{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:PP4WERPV5V2JK7Q43QTHKQSIQV","short_pith_number":"pith:PP4WERPV","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"},"canonical_sha256":"7bf96245f5ed74957e1cdc267542488554b7bc710f1354880459b507607c62ee","source":{"kind":"arxiv","id":"2305.13050","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:PP4WERPV5V2JK7Q43QTHKQSIQV","target":"record","payload":{"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"},"canonical_sha256":"7bf96245f5ed74957e1cdc267542488554b7bc710f1354880459b507607c62ee","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"},"source_kind":"arxiv","source_id":"2305.13050","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":"2026-07-05T06:12:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6q8uzv6VUC5NUQaeWsQwLk4mwngv4tepohtsDzz+/lgQaK8SPuFp9smItplOnDMHkyewAInaz2YRpfufPGduCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:50:21.465938Z"},"content_sha256":"fa36e648edc2e7deb6594cad79619df524b9122a596725d92aa05a74217e066f","schema_version":"1.0","event_id":"sha256:fa36e648edc2e7deb6594cad79619df524b9122a596725d92aa05a74217e066f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:PP4WERPV5V2JK7Q43QTHKQSIQV","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T06:12:25Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g53t1bR0SUFy/00tks+XZJytEcgW1ula4m3jP8iYY6K1quzgcDp+sf7w9qw2xLfuHWPoXjrBwYNTBpq/WDslBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T05:50:21.466538Z"},"content_sha256":"d05a470b3916516ec7b591ab825b3d429de75a5ad340640c02edb7183ac75ec1","schema_version":"1.0","event_id":"sha256:d05a470b3916516ec7b591ab825b3d429de75a5ad340640c02edb7183ac75ec1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PP4WERPV5V2JK7Q43QTHKQSIQV/bundle.json","state_url":"https://pith.science/pith/PP4WERPV5V2JK7Q43QTHKQSIQV/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PP4WERPV5V2JK7Q43QTHKQSIQV/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":"2026-08-09T05:50:21Z","links":{"resolver":"https://pith.science/pith/PP4WERPV5V2JK7Q43QTHKQSIQV","bundle":"https://pith.science/pith/PP4WERPV5V2JK7Q43QTHKQSIQV/bundle.json","state":"https://pith.science/pith/PP4WERPV5V2JK7Q43QTHKQSIQV/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PP4WERPV5V2JK7Q43QTHKQSIQV/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RXcRBQVFE2Pg1mbsHv5I3NS3yfNndqtmExasWDb8pLXFkYvErFbAqlw1uZUALwzHmbAonyNNzYwBCNwrb12zAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T05:50:21.470523Z","bundle_sha256":"fab62bded50c6d6d1c0d3cd891263336c8942ad6e0ac563eee3f7f327a6b2ace"}}