{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:2Q3YHA3XUVYMWYOW7O6ISC75QO","short_pith_number":"pith:2Q3YHA3X","canonical_record":{"source":{"id":"2211.03089","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-11-06T11:48:20Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"277c50a1432f70ffb9105f3b7daf6430945d9813ad9b409171fc305c1a378f65","abstract_canon_sha256":"70c58205e7783c4f8cf61eedfdc44132775f11f01632c881640b6270675b15f4"},"schema_version":"1.0"},"canonical_sha256":"d437838377a570cb61d6fbbc890bfd83b248d369fcdaf23b1a6948b321f97a0d","source":{"kind":"arxiv","id":"2211.03089","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.03089","created_at":"2026-07-05T05:45:34Z"},{"alias_kind":"arxiv_version","alias_value":"2211.03089v2","created_at":"2026-07-05T05:45:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.03089","created_at":"2026-07-05T05:45:34Z"},{"alias_kind":"pith_short_12","alias_value":"2Q3YHA3XUVYM","created_at":"2026-07-05T05:45:34Z"},{"alias_kind":"pith_short_16","alias_value":"2Q3YHA3XUVYMWYOW","created_at":"2026-07-05T05:45:34Z"},{"alias_kind":"pith_short_8","alias_value":"2Q3YHA3X","created_at":"2026-07-05T05:45:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:2Q3YHA3XUVYMWYOW7O6ISC75QO","target":"record","payload":{"canonical_record":{"source":{"id":"2211.03089","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-11-06T11:48:20Z","cross_cats_sorted":["eess.AS"],"title_canon_sha256":"277c50a1432f70ffb9105f3b7daf6430945d9813ad9b409171fc305c1a378f65","abstract_canon_sha256":"70c58205e7783c4f8cf61eedfdc44132775f11f01632c881640b6270675b15f4"},"schema_version":"1.0"},"canonical_sha256":"d437838377a570cb61d6fbbc890bfd83b248d369fcdaf23b1a6948b321f97a0d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:45:34.889838Z","signature_b64":"lShksa/57CxyYXYYjG+13CR3erKnpsC8P2Pin0mpOWnsZjCdHnSG4KZviH9qBzRmofvlihbkgkRunoE/QeX9CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d437838377a570cb61d6fbbc890bfd83b248d369fcdaf23b1a6948b321f97a0d","last_reissued_at":"2026-07-05T05:45:34.889398Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:45:34.889398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.03089","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:45:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xXVKkL+S3j5rvs8BNOZDxLb5xrxsoHH7+wtWNc+1axJUArkNaAVxu/mDGztRURsoYkT51JtTOa59XtxKBYQ0AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:22:32.949132Z"},"content_sha256":"317d763be930ade9d257000d9e1442af0be109b8d2d2513c0174b7698636866d","schema_version":"1.0","event_id":"sha256:317d763be930ade9d257000d9e1442af0be109b8d2d2513c0174b7698636866d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:2Q3YHA3XUVYMWYOW7O6ISC75QO","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"I Hear Your True Colors: Image Guided Audio Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.AS"],"primary_cat":"cs.SD","authors_text":"Roy Sheffer, Yossi Adi","submitted_at":"2022-11-06T11:48:20Z","abstract_excerpt":"We propose Im2Wav, an image guided open-domain audio generation system. Given an input image or a sequence of images, Im2Wav generates a semantically relevant sound. Im2Wav is based on two Transformer language models, that operate over a hierarchical discrete audio representation obtained from a VQ-VAE based model. We first produce a low-level audio representation using a language model. Then, we upsample the audio tokens using an additional language model to generate a high-fidelity audio sample. We use the rich semantics of a pre-trained CLIP (Contrastive Language-Image Pre-training) embeddi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.03089","kind":"arxiv","version":2},"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/2211.03089/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":"2026-07-05T05:45:34Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"dOgIXraKzn6GwvetShDkWOyJhYNEBvt+m1AHjDv7WhOLhdGuRvNvcoXg3unrra+XSleLl8ku1nRbmNoh+YNtCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T09:22:32.949734Z"},"content_sha256":"6d4040926ab501ae58b00bcaa5850d8d0b95b0d3dedafa71717a0efbe01b4508","schema_version":"1.0","event_id":"sha256:6d4040926ab501ae58b00bcaa5850d8d0b95b0d3dedafa71717a0efbe01b4508"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2Q3YHA3XUVYMWYOW7O6ISC75QO/bundle.json","state_url":"https://pith.science