{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:2J6MDGB7LOV3GUMJFNKPZJN7B4","short_pith_number":"pith:2J6MDGB7","canonical_record":{"source":{"id":"2507.13155","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-17T14:17:40Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"d6325c65aae1103e126990af4555c6970c12e3948f7e5c618e99459ab5d34eb6","abstract_canon_sha256":"a16e87af781fed65d72356a1175fc25ba78b08883b84940dff3ca5e9353065c3"},"schema_version":"1.0"},"canonical_sha256":"d27cc1983f5babb351892b54fca5bf0f13e2a5045d339dc4b6cf5e4d93bab490","source":{"kind":"arxiv","id":"2507.13155","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.13155","created_at":"2026-07-05T11:38:55Z"},{"alias_kind":"arxiv_version","alias_value":"2507.13155v1","created_at":"2026-07-05T11:38:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13155","created_at":"2026-07-05T11:38:55Z"},{"alias_kind":"pith_short_12","alias_value":"2J6MDGB7LOV3","created_at":"2026-07-05T11:38:55Z"},{"alias_kind":"pith_short_16","alias_value":"2J6MDGB7LOV3GUMJ","created_at":"2026-07-05T11:38:55Z"},{"alias_kind":"pith_short_8","alias_value":"2J6MDGB7","created_at":"2026-07-05T11:38:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:2J6MDGB7LOV3GUMJFNKPZJN7B4","target":"record","payload":{"canonical_record":{"source":{"id":"2507.13155","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-17T14:17:40Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"d6325c65aae1103e126990af4555c6970c12e3948f7e5c618e99459ab5d34eb6","abstract_canon_sha256":"a16e87af781fed65d72356a1175fc25ba78b08883b84940dff3ca5e9353065c3"},"schema_version":"1.0"},"canonical_sha256":"d27cc1983f5babb351892b54fca5bf0f13e2a5045d339dc4b6cf5e4d93bab490","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:38:55.605012Z","signature_b64":"NF7CwraGehdR/IAJRH4f9MFXBp4NaYM/DPC/tr4IdQKub36CdeLMgViI8pAkat6PB0lxTQRtWGmgVHvV2sekCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d27cc1983f5babb351892b54fca5bf0f13e2a5045d339dc4b6cf5e4d93bab490","last_reissued_at":"2026-07-05T11:38:55.604527Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:38:55.604527Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.13155","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":"2026-07-05T11:38:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Uk9fGJ/QW8nXCRlkENMHXsUETt2GU3Fu8DffyZSsyojZFqiUvZqA7PfPSb1ouIGKddDAfncd9QnASTHurTwuAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T13:08:50.975511Z"},"content_sha256":"4c19e142c2314fd11e2b8404d9cb04b7525a8deedbc4f76edc01a63c96d85270","schema_version":"1.0","event_id":"sha256:4c19e142c2314fd11e2b8404d9cb04b7525a8deedbc4f76edc01a63c96d85270"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:2J6MDGB7LOV3GUMJFNKPZJN7B4","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"NonverbalTTS: A Public English Corpus of Text-Aligned Nonverbal Vocalizations with Emotion Annotations for Text-to-Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"cs.LG","authors_text":"Daria Diatlova, Egor Spirin, Maksim Borisov","submitted_at":"2025-07-17T14:17:40Z","abstract_excerpt":"Current expressive speech synthesis models are constrained by the limited availability of open-source datasets containing diverse nonverbal vocalizations (NVs). In this work, we introduce NonverbalTTS (NVTTS), a 17-hour open-access dataset annotated with 10 types of NVs (e.g., laughter, coughs) and 8 emotional categories. The dataset is derived from popular sources, VoxCeleb and Expresso, using automated detection followed by human validation. We propose a comprehensive pipeline that integrates automatic speech recognition (ASR), NV tagging, emotion classification, and a fusion algorithm to me"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.13155","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/2507.13155/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":"2026-07-05T11:38:55Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gSGH+Tg/dyCqh+raY9e+N90o8qAc7MVVS/VST21vN99vbJ26xBtCTl3fAyi/EN1eCUmM/437AiKeeaU7DeBPCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T13:08:50.976175Z"},"content_sha256":"c2db4459fd1c3397c8e3499f4ac3a66466503fd919e37c877548903d2df3eebb","schema_version":"1.0","event_id":"sha256:c2db4459fd1c3397c8e3499f4ac3a66466503fd919e37c877548903d2df3eebb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2J6MDGB7LOV3GUMJFNKPZJN7B4/bundle.json","state_url":"https://pith.science