{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:6EN5FPCM4NE4JVD5XKOMQJVCWS","short_pith_number":"pith:6EN5FPCM","canonical_record":{"source":{"id":"2412.08918","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-12-12T04:01:28Z","cross_cats_sorted":[],"title_canon_sha256":"63fd901540f6792865915daf91318774f760be41364a805647d964b6d086815c","abstract_canon_sha256":"2579ede35a2820f1242bc9d1f70b89744942f877a02baa0976c68d59159d80a2"},"schema_version":"1.0"},"canonical_sha256":"f11bd2bc4ce349c4d47dba9cc826a2b4b1b3da5acede45108205ccf100abc456","source":{"kind":"arxiv","id":"2412.08918","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.08918","created_at":"2026-07-05T09:48:38Z"},{"alias_kind":"arxiv_version","alias_value":"2412.08918v2","created_at":"2026-07-05T09:48:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08918","created_at":"2026-07-05T09:48:38Z"},{"alias_kind":"pith_short_12","alias_value":"6EN5FPCM4NE4","created_at":"2026-07-05T09:48:38Z"},{"alias_kind":"pith_short_16","alias_value":"6EN5FPCM4NE4JVD5","created_at":"2026-07-05T09:48:38Z"},{"alias_kind":"pith_short_8","alias_value":"6EN5FPCM","created_at":"2026-07-05T09:48:38Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:6EN5FPCM4NE4JVD5XKOMQJVCWS","target":"record","payload":{"canonical_record":{"source":{"id":"2412.08918","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-12-12T04:01:28Z","cross_cats_sorted":[],"title_canon_sha256":"63fd901540f6792865915daf91318774f760be41364a805647d964b6d086815c","abstract_canon_sha256":"2579ede35a2820f1242bc9d1f70b89744942f877a02baa0976c68d59159d80a2"},"schema_version":"1.0"},"canonical_sha256":"f11bd2bc4ce349c4d47dba9cc826a2b4b1b3da5acede45108205ccf100abc456","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:48:38.683464Z","signature_b64":"UhE22miRG6jFuTwIj59XpMOtQdyvH6TSMH+/7xJnn5P3UURrqkRYoB8E17Nvq0w1eI5+PlV/b+vDeUQJjd8mDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f11bd2bc4ce349c4d47dba9cc826a2b4b1b3da5acede45108205ccf100abc456","last_reissued_at":"2026-07-05T09:48:38.682928Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:48:38.682928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2412.08918","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":"2026-07-05T09:48:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"v8GX16TnpmakX5wLkJ72Vr9lx0f68bIUh3vtmmfIfj8votsstrZmaFLXUYV7iuhSKOT2foLQNqG3llUNOXFeBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T20:04:35.179204Z"},"content_sha256":"ef7a1d2fa51062f7341cc62653f897094da0902bfa59487a089b8739a02c7894","schema_version":"1.0","event_id":"sha256:ef7a1d2fa51062f7341cc62653f897094da0902bfa59487a089b8739a02c7894"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:6EN5FPCM4NE4JVD5XKOMQJVCWS","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CSSinger: End-to-End Chunkwise Streaming Singing Voice Synthesis System Based on Conditional Variational Autoencoder","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"eess.AS","authors_text":"Jianwei Cui, Jie Zhang, Liping Chen, Lirong Dai, Shihao Chen, Yu Gu","submitted_at":"2024-12-12T04:01:28Z","abstract_excerpt":"Singing Voice Synthesis (SVS) aims to generate singing voices of high fidelity and expressiveness. Conventional SVS systems usually utilize an acoustic model to transform a music score into acoustic features, followed by a vocoder to reconstruct the singing voice. It was recently shown that end-to-end modeling is effective in the fields of SVS and Text to Speech (TTS). In this work, we thus present a fully end-to-end SVS method together with a chunkwise streaming inference to address the latency issue for practical usages. Note that this is the first attempt to fully implement end-to-end strea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08918","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/2412.08918/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":"2026-07-05T09:48:38Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ytxfLMFBY+GzzzrvwtaXyaFUjriuBeycXHd4FI9BRUBtotfpchdIFpKFiQTp4F4lQK/ROHQ7WYE1DUTMIZLECw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-12T20:04:35.179718Z"},"content_sha256":"b72d9265c964f1903b8df49dcd52a7b26d03642e64d4cba28cd2c54a3473e8c3","schema_version":"1.0","event_id":"sha256:b72d9265c964f1903b8df49dcd52a7b26d03642e64d4cba28cd2c54a3473e8c3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6EN5FPCM4NE4JVD5XKOMQJVCWS/bundle.json","state