{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:UERMLUC4YYB2V6XLCOKFITRCCY","short_pith_number":"pith:UERMLUC4","canonical_record":{"source":{"id":"2510.10774","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-10-12T19:33:11Z","cross_cats_sorted":["cs.AI","cs.HC","cs.LG"],"title_canon_sha256":"8359a9ae44721e2d5a687f0367e319560ad7ff47ada5f89f00e81b1a33d3ef5c","abstract_canon_sha256":"e6b64b31ec03d61a0514846c9369c215355c0aadded808dda5d83f0062c69dd8"},"schema_version":"1.0"},"canonical_sha256":"a122c5d05cc603aafaeb1394544e22161792372d9e2a242b83f88b53ae6d0a40","source":{"kind":"arxiv","id":"2510.10774","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.10774","created_at":"2026-05-27T01:05:38Z"},{"alias_kind":"arxiv_version","alias_value":"2510.10774v3","created_at":"2026-05-27T01:05:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.10774","created_at":"2026-05-27T01:05:38Z"},{"alias_kind":"pith_short_12","alias_value":"UERMLUC4YYB2","created_at":"2026-05-27T01:05:38Z"},{"alias_kind":"pith_short_16","alias_value":"UERMLUC4YYB2V6XL","created_at":"2026-05-27T01:05:38Z"},{"alias_kind":"pith_short_8","alias_value":"UERMLUC4","created_at":"2026-05-27T01:05:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:UERMLUC4YYB2V6XLCOKFITRCCY","target":"record","payload":{"canonical_record":{"source":{"id":"2510.10774","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-10-12T19:33:11Z","cross_cats_sorted":["cs.AI","cs.HC","cs.LG"],"title_canon_sha256":"8359a9ae44721e2d5a687f0367e319560ad7ff47ada5f89f00e81b1a33d3ef5c","abstract_canon_sha256":"e6b64b31ec03d61a0514846c9369c215355c0aadded808dda5d83f0062c69dd8"},"schema_version":"1.0"},"canonical_sha256":"a122c5d05cc603aafaeb1394544e22161792372d9e2a242b83f88b53ae6d0a40","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T01:05:38.768110Z","signature_b64":"wy7pQVWTi9KnrXEiHWB6XJ4Wa9D3BvuAthP2ApKhK8vpUc46pCLgmtAsru/l49tl9dPqjfppXyPDd5PXJ0msDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a122c5d05cc603aafaeb1394544e22161792372d9e2a242b83f88b53ae6d0a40","last_reissued_at":"2026-05-27T01:05:38.767488Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T01:05:38.767488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2510.10774","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":"2026-05-27T01:05:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"HVnvgFB+HK4mW3q7Yka+Ql4O+QO4coN5NnZspM1MHIU7fvbtBhk4gvcUU3r+ktWqGhPX11hNn0radsWiEE9kCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T19:42:51.830763Z"},"content_sha256":"183d4ad4d235422a212fa25f44f2455ad04d026f7a63bcea447e434676573d00","schema_version":"1.0","event_id":"sha256:183d4ad4d235422a212fa25f44f2455ad04d026f7a63bcea447e434676573d00"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:UERMLUC4YYB2V6XLCOKFITRCCY","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ParsVoice: A Large-Scale Multi-Speaker Persian Speech Corpus for Text-to-Speech Synthesis","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.LG"],"primary_cat":"cs.SD","authors_text":"Azadeh Shakery, Heshaam Faili, Mohammad Javad Ranjbar Kalahroodi","submitted_at":"2025-10-12T19:33:11Z","abstract_excerpt":"Persian remains substantially underrepresented in open speech-text resources, limiting progress in multi-speaker text-to-speech (TTS), speech-language modelling, and low-resource speech processing. We introduce ParsVoice, the largest publicly available Persian speech-text corpus tailored for training multi-speaker TTS systems, along with a scalable pipeline to construct high-quality speech-text data from long-form audiobook recordings. The pipeline combines a fine-tuned ParsBERT sentence-completion classifier, ASR-based boundary optimization, punctuation restoration, speaker identification, an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.10774","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/2510.10774/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":"2026-05-27T01:05:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3/8kGhzXb1AN8Z3URMJWIaZ3oosPfox7QeTL5lcIjx1zDNWn+vubgxUlxxXggneoN4V+fk6egoGh/oKtl4m/Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T19:42:51.831149Z"},"content_sha256":"b12c3abbbd06ec5f70aa7d3b7ccc75ab731714c0440f8022540717c93d96dfe1","schema_version":"1.0","event_id":"sha256:b12c3abbbd06ec5f70aa7d3b7ccc75ab731714c0440f8022540717c93d96dfe1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/UERMLUC4YYB2V6XLCOKFITRCCY/bundle.json","state_url":"https://pith.science/pith/UERMLUC4YYB2V6XLCOKFITRCCY/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/UERMLUC4YYB2V6XLCOKFITRCCY/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":"2026-05-27T19:42:51Z","links":{"resolver":"https://pith.science/pith/UERMLUC4YYB2V6XLCOKFITRCCY","bundle":"https://pith.science/pith/UERMLUC4YYB2V6XLCOKFITRCCY/bundle.json","state":"https://pith.science/pith/UERMLUC4YYB2V6XLCOKFITRCCY/state.json","well_known_bundle":"https://pith.science/.well-known/pith/UERMLUC4YYB2V6XLCOKFITRCCY/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:UERMLUC4YYB2V6XLCOKFITRCCY","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":"e6b64b31ec03d61a0514846c9369c215355c0aadded808dda5d83f0062c69dd8","cross_cats_sorted":["cs.AI","cs.HC","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-10-12T19:33:11Z","title_canon_sha256":"8359a9ae44721e2d5a687f0367e319560ad7ff47ada5f89f00e81b1a33d3ef5c"},"schema_version":"1.0","source":{"id":"2510.10774","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.10774","created_at":"2026-05-27T01:05:38Z"},{"alias_kind":"arxiv_version","alias_value":"2510.10774v3","created_at":"2026-05-27T01:05:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.10774","created_at":"2026-05-27T01:05:38Z"},{"alias_kind":"pith_short_12","alias_value":"UERMLUC4YYB2","created_at":"2026-05-27T01:05:38Z"},{"alias_kind":"pith_short_16","alias_value":"UERMLUC4YYB2V6XL","created_at":"2026-05-27T01:05:38Z"},{"alias_kind":"pith_short_8","alias_value":"UERMLUC4","created_at":"2026-05-27T01:05:38Z"}],"graph_snapshots":[{"event_id":"sha256:b12c3abbbd06ec5f70aa7d3b7ccc75ab731714c0440f8022540717c93d96dfe1","target":"graph","created_at":"2026-05-27T01:05:38Z","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/2510.10774/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Persian remains substantially underrepresented in open speech-text resources, limiting progress in multi-speaker text-to-speech (TTS), speech-language modelling, and low-resource speech processing. We introduce ParsVoice, the largest publicly available Persian speech-text corpus tailored for training multi-speaker TTS systems, along with a scalable pipeline to construct high-quality speech-text data from long-form audiobook recordings. The pipeline combines a fine-tuned ParsBERT sentence-completion classifier, ASR-based boundary optimization, punctuation restoration, speaker identification, an","authors_text":"Azadeh Shakery, Heshaam Faili, Mohammad Javad Ranjbar Kalahroodi","cross_cats":["cs.AI","cs.HC","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-10-12T19:33:11Z","title":"ParsVoice: A Large-Scale Multi-Speaker Persian Speech Corpus for Text-to-Speech Synthesis"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.10774","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":"sha256:183d4ad4d235422a212fa25f44f2455ad04d026f7a63bcea447e434676573d00","target":"record","created_at":"2026-05-27T01:05:38Z","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":"e6b64b31ec03d61a0514846c9369c215355c0aadded808dda5d83f0062c69dd8","cross_cats_sorted":["cs.AI","cs.HC","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-10-12T19:33:11Z","title_canon_sha256":"8359a9ae44721e2d5a687f0367e319560ad7ff47ada5f89f00e81b1a33d3ef5c"},"schema_version":"1.0","source":{"id":"2510.10774","kind":"arxiv","version":3}},"canonical_sha256":"a122c5d05cc603aafaeb1394544e22161792372d9e2a242b83f88b53ae6d0a40","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a122c5d05cc603aafaeb1394544e22161792372d9e2a242b83f88b53ae6d0a40","first_computed_at":"2026-05-27T01:05:38.767488Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:05:38.767488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"wy7pQVWTi9KnrXEiHWB6XJ4Wa9D3BvuAthP2ApKhK8vpUc46pCLgmtAsru/l49tl9dPqjfppXyPDd5PXJ0msDw==","signature_status":"signed_v1","signed_at":"2026-05-27T01:05:38.768110Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.10774","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:183d4ad4d235422a212fa25f44f2455ad04d026f7a63bcea447e434676573d00","sha256:b12c3abbbd06ec5f70aa7d3b7ccc75ab731714c0440f8022540717c93d96dfe1"],"state_sha256":"2cbbd02ac742320044cc66c6fc9987bf4127e2f3ac574963ebc06f08205cdb1d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GCEVsV0vuEKZSlTI8BNJBmySpQQK1cHKjAjZmJgppT4CHJmNz6TSTq0SCAMVqUbjjwL/H1sgDyECPoLV2T00CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T19:42:51.833385Z","bundle_sha256":"df8b704daf5154c8ac9561c22d4fb0cd3abfb45f054f66b6b22e1aebf801c538"}}