{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:NI2WW3YTR4BLBRCX4UT4DO45XU","short_pith_number":"pith:NI2WW3YT","canonical_record":{"source":{"id":"2505.19462","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-26T03:35:44Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"170471d650c36c82a4fe66ab58244a6f6aa3ea99e00bf742a2e6669521ff2e94","abstract_canon_sha256":"e957eb7ff6f26d343d0ee4e143e8ed603a3292eaa9dd8025d74fa8ffc128f0e7"},"schema_version":"1.0"},"canonical_sha256":"6a356b6f138f02b0c457e527c1bb9dbd100c6c02841f3c10d839ed584879b5eb","source":{"kind":"arxiv","id":"2505.19462","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19462","created_at":"2026-07-05T11:13:26Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19462v2","created_at":"2026-07-05T11:13:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19462","created_at":"2026-07-05T11:13:26Z"},{"alias_kind":"pith_short_12","alias_value":"NI2WW3YTR4BL","created_at":"2026-07-05T11:13:26Z"},{"alias_kind":"pith_short_16","alias_value":"NI2WW3YTR4BLBRCX","created_at":"2026-07-05T11:13:26Z"},{"alias_kind":"pith_short_8","alias_value":"NI2WW3YT","created_at":"2026-07-05T11:13:26Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:NI2WW3YTR4BLBRCX4UT4DO45XU","target":"record","payload":{"canonical_record":{"source":{"id":"2505.19462","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-26T03:35:44Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"170471d650c36c82a4fe66ab58244a6f6aa3ea99e00bf742a2e6669521ff2e94","abstract_canon_sha256":"e957eb7ff6f26d343d0ee4e143e8ed603a3292eaa9dd8025d74fa8ffc128f0e7"},"schema_version":"1.0"},"canonical_sha256":"6a356b6f138f02b0c457e527c1bb9dbd100c6c02841f3c10d839ed584879b5eb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:13:26.947405Z","signature_b64":"szW1YJHICTBIL76RDdIrwcYOlWrksFxHL7RQvQeEkFVofkFtOGosS1R0TiI1fDnhdZ1TirBr4e2g+ejngdqpBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6a356b6f138f02b0c457e527c1bb9dbd100c6c02841f3c10d839ed584879b5eb","last_reissued_at":"2026-07-05T11:13:26.946898Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:13:26.946898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.19462","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:13:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N5k3hkeVaUJzYKPbsrMmON8C+wH0gq09+KrMLV3pxS0sOn6SHvjdlSNUYggqjwQys1s75mFO+ulurJgzs50ZAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:50:25.146805Z"},"content_sha256":"5fd4a000d8e5f387d942f6bf9d1826df04c2d449ccb32fce06c86ef842bb505f","schema_version":"1.0","event_id":"sha256:5fd4a000d8e5f387d942f6bf9d1826df04c2d449ccb32fce06c86ef842bb505f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:NI2WW3YTR4BLBRCX4UT4DO45XU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"VoiceStar: Robust Zero-Shot Autoregressive TTS with Duration Control and Extrapolation","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Abdelrahman Mohamed, David Harwath, Puyuan Peng, Shang-Wen Li","submitted_at":"2025-05-26T03:35:44Z","abstract_excerpt":"We present VoiceStar, the first zero-shot TTS model that achieves both output duration control and extrapolation. VoiceStar is an autoregressive encoder-decoder neural codec language model, that leverages a novel Progress-Monitoring Rotary Position Embedding (PM-RoPE) and is trained with Continuation-Prompt Mixed (CPM) training. PM-RoPE enables the model to better align text and speech tokens, indicates the target duration for the generated speech, and also allows the model to generate speech waveforms much longer in duration than those seen during. CPM training also helps to mitigate the trai"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19462","kind":"arxiv","version":2},"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/2505.19462/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":"2026-07-05T11:13:26Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"20wQe907S7sdipUQulvf4rLHcRMCHq1nWpTJ5eAjQ/BfpjaQuRD7bmFaH+R5XvXTvxNK0YJuTV3bwboYzfceCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T20:50:25.147174Z"},"content_sha256":"fad7998fe7a165d836f5af1b85df37cb55932626df235eb5a3d2244ee73192c0","schema_version":"1.0","event_id":"sha256:fad7998fe7a165d836f5af1b85df37cb55932626df235eb5a3d2244ee73192c0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NI2WW3YTR4BLBRCX4UT4DO45XU/bundle.json","state_url":"https://pith.science/pith/NI2WW3YTR4BLBRCX4UT4DO45XU