{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:MVFXOD6HSVPDU5BQGS4DK6CCPC","short_pith_number":"pith:MVFXOD6H","schema_version":"1.0","canonical_sha256":"654b770fc7955e3a743034b835784278a8c0b99d0a0526f185916ced73a7a2c5","source":{"kind":"arxiv","id":"2608.03999","version":1},"attestation_state":"computed","paper":{"title":"Agogic: Performance-Timed Music Tokens for LLM-Native Text-to-Symbolic-Music Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SD","authors_text":"Hao Zhao, Henghaofan Zhang, Jingjia Mao, Junhao Chen, Liaoyuan Fan, Lin Chen, Mingjin Chen, Mingju Gao, Minglin Chen, Ruocheng Wu, Ruqi Huang, Saining Zhang, Wenyi Li, Yufei Wang, Zhihao Li","submitted_at":"2026-08-04T17:56:49Z","abstract_excerpt":"Text-to-music language models begin with a choice usually made by default: how to tokenize music. Normally entangled with backbone, data, and recipe, its effect has never been measured in isolation. We fix pretrained Qwen3.5 (0.8B-27B), data, budget, and decoding, and swap only the representation across seven tokenizations, anchoring texture metrics to each representation's model-free ceiling. The ordering is clean and surprising: representation, not model size, is the binding variable for distributional fidelity. Scaling the backbone 34x barely moves Frechet Music Distance (FMD), whereas swit"},"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":"2608.03999","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2026-08-04T17:56:49Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"0fee9d466619b809e33b33fc525cc7d0eb4566ce067cf6910ce069a27adc6fe8","abstract_canon_sha256":"f100f84dfb4a71e8501e1ffb6327a598464f6003765584d9b6aa50c1b73dc48a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-05T01:37:40.187628Z","signature_b64":"kfGIDYs5wpYzR2wUh96nY+d38y0Vl4YJeUuCu69V4uSPEg3KO4QjZyL1U/rJU1tgLayXMZpfNuquapeizarKBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"654b770fc7955e3a743034b835784278a8c0b99d0a0526f185916ced73a7a2c5","last_reissued_at":"2026-08-05T01:37:40.186108Z","signature_status":"signed_v1","first_computed_at":"2026-08-05T01:37:40.186108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Agogic: Performance-Timed Music Tokens for LLM-Native Text-to-Symbolic-Music Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.SD","authors_text":"Hao Zhao, Henghaofan Zhang, Jingjia Mao, Junhao Chen, Liaoyuan Fan, Lin Chen, Mingjin Chen, Mingju Gao, Minglin Chen, Ruocheng Wu, Ruqi Huang, Saining Zhang, Wenyi Li, Yufei Wang, Zhihao Li","submitted_at":"2026-08-04T17:56:49Z","abstract_excerpt":"Text-to-music language models begin with a choice usually made by default: how to tokenize music. Normally entangled with backbone, data, and recipe, its effect has never been measured in isolation. We fix pretrained Qwen3.5 (0.8B-27B), data, budget, and decoding, and swap only the representation across seven tokenizations, anchoring texture metrics to each representation's model-free ceiling. The ordering is clean and surprising: representation, not model size, is the binding variable for distributional fidelity. Scaling the backbone 34x barely moves Frechet Music Distance (FMD), whereas swit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.03999","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/2608.03999/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":"2608.03999","created_at":"2026-08-05T01:37:40.186681+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.03999v1","created_at":"2026-08-05T01:37:40.186681+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.03999","created_at":"2026-08-05T01:37:40.186681+00:00"},{"alias_kind":"pith_short_12","alias_value":"MVFXOD6HSVPD","created_at":"2026-08-05T01:37:40.186681+00:00"},{"alias_kind":"pith_short_16","alias_value":"MVFXOD6HSVPDU5BQ","created_at":"2026-08-05T01:37:40.186681+00:00"},{"alias_kind":"pith_short_8","alias_value":"MVFXOD6H","created_at":"2026-08-05T01:37:40.186681+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MVFXOD6HSVPDU5BQGS4DK6CCPC","json":"https://pith.science/pith/MVFXOD6HSVPDU5BQGS4DK6CCPC.json","graph_json":"https://pith.science/api/pith-number/MVFXOD6HSVPDU5BQGS4DK6CCPC/graph.json","events_json":"https://pith.science/api/pith-number/MVFXOD6HSVPDU5BQGS4DK6CCPC/events.json","paper":"https://pith.science/paper/MVFXOD6H"},"agent_actions":{"view_html":"https://pith.science/pith/MVFXOD6HSVPDU5BQGS4DK6CCPC","download_json":"https://pith.science/pith/MVFXOD6HSVPDU5BQGS4DK6CCPC.json","view_paper":"https://pith.science/paper/MVFXOD6H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.03999&json=true","fetch_graph":"https://pith.science/api/pith-number/MVFXOD6HSVPDU5BQGS4DK6CCPC/graph.json","fetch_events":"https://pith.science/api/pith-number/MVFXOD6HSVPDU5BQGS4DK6CCPC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MVFXOD6HSVPDU5BQGS4DK6CCPC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MVFXOD6HSVPDU5BQGS4DK6CCPC/action/storage_attestation","attest_author":"https://pith.science/pith/MVFXOD6HSVPDU5BQGS4DK6CCPC/action/author_attestation","sign_citation":"https://pith.science/pith/MVFXOD6HSVPDU5BQGS4DK6CCPC/action/citation_signature","submit_replication":"https://pith.science/pith/MVFXOD6HSVPDU5BQGS4DK6CCPC/action/replication_record"}},"created_at":"2026-08-05T01:37:40.186681+00:00","updated_at":"2026-08-05T01:37:40.186681+00:00"}