{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:AZLQ6BNNEW77YPFYVCT652ODJ2","short_pith_number":"pith:AZLQ6BNN","schema_version":"1.0","canonical_sha256":"06570f05ad25bffc3cb8a8a7eee9c34e8daf9dc740668793caf05e9e1c124496","source":{"kind":"arxiv","id":"2605.18613","version":1},"attestation_state":"computed","paper":{"title":"SAME: A Semantically-Aligned Music Autoencoder","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SD","authors_text":"CJ Carr, Jordi Pons, Josiah Taylor, Julian D. Parker, Matthew Rice, Zachary Zukowski, Zach Evans","submitted_at":"2026-05-18T16:23:16Z","abstract_excerpt":"Latent representations are at the heart of the majority of modern generative models. In the audio domain they are typically produced by a neural-audio-codec autoencoder. In this work we introduce SAME (Semantically-Aligned Music autoEncoder), an autoencoder for stereo music and general audio that reaches a 4096$\\times$ temporal compression ratio while maintaining reconstruction quality and downstream generative performance. We achieve this by combining a tranformer-based backbone with set of semantic regularisation approaches, phase-aware reconstruction losses and improved discriminator design"},"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":"2605.18613","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-05-18T16:23:16Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9df676aade87037c0e5b550a1f3694fa364d0e442cf9927ddf82895e92f6957d","abstract_canon_sha256":"4cff6d974da7952b2864fe97c84efb7fc88797d48b949f0f9d191b5770cfc1f5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:06:10.914721Z","signature_b64":"FKckcg7NAxhneuojaNgzgOebD7vnvvngfxbgjf/TOAwzC8Ww6WRVSYPBrdGWD6FQJOlPh6nSkjMfzSiOLIdACg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"06570f05ad25bffc3cb8a8a7eee9c34e8daf9dc740668793caf05e9e1c124496","last_reissued_at":"2026-05-20T00:06:10.913944Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:06:10.913944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SAME: A Semantically-Aligned Music Autoencoder","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.SD","authors_text":"CJ Carr, Jordi Pons, Josiah Taylor, Julian D. Parker, Matthew Rice, Zachary Zukowski, Zach Evans","submitted_at":"2026-05-18T16:23:16Z","abstract_excerpt":"Latent representations are at the heart of the majority of modern generative models. In the audio domain they are typically produced by a neural-audio-codec autoencoder. In this work we introduce SAME (Semantically-Aligned Music autoEncoder), an autoencoder for stereo music and general audio that reaches a 4096$\\times$ temporal compression ratio while maintaining reconstruction quality and downstream generative performance. We achieve this by combining a tranformer-based backbone with set of semantic regularisation approaches, phase-aware reconstruction losses and improved discriminator design"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18613","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/2605.18613/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T00:01:59.233734Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"663d132c0cfe3d6138d0f820a0b299d0354d7297316488be78cdb6355b1d203a"},"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":"2605.18613","created_at":"2026-05-20T00:06:10.914076+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18613v1","created_at":"2026-05-20T00:06:10.914076+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18613","created_at":"2026-05-20T00:06:10.914076+00:00"},{"alias_kind":"pith_short_12","alias_value":"AZLQ6BNNEW77","created_at":"2026-05-20T00:06:10.914076+00:00"},{"alias_kind":"pith_short_16","alias_value":"AZLQ6BNNEW77YPFY","created_at":"2026-05-20T00:06:10.914076+00:00"},{"alias_kind":"pith_short_8","alias_value":"AZLQ6BNN","created_at":"2026-05-20T00:06:10.914076+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AZLQ6BNNEW77YPFYVCT652ODJ2","json":"https://pith.science/pith/AZLQ6BNNEW77YPFYVCT652ODJ2.json","graph_json":"https://pith.science/api/pith-number/AZLQ6BNNEW77YPFYVCT652ODJ2/graph.json","events_json":"https://pith.science/api/pith-number/AZLQ6BNNEW77YPFYVCT652ODJ2/events.json","paper":"https://pith.science/paper/AZLQ6BNN"},"agent_actions":{"view_html":"https://pith.science/pith/AZLQ6BNNEW77YPFYVCT652ODJ2","download_json":"https://pith.science/pith/AZLQ6BNNEW77YPFYVCT652ODJ2.json","view_paper":"https://pith.science/paper/AZLQ6BNN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18613&json=true","fetch_graph":"https://pith.science/api/pith-number/AZLQ6BNNEW77YPFYVCT652ODJ2/graph.json","fetch_events":"https://pith.science/api/pith-number/AZLQ6BNNEW77YPFYVCT652ODJ2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AZLQ6BNNEW77YPFYVCT652ODJ2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AZLQ6BNNEW77YPFYVCT652ODJ2/action/storage_attestation","attest_author":"https://pith.science/pith/AZLQ6BNNEW77YPFYVCT652ODJ2/action/author_attestation","sign_citation":"https://pith.science/pith/AZLQ6BNNEW77YPFYVCT652ODJ2/action/citation_signature","submit_replication":"https://pith.science/pith/AZLQ6BNNEW77YPFYVCT652ODJ2/action/replication_record"}},"created_at":"2026-05-20T00:06:10.914076+00:00","updated_at":"2026-05-20T00:06:10.914076+00:00"}