{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:T7GNN4HBOMSSGWHJ5XR633GYJH","short_pith_number":"pith:T7GNN4HB","canonical_record":{"source":{"id":"2502.07711","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-02-11T17:10:31Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"6dda1342dfe58d426fb4a4c896b6c6faaf558bea0698254386b30f5c352f9c62","abstract_canon_sha256":"ffa609a8a0a66fd11c27120bbeb54cd64cfe5b7c0e14fceb8ed49f78f37738e3"},"schema_version":"1.0"},"canonical_sha256":"9fccd6f0e173252358e9ede3edecd849d5178c29aafe865750fc2d4a5ac51b2a","source":{"kind":"arxiv","id":"2502.07711","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.07711","created_at":"2026-07-05T10:12:52Z"},{"alias_kind":"arxiv_version","alias_value":"2502.07711v1","created_at":"2026-07-05T10:12:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07711","created_at":"2026-07-05T10:12:52Z"},{"alias_kind":"pith_short_12","alias_value":"T7GNN4HBOMSS","created_at":"2026-07-05T10:12:52Z"},{"alias_kind":"pith_short_16","alias_value":"T7GNN4HBOMSSGWHJ","created_at":"2026-07-05T10:12:52Z"},{"alias_kind":"pith_short_8","alias_value":"T7GNN4HB","created_at":"2026-07-05T10:12:52Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:T7GNN4HBOMSSGWHJ5XR633GYJH","target":"record","payload":{"canonical_record":{"source":{"id":"2502.07711","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-02-11T17:10:31Z","cross_cats_sorted":["cs.MM"],"title_canon_sha256":"6dda1342dfe58d426fb4a4c896b6c6faaf558bea0698254386b30f5c352f9c62","abstract_canon_sha256":"ffa609a8a0a66fd11c27120bbeb54cd64cfe5b7c0e14fceb8ed49f78f37738e3"},"schema_version":"1.0"},"canonical_sha256":"9fccd6f0e173252358e9ede3edecd849d5178c29aafe865750fc2d4a5ac51b2a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:12:52.865953Z","signature_b64":"aOZ819IkDTehYF0uSmBQCOCDloxQVQ37psXDx2HijivJYEVurWcjfWzoZVMKnSteQCcxc8QdkE2Vfe83BzvwBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9fccd6f0e173252358e9ede3edecd849d5178c29aafe865750fc2d4a5ac51b2a","last_reissued_at":"2026-07-05T10:12:52.865463Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:12:52.865463Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2502.07711","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:12:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"IyDDqIYn2uFpIVmyK2F8lQz3dGgJEBaYDO8RgMznqmk/ePTgwaiVdSCVfjTxV8Mv3CEw8oXyCkA+Or8XqlanCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:18:17.827478Z"},"content_sha256":"83d2c3d9cce5f5bdc02b29c0cfcb361d7360738f97fcc097895f504fca9d2cb7","schema_version":"1.0","event_id":"sha256:83d2c3d9cce5f5bdc02b29c0cfcb361d7360738f97fcc097895f504fca9d2cb7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:T7GNN4HBOMSSGWHJ5XR633GYJH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"RenderBox: Expressive Performance Rendering with Text Control","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.MM"],"primary_cat":"eess.AS","authors_text":"Akira Maezawa, Huan Zhang, Simon Dixon","submitted_at":"2025-02-11T17:10:31Z","abstract_excerpt":"Expressive music performance rendering involves interpreting symbolic scores with variations in timing, dynamics, articulation, and instrument-specific techniques, resulting in performances that capture musical can emotional intent. We introduce RenderBox, a unified framework for text-and-score controlled audio performance generation across multiple instruments, applying coarse-level controls through natural language descriptions and granular-level controls using music scores. Based on a diffusion transformer architecture and cross-attention joint conditioning, we propose a curriculum-based pa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07711","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/2502.07711/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":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:12:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"h29mu2Yqp4CZ8S85XYgH9izFYPGlTgxm7hA3s4NL1+44+rIHJzKHVPeEmCKVqYeGxynjXHIsd0oqv0jUtEttBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T17:18:17.827763Z"},"content_sha256":"bca684df5fa4fc3aba072b629304712345b035170290de7a2ec1dcd701e16e6d","schema_version":"1.0","event_id":"sha256:bca684df5fa4fc3aba072b629304712345b035170290de7a2ec1dcd701e16e6d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/T7GNN4HBOMSSGWHJ5XR633GYJH/bundle.json","state_url":"https://pith.science/pith/T7GNN4