alias_kind":"pith_short_16","alias_value":"KF3QR6E7PCISI5DB","created_at":"2026-07-05T11:24:35Z"},{"alias_kind":"pith_short_8","alias_value":"KF3QR6E7","created_at":"2026-07-05T11:24:35Z"}],"graph_snapshots":[{"event_id":"sha256:aa1ff36e2a8f8d50317ec99a58d85c003adff2abcea134d7a0199f17ec857df1","target":"graph","created_at":"2026-07-05T11:24:35Z","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/2506.16381/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In modern speech synthesis, paralinguistic information--such as a speaker's vocal timbre, emotional state, and dynamic prosody--plays a critical role in conveying nuance beyond mere semantics. Traditional Text-to-Speech (TTS) systems rely on fixed style labels or inserting a speech prompt to control these cues, which severely limits flexibility. Recent attempts seek to employ natural-language instructions to modulate paralinguistic features, substantially improving the generalization of instruction-driven TTS models. Although many TTS systems now support customized synthesis via textual descri","authors_text":"Chenchen Yang, Dong Zhang, Kexin Huang, Liwei Fan, Qian Tu, Qinyuan Cheng, Shimin Li, Xipeng Qiu, Zhaoye Fei","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-19T15:08:01Z","title":"InstructTTSEval: Benchmarking Complex Natural-Language Instruction Following in Text-to-Speech Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.16381","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":"sha256:8476e634b75a39b9e64fe37f7577339620f1f64fa2c9b32a3476517b98cba7fa","target":"record","created_at":"2026-07-05T11:24:35Z","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":"82169052f331a48a9c2d7f90eabf0739d3ceb0e1e325135fc39b79909058f0a6","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-19T15:08:01Z","title_canon_sha256":"3db0eb5b6ec43e419f4398a89e8acc4aa1121e7a3a7054d09c398d258392edd3"},"schema_version":"1.0","source":{"id":"2506.16381","kind":"arxiv","version":1}},"canonical_sha256":"517708f89f7891247461eee01ad756f51dd06b7c3f0f455109cacccbefa097a3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"517708f89f7891247461eee01ad756f51dd06b7c3f0f455109cacccbefa097a3","first_computed_at":"2026-07-05T11:24:35.532068Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:24:35.532068Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZwHTqi+6novCWDd9XXRNksNJ3n89kuzQP4KeNnCTcOjP/shJ9ksQdGdTLW2f9oNdUif+1hzJk+nMLytx5frNBA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:24:35.532611Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.16381","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8476e634b75a39b9e64fe37f7577339620f1f64fa2c9b32a3476517b98cba7fa","sha256:aa1ff36e2a8f8d50317ec99a58d85c003adff2abcea134d7a0199f17ec857df1"],"state_sha256":"df07c76203f390a74b4f505a18cbefca2012374196a7f8ad74315fabcea56ef6"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RHvtW72MXw1LbBN6w2bQv7ro0KBeGCPh2qjn7P7ka7waS484qbhtpoo3rVQUv2uvEolpqNLdSERI3ie4ltwaBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T07:11:12.413291Z","bundle_sha256":"01f9edcfcc7b828ca44ef46ee1cf55c7512b1296663502da0b8171fe9b426bd9"}}