{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:MKAB34CSDUFR22BEBBUUD2AILN","short_pith_number":"pith:MKAB34CS","canonical_record":{"source":{"id":"2605.01790","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-03T09:13:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3ca8828a13b0e569948878d6b6e2fed999420d9a647fe0d9258b72b39ef5ef5f","abstract_canon_sha256":"8300c44790c14bfa857ab7f201c8ac743c25adc7a6689602de6d76f4002e45ba"},"schema_version":"1.0"},"canonical_sha256":"62801df0521d0b1d6824086941e8085b6cfcd12566c2fb646448f2db2fdc6638","source":{"kind":"arxiv","id":"2605.01790","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.01790","created_at":"2026-07-07T02:19:51Z"},{"alias_kind":"arxiv_version","alias_value":"2605.01790v2","created_at":"2026-07-07T02:19:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.01790","created_at":"2026-07-07T02:19:51Z"},{"alias_kind":"pith_short_12","alias_value":"MKAB34CSDUFR","created_at":"2026-07-07T02:19:51Z"},{"alias_kind":"pith_short_16","alias_value":"MKAB34CSDUFR22BE","created_at":"2026-07-07T02:19:51Z"},{"alias_kind":"pith_short_8","alias_value":"MKAB34CS","created_at":"2026-07-07T02:19:51Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:MKAB34CSDUFR22BEBBUUD2AILN","target":"record","payload":{"canonical_record":{"source":{"id":"2605.01790","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-03T09:13:20Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3ca8828a13b0e569948878d6b6e2fed999420d9a647fe0d9258b72b39ef5ef5f","abstract_canon_sha256":"8300c44790c14bfa857ab7f201c8ac743c25adc7a6689602de6d76f4002e45ba"},"schema_version":"1.0"},"canonical_sha256":"62801df0521d0b1d6824086941e8085b6cfcd12566c2fb646448f2db2fdc6638","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-07T02:19:51.793654Z","signature_b64":"dqYXbI9RvtzF3kuhiv+zJ0udNQnsxCH113CZBvigEBnHVzr8Trr4tjA8JXKvlKDMcecMusKZ6NR6Q1cKKaF2Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62801df0521d0b1d6824086941e8085b6cfcd12566c2fb646448f2db2fdc6638","last_reissued_at":"2026-07-07T02:19:51.792108Z","signature_status":"signed_v1","first_computed_at":"2026-07-07T02:19:51.792108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.01790","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-07T02:19:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"c169GQJUbrsEJ+eg+30Je2IxyYqgRs+p1Vkt2Iz/luMwr9j1DknkYnee0KjrlLTeUoIXMMorjxMe9Y4s21dXDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T17:51:34.751459Z"},"content_sha256":"983cfe16071d3c9245d6592860682765ea7ece7b096330557358a19239ae91c9","schema_version":"1.0","event_id":"sha256:983cfe16071d3c9245d6592860682765ea7ece7b096330557358a19239ae91c9"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:MKAB34CSDUFR22BEBBUUD2AILN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Shao: Scaling Acoustic Token Language Models Toward High-Fidelity Music Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"High-fidelity music can be generated by progressively modeling structure and detail together inside one 64-layer acoustic token hierarchy.","cross_cats":["cs.AI"],"primary_cat":"cs.SD","authors_text":"Feng Yu, Hongjia Liu, Huijing Liang, Jiafeng Liu, Maosong Sun, Wenbo Zhan, Xiaobing Li, Yuanliang Dong, Yuming Sun, Yuqing Cheng, Zhancheng Guo","submitted_at":"2026-05-03T09:13:20Z","abstract_excerpt":"A common design pattern in high-quality music generation is to handle structure and fidelity in different representation spaces: a generator first models high-level structure, followed by diffusion-based or neural decoding stages that reconstruct fine details. In this work, we explore an alternative view: both may be progressively modeled within a single deep acoustic-token hierarchy. To study this, we build a 64-layer residual vector quantization (RVQ) acoustic representation and propose a two-stage coarse-to-fine generation framework. A backbone model first generates coarse acoustic tokens f"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Taken together, our results suggest that high-quality music generation can be effectively pursued without separating structure and fidelity into heterogeneous representation spaces. Instead, both can be progressively modeled within a unified acoustic-token hierarchy, pointing toward a simpler and more unified path to high-quality music generation.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That a single 64-layer RVQ acoustic token space can capture both high-level musical structure and fine-grained fidelity sufficiently to allow emergent alignment and high quality without information loss that would require separate semantic modeling.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A two-stage coarse-to-fine acoustic token language model with hybrid attention generates high-fidelity music and achieves emergent lyric alignment without separate semantic tokens.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"High-fidelity music can be generated by progressively modeling structure and detail together inside one 64-layer acoustic token hierarchy.