{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DTEJ3VG4MWKGOJMUEEPGFNCHFC","short_pith_number":"pith:DTEJ3VG4","schema_version":"1.0","canonical_sha256":"1cc89dd4dc6594672594211e62b447288ec7c26c89d31cde3b03f9211e27e99d","source":{"kind":"arxiv","id":"2410.02060","version":1},"attestation_state":"computed","paper":{"title":"PerTok: Expressive Encoding and Modeling of Symbolic Musical Ideas and Variations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Anirudh Mani, Julian Lenz","submitted_at":"2024-10-02T22:11:31Z","abstract_excerpt":"We introduce Cadenza, a new multi-stage generative framework for predicting expressive variations of symbolic musical ideas as well as unconditional generations. To accomplish this we propose a novel MIDI encoding method, PerTok (Performance Tokenizer) that captures minute expressive details whilst reducing sequence length up to 59% and vocabulary size up to 95% for polyphonic, monophonic and rhythmic tasks. The proposed framework comprises of two sequential stages: 1) Composer and 2) Performer. The Composer model is a transformer-based Variational Autoencoder (VAE), with Rotary Positional Emb"},"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":"2410.02060","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2024-10-02T22:11:31Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"5c6ab1fa94a36aa82b536dc9ec29829b03a5728ca721aadb516480b1a75076a9","abstract_canon_sha256":"8bd63be794113f3c70f2cd682269a15fba798498356003193d5e9a1138e2610f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:14:59.926773Z","signature_b64":"JUMfJ5FSzuaEML2yRtx+ngA3rJbSah+Y+AYeOzJhndT6m9SEcvQq4SrzG/BelytIr5u3fleWrewtOLY7CPg7Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1cc89dd4dc6594672594211e62b447288ec7c26c89d31cde3b03f9211e27e99d","last_reissued_at":"2026-07-05T09:14:59.926329Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:14:59.926329Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PerTok: Expressive Encoding and Modeling of Symbolic Musical Ideas and Variations","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Anirudh Mani, Julian Lenz","submitted_at":"2024-10-02T22:11:31Z","abstract_excerpt":"We introduce Cadenza, a new multi-stage generative framework for predicting expressive variations of symbolic musical ideas as well as unconditional generations. To accomplish this we propose a novel MIDI encoding method, PerTok (Performance Tokenizer) that captures minute expressive details whilst reducing sequence length up to 59% and vocabulary size up to 95% for polyphonic, monophonic and rhythmic tasks. The proposed framework comprises of two sequential stages: 1) Composer and 2) Performer. The Composer model is a transformer-based Variational Autoencoder (VAE), with Rotary Positional Emb"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02060","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/2410.02060/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":"2410.02060","created_at":"2026-07-05T09:14:59.926389+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.02060v1","created_at":"2026-07-05T09:14:59.926389+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02060","created_at":"2026-07-05T09:14:59.926389+00:00"},{"alias_kind":"pith_short_12","alias_value":"DTEJ3VG4MWKG","created_at":"2026-07-05T09:14:59.926389+00:00"},{"alias_kind":"pith_short_16","alias_value":"DTEJ3VG4MWKGOJMU","created_at":"2026-07-05T09:14:59.926389+00:00"},{"alias_kind":"pith_short_8","alias_value":"DTEJ3VG4","created_at":"2026-07-05T09:14:59.926389+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2502.04522","citing_title":"ImprovNet -- Generating Controllable Musical Improvisations with Iterative Corruption Refinement","ref_index":31,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DTEJ3VG4MWKGOJMUEEPGFNCHFC","json":"https://pith.science/pith/DTEJ3VG4MWKGOJMUEEPGFNCHFC.json","graph_json":"https://pith.science/api/pith-number/DTEJ3VG4MWKGOJMUEEPGFNCHFC/graph.json","events_json":"https://pith.science/api/pith-number/DTEJ3VG4MWKGOJMUEEPGFNCHFC/events.json","paper":"https://pith.science/paper/DTEJ3VG4"},"agent_actions":{"view_html":"https://pith.science/pith/DTEJ3VG4MWKGOJMUEEPGFNCHFC","download_json":"https://pith.science/pith/DTEJ3VG4MWKGOJMUEEPGFNCHFC.json","view_paper":"https://pith.science/paper/DTEJ3VG4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.02060&json=true","fetch_graph":"https://pith.science/api/pith-number/DTEJ3VG4MWKGOJMUEEPGFNCHFC/graph.json","fetch_events":"https://pith.science/api/pith-number/DTEJ3VG4MWKGOJMUEEPGFNCHFC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DTEJ3VG4MWKGOJMUEEPGFNCHFC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DTEJ3VG4MWKGOJMUEEPGFNCHFC/action/storage_attestation","attest_author":"https://pith.science/pith/DTEJ3VG4MWKGOJMUEEPGFNCHFC/action/author_attestation","sign_citation":"https://pith.science/pith/DTEJ3VG4MWKGOJMUEEPGFNCHFC/action/citation_signature","submit_replication":"https://pith.science/pith/DTEJ3VG4MWKGOJMUEEPGFNCHFC/action/replication_record"}},"created_at":"2026-07-05T09:14:59.926389+00:00","updated_at":"2026-07-05T09:14:59.926389+00:00"}