{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:YX6ODHKHGSMYSXNQJQHLKYPLCU","short_pith_number":"pith:YX6ODHKH","canonical_record":{"source":{"id":"2405.00878","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-01T21:43:57Z","cross_cats_sorted":[],"title_canon_sha256":"5939c929eee00f17a95c8adec15a6bec22214a6961d05fd2e55eb01c821eae1f","abstract_canon_sha256":"f81ef98ab1694c4783c28c8295c5a4a68eeaf932e28c5dda3298ec2e8ab4d803"},"schema_version":"1.0"},"canonical_sha256":"c5fce19d473499895db04c0eb561eb150857d0c7dba7bf630cb1da8a6a767703","source":{"kind":"arxiv","id":"2405.00878","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.00878","created_at":"2026-07-05T08:14:27Z"},{"alias_kind":"arxiv_version","alias_value":"2405.00878v1","created_at":"2026-07-05T08:14:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.00878","created_at":"2026-07-05T08:14:27Z"},{"alias_kind":"pith_short_12","alias_value":"YX6ODHKHGSMY","created_at":"2026-07-05T08:14:27Z"},{"alias_kind":"pith_short_16","alias_value":"YX6ODHKHGSMYSXNQ","created_at":"2026-07-05T08:14:27Z"},{"alias_kind":"pith_short_8","alias_value":"YX6ODHKH","created_at":"2026-07-05T08:14:27Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:YX6ODHKHGSMYSXNQJQHLKYPLCU","target":"record","payload":{"canonical_record":{"source":{"id":"2405.00878","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-01T21:43:57Z","cross_cats_sorted":[],"title_canon_sha256":"5939c929eee00f17a95c8adec15a6bec22214a6961d05fd2e55eb01c821eae1f","abstract_canon_sha256":"f81ef98ab1694c4783c28c8295c5a4a68eeaf932e28c5dda3298ec2e8ab4d803"},"schema_version":"1.0"},"canonical_sha256":"c5fce19d473499895db04c0eb561eb150857d0c7dba7bf630cb1da8a6a767703","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:14:27.427963Z","signature_b64":"6Nxaw/QkgCOYEWj/Xoe1idvDc4qaJTdKzIbP96mPhEcseNYS4hYWhy95jRn2CLhD7aLcTaUNlWmrCLTXEcBqCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c5fce19d473499895db04c0eb561eb150857d0c7dba7bf630cb1da8a6a767703","last_reissued_at":"2026-07-05T08:14:27.427504Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:14:27.427504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2405.00878","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":"2026-07-05T08:14:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sHigeOzmH5Jdsrxm4VHhqeGeZaQ7lXqqudyzPOQmVHKCUwqGipEYGqdyVu8CtOg74ByUqP9TsvsqOmInnr/QAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T04:10:19.835182Z"},"content_sha256":"a89d3db13a779a700064e05d24b86bec138ca972fd2b4dcc2d1ce00d6eb123c6","schema_version":"1.0","event_id":"sha256:a89d3db13a779a700064e05d24b86bec138ca972fd2b4dcc2d1ce00d6eb123c6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:YX6ODHKHGSMYSXNQJQHLKYPLCU","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SonicDiffusion: Audio-Driven Image Generation and Editing with Pretrained Diffusion Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aykut Erdem, Burak Can Biner, Duygu Ceylan, Erkut Erdem, Farrin Marouf Sofian, Umur Berkay Karaka\\c{s}","submitted_at":"2024-05-01T21:43:57Z","abstract_excerpt":"We are witnessing a revolution in conditional image synthesis with the recent success of large scale text-to-image generation methods. This success also opens up new opportunities in controlling the generation and editing process using multi-modal input. While spatial control using cues such as depth, sketch, and other images has attracted a lot of research, we argue that another equally effective modality is audio since sound and sight are two main components of human perception. Hence, we propose a method to enable audio-conditioning in large scale image diffusion models. Our method first ma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.00878","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/2405.00878/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":"2026-07-05T08:14:27Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Lv6UyCDeCsfvGWX7qXhBAohLw4ptmt4Bjh4B73iMoUrT5WgZkkXboCGs1twcQhoGuXh4SGBv4gg+xuTocqT2CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-23T04:10:19.835973Z"},"content_sha256":"0a98cabe1d7a217dab8b5d59a951cb9dec7c8f9a160ae61a5bff03db2846320d","schema_version":"1.0","event_id":"sha256:0a98cabe1d7a217dab8b5d59a951cb9dec7c8f9a160ae61a5bff03db2846320d"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YX6ODHKHGSMYSXNQJQHLKYPLCU/bundle.json","state_url":"https://