{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:T4IGN56CTYNPWGNC3X356VJITW","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":"693e44662d8101ecd26cd74b1aead657c88736bc5d9e1ab5c928ca841906a9c9","cross_cats_sorted":["eess.AS","eess.SP"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-03-15T17:27:42Z","title_canon_sha256":"0ddd576fe948d6898b05a0a75e062c6a69a742b19fc679698a287f684702c903"},"schema_version":"1.0","source":{"id":"2403.10493","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.10493","created_at":"2026-07-05T09:16:13Z"},{"alias_kind":"arxiv_version","alias_value":"2403.10493v4","created_at":"2026-07-05T09:16:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.10493","created_at":"2026-07-05T09:16:13Z"},{"alias_kind":"pith_short_12","alias_value":"T4IGN56CTYNP","created_at":"2026-07-05T09:16:13Z"},{"alias_kind":"pith_short_16","alias_value":"T4IGN56CTYNPWGNC","created_at":"2026-07-05T09:16:13Z"},{"alias_kind":"pith_short_8","alias_value":"T4IGN56C","created_at":"2026-07-05T09:16:13Z"}],"graph_snapshots":[{"event_id":"sha256:7d3993e7a9a7987c87af03e8594faa1e374aa474015b78d820962667db0bbdbb","target":"graph","created_at":"2026-07-05T09:16:13Z","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/2403.10493/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion-based audio and music generation models commonly perform generation by constructing an image representation of audio (e.g., a mel-spectrogram) and then convert it to audio using a phase reconstruction model or vocoder. Typical vocoders, however, produce monophonic audio at lower resolutions (e.g., 16-24 kHz), which limits their usefulness. We propose MusicHiFi -- an efficient high-fidelity stereophonic vocoder. Our method employs a cascade of three generative adversarial networks (GANs) that convert low-resolution mel-spectrograms to audio, upsamples to high-resolution audio via band","authors_text":"Ge Zhu, Juan-Pablo Caceres, Nicholas J. Bryan, Zhiyao Duan","cross_cats":["eess.AS","eess.SP"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-03-15T17:27:42Z","title":"MusicHiFi: Fast High-Fidelity Stereo Vocoding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.10493","kind":"arxiv","version":4},"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":"sha256:95593aef561d2a54f030ab65066869cd9b471921ae4ce3eeb1b5c2b1869f2efc","target":"record","created_at":"2026-07-05T09:16:13Z","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":"693e44662d8101ecd26cd74b1aead657c88736bc5d9e1ab5c928ca841906a9c9","cross_cats_sorted":["eess.AS","eess.SP"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-03-15T17:27:42Z","title_canon_sha256":"0ddd576fe948d6898b05a0a75e062c6a69a742b19fc679698a287f684702c903"},"schema_version":"1.0","source":{"id":"2403.10493","kind":"arxiv","version":4}},"canonical_sha256":"9f1066f7c29e1afb19a2ddf7df55289d8b609474a5fbcf9506f65935b04c24c7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9f1066f7c29e1afb19a2ddf7df55289d8b609474a5fbcf9506f65935b04c24c7","first_computed_at":"2026-07-05T09:16:13.613294Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:16:13.613294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MZOotpoZCGwceR9flJuNh8+vaK69Z7P/cv7i+KbaBqKJ3TFOHZTF5OBPPKQ8wimoAShezCTeHK/MtM8Fn7WnBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:16:13.613827Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.10493","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:95593aef561d2a54f030ab65066869cd9b471921ae4ce3eeb1b5c2b1869f2efc","sha256:7d3993e7a9a7987c87af03e8594faa1e374aa474015b78d820962667db0bbdbb"],"state_sha256":"f968efd1e4832ef37dd1b7123681f5d413475e1a1d67042b7fbde30d13cd88e1"}