{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:BIDMVHYEFSRVUK54DW3F4UVZS3","short_pith_number":"pith:BIDMVHYE","canonical_record":{"source":{"id":"2405.12221","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-20T17:59:59Z","cross_cats_sorted":["cs.LG","cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"3b403109f05ee32c946ecc2756f47ba777f3399657edd79f78acdcf8b0450af6","abstract_canon_sha256":"5702a89669fde03ff541c8a159e4a884115b39384e3ff4e355d231b1f13ca66c"},"schema_version":"1.0"},"canonical_sha256":"0a06ca9f042ca35a2bbc1db65e52b996c751e400157837b5f9c8462c8fa58d42","source":{"kind":"arxiv","id":"2405.12221","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.12221","created_at":"2026-07-05T10:09:44Z"},{"alias_kind":"arxiv_version","alias_value":"2405.12221v3","created_at":"2026-07-05T10:09:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.12221","created_at":"2026-07-05T10:09:44Z"},{"alias_kind":"pith_short_12","alias_value":"BIDMVHYEFSRV","created_at":"2026-07-05T10:09:44Z"},{"alias_kind":"pith_short_16","alias_value":"BIDMVHYEFSRVUK54","created_at":"2026-07-05T10:09:44Z"},{"alias_kind":"pith_short_8","alias_value":"BIDMVHYE","created_at":"2026-07-05T10:09:44Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:BIDMVHYEFSRVUK54DW3F4UVZS3","target":"record","payload":{"canonical_record":{"source":{"id":"2405.12221","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-20T17:59:59Z","cross_cats_sorted":["cs.LG","cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"3b403109f05ee32c946ecc2756f47ba777f3399657edd79f78acdcf8b0450af6","abstract_canon_sha256":"5702a89669fde03ff541c8a159e4a884115b39384e3ff4e355d231b1f13ca66c"},"schema_version":"1.0"},"canonical_sha256":"0a06ca9f042ca35a2bbc1db65e52b996c751e400157837b5f9c8462c8fa58d42","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:09:44.048032Z","signature_b64":"9ISQx/68yqFhxF+XZ94qshebs49uETXO2uLmpjOvIvQK+V8wHvDr3E7gqcyJRLIUWZnWZc+QX4jGzMunHe7tDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0a06ca9f042ca35a2bbc1db65e52b996c751e400157837b5f9c8462c8fa58d42","last_reissued_at":"2026-07-05T10:09:44.047620Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:09:44.047620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.12221","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":"2026-07-05T10:09:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XsEZV+/ZyPCpHiB/zTWRWQi4OF59QyImLWTjlWc2Hm7p5QuHD3aDeglEycodTfEePRfCbgts+Kp1qfehmWY0Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T05:31:13.907340Z"},"content_sha256":"dc04c8b554df3730de4f3d7cf056bcd7f23ff04f70e4619ad7e4135785cb1cd0","schema_version":"1.0","event_id":"sha256:dc04c8b554df3730de4f3d7cf056bcd7f23ff04f70e4619ad7e4135785cb1cd0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:BIDMVHYEFSRVUK54DW3F4UVZS3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Images that Sound: Composing Images and Sounds on a Single Canvas","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Andrew Owens, Daniel Geng, Ziyang Chen","submitted_at":"2024-05-20T17:59:59Z","abstract_excerpt":"Spectrograms are 2D representations of sound that look very different from the images found in our visual world. And natural images, when played as spectrograms, make unnatural sounds. In this paper, we show that it is possible to synthesize spectrograms that simultaneously look like natural images and sound like natural audio. We call these visual spectrograms images that sound. Our approach is simple and zero-shot, and it leverages pre-trained text-to-image and text-to-spectrogram diffusion models that operate in a shared latent space. During the reverse process, we denoise noisy latents wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.12221","kind":"arxiv","version":3},"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/2405.12221/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":"2026-07-05T10:09:44Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K4NKLF08JEiaKcqwDjDfdpr99Xn2QCOCYsxwTMVQlr8HaE+0HRZMOA3zDgQQA1BJV/k8FLf5uJXcGky0h8wuCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T05:31:13.908281Z"},"content_sha256":"8a7b6e42a4e719c27057bb822298de6cbd0af550126025268db226f6bdfb8df0","schema_version":"1.0","event_id":"sha256:8a7b6e42a4e719c27057bb822298de6cbd0af550126025268db226f6bdfb8df0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BIDMVHYEFSRVUK54DW3F4UVZS3/bundle.json","state_url":"https://pith.science