{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:CBG6ML7TXIJELKW3FF6FR7W4JO","short_pith_number":"pith:CBG6ML7T","canonical_record":{"source":{"id":"2411.15913","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-11-24T16:53:34Z","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"title_canon_sha256":"01b41f410aa48e17c27ef490a5e6258191a3a72990af6caf3e5fb947c9a06435","abstract_canon_sha256":"7fadb84514cb0aa3a2df639effb9d5beb196efc071800c4fafd67ff0d4200ea7"},"schema_version":"1.0"},"canonical_sha256":"104de62ff3ba1245aadb297c58fedc4bbe9fa3273a33c7aadb82baf3f6635509","source":{"kind":"arxiv","id":"2411.15913","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.15913","created_at":"2026-05-18T02:45:14Z"},{"alias_kind":"arxiv_version","alias_value":"2411.15913v4","created_at":"2026-05-18T02:45:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15913","created_at":"2026-05-18T02:45:14Z"},{"alias_kind":"pith_short_12","alias_value":"CBG6ML7TXIJE","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"CBG6ML7TXIJELKW3","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"CBG6ML7T","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:CBG6ML7TXIJELKW3FF6FR7W4JO","target":"record","payload":{"canonical_record":{"source":{"id":"2411.15913","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-11-24T16:53:34Z","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"title_canon_sha256":"01b41f410aa48e17c27ef490a5e6258191a3a72990af6caf3e5fb947c9a06435","abstract_canon_sha256":"7fadb84514cb0aa3a2df639effb9d5beb196efc071800c4fafd67ff0d4200ea7"},"schema_version":"1.0"},"canonical_sha256":"104de62ff3ba1245aadb297c58fedc4bbe9fa3273a33c7aadb82baf3f6635509","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:45:14.710991Z","signature_b64":"QIQE6vbLB0czu9lGIDsPiZX9B/1lXl6FrI6z9mKuKYQUycqAG+CwQCtgCY6ngLKwE6qK9waFxj/Wac1CKBQtBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"104de62ff3ba1245aadb297c58fedc4bbe9fa3273a33c7aadb82baf3f6635509","last_reissued_at":"2026-05-18T02:45:14.710342Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:45:14.710342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.15913","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:45:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PRNBeMvyYOoozK1ilNCUaCB4fJOlpEB7O6sjXnQxhcxmDO040simDVMgJI42eX4M/bybKxu2OD4u/vfWMQ/GCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T08:38:17.116982Z"},"content_sha256":"861193b4c1dc685713c6ba6dfdee5b26cc590c0dc357a6e5749d5be7e0194fa1","schema_version":"1.0","event_id":"sha256:861193b4c1dc685713c6ba6dfdee5b26cc590c0dc357a6e5749d5be7e0194fa1"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:CBG6ML7TXIJELKW3FF6FR7W4JO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Repurposing Image Diffusion Models for Training-Free Music Style Transfer on Mel-spectrograms","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Heehwan Wang, Jiook Cha, Joonwoo Kwon, Jungwoo Seo, Shinjae Yoo, Sooyoung Kim, Yuewei Lin","submitted_at":"2024-11-24T16:53:34Z","abstract_excerpt":"Music style transfer blends source structure with reference style to enable personalized music creation. However, existing zero-shot methods often struggle to capture fine-grained audio nuances, relying on coarse text descriptions or requiring expensive task-specific training. We propose Stylus, a training-free framework that repurposes pretrained image diffusion models for music style transfer in the Mel-spectrogram domain. By treating audio as structured time-frequency images, Stylus manipulates self-attention by injecting style keys and values while preserving source structural queries. To "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15913","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2026-05-18T02:45:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"euXFQUT40+RX1OAgod6gnvn8KOK6YW7iX+aip09bTlY77/PxHoNRbHbIIyj2LLN7vLm2bODO1xAko5U1msM2DA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T08:38:17.117737Z"},"content_sha256":"7c5eacd93c24e5678a1344bc7d4f4a7379c0f30d5d212ec31421deb7dd2fd36d","schema_version":"1.0","event_id":"sha256:7c5eacd93c24e5678a1344bc7d4f4a7379c0f30d5d212ec31421deb7dd2fd36d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/CBG6ML7TXIJELKW3FF6FR7W4JO/bundle.json","state_url":"https://pith.science/pith/CBG6ML7TXIJELKW3FF6FR7W4JO