HBOMSSGWHJ5XR633GYJH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/T7GNN4HBOMSSGWHJ5XR633GYJH/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":"2026-08-05T17:18:17Z","links":{"resolver":"https://pith.science/pith/T7GNN4HBOMSSGWHJ5XR633GYJH","bundle":"https://pith.science/pith/T7GNN4HBOMSSGWHJ5XR633GYJH/bundle.json","state":"https://pith.science/pith/T7GNN4HBOMSSGWHJ5XR633GYJH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/T7GNN4HBOMSSGWHJ5XR633GYJH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:T7GNN4HBOMSSGWHJ5XR633GYJH","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":"ffa609a8a0a66fd11c27120bbeb54cd64cfe5b7c0e14fceb8ed49f78f37738e3","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-02-11T17:10:31Z","title_canon_sha256":"6dda1342dfe58d426fb4a4c896b6c6faaf558bea0698254386b30f5c352f9c62"},"schema_version":"1.0","source":{"id":"2502.07711","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2502.07711","created_at":"2026-07-05T10:12:52Z"},{"alias_kind":"arxiv_version","alias_value":"2502.07711v1","created_at":"2026-07-05T10:12:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.07711","created_at":"2026-07-05T10:12:52Z"},{"alias_kind":"pith_short_12","alias_value":"T7GNN4HBOMSS","created_at":"2026-07-05T10:12:52Z"},{"alias_kind":"pith_short_16","alias_value":"T7GNN4HBOMSSGWHJ","created_at":"2026-07-05T10:12:52Z"},{"alias_kind":"pith_short_8","alias_value":"T7GNN4HB","created_at":"2026-07-05T10:12:52Z"}],"graph_snapshots":[{"event_id":"sha256:bca684df5fa4fc3aba072b629304712345b035170290de7a2ec1dcd701e16e6d","target":"graph","created_at":"2026-07-05T10:12:52Z","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/2502.07711/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Expressive music performance rendering involves interpreting symbolic scores with variations in timing, dynamics, articulation, and instrument-specific techniques, resulting in performances that capture musical can emotional intent. We introduce RenderBox, a unified framework for text-and-score controlled audio performance generation across multiple instruments, applying coarse-level controls through natural language descriptions and granular-level controls using music scores. Based on a diffusion transformer architecture and cross-attention joint conditioning, we propose a curriculum-based pa","authors_text":"Akira Maezawa, Huan Zhang, Simon Dixon","cross_cats":["cs.MM"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-02-11T17:10:31Z","title":"RenderBox: Expressive Performance Rendering with Text Control"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.07711","kind":"arxiv","version":1},"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":"sha256:83d2c3d9cce5f5bdc02b29c0cfcb361d7360738f97fcc097895f504fca9d2cb7","target":"record","created_at":"2026-07-05T10:12:52Z","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":"ffa609a8a0a66fd11c27120bbeb54cd64cfe5b7c0e14fceb8ed49f78f37738e3","cross_cats_sorted":["cs.MM"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.AS","submitted_at":"2025-02-11T17:10:31Z","title_canon_sha256":"6dda1342dfe58d426fb4a4c896b6c6faaf558bea0698254386b30f5c352f9c62"},"schema_version":"1.0","source":{"id":"2502.07711","kind":"arxiv","version":1}},"canonical_sha256":"9fccd6f0e173252358e9ede3edecd849d5178c29aafe865750fc2d4a5ac51b2a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9fccd6f0e173252358e9ede3edecd849d5178c29aafe865750fc2d4a5ac51b2a","first_computed_at":"2026-07-05T10:12:52.865463Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:12:52.865463Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aOZ819IkDTehYF0uSmBQCOCDloxQVQ37psXDx2HijivJYEVurWcjfWzoZVMKnSteQCcxc8QdkE2Vfe83BzvwBA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:12:52.865953Z","signed_message":"canonical_sha256_bytes"},"source_id":"2502.07711","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:83d2c3d9cce5f5bdc02b29c0cfcb361d7360738f97fcc097895f504fca9d2cb7","sha256:bca684df5fa4fc3aba072b629304712345b035170290de7a2ec1dcd701e16e6d"],"state_sha256":"d9f6f382f71675cd490e124e172f2fa47ae8d6aa5ca80d1d6bf1491dbcdc49af"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2DMPhoj6TX1lXxnRedsUjIkgaKU+0JK2Z54i8tMAXYwJ+mCxx2odOVqobmTyZW535IM+aYBmTtPe9w+Nr3kcDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T17:18:17.831299Z","bundle_sha256":"24c60e26f63b83480b0e0ef8f16dbbad47d09465b06d27e9e7e0a60a7e5c7c4b"}}