{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:W3LLJADOOQ5KYHTS24GIEQECB3","short_pith_number":"pith:W3LLJADO","canonical_record":{"source":{"id":"2309.02405","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-05T17:36:40Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"49b0c18ad8dd3ea985c842e36c63d6c97f7490085e4e0316020279d7bbe4e215","abstract_canon_sha256":"324aa5a275dbe6ef60c11f6a1463e2ecdefd210dee89219afe607b43dc2c38cb"},"schema_version":"1.0"},"canonical_sha256":"b6d6b4806e743aac1e72d70c8240820efcc545d86e48b3ce65bfb7ab0671c915","source":{"kind":"arxiv","id":"2309.02405","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.02405","created_at":"2026-07-05T06:47:59Z"},{"alias_kind":"arxiv_version","alias_value":"2309.02405v1","created_at":"2026-07-05T06:47:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.02405","created_at":"2026-07-05T06:47:59Z"},{"alias_kind":"pith_short_12","alias_value":"W3LLJADOOQ5K","created_at":"2026-07-05T06:47:59Z"},{"alias_kind":"pith_short_16","alias_value":"W3LLJADOOQ5KYHTS","created_at":"2026-07-05T06:47:59Z"},{"alias_kind":"pith_short_8","alias_value":"W3LLJADO","created_at":"2026-07-05T06:47:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:W3LLJADOOQ5KYHTS24GIEQECB3","target":"record","payload":{"canonical_record":{"source":{"id":"2309.02405","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-05T17:36:40Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"49b0c18ad8dd3ea985c842e36c63d6c97f7490085e4e0316020279d7bbe4e215","abstract_canon_sha256":"324aa5a275dbe6ef60c11f6a1463e2ecdefd210dee89219afe607b43dc2c38cb"},"schema_version":"1.0"},"canonical_sha256":"b6d6b4806e743aac1e72d70c8240820efcc545d86e48b3ce65bfb7ab0671c915","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:47:59.788819Z","signature_b64":"LHE97sGw4sujsGrjB+expwKM+sR96OrlTLUysvxD89wiMNyigh4bXkyAgTX635qeHdKjnhljVjlpOn2mWtY9BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b6d6b4806e743aac1e72d70c8240820efcc545d86e48b3ce65bfb7ab0671c915","last_reissued_at":"2026-07-05T06:47:59.788376Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:47:59.788376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.02405","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":"2026-07-05T06:47:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1QD4hFrGz5rbNhFMCO76Zs49HCHH5c3mJpMg8SmchqGV408KD1D589AJdj8uyWl7BPkFZFFoYrS3U0JJ4ryrAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T15:56:13.930146Z"},"content_sha256":"62ae87dbe26c96115688e76828dba02275663f39190f2f432de90e6d98708d1c","schema_version":"1.0","event_id":"sha256:62ae87dbe26c96115688e76828dba02275663f39190f2f432de90e6d98708d1c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:W3LLJADOOQ5KYHTS24GIEQECB3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Generating Realistic Images from In-the-wild Sounds","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Hyeonyu Kim, Jeonghun Kang, Taegyeong Lee, Taehwan Kim","submitted_at":"2023-09-05T17:36:40Z","abstract_excerpt":"Representing wild sounds as images is an important but challenging task due to the lack of paired datasets between sound and images and the significant differences in the characteristics of these two modalities. Previous studies have focused on generating images from sound in limited categories or music. In this paper, we propose a novel approach to generate images from in-the-wild sounds. First, we convert sound into text using audio captioning. Second, we propose audio attention and sentence attention to represent the rich characteristics of sound and visualize the sound. Lastly, we propose "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.02405","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/2309.02405/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":"2026-07-05T06:47:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GpS3dZLLYGtQazrYQdLp7fsUQRVVx3z6z7TyZnnmcvy3uIXt5Y7Ii8Tq8ccWLycl/aFKrqxPTBUD2TyrWiBUCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T15:56:13.931063Z"},"content_sha256":"ebc1a0869e4e1ceec29c85f1c151380d087e46b16b38136e39b6b1194bfd8d57","schema_version":"1.0","event_id":"sha256:ebc1a0869e4e1ceec29c85f1c151380d087e46b16b38136e39b6b1194bfd8d57"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/W3LLJADOOQ5KYHTS24GIEQECB3/bundle.json","state_url":"https://pith.