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"79cdbd1fc42166f36886992f6fcb8b90d3139c0d4bcb53ae57e9441fc34b3b89"},"source":{"id":"2605.01790","kind":"arxiv","version":2},"verdict":{"id":"6ff8e938-02e5-40ed-b318-49fb28c8d039","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-09T16:32:11.293019Z","strongest_claim":"Taken together, our results suggest that high-quality music generation can be effectively pursued without separating structure and fidelity into heterogeneous representation spaces. Instead, both can be progressively modeled within a unified acoustic-token hierarchy, pointing toward a simpler and more unified path to high-quality music generation.","one_line_summary":"A two-stage coarse-to-fine acoustic token language model with hybrid attention generates high-fidelity music and achieves emergent lyric alignment without separate semantic tokens.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That a single 64-layer RVQ acoustic token space can capture both high-level musical structure and fine-grained fidelity sufficiently to allow emergent alignment and high quality without information loss that would require separate semantic modeling.","pith_extraction_headline":"High-fidelity music can be generated by progressively modeling structure and detail together inside one 64-layer acoustic token hierarchy."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.01790/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T17:36:02.204905Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-20T05:01:22.725690Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T16:58:40.484608Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"4a14a298611371a5ff6ca02ea171bf38ffacad0428e6e515ccb07605be932254"},"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"},"verdict_id":"6ff8e938-02e5-40ed-b318-49fb28c8d039"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-07T02:19:51Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xDqkOk46xqd26bjk1LPfISYqhpJ608vGXRgbpsz8JnWsUoZ52w+dF31FeKeVcYnC40q1HL/Zmcyl9l06ZC5LAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-01T17:51:34.751988Z"},"content_sha256":"b84051f54f41428a960ca13c219e3ddbf1db3f371146940e494702a9e633ab98","schema_version":"1.0","event_id":"sha256:b84051f54f41428a960ca13c219e3ddbf1db3f371146940e494702a9e633ab98"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MKAB34CSDUFR22BEBBUUD2AILN/bundle.json","state_url":"https://pith.science/pith/MKAB34CSDUFR22BEBBUUD2AILN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MKAB34CSDUFR22BEBBUUD2AILN/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-01T17:51:34Z","links":{"resolver":"https://pith.science/pith/MKAB34CSDUFR22BEBBUUD2AILN","bundle":"https://pith.science/pith/MKAB34CSDUFR22BEBBUUD2AILN/bundle.json","state":"https://pith.science/pith/MKAB34CSDUFR22BEBBUUD2AILN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MKAB34CSDUFR22BEBBUUD2AILN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MKAB34CSDUFR22BEBBUUD2AILN","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":"8300c44790c14bfa857ab7f201c8ac743c25adc7a6689602de6d76f4002e45ba","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-03T09:13:20Z","title_canon_sha256":"3ca8828a13b0e569948878d6b6e2fed999420d9a647fe0d9258b72b39ef5ef5f"},"schema_version":"1.0","source":{"id":"2605.01790","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.01790","created_at":"2026-07-07T02:19:51Z"},{"alias_kind":"arxiv_version","alias_value":"2605.01790v2","created_at":"2026-07-07T02:19:51Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.01790","created_at":"2026-07-07T02:19:51Z"},{"alias_kind":"pith_short_12","alias_value":"MKAB34CSDUFR","created_at":"2026-07-07T02:19:51Z"},{"alias_kind":"pith_short_16","alias_value":"MKAB34CSDUFR22BE","created_at":"2026-07-07T02:19:51Z"},{"alias_kind":"pith_short_8","alias_value":"MKAB34CS","created_at":"2026-07-07T02:19:51Z"}],"graph_snapshots":[{"event_id":"sha256:b84051f54f41428a960ca13c219e3ddbf1db3f371146940e494702a9e633ab98","target":"graph","created_at":"2026-07-07T02:19:51Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"Taken together, our results suggest that high-quality music generation can be effectively pursued without separating structure and fidelity into heterogeneous representation spaces. Instead, both can be progressively modeled within a unified acoustic-token hierarchy, pointing toward a simpler and more unified path to high-quality music generation."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That a single 64-layer RVQ acoustic token space can capture both high-level musical structure and fine-grained fidelity sufficiently to allow emergent alignment and high quality without information loss that would require separate semantic modeling."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A two-stage coarse-to-fine acoustic token language model with hybrid attention generates high-fidelity music and achieves emergent lyric alignment without separate semantic tokens."