/pith/2Q3YHA3XUVYMWYOW7O6ISC75QO/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2Q3YHA3XUVYMWYOW7O6ISC75QO/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":"2026-08-08T09:22:32Z","links":{"resolver":"https://pith.science/pith/2Q3YHA3XUVYMWYOW7O6ISC75QO","bundle":"https://pith.science/pith/2Q3YHA3XUVYMWYOW7O6ISC75QO/bundle.json","state":"https://pith.science/pith/2Q3YHA3XUVYMWYOW7O6ISC75QO/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2Q3YHA3XUVYMWYOW7O6ISC75QO/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:2Q3YHA3XUVYMWYOW7O6ISC75QO","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":"70c58205e7783c4f8cf61eedfdc44132775f11f01632c881640b6270675b15f4","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-11-06T11:48:20Z","title_canon_sha256":"277c50a1432f70ffb9105f3b7daf6430945d9813ad9b409171fc305c1a378f65"},"schema_version":"1.0","source":{"id":"2211.03089","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.03089","created_at":"2026-07-05T05:45:34Z"},{"alias_kind":"arxiv_version","alias_value":"2211.03089v2","created_at":"2026-07-05T05:45:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.03089","created_at":"2026-07-05T05:45:34Z"},{"alias_kind":"pith_short_12","alias_value":"2Q3YHA3XUVYM","created_at":"2026-07-05T05:45:34Z"},{"alias_kind":"pith_short_16","alias_value":"2Q3YHA3XUVYMWYOW","created_at":"2026-07-05T05:45:34Z"},{"alias_kind":"pith_short_8","alias_value":"2Q3YHA3X","created_at":"2026-07-05T05:45:34Z"}],"graph_snapshots":[{"event_id":"sha256:6d4040926ab501ae58b00bcaa5850d8d0b95b0d3dedafa71717a0efbe01b4508","target":"graph","created_at":"2026-07-05T05:45:34Z","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/2211.03089/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose Im2Wav, an image guided open-domain audio generation system. Given an input image or a sequence of images, Im2Wav generates a semantically relevant sound. Im2Wav is based on two Transformer language models, that operate over a hierarchical discrete audio representation obtained from a VQ-VAE based model. We first produce a low-level audio representation using a language model. Then, we upsample the audio tokens using an additional language model to generate a high-fidelity audio sample. We use the rich semantics of a pre-trained CLIP (Contrastive Language-Image Pre-training) embeddi","authors_text":"Roy Sheffer, Yossi Adi","cross_cats":["eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-11-06T11:48:20Z","title":"I Hear Your True Colors: Image Guided Audio Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.03089","kind":"arxiv","version":2},"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":"sha256:317d763be930ade9d257000d9e1442af0be109b8d2d2513c0174b7698636866d","target":"record","created_at":"2026-07-05T05:45:34Z","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":"70c58205e7783c4f8cf61eedfdc44132775f11f01632c881640b6270675b15f4","cross_cats_sorted":["eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2022-11-06T11:48:20Z","title_canon_sha256":"277c50a1432f70ffb9105f3b7daf6430945d9813ad9b409171fc305c1a378f65"},"schema_version":"1.0","source":{"id":"2211.03089","kind":"arxiv","version":2}},"canonical_sha256":"d437838377a570cb61d6fbbc890bfd83b248d369fcdaf23b1a6948b321f97a0d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d437838377a570cb61d6fbbc890bfd83b248d369fcdaf23b1a6948b321f97a0d","first_computed_at":"2026-07-05T05:45:34.889398Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:45:34.889398Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"lShksa/57CxyYXYYjG+13CR3erKnpsC8P2Pin0mpOWnsZjCdHnSG4KZviH9qBzRmofvlihbkgkRunoE/QeX9CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T05:45:34.889838Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.03089","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:317d763be930ade9d257000d9e1442af0be109b8d2d2513c0174b7698636866d","sha256:6d4040926ab501ae58b00bcaa5850d8d0b95b0d3dedafa71717a0efbe01b4508"],"state_sha256":"2ce02e40141fd14d0aeb105001ed69c8edce0f0c0cd41141b41a8459472739e9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hUFOnu8EMFQuwS83bfpZaWRNX6PDiSTEbTKPjy3YGr5FlneSIGiQlBSe34GfK0BpxsAV2J9OP66OAw/jkne1BA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T09:22:32.953836Z","bundle_sha256":"2730c9599c9dc8fa5ce88134d6a8550e69558b18f8d17034824a1a471e974adc"}}