{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:N2YQYY4P6SWQOI7ATH6PSPZU3Y","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":"3e545afa8eafbd13adb9d2464ce5ce6f4c5e4b8336a4ed6182fca36b2e1df416","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GR","submitted_at":"2023-06-20T12:50:49Z","title_canon_sha256":"d584f1e8de273f8c3ecee93fc02a15e388198f8ddc9e404d07d0664868b5fa7e"},"schema_version":"1.0","source":{"id":"2306.11504","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2306.11504","created_at":"2026-07-05T06:22:20Z"},{"alias_kind":"arxiv_version","alias_value":"2306.11504v1","created_at":"2026-07-05T06:22:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.11504","created_at":"2026-07-05T06:22:20Z"},{"alias_kind":"pith_short_12","alias_value":"N2YQYY4P6SWQ","created_at":"2026-07-05T06:22:20Z"},{"alias_kind":"pith_short_16","alias_value":"N2YQYY4P6SWQOI7A","created_at":"2026-07-05T06:22:20Z"},{"alias_kind":"pith_short_8","alias_value":"N2YQYY4P","created_at":"2026-07-05T06:22:20Z"}],"graph_snapshots":[{"event_id":"sha256:3077ef8e2fada397c7bf6f9fd45010d117b8d3cbc1fbbf5d3b8ac8e30365e3b0","target":"graph","created_at":"2026-07-05T06:22:20Z","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/2306.11504/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Text-guided image generation has witnessed unprecedented progress due to the development of diffusion models. Beyond text and image, sound is a vital element within the sphere of human perception, offering vivid representations and naturally coinciding with corresponding scenes. Taking advantage of sound therefore presents a promising avenue for exploration within image generation research. However, the relationship between audio and image supervision remains significantly underdeveloped, and the scarcity of related, high-quality datasets brings further obstacles. In this paper, we propose a u","authors_text":"Kaipeng Zhang, Ping Luo, Wenqi Shao, Yue Yang, Yu Qiao, Yuying Ge, Zeyue Xue","cross_cats":["cs.CV","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GR","submitted_at":"2023-06-20T12:50:49Z","title":"Align, Adapt and Inject: Sound-guided Unified Image Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.11504","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":"sha256:3edd169a46aaefc8139e1cd9fac91f819629363529cb349dc0a01337f1508cd5","target":"record","created_at":"2026-07-05T06:22:20Z","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":"3e545afa8eafbd13adb9d2464ce5ce6f4c5e4b8336a4ed6182fca36b2e1df416","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.GR","submitted_at":"2023-06-20T12:50:49Z","title_canon_sha256":"d584f1e8de273f8c3ecee93fc02a15e388198f8ddc9e404d07d0664868b5fa7e"},"schema_version":"1.0","source":{"id":"2306.11504","kind":"arxiv","version":1}},"canonical_sha256":"6eb10c638ff4ad0723e099fcf93f34de31734aeb64c824be3a3e7c09816e0d0a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6eb10c638ff4ad0723e099fcf93f34de31734aeb64c824be3a3e7c09816e0d0a","first_computed_at":"2026-07-05T06:22:20.522640Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:22:20.522640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ntng+Qln46Kbli9PlnbF7nIDmlJUj4MmBQfoLO5rCq7eI6r8dglOcgErw6I8A+L8lrukGctAX4TOfUIL0FB2AA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:22:20.523125Z","signed_message":"canonical_sha256_bytes"},"source_id":"2306.11504","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3edd169a46aaefc8139e1cd9fac91f819629363529cb349dc0a01337f1508cd5","sha256:3077ef8e2fada397c7bf6f9fd45010d117b8d3cbc1fbbf5d3b8ac8e30365e3b0"],"state_sha256":"c1317e30ec2100582293c1696f3c72cbcdc62e69f66da609c5c157e1b785ba68"}