{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:TZ7FBYGXSKWXSJTVBJJIZJUYAM","short_pith_number":"pith:TZ7FBYGX","schema_version":"1.0","canonical_sha256":"9e7e50e0d792ad7926750a528ca698033ed4f6606978b05136b59c33502001e4","source":{"kind":"arxiv","id":"2304.08953","version":2},"attestation_state":"computed","paper":{"title":"From Words to Music: A Study of Subword Tokenization Techniques in Symbolic Music Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Adarsh Kumar, Pedro Sarmento","submitted_at":"2023-04-18T12:46:12Z","abstract_excerpt":"Subword tokenization has been widely successful in text-based natural language processing (NLP) tasks with Transformer-based models. As Transformer models become increasingly popular in symbolic music-related studies, it is imperative to investigate the efficacy of subword tokenization in the symbolic music domain. In this paper, we explore subword tokenization techniques, such as byte-pair encoding (BPE), in symbolic music generation and its impact on the overall structure of generated songs. Our experiments are based on three types of MIDI datasets: single track-melody only, multi-track with"},"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":"2304.08953","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-04-18T12:46:12Z","cross_cats_sorted":["cs.LG","eess.AS"],"title_canon_sha256":"3818e239ce51c400e3e20fced2fd0960153570c0107baca9d9ac4f30c5329803","abstract_canon_sha256":"8ecd9cf0d70703ec66b7d1951411042ccbb13ab711ba30b86ae17b99b2465050"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:04:14.113594Z","signature_b64":"repKg4OSHPGVC7eTyOlNoJobmZWUPUdUZNmRsacnpe5OijDpJm86qAuuDswgfuK5LZZqspaO0fhxlhzWypeRAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e7e50e0d792ad7926750a528ca698033ed4f6606978b05136b59c33502001e4","last_reissued_at":"2026-07-05T06:04:14.113099Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:04:14.113099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Words to Music: A Study of Subword Tokenization Techniques in Symbolic Music Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Adarsh Kumar, Pedro Sarmento","submitted_at":"2023-04-18T12:46:12Z","abstract_excerpt":"Subword tokenization has been widely successful in text-based natural language processing (NLP) tasks with Transformer-based models. As Transformer models become increasingly popular in symbolic music-related studies, it is imperative to investigate the efficacy of subword tokenization in the symbolic music domain. In this paper, we explore subword tokenization techniques, such as byte-pair encoding (BPE), in symbolic music generation and its impact on the overall structure of generated songs. Our experiments are based on three types of MIDI datasets: single track-melody only, multi-track with"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.08953","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/2304.08953/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":"2304.08953","created_at":"2026-07-05T06:04:14.113155+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.08953v2","created_at":"2026-07-05T06:04:14.113155+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.08953","created_at":"2026-07-05T06:04:14.113155+00:00"},{"alias_kind":"pith_short_12","alias_value":"TZ7FBYGXSKWX","created_at":"2026-07-05T06:04:14.113155+00:00"},{"alias_kind":"pith_short_16","alias_value":"TZ7FBYGXSKWXSJTV","created_at":"2026-07-05T06:04:14.113155+00:00"},{"alias_kind":"pith_short_8","alias_value":"TZ7FBYGX","created_at":"2026-07-05T06:04:14.113155+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.19532","citing_title":"BEAT: Tokenizing and Generating Symbolic Music by Uniform Temporal Steps","ref_index":95,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TZ7FBYGXSKWXSJTVBJJIZJUYAM","json":"https://pith.science/pith/TZ7FBYGXSKWXSJTVBJJIZJUYAM.json","graph_json":"https://pith.science/api/pith-number/TZ7FBYGXSKWXSJTVBJJIZJUYAM/graph.json","events_json":"https://pith.science/api/pith-number/TZ7FBYGXSKWXSJTVBJJIZJUYAM/events.json","paper":"https://pith.science/paper/TZ7FBYGX"},"agent_actions":{"view_html":"https://pith.science/pith/TZ7FBYGXSKWXSJTVBJJIZJUYAM","download_json":"https://pith.science/pith/TZ7FBYGXSKWXSJTVBJJIZJUYAM.json","view_paper":"https://pith.science/paper/TZ7FBYGX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.08953&json=true","fetch_graph":"https://pith.science/api/pith-number/TZ7FBYGXSKWXSJTVBJJIZJUYAM/graph.json","fetch_events":"https://pith.science/api/pith-number/TZ7FBYGXSKWXSJTVBJJIZJUYAM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TZ7FBYGXSKWXSJTVBJJIZJUYAM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TZ7FBYGXSKWXSJTVBJJIZJUYAM/action/storage_attestation","attest_author":"https://pith.science/pith/TZ7FBYGXSKWXSJTVBJJIZJUYAM/action/author_attestation","sign_citation":"https://pith.science/pith/TZ7FBYGXSKWXSJTVBJJIZJUYAM/action/citation_signature","submit_replication":"https://pith.science/pith/TZ7FBYGXSKWXSJTVBJJIZJUYAM/action/replication_record"}},"created_at":"2026-07-05T06:04:14.113155+00:00","updated_at":"2026-07-05T06:04:14.113155+00:00"}