{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:PP4WERPV5V2JK7Q43QTHKQSIQV","short_pith_number":"pith:PP4WERPV","schema_version":"1.0","canonical_sha256":"7bf96245f5ed74957e1cdc267542488554b7bc710f1354880459b507607c62ee","source":{"kind":"arxiv","id":"2305.13050","version":1},"attestation_state":"computed","paper":{"title":"AudioToken: Adaptation of Text-Conditioned Diffusion Models for Audio-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Guy Yariv, Idan Schwartz, Itai Gat, Lior Wolf, Yossi Adi","submitted_at":"2023-05-22T14:02:44Z","abstract_excerpt":"In recent years, image generation has shown a great leap in performance, where diffusion models play a central role. Although generating high-quality images, such models are mainly conditioned on textual descriptions. This begs the question: \"how can we adopt such models to be conditioned on other modalities?\". In this paper, we propose a novel method utilizing latent diffusion models trained for text-to-image-generation to generate images conditioned on audio recordings. Using a pre-trained audio encoding model, the proposed method encodes audio into a new token, which can be considered as an"},"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":"2305.13050","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-05-22T14:02:44Z","cross_cats_sorted":["cs.CV","cs.LG","eess.AS"],"title_canon_sha256":"a0c181d12786da6db794037fd010a9ee1f18726b4197e31bd5f9970c2ce6cb01","abstract_canon_sha256":"3b5fd1cae009f1e9c3fe5117794914439e82ccd439393652ad3e736317dacc50"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:12:25.964299Z","signature_b64":"n9ePl2m83dg94Q/ynHhbznGW6h+5oiRv3nSFRKSI+VW6nOFrdAVtLvQwFQjQKQYhFwbg48BFOz3I7Y7I4MOmDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7bf96245f5ed74957e1cdc267542488554b7bc710f1354880459b507607c62ee","last_reissued_at":"2026-07-05T06:12:25.963905Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:12:25.963905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AudioToken: Adaptation of Text-Conditioned Diffusion Models for Audio-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Guy Yariv, Idan Schwartz, Itai Gat, Lior Wolf, Yossi Adi","submitted_at":"2023-05-22T14:02:44Z","abstract_excerpt":"In recent years, image generation has shown a great leap in performance, where diffusion models play a central role. Although generating high-quality images, such models are mainly conditioned on textual descriptions. This begs the question: \"how can we adopt such models to be conditioned on other modalities?\". In this paper, we propose a novel method utilizing latent diffusion models trained for text-to-image-generation to generate images conditioned on audio recordings. Using a pre-trained audio encoding model, the proposed method encodes audio into a new token, which can be considered as an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13050","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/2305.13050/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":"2305.13050","created_at":"2026-07-05T06:12:25.963963+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.13050v1","created_at":"2026-07-05T06:12:25.963963+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13050","created_at":"2026-07-05T06:12:25.963963+00:00"},{"alias_kind":"pith_short_12","alias_value":"PP4WERPV5V2J","created_at":"2026-07-05T06:12:25.963963+00:00"},{"alias_kind":"pith_short_16","alias_value":"PP4WERPV5V2JK7Q4","created_at":"2026-07-05T06:12:25.963963+00:00"},{"alias_kind":"pith_short_8","alias_value":"PP4WERPV","created_at":"2026-07-05T06:12:25.963963+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.10571","citing_title":"AVI-Edit: Audio-sync Video Instance Editing with Granularity-Aware Mask Refiner","ref_index":72,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PP4WERPV5V2JK7Q43QTHKQSIQV","json":"https://pith.science/pith/PP4WERPV5V2JK7Q43QTHKQSIQV.json","graph_json":"https://pith.science/api/pith-number/PP4WERPV5V2JK7Q43QTHKQSIQV/graph.json","events_json":"https://pith.science/api/pith-number/PP4WERPV5V2JK7Q43QTHKQSIQV/events.json","paper":"https://pith.science/paper/PP4WERPV"},"agent_actions":{"view_html":"https://pith.science/pith/PP4WERPV5V2JK7Q43QTHKQSIQV","download_json":"https://pith.science/pith/PP4WERPV5V2JK7Q43QTHKQSIQV.json","view_paper":"https://pith.science/paper/PP4WERPV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.13050&json=true","fetch_graph":"https://pith.science/api/pith-number/PP4WERPV5V2JK7Q43QTHKQSIQV/graph.json","fetch_events":"https://pith.science/api/pith-number/PP4WERPV5V2JK7Q43QTHKQSIQV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PP4WERPV5V2JK7Q43QTHKQSIQV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PP4WERPV5V2JK7Q43QTHKQSIQV/action/storage_attestation","attest_author":"https://pith.science/pith/PP4WERPV5V2JK7Q43QTHKQSIQV/action/author_attestation","sign_citation":"https://pith.science/pith/PP4WERPV5V2JK7Q43QTHKQSIQV/action/citation_signature","submit_replication":"https://pith.science/pith/PP4WERPV5V2JK7Q43QTHKQSIQV/action/replication_record"}},"created_at":"2026-07-05T06:12:25.963963+00:00","updated_at":"2026-07-05T06:12:25.963963+00:00"}