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/CBG6ML7TXIJELKW3FF6FR7W4JO/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":"2026-06-06T08:38:17Z","links":{"resolver":"https://pith.science/pith/CBG6ML7TXIJELKW3FF6FR7W4JO","bundle":"https://pith.science/pith/CBG6ML7TXIJELKW3FF6FR7W4JO/bundle.json","state":"https://pith.science/pith/CBG6ML7TXIJELKW3FF6FR7W4JO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/CBG6ML7TXIJELKW3FF6FR7W4JO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:CBG6ML7TXIJELKW3FF6FR7W4JO","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":"7fadb84514cb0aa3a2df639effb9d5beb196efc071800c4fafd67ff0d4200ea7","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-11-24T16:53:34Z","title_canon_sha256":"01b41f410aa48e17c27ef490a5e6258191a3a72990af6caf3e5fb947c9a06435"},"schema_version":"1.0","source":{"id":"2411.15913","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.15913","created_at":"2026-05-18T02:45:14Z"},{"alias_kind":"arxiv_version","alias_value":"2411.15913v4","created_at":"2026-05-18T02:45:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15913","created_at":"2026-05-18T02:45:14Z"},{"alias_kind":"pith_short_12","alias_value":"CBG6ML7TXIJE","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"CBG6ML7TXIJELKW3","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"CBG6ML7T","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:7c5eacd93c24e5678a1344bc7d4f4a7379c0f30d5d212ec31421deb7dd2fd36d","target":"graph","created_at":"2026-05-18T02:45:14Z","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"},"paper":{"abstract_excerpt":"Music style transfer blends source structure with reference style to enable personalized music creation. However, existing zero-shot methods often struggle to capture fine-grained audio nuances, relying on coarse text descriptions or requiring expensive task-specific training. We propose Stylus, a training-free framework that repurposes pretrained image diffusion models for music style transfer in the Mel-spectrogram domain. By treating audio as structured time-frequency images, Stylus manipulates self-attention by injecting style keys and values while preserving source structural queries. To ","authors_text":"Heehwan Wang, Jiook Cha, Joonwoo Kwon, Jungwoo Seo, Shinjae Yoo, Sooyoung Kim, Yuewei Lin","cross_cats":["cs.AI","cs.LG","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-11-24T16:53:34Z","title":"Repurposing Image Diffusion Models for Training-Free Music Style Transfer on Mel-spectrograms"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15913","kind":"arxiv","version":4},"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":"sha256:861193b4c1dc685713c6ba6dfdee5b26cc590c0dc357a6e5749d5be7e0194fa1","target":"record","created_at":"2026-05-18T02:45:14Z","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":"7fadb84514cb0aa3a2df639effb9d5beb196efc071800c4fafd67ff0d4200ea7","cross_cats_sorted":["cs.AI","cs.LG","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-11-24T16:53:34Z","title_canon_sha256":"01b41f410aa48e17c27ef490a5e6258191a3a72990af6caf3e5fb947c9a06435"},"schema_version":"1.0","source":{"id":"2411.15913","kind":"arxiv","version":4}},"canonical_sha256":"104de62ff3ba1245aadb297c58fedc4bbe9fa3273a33c7aadb82baf3f6635509","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"104de62ff3ba1245aadb297c58fedc4bbe9fa3273a33c7aadb82baf3f6635509","first_computed_at":"2026-05-18T02:45:14.710342Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:45:14.710342Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QIQE6vbLB0czu9lGIDsPiZX9B/1lXl6FrI6z9mKuKYQUycqAG+CwQCtgCY6ngLKwE6qK9waFxj/Wac1CKBQtBw==","signature_status":"signed_v1","signed_at":"2026-05-18T02:45:14.710991Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.15913","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:861193b4c1dc685713c6ba6dfdee5b26cc590c0dc357a6e5749d5be7e0194fa1","sha256:7c5eacd93c24e5678a1344bc7d4f4a7379c0f30d5d212ec31421deb7dd2fd36d"],"state_sha256":"6f2184c1c382d1fd25a87daa8d5fb5914fe8e7bdde68d77dcff87de2fe5e3b08"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2RQyupodWp2ZswALS39ZwDYfgg/hkfwKiOnyCw29W2Mh/Ze4ZmEQmE1abLR8a2yedwDKARc797xDTHVu3xcBCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T08:38:17.122087Z","bundle_sha256":"811cf73509a948b621bfbd43b581e8fa123f201470deac2a037c1333b869e5b7"}}