{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:E35ZISDKGSI6VMHQ4VRGMGGQH5","short_pith_number":"pith:E35ZISDK","schema_version":"1.0","canonical_sha256":"26fb94486a3491eab0f0e5626618d03f7229591d1a8786a8614461c3c9f3df5b","source":{"kind":"arxiv","id":"2108.01450","version":1},"attestation_state":"computed","paper":{"title":"Is Disentanglement enough? On Latent Representations for Controllable Music Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Alexander Lerch, Ashis Pati","submitted_at":"2021-08-01T18:37:43Z","abstract_excerpt":"Improving controllability or the ability to manipulate one or more attributes of the generated data has become a topic of interest in the context of deep generative models of music. Recent attempts in this direction have relied on learning disentangled representations from data such that the underlying factors of variation are well separated. In this paper, we focus on the relationship between disentanglement and controllability by conducting a systematic study using different supervised disentanglement learning algorithms based on the Variational Auto-Encoder (VAE) architecture. Our experimen"},"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":"2108.01450","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-08-01T18:37:43Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"521bd3423c488d289a4bf102847ee154020452ece4c34dec3973fcf0c5f5fcd2","abstract_canon_sha256":"b5c2814a37db4067fd5d3e292436f2dc7a51b1296026c3adc97a1e55400e84c9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:03:03.095981Z","signature_b64":"+UXd/wyYv9JkKcLuwrXpBYiznLXGE6wvfVAl6VOjfPWBKnyFXNWKv2KIqCn1At/9bvIkNCtlDyqADCZvzu4fAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26fb94486a3491eab0f0e5626618d03f7229591d1a8786a8614461c3c9f3df5b","last_reissued_at":"2026-07-05T03:03:03.095443Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:03:03.095443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Is Disentanglement enough? On Latent Representations for Controllable Music Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Alexander Lerch, Ashis Pati","submitted_at":"2021-08-01T18:37:43Z","abstract_excerpt":"Improving controllability or the ability to manipulate one or more attributes of the generated data has become a topic of interest in the context of deep generative models of music. Recent attempts in this direction have relied on learning disentangled representations from data such that the underlying factors of variation are well separated. In this paper, we focus on the relationship between disentanglement and controllability by conducting a systematic study using different supervised disentanglement learning algorithms based on the Variational Auto-Encoder (VAE) architecture. Our experimen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.01450","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/2108.01450/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":"2108.01450","created_at":"2026-07-05T03:03:03.095505+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.01450v1","created_at":"2026-07-05T03:03:03.095505+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.01450","created_at":"2026-07-05T03:03:03.095505+00:00"},{"alias_kind":"pith_short_12","alias_value":"E35ZISDKGSI6","created_at":"2026-07-05T03:03:03.095505+00:00"},{"alias_kind":"pith_short_16","alias_value":"E35ZISDKGSI6VMHQ","created_at":"2026-07-05T03:03:03.095505+00:00"},{"alias_kind":"pith_short_8","alias_value":"E35ZISDK","created_at":"2026-07-05T03:03:03.095505+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31053","citing_title":"AnchorSteer: Self-Discovered Concept Injection for Structure-Preserving Music Editing","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/E35ZISDKGSI6VMHQ4VRGMGGQH5","json":"https://pith.science/pith/E35ZISDKGSI6VMHQ4VRGMGGQH5.json","graph_json":"https://pith.science/api/pith-number/E35ZISDKGSI6VMHQ4VRGMGGQH5/graph.json","events_json":"https://pith.science/api/pith-number/E35ZISDKGSI6VMHQ4VRGMGGQH5/events.json","paper":"https://pith.science/paper/E35ZISDK"},"agent_actions":{"view_html":"https://pith.science/pith/E35ZISDKGSI6VMHQ4VRGMGGQH5","download_json":"https://pith.science/pith/E35ZISDKGSI6VMHQ4VRGMGGQH5.json","view_paper":"https://pith.science/paper/E35ZISDK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.01450&json=true","fetch_graph":"https://pith.science/api/pith-number/E35ZISDKGSI6VMHQ4VRGMGGQH5/graph.json","fetch_events":"https://pith.science/api/pith-number/E35ZISDKGSI6VMHQ4VRGMGGQH5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E35ZISDKGSI6VMHQ4VRGMGGQH5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E35ZISDKGSI6VMHQ4VRGMGGQH5/action/storage_attestation","attest_author":"https://pith.science/pith/E35ZISDKGSI6VMHQ4VRGMGGQH5/action/author_attestation","sign_citation":"https://pith.science/pith/E35ZISDKGSI6VMHQ4VRGMGGQH5/action/citation_signature","submit_replication":"https://pith.science/pith/E35ZISDKGSI6VMHQ4VRGMGGQH5/action/replication_record"}},"created_at":"2026-07-05T03:03:03.095505+00:00","updated_at":"2026-07-05T03:03:03.095505+00:00"}