{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:7BCXFZRG4DXGVSR72CGJJ4Z4CN","short_pith_number":"pith:7BCXFZRG","schema_version":"1.0","canonical_sha256":"f84572e626e0ee6aca3fd08c94f33c136a649795be7746bd471ca1ce0256b24a","source":{"kind":"arxiv","id":"2111.04093","version":2},"attestation_state":"computed","paper":{"title":"Theme Transformer: Symbolic Music Generation with Theme-Conditioned Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Frank Zalkow, Meinard M\\\"uller, Shih-Lun Wu, Yi-Hsuan Yang, Yi-Jen Shih","submitted_at":"2021-11-07T13:55:39Z","abstract_excerpt":"Attention-based Transformer models have been increasingly employed for automatic music generation. To condition the generation process of such a model with a user-specified sequence, a popular approach is to take that conditioning sequence as a priming sequence and ask a Transformer decoder to generate a continuation. However, this prompt-based conditioning cannot guarantee that the conditioning sequence would develop or even simply repeat itself in the generated continuation. In this paper, we propose an alternative conditioning approach, called theme-based conditioning, that explicitly train"},"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":"2111.04093","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2021-11-07T13:55:39Z","cross_cats_sorted":["cs.MM","eess.AS"],"title_canon_sha256":"75dde8c4962e2f580a74c41373f8b6f87c0040ce4e9914e1066558944a6eae4a","abstract_canon_sha256":"274b4571e2c9fe0c6d47505e3d5ade89447e3f9295e6ebdbcf6879b37daaea4d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:06:46.785984Z","signature_b64":"Sb8FCxY5ogiX8adRP/sjhV3FGiP4ySo3eGCGTJuOqd0k0qzyeLahC0u1v4GuUQhUNJLMLXYdB0iYi+5Q8yi5Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f84572e626e0ee6aca3fd08c94f33c136a649795be7746bd471ca1ce0256b24a","last_reissued_at":"2026-07-05T04:06:46.785535Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:06:46.785535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Theme Transformer: Symbolic Music Generation with Theme-Conditioned Transformer","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Frank Zalkow, Meinard M\\\"uller, Shih-Lun Wu, Yi-Hsuan Yang, Yi-Jen Shih","submitted_at":"2021-11-07T13:55:39Z","abstract_excerpt":"Attention-based Transformer models have been increasingly employed for automatic music generation. To condition the generation process of such a model with a user-specified sequence, a popular approach is to take that conditioning sequence as a priming sequence and ask a Transformer decoder to generate a continuation. However, this prompt-based conditioning cannot guarantee that the conditioning sequence would develop or even simply repeat itself in the generated continuation. In this paper, we propose an alternative conditioning approach, called theme-based conditioning, that explicitly train"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2111.04093","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/2111.04093/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":"2111.04093","created_at":"2026-07-05T04:06:46.785598+00:00"},{"alias_kind":"arxiv_version","alias_value":"2111.04093v2","created_at":"2026-07-05T04:06:46.785598+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2111.04093","created_at":"2026-07-05T04:06:46.785598+00:00"},{"alias_kind":"pith_short_12","alias_value":"7BCXFZRG4DXG","created_at":"2026-07-05T04:06:46.785598+00:00"},{"alias_kind":"pith_short_16","alias_value":"7BCXFZRG4DXGVSR7","created_at":"2026-07-05T04:06:46.785598+00:00"},{"alias_kind":"pith_short_8","alias_value":"7BCXFZRG","created_at":"2026-07-05T04:06:46.785598+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.10225","citing_title":"Genre Controlled Music Generation via Activation Steering","ref_index":3,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7BCXFZRG4DXGVSR72CGJJ4Z4CN","json":"https://pith.science/pith/7BCXFZRG4DXGVSR72CGJJ4Z4CN.json","graph_json":"https://pith.science/api/pith-number/7BCXFZRG4DXGVSR72CGJJ4Z4CN/graph.json","events_json":"https://pith.science/api/pith-number/7BCXFZRG4DXGVSR72CGJJ4Z4CN/events.json","paper":"https://pith.science/paper/7BCXFZRG"},"agent_actions":{"view_html":"https://pith.science/pith/7BCXFZRG4DXGVSR72CGJJ4Z4CN","download_json":"https://pith.science/pith/7BCXFZRG4DXGVSR72CGJJ4Z4CN.json","view_paper":"https://pith.science/paper/7BCXFZRG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2111.04093&json=true","fetch_graph":"https://pith.science/api/pith-number/7BCXFZRG4DXGVSR72CGJJ4Z4CN/graph.json","fetch_events":"https://pith.science/api/pith-number/7BCXFZRG4DXGVSR72CGJJ4Z4CN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7BCXFZRG4DXGVSR72CGJJ4Z4CN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7BCXFZRG4DXGVSR72CGJJ4Z4CN/action/storage_attestation","attest_author":"https://pith.science/pith/7BCXFZRG4DXGVSR72CGJJ4Z4CN/action/author_attestation","sign_citation":"https://pith.science/pith/7BCXFZRG4DXGVSR72CGJJ4Z4CN/action/citation_signature","submit_replication":"https://pith.science/pith/7BCXFZRG4DXGVSR72CGJJ4Z4CN/action/replication_record"}},"created_at":"2026-07-05T04:06:46.785598+00:00","updated_at":"2026-07-05T04:06:46.785598+00:00"}