{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TXLB2H3SHZKTB4QVBIOSFE5ZGO","short_pith_number":"pith:TXLB2H3S","schema_version":"1.0","canonical_sha256":"9dd61d1f723e5530f2150a1d2293b933aabba92f416cc31d445c2018f46c5c32","source":{"kind":"arxiv","id":"2605.27346","version":1},"attestation_state":"computed","paper":{"title":"MERIT: Learning Disentangled Music Representations for Audio Similarity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Abhinaba Roy, Dorien Herremans, Junyi Liang","submitted_at":"2026-05-26T17:49:18Z","abstract_excerpt":"Current music similarity models typically compute a single, monolithic score, entangling distinct musical dimensions like melody, rhythm, and timbre. This limits user control and interpretability, making it impossible to execute nuanced queries. We introduce MERIT, a framework for learning disentangled, factor-specific music representations tailored to these three core dimensions. To overcome the lack of isolated musical variations in real-world audio, we use a novel training strategy that uses conditional audio generation and source-separated stems to strongly encourage single-factor variatio"},"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":"2605.27346","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2026-05-26T17:49:18Z","cross_cats_sorted":[],"title_canon_sha256":"0f44c1f5bf83ae617f984b399343f57ba9296bec5e820391215260a02f7a54c2","abstract_canon_sha256":"9ab6a6ca163524e9cf11444f3b97d3a556ccf3844633ff1716221d0cff45c7ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T02:06:19.049800Z","signature_b64":"YP0VHBpK5Gcgilc0tFfTQrsaJQZOwNhSM0Y7P2ST1ejDL62yRIMeOq07hF2h4hUdHSebD/8YiWdwNGZI0MxBDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9dd61d1f723e5530f2150a1d2293b933aabba92f416cc31d445c2018f46c5c32","last_reissued_at":"2026-05-27T02:06:19.049150Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T02:06:19.049150Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MERIT: Learning Disentangled Music Representations for Audio Similarity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.SD","authors_text":"Abhinaba Roy, Dorien Herremans, Junyi Liang","submitted_at":"2026-05-26T17:49:18Z","abstract_excerpt":"Current music similarity models typically compute a single, monolithic score, entangling distinct musical dimensions like melody, rhythm, and timbre. This limits user control and interpretability, making it impossible to execute nuanced queries. We introduce MERIT, a framework for learning disentangled, factor-specific music representations tailored to these three core dimensions. To overcome the lack of isolated musical variations in real-world audio, we use a novel training strategy that uses conditional audio generation and source-separated stems to strongly encourage single-factor variatio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27346","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/2605.27346/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":"2605.27346","created_at":"2026-05-27T02:06:19.049266+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.27346v1","created_at":"2026-05-27T02:06:19.049266+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27346","created_at":"2026-05-27T02:06:19.049266+00:00"},{"alias_kind":"pith_short_12","alias_value":"TXLB2H3SHZKT","created_at":"2026-05-27T02:06:19.049266+00:00"},{"alias_kind":"pith_short_16","alias_value":"TXLB2H3SHZKTB4QV","created_at":"2026-05-27T02:06:19.049266+00:00"},{"alias_kind":"pith_short_8","alias_value":"TXLB2H3S","created_at":"2026-05-27T02:06:19.049266+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/TXLB2H3SHZKTB4QVBIOSFE5ZGO","json":"https://pith.science/pith/TXLB2H3SHZKTB4QVBIOSFE5ZGO.json","graph_json":"https://pith.science/api/pith-number/TXLB2H3SHZKTB4QVBIOSFE5ZGO/graph.json","events_json":"https://pith.science/api/pith-number/TXLB2H3SHZKTB4QVBIOSFE5ZGO/events.json","paper":"https://pith.science/paper/TXLB2H3S"},"agent_actions":{"view_html":"https://pith.science/pith/TXLB2H3SHZKTB4QVBIOSFE5ZGO","download_json":"https://pith.science/pith/TXLB2H3SHZKTB4QVBIOSFE5ZGO.json","view_paper":"https://pith.science/paper/TXLB2H3S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.27346&json=true","fetch_graph":"https://pith.science/api/pith-number/TXLB2H3SHZKTB4QVBIOSFE5ZGO/graph.json","fetch_events":"https://pith.science/api/pith-number/TXLB2H3SHZKTB4QVBIOSFE5ZGO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TXLB2H3SHZKTB4QVBIOSFE5ZGO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TXLB2H3SHZKTB4QVBIOSFE5ZGO/action/storage_attestation","attest_author":"https://pith.science/pith/TXLB2H3SHZKTB4QVBIOSFE5ZGO/action/author_attestation","sign_citation":"https://pith.science/pith/TXLB2H3SHZKTB4QVBIOSFE5ZGO/action/citation_signature","submit_replication":"https://pith.science/pith/TXLB2H3SHZKTB4QVBIOSFE5ZGO/action/replication_record"}},"created_at":"2026-05-27T02:06:19.049266+00:00","updated_at":"2026-05-27T02:06:19.049266+00:00"}