{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XUUTGXMM3TWNK3AXWLQT4B5CMH","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":"3fa84e2b9b170db5c967ee224f6a19d138c6e6d38d2afd4015f1ab335c68e62d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-28T03:00:30Z","title_canon_sha256":"216d92e6e790c6b0edff8351981f86e3718f46fa91a0c33e98ccd426a5adc022"},"schema_version":"1.0","source":{"id":"2508.20379","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.20379","created_at":"2026-07-05T12:00:35Z"},{"alias_kind":"arxiv_version","alias_value":"2508.20379v1","created_at":"2026-07-05T12:00:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.20379","created_at":"2026-07-05T12:00:35Z"},{"alias_kind":"pith_short_12","alias_value":"XUUTGXMM3TWN","created_at":"2026-07-05T12:00:35Z"},{"alias_kind":"pith_short_16","alias_value":"XUUTGXMM3TWNK3AX","created_at":"2026-07-05T12:00:35Z"},{"alias_kind":"pith_short_8","alias_value":"XUUTGXMM","created_at":"2026-07-05T12:00:35Z"}],"graph_snapshots":[{"event_id":"sha256:751a06a01c8f2a2b897d29cc9fbab340c2b7d2fa1bed49c2ca5e1084ee82399c","target":"graph","created_at":"2026-07-05T12:00:35Z","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/2508.20379/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Visual editing with diffusion models has made significant progress but often struggles with complex scenarios that textual guidance alone could not adequately describe, highlighting the need for additional non-text editing prompts. In this work, we introduce a novel audio-guided visual editing framework that can handle complex editing tasks with multiple text and audio prompts without requiring additional training. Existing audio-guided visual editing methods often necessitate training on specific datasets to align audio with text, limiting their generalization to real-world situations. We lev","authors_text":"Chanhyuk Choi, Hyeonyu Kim, Seokhoon Jeong, Seonghee Han, Taehwan Kim","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-28T03:00:30Z","title":"Audio-Guided Visual Editing with Complex Multi-Modal Prompts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.20379","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":"sha256:41b2cff2558d4f3ae4a22c400946e90ad320707b5b1d6d9da6eff3c01b4f7be2","target":"record","created_at":"2026-07-05T12:00:35Z","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":"3fa84e2b9b170db5c967ee224f6a19d138c6e6d38d2afd4015f1ab335c68e62d","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2025-08-28T03:00:30Z","title_canon_sha256":"216d92e6e790c6b0edff8351981f86e3718f46fa91a0c33e98ccd426a5adc022"},"schema_version":"1.0","source":{"id":"2508.20379","kind":"arxiv","version":1}},"canonical_sha256":"bd29335d8cdcecd56c17b2e13e07a261c825b8f6fb8bfe53342e7127933f1aae","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd29335d8cdcecd56c17b2e13e07a261c825b8f6fb8bfe53342e7127933f1aae","first_computed_at":"2026-07-05T12:00:35.737531Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:00:35.737531Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"S9QvdFaunKhD5kYZFm6zL2OjpZkPfJPdlPXGJiuOo3QjL18YhI6bru/U64i0dHCE2OK+BS8yw7A/rmFkySDKAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T12:00:35.738060Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.20379","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:41b2cff2558d4f3ae4a22c400946e90ad320707b5b1d6d9da6eff3c01b4f7be2","sha256:751a06a01c8f2a2b897d29cc9fbab340c2b7d2fa1bed49c2ca5e1084ee82399c"],"state_sha256":"2f4c92e9551a99327f746e2562c019c574409fe46e5093cf706f1f1526ec8119"}