{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:D2WMPN36J55TYCQTRWTNLACTNL","short_pith_number":"pith:D2WMPN36","canonical_record":{"source":{"id":"2604.09054","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-04-10T07:27:55Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"d8e0e9ad02905b9131b216d81008c5232ddcab7166f0a470850d29f86a7e4ce9","abstract_canon_sha256":"504e6d6be6200a27b168d7e58240be2e74f7d4e79e0bf51b5133400e7c9c40fe"},"schema_version":"1.0"},"canonical_sha256":"1eacc7b77e4f7b3c0a138da6d580536ae8147e1ce568b073e40963c007d339ce","source":{"kind":"arxiv","id":"2604.09054","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.09054","created_at":"2026-06-23T01:13:05Z"},{"alias_kind":"arxiv_version","alias_value":"2604.09054v3","created_at":"2026-06-23T01:13:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.09054","created_at":"2026-06-23T01:13:05Z"},{"alias_kind":"pith_short_12","alias_value":"D2WMPN36J55T","created_at":"2026-06-23T01:13:05Z"},{"alias_kind":"pith_short_16","alias_value":"D2WMPN36J55TYCQT","created_at":"2026-06-23T01:13:05Z"},{"alias_kind":"pith_short_8","alias_value":"D2WMPN36","created_at":"2026-06-23T01:13:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:D2WMPN36J55TYCQTRWTNLACTNL","target":"record","payload":{"canonical_record":{"source":{"id":"2604.09054","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-04-10T07:27:55Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"d8e0e9ad02905b9131b216d81008c5232ddcab7166f0a470850d29f86a7e4ce9","abstract_canon_sha256":"504e6d6be6200a27b168d7e58240be2e74f7d4e79e0bf51b5133400e7c9c40fe"},"schema_version":"1.0"},"canonical_sha256":"1eacc7b77e4f7b3c0a138da6d580536ae8147e1ce568b073e40963c007d339ce","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:13:05.067564Z","signature_b64":"GUUav/Hzonompk4YUHKJnVgYKYG+YkJ/t/+7ISP2VIcwTWCQ/iLWjmB/Ndg2xeF9bK79vA5SNe36RVyy5c+0Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1eacc7b77e4f7b3c0a138da6d580536ae8147e1ce568b073e40963c007d339ce","last_reissued_at":"2026-06-23T01:13:05.066943Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:13:05.066943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2604.09054","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T01:13:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rpXMu7WgBZbREspSVOfbUilzu9JIQf0Vzz0qsl6/gNSkkElpJHMNE5FVoBI1bOw6yrwGag1Fl5pGJONrFj89AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T19:00:22.698572Z"},"content_sha256":"0f7a33a1369da9c0241108fc1422bfa4d22bf5411c2dcf1a49de70765c85d748","schema_version":"1.0","event_id":"sha256:0f7a33a1369da9c0241108fc1422bfa4d22bf5411c2dcf1a49de70765c85d748"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:D2WMPN36J55TYCQTRWTNLACTNL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"HAFM: Hierarchical Autoregressive Foundation Model for Music Accompaniment Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"A hierarchical autoregressive model generates coherent instrumental accompaniments from isolated vocals using dual-rate tokenization.","cross_cats":["cs.MM"],"primary_cat":"cs.SD","authors_text":"Cheng Luo, Jianwei Cui, Jian Zhu, Jun Sun, Shihao Chen, Yubang Zhang, Yunlong Xue","submitted_at":"2026-04-10T07:27:55Z","abstract_excerpt":"Music accompaniment generation aims to automatically produce instrumental accompaniments that are rhythmically, harmonically, and timbrally coherent with a given vocal input, with broad applications in personalized music creation, arrangement assistance, and music education. Existing approaches, primarily operating in the symbolic domain or relying on single-stage audio generation frameworks, commonly suffer from insufficient high-level semantic structure modeling, limited acoustic detail reconstruction, and weak conditional controllability. To address these limitations, this paper proposes HA"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Experiments on MUSDB18 demonstrate that HAFM achieves a Fréchet Audio Distance (FAD) of 2.08 on isolated vocal inputs, outperforming retrieval baselines and matching prior state-of-the-art systems with fewer parameters.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The dual-rate codec tokenization scheme using HuBERT at 50 Hz for vocals and EnCodec at 75 Hz for instrumentals, combined with the three-stage hierarchical autoregressive architecture, produces time-aligned and coherent accompaniments without needing additional explicit alignment or synchronization steps.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"HAFM uses a hierarchical autoregressive model with dual-rate HuBERT and EnCodec tokens to generate coherent instrumental music from vocals, achieving FAD 2.08 on MUSDB18 while matching prior systems with fewer parameters.