{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:TZ7FBYGXSKWXSJTVBJJIZJUYAM","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"8ecd9cf0d70703ec66b7d1951411042ccbb13ab711ba30b86ae17b99b2465050","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-04-18T12:46:12Z","title_canon_sha256":"3818e239ce51c400e3e20fced2fd0960153570c0107baca9d9ac4f30c5329803"},"schema_version":"1.0","source":{"id":"2304.08953","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.08953","created_at":"2026-07-05T06:04:14Z"},{"alias_kind":"arxiv_version","alias_value":"2304.08953v2","created_at":"2026-07-05T06:04:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.08953","created_at":"2026-07-05T06:04:14Z"},{"alias_kind":"pith_short_12","alias_value":"TZ7FBYGXSKWX","created_at":"2026-07-05T06:04:14Z"},{"alias_kind":"pith_short_16","alias_value":"TZ7FBYGXSKWXSJTV","created_at":"2026-07-05T06:04:14Z"},{"alias_kind":"pith_short_8","alias_value":"TZ7FBYGX","created_at":"2026-07-05T06:04:14Z"}],"graph_snapshots":[{"event_id":"sha256:d647fe41ba2bb6cec3cfca54b18f13770a269c2a29a5a560d65993dd5dad9271","target":"graph","created_at":"2026-07-05T06:04:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2304.08953/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Adarsh Kumar, Pedro Sarmento","cross_cats":["cs.LG","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-04-18T12:46:12Z","title":"From Words to Music: A Study of Subword Tokenization Techniques in Symbolic Music Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.08953","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:234dce4c8a2848b9b3a8ee10571220b5ed0f5fbac2751f474aee2acd2b76592d","target":"record","created_at":"2026-07-05T06:04:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"8ecd9cf0d70703ec66b7d1951411042ccbb13ab711ba30b86ae17b99b2465050","cross_cats_sorted":["cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2023-04-18T12:46:12Z","title_canon_sha256":"3818e239ce51c400e3e20fced2fd0960153570c0107baca9d9ac4f30c5329803"},"schema_version":"1.0","source":{"id":"2304.08953","kind":"arxiv","version":2}},"canonical_sha256":"9e7e50e0d792ad7926750a528ca698033ed4f6606978b05136b59c33502001e4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9e7e50e0d792ad7926750a528ca698033ed4f6606978b05136b59c33502001e4","first_computed_at":"2026-07-05T06:04:14.113099Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:04:14.113099Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"repKg4OSHPGVC7eTyOlNoJobmZWUPUdUZNmRsacnpe5OijDpJm86qAuuDswgfuK5LZZqspaO0fhxlhzWypeRAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:04:14.113594Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.08953","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:234dce4c8a2848b9b3a8ee10571220b5ed0f5fbac2751f474aee2acd2b76592d","sha256:d647fe41ba2bb6cec3cfca54b18f13770a269c2a29a5a560d65993dd5dad9271"],"state_sha256":"7a3767c992452a5422803ea67f9541bf996f2b7ac22288eb76c0605256e6e490"}