{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:TU6CWTJ5I5XRSEYOEHSB57Y3S5","short_pith_number":"pith:TU6CWTJ5","schema_version":"1.0","canonical_sha256":"9d3c2b4d3d476f19130e21e41eff1b9777d647730b1f99d35e92592e5c2911af","source":{"kind":"arxiv","id":"2408.06500","version":1},"attestation_state":"computed","paper":{"title":"Music2Latent: Consistency Autoencoders for Latent Audio Compression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"George Fazekas, Marco Pasini, Stefan Lattner","submitted_at":"2024-08-12T21:25:19Z","abstract_excerpt":"Efficient audio representations in a compressed continuous latent space are critical for generative audio modeling and Music Information Retrieval (MIR) tasks. However, some existing audio autoencoders have limitations, such as multi-stage training procedures, slow iterative sampling, or low reconstruction quality. We introduce Music2Latent, an audio autoencoder that overcomes these limitations by leveraging consistency models. Music2Latent encodes samples into a compressed continuous latent space in a single end-to-end training process while enabling high-fidelity single-step reconstruction. "},"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":"2408.06500","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-08-12T21:25:19Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"67e734aedda058f6b4933e9a70f0810f2d142c65473a898319cb002698cdea77","abstract_canon_sha256":"ca0e1672fc7b438f3c6634e1b4d4fab6817d59f4412a497247790244859b1e09"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:54:57.842609Z","signature_b64":"24bOfjZ6lypQvxZWjmR4sKMFHOTN9jRLSgiROkPHct4xeSXsMCg0qG5tRkSVpJhZ1ZUPKpOWdcLZ93LEaM+RBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9d3c2b4d3d476f19130e21e41eff1b9777d647730b1f99d35e92592e5c2911af","last_reissued_at":"2026-07-05T08:54:57.842131Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:54:57.842131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Music2Latent: Consistency Autoencoders for Latent Audio Compression","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"George Fazekas, Marco Pasini, Stefan Lattner","submitted_at":"2024-08-12T21:25:19Z","abstract_excerpt":"Efficient audio representations in a compressed continuous latent space are critical for generative audio modeling and Music Information Retrieval (MIR) tasks. However, some existing audio autoencoders have limitations, such as multi-stage training procedures, slow iterative sampling, or low reconstruction quality. We introduce Music2Latent, an audio autoencoder that overcomes these limitations by leveraging consistency models. Music2Latent encodes samples into a compressed continuous latent space in a single end-to-end training process while enabling high-fidelity single-step reconstruction. "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.06500","kind":"arxiv","version":1},"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/2408.06500/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":"2408.06500","created_at":"2026-07-05T08:54:57.842185+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.06500v1","created_at":"2026-07-05T08:54:57.842185+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.06500","created_at":"2026-07-05T08:54:57.842185+00:00"},{"alias_kind":"pith_short_12","alias_value":"TU6CWTJ5I5XR","created_at":"2026-07-05T08:54:57.842185+00:00"},{"alias_kind":"pith_short_16","alias_value":"TU6CWTJ5I5XRSEYO","created_at":"2026-07-05T08:54:57.842185+00:00"},{"alias_kind":"pith_short_8","alias_value":"TU6CWTJ5","created_at":"2026-07-05T08:54:57.842185+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07271","citing_title":"Where Flow Matching Leaks: Characterising Membership Signals Along the Interpolation Path","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17986","citing_title":"Latent Fourier Transform","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TU6CWTJ5I5XRSEYOEHSB57Y3S5","json":"https://pith.science/pith/TU6CWTJ5I5XRSEYOEHSB57Y3S5.json","graph_json":"https://pith.science/api/pith-number/TU6CWTJ5I5XRSEYOEHSB57Y3S5/graph.json","events_json":"https://pith.science/api/pith-number/TU6CWTJ5I5XRSEYOEHSB57Y3S5/events.json","paper":"https://pith.science/paper/TU6CWTJ5"},"agent_actions":{"view_html":"https://pith.science/pith/TU6CWTJ5I5XRSEYOEHSB57Y3S5","download_json":"https://pith.science/pith/TU6CWTJ5I5XRSEYOEHSB57Y3S5.json","view_paper":"https://pith.science/paper/TU6CWTJ5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.06500&json=true","fetch_graph":"https://pith.science/api/pith-number/TU6CWTJ5I5XRSEYOEHSB57Y3S5/graph.json","fetch_events":"https://pith.science/api/pith-number/TU6CWTJ5I5XRSEYOEHSB57Y3S5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TU6CWTJ5I5XRSEYOEHSB57Y3S5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TU6CWTJ5I5XRSEYOEHSB57Y3S5/action/storage_attestation","attest_author":"https://pith.science/pith/TU6CWTJ5I5XRSEYOEHSB57Y3S5/action/author_attestation","sign_citation":"https://pith.science/pith/TU6CWTJ5I5XRSEYOEHSB57Y3S5/action/citation_signature","submit_replication":"https://pith.science/pith/TU6CWTJ5I5XRSEYOEHSB57Y3S5/action/replication_record"}},"created_at":"2026-07-05T08:54:57.842185+00:00","updated_at":"2026-07-05T08:54:57.842185+00:00"}