{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:PP4WERPV5V2JK7Q43QTHKQSIQV","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":"3b5fd1cae009f1e9c3fe5117794914439e82ccd439393652ad3e736317dacc50","cross_cats_sorted":["cs.CV","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-05-22T14:02:44Z","title_canon_sha256":"a0c181d12786da6db794037fd010a9ee1f18726b4197e31bd5f9970c2ce6cb01"},"schema_version":"1.0","source":{"id":"2305.13050","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.13050","created_at":"2026-07-05T06:12:25Z"},{"alias_kind":"arxiv_version","alias_value":"2305.13050v1","created_at":"2026-07-05T06:12:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.13050","created_at":"2026-07-05T06:12:25Z"},{"alias_kind":"pith_short_12","alias_value":"PP4WERPV5V2J","created_at":"2026-07-05T06:12:25Z"},{"alias_kind":"pith_short_16","alias_value":"PP4WERPV5V2JK7Q4","created_at":"2026-07-05T06:12:25Z"},{"alias_kind":"pith_short_8","alias_value":"PP4WERPV","created_at":"2026-07-05T06:12:25Z"}],"graph_snapshots":[{"event_id":"sha256:d05a470b3916516ec7b591ab825b3d429de75a5ad340640c02edb7183ac75ec1","target":"graph","created_at":"2026-07-05T06:12:25Z","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/2305.13050/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Guy Yariv, Idan Schwartz, Itai Gat, Lior Wolf, Yossi Adi","cross_cats":["cs.CV","cs.LG","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-05-22T14:02:44Z","title":"AudioToken: Adaptation of Text-Conditioned Diffusion Models for Audio-to-Image Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.13050","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:fa36e648edc2e7deb6594cad79619df524b9122a596725d92aa05a74217e066f","target":"record","created_at":"2026-07-05T06:12:25Z","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":"3b5fd1cae009f1e9c3fe5117794914439e82ccd439393652ad3e736317dacc50","cross_cats_sorted":["cs.CV","cs.LG","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-05-22T14:02:44Z","title_canon_sha256":"a0c181d12786da6db794037fd010a9ee1f18726b4197e31bd5f9970c2ce6cb01"},"schema_version":"1.0","source":{"id":"2305.13050","kind":"arxiv","version":1}},"canonical_sha256":"7bf96245f5ed74957e1cdc267542488554b7bc710f1354880459b507607c62ee","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7bf96245f5ed74957e1cdc267542488554b7bc710f1354880459b507607c62ee","first_computed_at":"2026-07-05T06:12:25.963905Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:12:25.963905Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"n9ePl2m83dg94Q/ynHhbznGW6h+5oiRv3nSFRKSI+VW6nOFrdAVtLvQwFQjQKQYhFwbg48BFOz3I7Y7I4MOmDA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:12:25.964299Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.13050","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fa36e648edc2e7deb6594cad79619df524b9122a596725d92aa05a74217e066f","sha256:d05a470b3916516ec7b591ab825b3d429de75a5ad340640c02edb7183ac75ec1"],"state_sha256":"646135a255231048453d5385f7622715f9e2ca082862b8e480dea31ed07baf2a"}