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"A hierarchical autoregressive model generates coherent instrumental accompaniments from isolated vocals using dual-rate tokenization.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"3cfdff9d5b0157a1a4694375e156ea172d81284e08f02fd5a9bc8161c39bcf16"},"source":{"id":"2604.09054","kind":"arxiv","version":3},"verdict":{"id":"2bbe5bb4-1555-4d6f-a681-853c4c16b3b9","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T17:23:06.028909Z","strongest_claim":"Experiments on MUSDB18 demonstrate that HAFM achieves a Fréchet Audio Distance (FAD) of 2.08 on isolated vocal inputs, outperforming retrieval baselines and matching prior state-of-the-art systems with fewer parameters.","one_line_summary":"HAFM uses a hierarchical autoregressive model with dual-rate HuBERT and EnCodec tokens to generate coherent instrumental music from vocals, achieving FAD 2.08 on MUSDB18 while matching prior systems with fewer parameters.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The dual-rate codec tokenization scheme using HuBERT at 50 Hz for vocals and EnCodec at 75 Hz for instrumentals, combined with the three-stage hierarchical autoregressive architecture, produces time-aligned and coherent accompaniments without needing additional explicit alignment or synchronization steps.","pith_extraction_headline":"A hierarchical autoregressive model generates coherent instrumental accompaniments from isolated vocals using dual-rate tokenization."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.09054/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"},"verdict_id":"2bbe5bb4-1555-4d6f-a681-853c4c16b3b9"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-23T01:13:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NGQ8nlwElnBxI5f1aegS3R5+8ZsEhX4qM9ZBmJv7MFkX+Lj4FW830kVEK1pbj6YzDLn+x8a9000Fc+/1LublDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-10T19:00:22.699036Z"},"content_sha256":"6162e073f928fe8c3f35b628a506ee27f9b3d261dcf775195affd95a5fd3f5d5","schema_version":"1.0","event_id":"sha256:6162e073f928fe8c3f35b628a506ee27f9b3d261dcf775195affd95a5fd3f5d5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/D2WMPN36J55TYCQTRWTNLACTNL/bundle.json","state_url":"https://pith.science/pith/D2WMPN36J55TYCQTRWTNLACTNL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/D2WMPN36J55TYCQTRWTNLACTNL/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":"2026-07-10T19:00:22Z","links":{"resolver":"https://pith.science/pith/D2WMPN36J55TYCQTRWTNLACTNL","bundle":"https://pith.science/pith/D2WMPN36J55TYCQTRWTNLACTNL/bundle.json","state":"https://pith.science/pith/D2WMPN36J55TYCQTRWTNLACTNL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/D2WMPN36J55TYCQTRWTNLACTNL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:D2WMPN36J55TYCQTRWTNLACTNL","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":"504e6d6be6200a27b168d7e58240be2e74f7d4e79e0bf51b5133400e7c9c40fe","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-04-10T07:27:55Z","title_canon_sha256":"d8e0e9ad02905b9131b216d81008c5232ddcab7166f0a470850d29f86a7e4ce9"},"schema_version":"1.0","source":{"id":"2604.09054","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.09054","created_at":"2026-06-23T01:13:05Z"},{"alias_kind":"arxiv_version","alias_value":"2604.09054v3","created_at":"2026-06-23T01:13:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.09054","created_at":"2026-06-23T01:13:05Z"},{"alias_kind":"pith_short_12","alias_value":"D2WMPN36J55T","created_at":"2026-06-23T01:13:05Z"},{"alias_kind":"pith_short_16","alias_value":"D2WMPN36J55TYCQT","created_at":"2026-06-23T01:13:05Z"},{"alias_kind":"pith_short_8","alias_value":"D2WMPN36","created_at":"2026-06-23T01:13:05Z"}],"graph_snapshots":[{"event_id":"sha256:6162e073f928fe8c3f35b628a506ee27f9b3d261dcf775195affd95a5fd3f5d5","target":"graph","created_at":"2026-06-23T01:13:05Z","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":"Experiments on MUSDB18 demonstrate that HAFM achieves a Fréchet Audio Distance (FAD) of 2.08 on isolated vocal inputs, outperforming retrieval baselines and matching prior state-of-the-art systems with fewer parameters."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The dual-rate codec tokenization scheme using HuBERT at 50 Hz for vocals and EnCodec at 75 Hz for instrumentals, combined with the three-stage hierarchical autoregressive architecture, produces time-aligned and coherent accompaniments without needing additional explicit alignment or synchronization steps."