{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XBAZYRAJU27NNA4I6P26BFYMUX","short_pith_number":"pith:XBAZYRAJ","schema_version":"1.0","canonical_sha256":"b8419c4409a6bed68388f3f5e0970ca5dab489d2549d5040122bfac2e84143fa","source":{"kind":"arxiv","id":"2506.00681","version":2},"attestation_state":"computed","paper":{"title":"Learning to Upsample and Upmix Audio in the Latent Domain","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Dimitrios Bralios, Jonah Casebeer, Paris Smaragdis","submitted_at":"2025-05-31T19:27:22Z","abstract_excerpt":"Neural audio autoencoders create compact latent representations that preserve perceptually important information, serving as the foundation for both modern audio compression systems and generation approaches like next-token prediction and latent diffusion. Despite their prevalence, most audio processing operations, such as spatial and spectral up-sampling, still inefficiently operate on raw waveforms or spectral representations rather than directly on these compressed representations. We propose a framework that performs audio processing operations entirely within an autoencoder's latent space"},"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":"2506.00681","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2025-05-31T19:27:22Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"585a24a1affd6921fca4b8f535ca14c2d1c3cbae22d5c441bea64797992488f5","abstract_canon_sha256":"3cb3b2b01ae16996a17ac539e4644bb7bc1ffdc8047fbe0109b860cb90421184"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-29T01:15:02.725278Z","signature_b64":"1whRIUqBIuh5QIQ16LCq1sShqsc1W0md6t0IvpB3rOpxbeJMnlrcjS35e6rbjjzRWNj4MxDLS1DObINVDJiLAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b8419c4409a6bed68388f3f5e0970ca5dab489d2549d5040122bfac2e84143fa","last_reissued_at":"2026-06-29T01:15:02.724786Z","signature_status":"signed_v1","first_computed_at":"2026-06-29T01:15:02.724786Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning to Upsample and Upmix Audio in the Latent Domain","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Dimitrios Bralios, Jonah Casebeer, Paris Smaragdis","submitted_at":"2025-05-31T19:27:22Z","abstract_excerpt":"Neural audio autoencoders create compact latent representations that preserve perceptually important information, serving as the foundation for both modern audio compression systems and generation approaches like next-token prediction and latent diffusion. Despite their prevalence, most audio processing operations, such as spatial and spectral up-sampling, still inefficiently operate on raw waveforms or spectral representations rather than directly on these compressed representations. We propose a framework that performs audio processing operations entirely within an autoencoder's latent space"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.00681","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/2506.00681/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":"2506.00681","created_at":"2026-06-29T01:15:02.724845+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.00681v2","created_at":"2026-06-29T01:15:02.724845+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.00681","created_at":"2026-06-29T01:15:02.724845+00:00"},{"alias_kind":"pith_short_12","alias_value":"XBAZYRAJU27N","created_at":"2026-06-29T01:15:02.724845+00:00"},{"alias_kind":"pith_short_16","alias_value":"XBAZYRAJU27NNA4I","created_at":"2026-06-29T01:15:02.724845+00:00"},{"alias_kind":"pith_short_8","alias_value":"XBAZYRAJ","created_at":"2026-06-29T01:15:02.724845+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.07867","citing_title":"Re-Bottleneck: Latent Re-Structuring for Neural Audio Autoencoders","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XBAZYRAJU27NNA4I6P26BFYMUX","json":"https://pith.science/pith/XBAZYRAJU27NNA4I6P26BFYMUX.json","graph_json":"https://pith.science/api/pith-number/XBAZYRAJU27NNA4I6P26BFYMUX/graph.json","events_json":"https://pith.science/api/pith-number/XBAZYRAJU27NNA4I6P26BFYMUX/events.json","paper":"https://pith.science/paper/XBAZYRAJ"},"agent_actions":{"view_html":"https://pith.science/pith/XBAZYRAJU27NNA4I6P26BFYMUX","download_json":"https://pith.science/pith/XBAZYRAJU27NNA4I6P26BFYMUX.json","view_paper":"https://pith.science/paper/XBAZYRAJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.00681&json=true","fetch_graph":"https://pith.science/api/pith-number/XBAZYRAJU27NNA4I6P26BFYMUX/graph.json","fetch_events":"https://pith.science/api/pith-number/XBAZYRAJU27NNA4I6P26BFYMUX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XBAZYRAJU27NNA4I6P26BFYMUX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XBAZYRAJU27NNA4I6P26BFYMUX/action/storage_attestation","attest_author":"https://pith.science/pith/XBAZYRAJU27NNA4I6P26BFYMUX/action/author_attestation","sign_citation":"https://pith.science/pith/XBAZYRAJU27NNA4I6P26BFYMUX/action/citation_signature","submit_replication":"https://pith.science/pith/XBAZYRAJU27NNA4I6P26BFYMUX/action/replication_record"}},"created_at":"2026-06-29T01:15:02.724845+00:00","updated_at":"2026-06-29T01:15:02.724845+00:00"}