science/pith/W3LLJADOOQ5KYHTS24GIEQECB3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/W3LLJADOOQ5KYHTS24GIEQECB3/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":"2026-08-16T15:56:13Z","links":{"resolver":"https://pith.science/pith/W3LLJADOOQ5KYHTS24GIEQECB3","bundle":"https://pith.science/pith/W3LLJADOOQ5KYHTS24GIEQECB3/bundle.json","state":"https://pith.science/pith/W3LLJADOOQ5KYHTS24GIEQECB3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/W3LLJADOOQ5KYHTS24GIEQECB3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:W3LLJADOOQ5KYHTS24GIEQECB3","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":"324aa5a275dbe6ef60c11f6a1463e2ecdefd210dee89219afe607b43dc2c38cb","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-05T17:36:40Z","title_canon_sha256":"49b0c18ad8dd3ea985c842e36c63d6c97f7490085e4e0316020279d7bbe4e215"},"schema_version":"1.0","source":{"id":"2309.02405","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.02405","created_at":"2026-07-05T06:47:59Z"},{"alias_kind":"arxiv_version","alias_value":"2309.02405v1","created_at":"2026-07-05T06:47:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.02405","created_at":"2026-07-05T06:47:59Z"},{"alias_kind":"pith_short_12","alias_value":"W3LLJADOOQ5K","created_at":"2026-07-05T06:47:59Z"},{"alias_kind":"pith_short_16","alias_value":"W3LLJADOOQ5KYHTS","created_at":"2026-07-05T06:47:59Z"},{"alias_kind":"pith_short_8","alias_value":"W3LLJADO","created_at":"2026-07-05T06:47:59Z"}],"graph_snapshots":[{"event_id":"sha256:ebc1a0869e4e1ceec29c85f1c151380d087e46b16b38136e39b6b1194bfd8d57","target":"graph","created_at":"2026-07-05T06:47:59Z","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/2309.02405/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Representing wild sounds as images is an important but challenging task due to the lack of paired datasets between sound and images and the significant differences in the characteristics of these two modalities. Previous studies have focused on generating images from sound in limited categories or music. In this paper, we propose a novel approach to generate images from in-the-wild sounds. First, we convert sound into text using audio captioning. Second, we propose audio attention and sentence attention to represent the rich characteristics of sound and visualize the sound. Lastly, we propose ","authors_text":"Hyeonyu Kim, Jeonghun Kang, Taegyeong Lee, Taehwan Kim","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-05T17:36:40Z","title":"Generating Realistic Images from In-the-wild Sounds"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.02405","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":"sha256:62ae87dbe26c96115688e76828dba02275663f39190f2f432de90e6d98708d1c","target":"record","created_at":"2026-07-05T06:47:59Z","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":"324aa5a275dbe6ef60c11f6a1463e2ecdefd210dee89219afe607b43dc2c38cb","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-05T17:36:40Z","title_canon_sha256":"49b0c18ad8dd3ea985c842e36c63d6c97f7490085e4e0316020279d7bbe4e215"},"schema_version":"1.0","source":{"id":"2309.02405","kind":"arxiv","version":1}},"canonical_sha256":"b6d6b4806e743aac1e72d70c8240820efcc545d86e48b3ce65bfb7ab0671c915","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b6d6b4806e743aac1e72d70c8240820efcc545d86e48b3ce65bfb7ab0671c915","first_computed_at":"2026-07-05T06:47:59.788376Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:47:59.788376Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LHE97sGw4sujsGrjB+expwKM+sR96OrlTLUysvxD89wiMNyigh4bXkyAgTX635qeHdKjnhljVjlpOn2mWtY9BA==","signature_status":"signed_v1","signed_at":"2026-07-05T06:47:59.788819Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.02405","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:62ae87dbe26c96115688e76828dba02275663f39190f2f432de90e6d98708d1c","sha256:ebc1a0869e4e1ceec29c85f1c151380d087e46b16b38136e39b6b1194bfd8d57"],"state_sha256":"5d1ba742baf7ac52e10db5e418bbb299d56bf9053181e630c5cad2cf3bdc84e9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b9J2SB0U/Z4N/J/jgd3afsZ3SmgaCVrV7D29n3Q2ciPu/hFuqrXmKq1jLNnf37MXy30rG53fJl3RQqoxH/tuAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T15:56:13.939527Z","bundle_sha256":"bcc9d953bad6856065c7d0c16ca5faea7f938120d342fb147ff0837cd78dda86"}}