{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:IWRF3EOCIEQY3KPYLQR7K7ECNQ","short_pith_number":"pith:IWRF3EOC","canonical_record":{"source":{"id":"2409.07259","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-11T13:28:41Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"23172a1b273ef2db6f6bf3960a32c93ca3e936a8a0f130ab2c1aa92bd101d2e9","abstract_canon_sha256":"0b0d619f1fca3f4ee7ec7eba4addc116ac2efd3c58a908c3b29f1bad6e301245"},"schema_version":"1.0"},"canonical_sha256":"45a25d91c241218da9f85c23f57c826c0a9d7226bc4efa4c1db36cb7dd11606d","source":{"kind":"arxiv","id":"2409.07259","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.07259","created_at":"2026-07-05T09:05:47Z"},{"alias_kind":"arxiv_version","alias_value":"2409.07259v1","created_at":"2026-07-05T09:05:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.07259","created_at":"2026-07-05T09:05:47Z"},{"alias_kind":"pith_short_12","alias_value":"IWRF3EOCIEQY","created_at":"2026-07-05T09:05:47Z"},{"alias_kind":"pith_short_16","alias_value":"IWRF3EOCIEQY3KPY","created_at":"2026-07-05T09:05:47Z"},{"alias_kind":"pith_short_8","alias_value":"IWRF3EOC","created_at":"2026-07-05T09:05:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:IWRF3EOCIEQY3KPYLQR7K7ECNQ","target":"record","payload":{"canonical_record":{"source":{"id":"2409.07259","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-11T13:28:41Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"23172a1b273ef2db6f6bf3960a32c93ca3e936a8a0f130ab2c1aa92bd101d2e9","abstract_canon_sha256":"0b0d619f1fca3f4ee7ec7eba4addc116ac2efd3c58a908c3b29f1bad6e301245"},"schema_version":"1.0"},"canonical_sha256":"45a25d91c241218da9f85c23f57c826c0a9d7226bc4efa4c1db36cb7dd11606d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:05:47.938290Z","signature_b64":"X2guGqrTBN6syPHCmWTIOBZ1zEUeKHBHXQCX+6Zvh+LFlgPYT7ZAeBpmS/TldhyxRpNsWSraaghXCUMf1H4zDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45a25d91c241218da9f85c23f57c826c0a9d7226bc4efa4c1db36cb7dd11606d","last_reissued_at":"2026-07-05T09:05:47.937808Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:05:47.937808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2409.07259","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":"2026-07-05T09:05:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N2h9UZIpK1LNHIVbVlM/v9rdMa2etD5N9E42+n3ysyBxI7D3RtYYRtx5sEIJO8T2zwxe9TMey8a5J6pWIXpFCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:22:55.122216Z"},"content_sha256":"20827f008d06d2158d7135f3bfe86276edd459fc6349f0e646e617587b9b63ee","schema_version":"1.0","event_id":"sha256:20827f008d06d2158d7135f3bfe86276edd459fc6349f0e646e617587b9b63ee"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:IWRF3EOCIEQY3KPYLQR7K7ECNQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ManaTTS Persian: a recipe for creating TTS datasets for lower resource languages","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Hamid R. Rabiee, Mahta Fetrat Qharabagh, Zahra Dehghanian","submitted_at":"2024-09-11T13:28:41Z","abstract_excerpt":"In this study, we introduce ManaTTS, the most extensive publicly accessible single-speaker Persian corpus, and a comprehensive framework for collecting transcribed speech datasets for the Persian language. ManaTTS, released under the open CC-0 license, comprises approximately 86 hours of audio with a sampling rate of 44.1 kHz. Alongside ManaTTS, we also generated the VirgoolInformal dataset to evaluate Persian speech recognition models used for forced alignment, extending over 5 hours of audio. The datasets are supported by a fully transparent, MIT-licensed pipeline, a testament to innovation "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.07259","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/2409.07259/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":"2026-07-05T09:05:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tAgaamf2Vg7y+DxhxxPP2SaKjoWSoDE+anpAHRCTVJLAzsoKAFoV/LY1XMu8GAM/cpqA+EkjKECltuekr98rCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T16:22:55.123038Z"},"content_sha256":"7c5db515bce042031a8cb48527fdcdd452359787ad139debdd08a38293eec942","schema_version":"1.0","event_id":"sha256:7c5db515bce042031a8cb48527fdcdd452359787ad139debdd08a38293eec942"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IWRF3EOCIEQY3KPYLQR7K7ECNQ/bundle.json","state_url":"https://