{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:2Q3YHA3XUVYMWYOW7O6ISC75QO","short_pith_number":"pith:2Q3YHA3X","schema_version":"1.0","canonical_sha256":"d437838377a570cb61d6fbbc890bfd83b248d369fcdaf23b1a6948b321f97a0d","source":{"kind":"arxiv","id":"2211.03089","version":2},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2211.03089","created_at":"2026-07-05T05:45:34.889462+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.03089v2","created_at":"2026-07-05T05:45:34.889462+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.03089","created_at":"2026-07-05T05:45:34.889462+00:00"},{"alias_kind":"pith_short_12","alias_value":"2Q3YHA3XUVYM","created_at":"2026-07-05T05:45:34.889462+00:00"},{"alias_kind":"pith_short_16","alias_value":"2Q3YHA3XUVYMWYOW","created_at":"2026-07-05T05:45:34.889462+00:00"},{"alias_kind":"pith_short_8","alias_value":"2Q3YHA3X","created_at":"2026-07-05T05:45:34.889462+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.09717","citing_title":"Testing chatbots on the creation of encoders for audio conditioned image generation","ref_index":89,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2Q3YHA3XUVYMWYOW7O6ISC75QO","json":"https://pith.science/pith/2Q3YHA3XUVYMWYOW7O6ISC75QO.json","graph_json":"https://pith.science/api/pith-number/2Q3YHA3XUVYMWYOW7O6ISC75QO/graph.json","events_json":"https://pith.science/api/pith-number/2Q3YHA3XUVYMWYOW7O6ISC75QO/events.json","paper":"https://pith.science/paper/2Q3YHA3X"},"agent_actions":{"view_html":"https://pith.science/pith/2Q3YHA3XUVYMWYOW7O6ISC75QO","download_json":"https://pith.science/pith/2Q3YHA3XUVYMWYOW7O6ISC75QO.json","view_paper":"https://pith.science/paper/2Q3YHA3X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.03089&json=true","fetch_graph":"https://pith.science/api/pith-number/2Q3YHA3XUVYMWYOW7O6ISC75QO/graph.json","fetch_events":"https://pith.science/api/pith-number/2Q3YHA3XUVYMWYOW7O6ISC75QO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2Q3YHA3XUVYMWYOW7O6ISC75QO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2Q3YHA3XUVYMWYOW7O6ISC75QO/action/storage_attestation","attest_author":"https://pith.science/pith/2Q3YHA3XUVYMWYOW7O6ISC75QO/action/author_attestation","sign_citation":"https://pith.science/pith/2Q3YHA3XUVYMWYOW7O6ISC75QO/action/citation_signature","submit_replication":"https://pith.science/pith/2Q3YHA3XUVYMWYOW7O6ISC75QO/action/replication_record"}},"created_at":"2026-07-05T05:45:34.889462+00:00","updated_at":"2026-07-05T05:45:34.889462+00:00"}