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"High-fidelity music can be generated by progressively modeling structure and detail together inside one 64-layer acoustic token hierarchy."}],"snapshot_sha256":"79cdbd1fc42166f36886992f6fcb8b90d3139c0d4bcb53ae57e9441fc34b3b89"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"name":"ai_meta_artifact","ran_at":"2026-05-20T17:36:02.204905Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_title_agreement","ran_at":"2026-05-20T05:01:22.725690Z","status":"completed","version":"1.0.0"},{"findings_count":0,"name":"doi_compliance","ran_at":"2026-05-19T16:58:40.484608Z","status":"completed","version":"1.0.0"}],"endpoint":"/pith/2605.01790/integrity.json","findings":[],"snapshot_sha256":"4a14a298611371a5ff6ca02ea171bf38ffacad0428e6e515ccb07605be932254","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A common design pattern in high-quality music generation is to handle structure and fidelity in different representation spaces: a generator first models high-level structure, followed by diffusion-based or neural decoding stages that reconstruct fine details. In this work, we explore an alternative view: both may be progressively modeled within a single deep acoustic-token hierarchy. To study this, we build a 64-layer residual vector quantization (RVQ) acoustic representation and propose a two-stage coarse-to-fine generation framework. A backbone model first generates coarse acoustic tokens f","authors_text":"Feng Yu, Hongjia Liu, Huijing Liang, Jiafeng Liu, Maosong Sun, Wenbo Zhan, Xiaobing Li, Yuanliang Dong, Yuming Sun, Yuqing Cheng, Zhancheng Guo","cross_cats":["cs.AI"],"headline":"High-fidelity music can be generated by progressively modeling structure and detail together inside one 64-layer acoustic token hierarchy.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-03T09:13:20Z","title":"Shao: Scaling Acoustic Token Language Models Toward High-Fidelity Music Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.01790","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-09T16:32:11.293019Z","id":"6ff8e938-02e5-40ed-b318-49fb28c8d039","model_set":{"reader":"grok-4.3"},"one_line_summary":"A two-stage coarse-to-fine acoustic token language model with hybrid attention generates high-fidelity music and achieves emergent lyric alignment without separate semantic tokens.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"High-fidelity music can be generated by progressively modeling structure and detail together inside one 64-layer acoustic token hierarchy.","strongest_claim":"Taken together, our results suggest that high-quality music generation can be effectively pursued without separating structure and fidelity into heterogeneous representation spaces. Instead, both can be progressively modeled within a unified acoustic-token hierarchy, pointing toward a simpler and more unified path to high-quality music generation.","weakest_assumption":"That a single 64-layer RVQ acoustic token space can capture both high-level musical structure and fine-grained fidelity sufficiently to allow emergent alignment and high quality without information loss that would require separate semantic modeling."}},"verdict_id":"6ff8e938-02e5-40ed-b318-49fb28c8d039"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:983cfe16071d3c9245d6592860682765ea7ece7b096330557358a19239ae91c9","target":"record","created_at":"2026-07-07T02:19:51Z","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":"8300c44790c14bfa857ab7f201c8ac743c25adc7a6689602de6d76f4002e45ba","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-05-03T09:13:20Z","title_canon_sha256":"3ca8828a13b0e569948878d6b6e2fed999420d9a647fe0d9258b72b39ef5ef5f"},"schema_version":"1.0","source":{"id":"2605.01790","kind":"arxiv","version":2}},"canonical_sha256":"62801df0521d0b1d6824086941e8085b6cfcd12566c2fb646448f2db2fdc6638","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"62801df0521d0b1d6824086941e8085b6cfcd12566c2fb646448f2db2fdc6638","first_computed_at":"2026-07-07T02:19:51.792108Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-07T02:19:51.792108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"dqYXbI9RvtzF3kuhiv+zJ0udNQnsxCH113CZBvigEBnHVzr8Trr4tjA8JXKvlKDMcecMusKZ6NR6Q1cKKaF2Cg==","signature_status":"signed_v1","signed_at":"2026-07-07T02:19:51.793654Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.01790","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:983cfe16071d3c9245d6592860682765ea7ece7b096330557358a19239ae91c9","sha256:b84051f54f41428a960ca13c219e3ddbf1db3f371146940e494702a9e633ab98"],"state_sha256":"76f13fab5799c62222a38cdb485dabfd46a9e9dae78295037c43baaafa262530"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"16jCtEMr1R4BHqhJWjyp8mXK5OmlsXei8XFR9VxtpkBMcwa+j9LGH6pFhVSr4y/M9si8lCiSSGKdhCLGzkRZAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-01T17:51:34.754551Z","bundle_sha256":"42419da394a8eb3b34dafe18836a9dd19108996bbd8c9eba25decb60ebdd382f"}}