_url":"https://pith.science/pith/6EN5FPCM4NE4JVD5XKOMQJVCWS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6EN5FPCM4NE4JVD5XKOMQJVCWS/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":"2026-08-12T20:04:35Z","links":{"resolver":"https://pith.science/pith/6EN5FPCM4NE4JVD5XKOMQJVCWS","bundle":"https://pith.science/pith/6EN5FPCM4NE4JVD5XKOMQJVCWS/bundle.json","state":"https://pith.science/pith/6EN5FPCM4NE4JVD5XKOMQJVCWS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6EN5FPCM4NE4JVD5XKOMQJVCWS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6EN5FPCM4NE4JVD5XKOMQJVCWS","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":"2579ede35a2820f1242bc9d1f70b89744942f877a02baa0976c68d59159d80a2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-12-12T04:01:28Z","title_canon_sha256":"63fd901540f6792865915daf91318774f760be41364a805647d964b6d086815c"},"schema_version":"1.0","source":{"id":"2412.08918","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.08918","created_at":"2026-07-05T09:48:38Z"},{"alias_kind":"arxiv_version","alias_value":"2412.08918v2","created_at":"2026-07-05T09:48:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.08918","created_at":"2026-07-05T09:48:38Z"},{"alias_kind":"pith_short_12","alias_value":"6EN5FPCM4NE4","created_at":"2026-07-05T09:48:38Z"},{"alias_kind":"pith_short_16","alias_value":"6EN5FPCM4NE4JVD5","created_at":"2026-07-05T09:48:38Z"},{"alias_kind":"pith_short_8","alias_value":"6EN5FPCM","created_at":"2026-07-05T09:48:38Z"}],"graph_snapshots":[{"event_id":"sha256:b72d9265c964f1903b8df49dcd52a7b26d03642e64d4cba28cd2c54a3473e8c3","target":"graph","created_at":"2026-07-05T09:48:38Z","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/2412.08918/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Singing Voice Synthesis (SVS) aims to generate singing voices of high fidelity and expressiveness. Conventional SVS systems usually utilize an acoustic model to transform a music score into acoustic features, followed by a vocoder to reconstruct the singing voice. It was recently shown that end-to-end modeling is effective in the fields of SVS and Text to Speech (TTS). In this work, we thus present a fully end-to-end SVS method together with a chunkwise streaming inference to address the latency issue for practical usages. Note that this is the first attempt to fully implement end-to-end strea","authors_text":"Jianwei Cui, Jie Zhang, Liping Chen, Lirong Dai, Shihao Chen, Yu Gu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-12-12T04:01:28Z","title":"CSSinger: End-to-End Chunkwise Streaming Singing Voice Synthesis System Based on Conditional Variational Autoencoder"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.08918","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:ef7a1d2fa51062f7341cc62653f897094da0902bfa59487a089b8739a02c7894","target":"record","created_at":"2026-07-05T09:48:38Z","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":"2579ede35a2820f1242bc9d1f70b89744942f877a02baa0976c68d59159d80a2","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2024-12-12T04:01:28Z","title_canon_sha256":"63fd901540f6792865915daf91318774f760be41364a805647d964b6d086815c"},"schema_version":"1.0","source":{"id":"2412.08918","kind":"arxiv","version":2}},"canonical_sha256":"f11bd2bc4ce349c4d47dba9cc826a2b4b1b3da5acede45108205ccf100abc456","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f11bd2bc4ce349c4d47dba9cc826a2b4b1b3da5acede45108205ccf100abc456","first_computed_at":"2026-07-05T09:48:38.682928Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:48:38.682928Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UhE22miRG6jFuTwIj59XpMOtQdyvH6TSMH+/7xJnn5P3UURrqkRYoB8E17Nvq0w1eI5+PlV/b+vDeUQJjd8mDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:48:38.683464Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.08918","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ef7a1d2fa51062f7341cc62653f897094da0902bfa59487a089b8739a02c7894","sha256:b72d9265c964f1903b8df49dcd52a7b26d03642e64d4cba28cd2c54a3473e8c3"],"state_sha256":"bae9038cdf50a447bb4acebf45e1dda0d47a5961babb528b8f554c014c046343"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vyYQ/LZdqNizjHaB+iuYk4PFDhwv90jKg2t7LZ/jv29StiB5dMud+ec7vmiiWBD5sFsHF2k196tvFe+dJdhpBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-12T20:04:35.184862Z","bundle_sha256":"d1c406852879b56d8b494703a48a20cb1a62432b018a17c5b3aab2e05ba5c060"}}