/pith/BIDMVHYEFSRVUK54DW3F4UVZS3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BIDMVHYEFSRVUK54DW3F4UVZS3/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":"2026-08-11T05:31:13Z","links":{"resolver":"https://pith.science/pith/BIDMVHYEFSRVUK54DW3F4UVZS3","bundle":"https://pith.science/pith/BIDMVHYEFSRVUK54DW3F4UVZS3/bundle.json","state":"https://pith.science/pith/BIDMVHYEFSRVUK54DW3F4UVZS3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BIDMVHYEFSRVUK54DW3F4UVZS3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BIDMVHYEFSRVUK54DW3F4UVZS3","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":"5702a89669fde03ff541c8a159e4a884115b39384e3ff4e355d231b1f13ca66c","cross_cats_sorted":["cs.LG","cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-20T17:59:59Z","title_canon_sha256":"3b403109f05ee32c946ecc2756f47ba777f3399657edd79f78acdcf8b0450af6"},"schema_version":"1.0","source":{"id":"2405.12221","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.12221","created_at":"2026-07-05T10:09:44Z"},{"alias_kind":"arxiv_version","alias_value":"2405.12221v3","created_at":"2026-07-05T10:09:44Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.12221","created_at":"2026-07-05T10:09:44Z"},{"alias_kind":"pith_short_12","alias_value":"BIDMVHYEFSRV","created_at":"2026-07-05T10:09:44Z"},{"alias_kind":"pith_short_16","alias_value":"BIDMVHYEFSRVUK54","created_at":"2026-07-05T10:09:44Z"},{"alias_kind":"pith_short_8","alias_value":"BIDMVHYE","created_at":"2026-07-05T10:09:44Z"}],"graph_snapshots":[{"event_id":"sha256:8a7b6e42a4e719c27057bb822298de6cbd0af550126025268db226f6bdfb8df0","target":"graph","created_at":"2026-07-05T10:09:44Z","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/2405.12221/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Spectrograms are 2D representations of sound that look very different from the images found in our visual world. And natural images, when played as spectrograms, make unnatural sounds. In this paper, we show that it is possible to synthesize spectrograms that simultaneously look like natural images and sound like natural audio. We call these visual spectrograms images that sound. Our approach is simple and zero-shot, and it leverages pre-trained text-to-image and text-to-spectrogram diffusion models that operate in a shared latent space. During the reverse process, we denoise noisy latents wit","authors_text":"Andrew Owens, Daniel Geng, Ziyang Chen","cross_cats":["cs.LG","cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-20T17:59:59Z","title":"Images that Sound: Composing Images and Sounds on a Single Canvas"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.12221","kind":"arxiv","version":3},"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:dc04c8b554df3730de4f3d7cf056bcd7f23ff04f70e4619ad7e4135785cb1cd0","target":"record","created_at":"2026-07-05T10:09:44Z","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":"5702a89669fde03ff541c8a159e4a884115b39384e3ff4e355d231b1f13ca66c","cross_cats_sorted":["cs.LG","cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-05-20T17:59:59Z","title_canon_sha256":"3b403109f05ee32c946ecc2756f47ba777f3399657edd79f78acdcf8b0450af6"},"schema_version":"1.0","source":{"id":"2405.12221","kind":"arxiv","version":3}},"canonical_sha256":"0a06ca9f042ca35a2bbc1db65e52b996c751e400157837b5f9c8462c8fa58d42","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0a06ca9f042ca35a2bbc1db65e52b996c751e400157837b5f9c8462c8fa58d42","first_computed_at":"2026-07-05T10:09:44.047620Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:09:44.047620Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9ISQx/68yqFhxF+XZ94qshebs49uETXO2uLmpjOvIvQK+V8wHvDr3E7gqcyJRLIUWZnWZc+QX4jGzMunHe7tDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:09:44.048032Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.12221","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dc04c8b554df3730de4f3d7cf056bcd7f23ff04f70e4619ad7e4135785cb1cd0","sha256:8a7b6e42a4e719c27057bb822298de6cbd0af550126025268db226f6bdfb8df0"],"state_sha256":"3d74c02110f300713fe061566bf78c853655cad5d89b3a4a875bdde1efe03c42"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1DqBTa+3NMGWPaGU/Cii8wkFSz8pvgXA4/te3jKeUTFq+iGhefUy4/u/Xq0MNkPNI2DKgdmdbvMoLbUIwFgpAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T05:31:13.915916Z","bundle_sha256":"486427e4f2205c1b106ede026521ec00bc58c5608e621480c738b58514d1e6e7"}}