pith.science/pith/YX6ODHKHGSMYSXNQJQHLKYPLCU/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YX6ODHKHGSMYSXNQJQHLKYPLCU/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":"2026-08-23T04:10:19Z","links":{"resolver":"https://pith.science/pith/YX6ODHKHGSMYSXNQJQHLKYPLCU","bundle":"https://pith.science/pith/YX6ODHKHGSMYSXNQJQHLKYPLCU/bundle.json","state":"https://pith.science/pith/YX6ODHKHGSMYSXNQJQHLKYPLCU/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YX6ODHKHGSMYSXNQJQHLKYPLCU/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YX6ODHKHGSMYSXNQJQHLKYPLCU","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":"f81ef98ab1694c4783c28c8295c5a4a68eeaf932e28c5dda3298ec2e8ab4d803","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-01T21:43:57Z","title_canon_sha256":"5939c929eee00f17a95c8adec15a6bec22214a6961d05fd2e55eb01c821eae1f"},"schema_version":"1.0","source":{"id":"2405.00878","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.00878","created_at":"2026-07-05T08:14:27Z"},{"alias_kind":"arxiv_version","alias_value":"2405.00878v1","created_at":"2026-07-05T08:14:27Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.00878","created_at":"2026-07-05T08:14:27Z"},{"alias_kind":"pith_short_12","alias_value":"YX6ODHKHGSMY","created_at":"2026-07-05T08:14:27Z"},{"alias_kind":"pith_short_16","alias_value":"YX6ODHKHGSMYSXNQ","created_at":"2026-07-05T08:14:27Z"},{"alias_kind":"pith_short_8","alias_value":"YX6ODHKH","created_at":"2026-07-05T08:14:27Z"}],"graph_snapshots":[{"event_id":"sha256:0a98cabe1d7a217dab8b5d59a951cb9dec7c8f9a160ae61a5bff03db2846320d","target":"graph","created_at":"2026-07-05T08:14:27Z","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/2405.00878/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We are witnessing a revolution in conditional image synthesis with the recent success of large scale text-to-image generation methods. This success also opens up new opportunities in controlling the generation and editing process using multi-modal input. While spatial control using cues such as depth, sketch, and other images has attracted a lot of research, we argue that another equally effective modality is audio since sound and sight are two main components of human perception. Hence, we propose a method to enable audio-conditioning in large scale image diffusion models. Our method first ma","authors_text":"Aykut Erdem, Burak Can Biner, Duygu Ceylan, Erkut Erdem, Farrin Marouf Sofian, Umur Berkay Karaka\\c{s}","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-01T21:43:57Z","title":"SonicDiffusion: Audio-Driven Image Generation and Editing with Pretrained Diffusion Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.00878","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:a89d3db13a779a700064e05d24b86bec138ca972fd2b4dcc2d1ce00d6eb123c6","target":"record","created_at":"2026-07-05T08:14:27Z","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":"f81ef98ab1694c4783c28c8295c5a4a68eeaf932e28c5dda3298ec2e8ab4d803","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-01T21:43:57Z","title_canon_sha256":"5939c929eee00f17a95c8adec15a6bec22214a6961d05fd2e55eb01c821eae1f"},"schema_version":"1.0","source":{"id":"2405.00878","kind":"arxiv","version":1}},"canonical_sha256":"c5fce19d473499895db04c0eb561eb150857d0c7dba7bf630cb1da8a6a767703","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c5fce19d473499895db04c0eb561eb150857d0c7dba7bf630cb1da8a6a767703","first_computed_at":"2026-07-05T08:14:27.427504Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:14:27.427504Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"6Nxaw/QkgCOYEWj/Xoe1idvDc4qaJTdKzIbP96mPhEcseNYS4hYWhy95jRn2CLhD7aLcTaUNlWmrCLTXEcBqCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:14:27.427963Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.00878","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a89d3db13a779a700064e05d24b86bec138ca972fd2b4dcc2d1ce00d6eb123c6","sha256:0a98cabe1d7a217dab8b5d59a951cb9dec7c8f9a160ae61a5bff03db2846320d"],"state_sha256":"e4861fdfac56eb003eb33b84a6aaad019d598c8ab8c995ef2f809540a3496414"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xmuVDsOMjzaGpsfDW4S95A32vOEEbjwwqiRs8WJWtPxh+FNgxxA6KGxzG66IF76yJx1bx2HgHESAs+DNFQ+ZDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-23T04:10:19.840972Z","bundle_sha256":"2ef6bcf1748600dd1857a7eaf338442a2c452c92f0abc4e1c265ab0854fc49f4"}}