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NI2WW3YTR4BLBRCX4UT4DO45XU/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":"2026-07-06T20:50:25Z","links":{"resolver":"https://pith.science/pith/NI2WW3YTR4BLBRCX4UT4DO45XU","bundle":"https://pith.science/pith/NI2WW3YTR4BLBRCX4UT4DO45XU/bundle.json","state":"https://pith.science/pith/NI2WW3YTR4BLBRCX4UT4DO45XU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NI2WW3YTR4BLBRCX4UT4DO45XU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:NI2WW3YTR4BLBRCX4UT4DO45XU","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":"e957eb7ff6f26d343d0ee4e143e8ed603a3292eaa9dd8025d74fa8ffc128f0e7","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-26T03:35:44Z","title_canon_sha256":"170471d650c36c82a4fe66ab58244a6f6aa3ea99e00bf742a2e6669521ff2e94"},"schema_version":"1.0","source":{"id":"2505.19462","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19462","created_at":"2026-07-05T11:13:26Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19462v2","created_at":"2026-07-05T11:13:26Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19462","created_at":"2026-07-05T11:13:26Z"},{"alias_kind":"pith_short_12","alias_value":"NI2WW3YTR4BL","created_at":"2026-07-05T11:13:26Z"},{"alias_kind":"pith_short_16","alias_value":"NI2WW3YTR4BLBRCX","created_at":"2026-07-05T11:13:26Z"},{"alias_kind":"pith_short_8","alias_value":"NI2WW3YT","created_at":"2026-07-05T11:13:26Z"}],"graph_snapshots":[{"event_id":"sha256:fad7998fe7a165d836f5af1b85df37cb55932626df235eb5a3d2244ee73192c0","target":"graph","created_at":"2026-07-05T11:13:26Z","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/2505.19462/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present VoiceStar, the first zero-shot TTS model that achieves both output duration control and extrapolation. VoiceStar is an autoregressive encoder-decoder neural codec language model, that leverages a novel Progress-Monitoring Rotary Position Embedding (PM-RoPE) and is trained with Continuation-Prompt Mixed (CPM) training. PM-RoPE enables the model to better align text and speech tokens, indicates the target duration for the generated speech, and also allows the model to generate speech waveforms much longer in duration than those seen during. CPM training also helps to mitigate the trai","authors_text":"Abdelrahman Mohamed, David Harwath, Puyuan Peng, Shang-Wen Li","cross_cats":["cs.SD"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-26T03:35:44Z","title":"VoiceStar: Robust Zero-Shot Autoregressive TTS with Duration Control and Extrapolation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19462","kind":"arxiv","version":2},"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":"sha256:5fd4a000d8e5f387d942f6bf9d1826df04c2d449ccb32fce06c86ef842bb505f","target":"record","created_at":"2026-07-05T11:13:26Z","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":"e957eb7ff6f26d343d0ee4e143e8ed603a3292eaa9dd8025d74fa8ffc128f0e7","cross_cats_sorted":["cs.SD"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"eess.AS","submitted_at":"2025-05-26T03:35:44Z","title_canon_sha256":"170471d650c36c82a4fe66ab58244a6f6aa3ea99e00bf742a2e6669521ff2e94"},"schema_version":"1.0","source":{"id":"2505.19462","kind":"arxiv","version":2}},"canonical_sha256":"6a356b6f138f02b0c457e527c1bb9dbd100c6c02841f3c10d839ed584879b5eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6a356b6f138f02b0c457e527c1bb9dbd100c6c02841f3c10d839ed584879b5eb","first_computed_at":"2026-07-05T11:13:26.946898Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:13:26.946898Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"szW1YJHICTBIL76RDdIrwcYOlWrksFxHL7RQvQeEkFVofkFtOGosS1R0TiI1fDnhdZ1TirBr4e2g+ejngdqpBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:13:26.947405Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.19462","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5fd4a000d8e5f387d942f6bf9d1826df04c2d449ccb32fce06c86ef842bb505f","sha256:fad7998fe7a165d836f5af1b85df37cb55932626df235eb5a3d2244ee73192c0"],"state_sha256":"545245c589fa33d341b2f8e3738a19d6d5150c3c3f3f2c51346fc24c70010d36"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Em3H+QG1PHPYQwgFrSVQWH6+i8NUf/6+LAIKWzidfTWrks1YpzlYgtzacq/9zODh0ZeQHV0KuVJMvFO22vvmAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T20:50:25.149068Z","bundle_sha256":"e1c4819747bb9142c9bf631850328ff045ba8fbf0f19b508e18df96a97e73c69"}}