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"HAFM uses a hierarchical autoregressive model with dual-rate HuBERT and EnCodec tokens to generate coherent instrumental music from vocals, achieving FAD 2.08 on MUSDB18 while matching prior systems with fewer parameters."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"A hierarchical autoregressive model generates coherent instrumental accompaniments from isolated vocals using dual-rate tokenization."}],"snapshot_sha256":"3cfdff9d5b0157a1a4694375e156ea172d81284e08f02fd5a9bc8161c39bcf16"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.09054/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Music accompaniment generation aims to automatically produce instrumental accompaniments that are rhythmically, harmonically, and timbrally coherent with a given vocal input, with broad applications in personalized music creation, arrangement assistance, and music education. Existing approaches, primarily operating in the symbolic domain or relying on single-stage audio generation frameworks, commonly suffer from insufficient high-level semantic structure modeling, limited acoustic detail reconstruction, and weak conditional controllability. To address these limitations, this paper proposes HA","authors_text":"Cheng Luo, Jianwei Cui, Jian Zhu, Jun Sun, Shihao Chen, Yubang Zhang, Yunlong Xue","cross_cats":["cs.MM"],"headline":"A hierarchical autoregressive model generates coherent instrumental accompaniments from isolated vocals using dual-rate tokenization.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-04-10T07:27:55Z","title":"HAFM: Hierarchical Autoregressive Foundation Model for Music Accompaniment Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.09054","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-10T17:23:06.028909Z","id":"2bbe5bb4-1555-4d6f-a681-853c4c16b3b9","model_set":{"reader":"grok-4.3"},"one_line_summary":"HAFM uses a hierarchical autoregressive model with dual-rate HuBERT and EnCodec tokens to generate coherent instrumental music from vocals, achieving FAD 2.08 on MUSDB18 while matching prior systems with fewer parameters.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"A hierarchical autoregressive model generates coherent instrumental accompaniments from isolated vocals using dual-rate tokenization.","strongest_claim":"Experiments on MUSDB18 demonstrate that HAFM achieves a Fréchet Audio Distance (FAD) of 2.08 on isolated vocal inputs, outperforming retrieval baselines and matching prior state-of-the-art systems with fewer parameters.","weakest_assumption":"The dual-rate codec tokenization scheme using HuBERT at 50 Hz for vocals and EnCodec at 75 Hz for instrumentals, combined with the three-stage hierarchical autoregressive architecture, produces time-aligned and coherent accompaniments without needing additional explicit alignment or synchronization steps."}},"verdict_id":"2bbe5bb4-1555-4d6f-a681-853c4c16b3b9"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0f7a33a1369da9c0241108fc1422bfa4d22bf5411c2dcf1a49de70765c85d748","target":"record","created_at":"2026-06-23T01:13:05Z","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":"504e6d6be6200a27b168d7e58240be2e74f7d4e79e0bf51b5133400e7c9c40fe","cross_cats_sorted":["cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-04-10T07:27:55Z","title_canon_sha256":"d8e0e9ad02905b9131b216d81008c5232ddcab7166f0a470850d29f86a7e4ce9"},"schema_version":"1.0","source":{"id":"2604.09054","kind":"arxiv","version":3}},"canonical_sha256":"1eacc7b77e4f7b3c0a138da6d580536ae8147e1ce568b073e40963c007d339ce","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1eacc7b77e4f7b3c0a138da6d580536ae8147e1ce568b073e40963c007d339ce","first_computed_at":"2026-06-23T01:13:05.066943Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T01:13:05.066943Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"GUUav/Hzonompk4YUHKJnVgYKYG+YkJ/t/+7ISP2VIcwTWCQ/iLWjmB/Ndg2xeF9bK79vA5SNe36RVyy5c+0Aw==","signature_status":"signed_v1","signed_at":"2026-06-23T01:13:05.067564Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.09054","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f7a33a1369da9c0241108fc1422bfa4d22bf5411c2dcf1a49de70765c85d748","sha256:6162e073f928fe8c3f35b628a506ee27f9b3d261dcf775195affd95a5fd3f5d5"],"state_sha256":"f87b13ff992d5e508b9fc4cd0ae808360ffc7b702be62ca0feb603c5c51798a1"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lcuvlHaGCmS1aygxX/hP6YwQafAZpt7ZaEsZoCLzdKP6gGT0sLteAbkuJTCKGwqc5Y11EKC6zqCpt1AODx45Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-10T19:00:22.701266Z","bundle_sha256":"3379ba45d92ba7c482e3a814f5d9105477c870ba6726009140fa7ea58d8d4998"}}