{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5P2XZYPNSWKTEMXS4MUJ6FQK42","short_pith_number":"pith:5P2XZYPN","schema_version":"1.0","canonical_sha256":"ebf57ce1ed95953232f2e3289f160ae69c4f7a1fa4ee706be5e36e7541bb001a","source":{"kind":"arxiv","id":"2501.11311","version":2},"attestation_state":"computed","paper":{"title":"A2SB: Audio-to-Audio Schrodinger Bridges","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Ante Jukic, Arash Vahdat, Bryan Catanzaro, Joao Felipe Santos, Kevin J Shih, Rafael Valle, Sang-gil Lee, Weili Nie, Zhifeng Kong","submitted_at":"2025-01-20T07:28:41Z","abstract_excerpt":"Real-world audio is often degraded by numerous factors. This work presents an audio restoration model tailored for high-res music at 44.1kHz. Our model, Audio-to-Audio Schr\\\"odinger Bridges (A2SB), is capable of both bandwidth extension (predicting high-frequency components) and inpainting (re-generating missing segments). Critically, A2SB is end-to-end requiring no vocoder to predict waveform outputs, able to restore hour-long audio inputs, and trained on permissively licensed music data. A2SB is capable of achieving state-of-the-art band-width extension and inpainting quality on several out-"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2501.11311","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2025-01-20T07:28:41Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"03350fdc2377d7f4f1fff548e1c2a713f1437cf5284db42ae92bb0af89293bcb","abstract_canon_sha256":"fe034596e14955709e64f1238d7eac126721ea0e1f1dac821051d9c2dd50f8af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:52:58.935009Z","signature_b64":"K1fKdsspaFDs/doS5KEhLzLGYmNRwVgE4ZaxEKbIMeRWFhR3Qj+xx1YW6nmfwJfhw5yeDg9UB0dgnMACJ5mNBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ebf57ce1ed95953232f2e3289f160ae69c4f7a1fa4ee706be5e36e7541bb001a","last_reissued_at":"2026-07-05T11:52:58.934502Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:52:58.934502Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A2SB: Audio-to-Audio Schrodinger Bridges","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Ante Jukic, Arash Vahdat, Bryan Catanzaro, Joao Felipe Santos, Kevin J Shih, Rafael Valle, Sang-gil Lee, Weili Nie, Zhifeng Kong","submitted_at":"2025-01-20T07:28:41Z","abstract_excerpt":"Real-world audio is often degraded by numerous factors. This work presents an audio restoration model tailored for high-res music at 44.1kHz. Our model, Audio-to-Audio Schr\\\"odinger Bridges (A2SB), is capable of both bandwidth extension (predicting high-frequency components) and inpainting (re-generating missing segments). Critically, A2SB is end-to-end requiring no vocoder to predict waveform outputs, able to restore hour-long audio inputs, and trained on permissively licensed music data. A2SB is capable of achieving state-of-the-art band-width extension and inpainting quality on several out-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.11311","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/2501.11311/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2501.11311","created_at":"2026-07-05T11:52:58.934567+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.11311v2","created_at":"2026-07-05T11:52:58.934567+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.11311","created_at":"2026-07-05T11:52:58.934567+00:00"},{"alias_kind":"pith_short_12","alias_value":"5P2XZYPNSWKT","created_at":"2026-07-05T11:52:58.934567+00:00"},{"alias_kind":"pith_short_16","alias_value":"5P2XZYPNSWKTEMXS","created_at":"2026-07-05T11:52:58.934567+00:00"},{"alias_kind":"pith_short_8","alias_value":"5P2XZYPN","created_at":"2026-07-05T11:52:58.934567+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.00572","citing_title":"AnyBand: Unified Multi-Bandwidth Speech Extension via Frequency-Aware In-Context Spectral Infilling","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5P2XZYPNSWKTEMXS4MUJ6FQK42","json":"https://pith.science/pith/5P2XZYPNSWKTEMXS4MUJ6FQK42.json","graph_json":"https://pith.science/api/pith-number/5P2XZYPNSWKTEMXS4MUJ6FQK42/graph.json","events_json":"https://pith.science/api/pith-number/5P2XZYPNSWKTEMXS4MUJ6FQK42/events.json","paper":"https://pith.science/paper/5P2XZYPN"},"agent_actions":{"view_html":"https://pith.science/pith/5P2XZYPNSWKTEMXS4MUJ6FQK42","download_json":"https://pith.science/pith/5P2XZYPNSWKTEMXS4MUJ6FQK42.json","view_paper":"https://pith.science/paper/5P2XZYPN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.11311&json=true","fetch_graph":"https://pith.science/api/pith-number/5P2XZYPNSWKTEMXS4MUJ6FQK42/graph.json","fetch_events":"https://pith.science/api/pith-number/5P2XZYPNSWKTEMXS4MUJ6FQK42/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5P2XZYPNSWKTEMXS4MUJ6FQK42/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5P2XZYPNSWKTEMXS4MUJ6FQK42/action/storage_attestation","attest_author":"https://pith.science/pith/5P2XZYPNSWKTEMXS4MUJ6FQK42/action/author_attestation","sign_citation":"https://pith.science/pith/5P2XZYPNSWKTEMXS4MUJ6FQK42/action/citation_signature","submit_replication":"https://pith.science/pith/5P2XZYPNSWKTEMXS4MUJ6FQK42/action/replication_record"}},"created_at":"2026-07-05T11:52:58.934567+00:00","updated_at":"2026-07-05T11:52:58.934567+00:00"}