/pith/2J6MDGB7LOV3GUMJFNKPZJN7B4/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2J6MDGB7LOV3GUMJFNKPZJN7B4/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":"2026-08-12T13:08:50Z","links":{"resolver":"https://pith.science/pith/2J6MDGB7LOV3GUMJFNKPZJN7B4","bundle":"https://pith.science/pith/2J6MDGB7LOV3GUMJFNKPZJN7B4/bundle.json","state":"https://pith.science/pith/2J6MDGB7LOV3GUMJFNKPZJN7B4/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2J6MDGB7LOV3GUMJFNKPZJN7B4/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2J6MDGB7LOV3GUMJFNKPZJN7B4","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":"a16e87af781fed65d72356a1175fc25ba78b08883b84940dff3ca5e9353065c3","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-17T14:17:40Z","title_canon_sha256":"d6325c65aae1103e126990af4555c6970c12e3948f7e5c618e99459ab5d34eb6"},"schema_version":"1.0","source":{"id":"2507.13155","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.13155","created_at":"2026-07-05T11:38:55Z"},{"alias_kind":"arxiv_version","alias_value":"2507.13155v1","created_at":"2026-07-05T11:38:55Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.13155","created_at":"2026-07-05T11:38:55Z"},{"alias_kind":"pith_short_12","alias_value":"2J6MDGB7LOV3","created_at":"2026-07-05T11:38:55Z"},{"alias_kind":"pith_short_16","alias_value":"2J6MDGB7LOV3GUMJ","created_at":"2026-07-05T11:38:55Z"},{"alias_kind":"pith_short_8","alias_value":"2J6MDGB7","created_at":"2026-07-05T11:38:55Z"}],"graph_snapshots":[{"event_id":"sha256:c2db4459fd1c3397c8e3499f4ac3a66466503fd919e37c877548903d2df3eebb","target":"graph","created_at":"2026-07-05T11:38:55Z","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/2507.13155/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current expressive speech synthesis models are constrained by the limited availability of open-source datasets containing diverse nonverbal vocalizations (NVs). In this work, we introduce NonverbalTTS (NVTTS), a 17-hour open-access dataset annotated with 10 types of NVs (e.g., laughter, coughs) and 8 emotional categories. The dataset is derived from popular sources, VoxCeleb and Expresso, using automated detection followed by human validation. We propose a comprehensive pipeline that integrates automatic speech recognition (ASR), NV tagging, emotion classification, and a fusion algorithm to me","authors_text":"Daria Diatlova, Egor Spirin, Maksim Borisov","cross_cats":["cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-17T14:17:40Z","title":"NonverbalTTS: A Public English Corpus of Text-Aligned Nonverbal Vocalizations with Emotion Annotations for Text-to-Speech"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.13155","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":"sha256:4c19e142c2314fd11e2b8404d9cb04b7525a8deedbc4f76edc01a63c96d85270","target":"record","created_at":"2026-07-05T11:38:55Z","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":"a16e87af781fed65d72356a1175fc25ba78b08883b84940dff3ca5e9353065c3","cross_cats_sorted":["cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-07-17T14:17:40Z","title_canon_sha256":"d6325c65aae1103e126990af4555c6970c12e3948f7e5c618e99459ab5d34eb6"},"schema_version":"1.0","source":{"id":"2507.13155","kind":"arxiv","version":1}},"canonical_sha256":"d27cc1983f5babb351892b54fca5bf0f13e2a5045d339dc4b6cf5e4d93bab490","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d27cc1983f5babb351892b54fca5bf0f13e2a5045d339dc4b6cf5e4d93bab490","first_computed_at":"2026-07-05T11:38:55.604527Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:38:55.604527Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"NF7CwraGehdR/IAJRH4f9MFXBp4NaYM/DPC/tr4IdQKub36CdeLMgViI8pAkat6PB0lxTQRtWGmgVHvV2sekCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:38:55.605012Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.13155","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4c19e142c2314fd11e2b8404d9cb04b7525a8deedbc4f76edc01a63c96d85270","sha256:c2db4459fd1c3397c8e3499f4ac3a66466503fd919e37c877548903d2df3eebb"],"state_sha256":"410a54378ac3a208dfdfa1c48001d091005242f5271794a5eb171645a468ff89"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y+orPZRqkVBH7On2g1e/L3nIK58FPfa7o3iZeZ2g7ZFXdEIrWmZUpxavd8eiX+7KY+MWKR/daWi+BmPIYVZlAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T13:08:50.980887Z","bundle_sha256":"59713b2d29cb22d7afa55410ff4d44896322d0c548bd55833bdbed0ded705d1e"}}