pith.science/pith/IWRF3EOCIEQY3KPYLQR7K7ECNQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IWRF3EOCIEQY3KPYLQR7K7ECNQ/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":"2026-08-08T16:22:55Z","links":{"resolver":"https://pith.science/pith/IWRF3EOCIEQY3KPYLQR7K7ECNQ","bundle":"https://pith.science/pith/IWRF3EOCIEQY3KPYLQR7K7ECNQ/bundle.json","state":"https://pith.science/pith/IWRF3EOCIEQY3KPYLQR7K7ECNQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IWRF3EOCIEQY3KPYLQR7K7ECNQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:IWRF3EOCIEQY3KPYLQR7K7ECNQ","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":"0b0d619f1fca3f4ee7ec7eba4addc116ac2efd3c58a908c3b29f1bad6e301245","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-11T13:28:41Z","title_canon_sha256":"23172a1b273ef2db6f6bf3960a32c93ca3e936a8a0f130ab2c1aa92bd101d2e9"},"schema_version":"1.0","source":{"id":"2409.07259","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.07259","created_at":"2026-07-05T09:05:47Z"},{"alias_kind":"arxiv_version","alias_value":"2409.07259v1","created_at":"2026-07-05T09:05:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.07259","created_at":"2026-07-05T09:05:47Z"},{"alias_kind":"pith_short_12","alias_value":"IWRF3EOCIEQY","created_at":"2026-07-05T09:05:47Z"},{"alias_kind":"pith_short_16","alias_value":"IWRF3EOCIEQY3KPY","created_at":"2026-07-05T09:05:47Z"},{"alias_kind":"pith_short_8","alias_value":"IWRF3EOC","created_at":"2026-07-05T09:05:47Z"}],"graph_snapshots":[{"event_id":"sha256:7c5db515bce042031a8cb48527fdcdd452359787ad139debdd08a38293eec942","target":"graph","created_at":"2026-07-05T09:05:47Z","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/2409.07259/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this study, we introduce ManaTTS, the most extensive publicly accessible single-speaker Persian corpus, and a comprehensive framework for collecting transcribed speech datasets for the Persian language. ManaTTS, released under the open CC-0 license, comprises approximately 86 hours of audio with a sampling rate of 44.1 kHz. Alongside ManaTTS, we also generated the VirgoolInformal dataset to evaluate Persian speech recognition models used for forced alignment, extending over 5 hours of audio. The datasets are supported by a fully transparent, MIT-licensed pipeline, a testament to innovation ","authors_text":"Hamid R. Rabiee, Mahta Fetrat Qharabagh, Zahra Dehghanian","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-11T13:28:41Z","title":"ManaTTS Persian: a recipe for creating TTS datasets for lower resource languages"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.07259","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":"sha256:20827f008d06d2158d7135f3bfe86276edd459fc6349f0e646e617587b9b63ee","target":"record","created_at":"2026-07-05T09:05:47Z","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":"0b0d619f1fca3f4ee7ec7eba4addc116ac2efd3c58a908c3b29f1bad6e301245","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-09-11T13:28:41Z","title_canon_sha256":"23172a1b273ef2db6f6bf3960a32c93ca3e936a8a0f130ab2c1aa92bd101d2e9"},"schema_version":"1.0","source":{"id":"2409.07259","kind":"arxiv","version":1}},"canonical_sha256":"45a25d91c241218da9f85c23f57c826c0a9d7226bc4efa4c1db36cb7dd11606d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"45a25d91c241218da9f85c23f57c826c0a9d7226bc4efa4c1db36cb7dd11606d","first_computed_at":"2026-07-05T09:05:47.937808Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:05:47.937808Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"X2guGqrTBN6syPHCmWTIOBZ1zEUeKHBHXQCX+6Zvh+LFlgPYT7ZAeBpmS/TldhyxRpNsWSraaghXCUMf1H4zDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:05:47.938290Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.07259","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:20827f008d06d2158d7135f3bfe86276edd459fc6349f0e646e617587b9b63ee","sha256:7c5db515bce042031a8cb48527fdcdd452359787ad139debdd08a38293eec942"],"state_sha256":"474d885ff410c873fee9be5981929ec458b4a37f401bafd28a2ae69c160ba0ab"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wdU2iXdxizHsPraehxprEa4H4wjpVlOgzZSy0rxJMCs0OPeDrMUVdLAO1ecZiJ2cnrq5HmYop8OZRQOUm+5mCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T16:22:55.127996Z","bundle_sha256":"317986713978d9239caa7e0d01a19c95e0a87c1d1f220661b805cb0a6efc930c"}}