{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GWPCHKSLWPUPYRLFAGNFRH3NHC","short_pith_number":"pith:GWPCHKSL","schema_version":"1.0","canonical_sha256":"359e23aa4bb3e8fc4565019a589f6d388a1d5a1053947434ea93c23152c5ae48","source":{"kind":"arxiv","id":"2507.18750","version":1},"attestation_state":"computed","paper":{"title":"CatchPhrase: EXPrompt-Guided Encoder Adaptation for Audio-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Dong-Jin Kim, Hyunwoo Oh, Kwanyoung Lee, SeungJu Cha, Si-Woo Kim","submitted_at":"2025-07-24T19:01:05Z","abstract_excerpt":"We propose CatchPhrase, a novel audio-to-image generation framework designed to mitigate semantic misalignment between audio inputs and generated images. While recent advances in multi-modal encoders have enabled progress in cross-modal generation, ambiguity stemming from homographs and auditory illusions continues to hinder accurate alignment. To address this issue, CatchPhrase generates enriched cross-modal semantic prompts (EXPrompt Mining) from weak class labels by leveraging large language models (LLMs) and audio captioning models (ACMs). To address both class-level and instance-level mis"},"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":"2507.18750","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2025-07-24T19:01:05Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"4f0feb244f0cfd952b41c7ce87ab7ba498d703601c9445ef662c62e0df42d46d","abstract_canon_sha256":"cddc710fab4e7c410fc6da15de54cfc74a710825c7ca8190dd814b80acd0fe95"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:42:57.203221Z","signature_b64":"j9weLynSiVJiZyWZwsNm6XbxFtRpRGYfgxzMwPyEdVQv0EIJFTW2O58nsvrxJPC9o5nr2FF5IPowp5cbQqSYBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"359e23aa4bb3e8fc4565019a589f6d388a1d5a1053947434ea93c23152c5ae48","last_reissued_at":"2026-07-05T11:42:57.202800Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:42:57.202800Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CatchPhrase: EXPrompt-Guided Encoder Adaptation for Audio-to-Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Dong-Jin Kim, Hyunwoo Oh, Kwanyoung Lee, SeungJu Cha, Si-Woo Kim","submitted_at":"2025-07-24T19:01:05Z","abstract_excerpt":"We propose CatchPhrase, a novel audio-to-image generation framework designed to mitigate semantic misalignment between audio inputs and generated images. While recent advances in multi-modal encoders have enabled progress in cross-modal generation, ambiguity stemming from homographs and auditory illusions continues to hinder accurate alignment. To address this issue, CatchPhrase generates enriched cross-modal semantic prompts (EXPrompt Mining) from weak class labels by leveraging large language models (LLMs) and audio captioning models (ACMs). To address both class-level and instance-level mis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.18750","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/2507.18750/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":"2507.18750","created_at":"2026-07-05T11:42:57.202854+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.18750v1","created_at":"2026-07-05T11:42:57.202854+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.18750","created_at":"2026-07-05T11:42:57.202854+00:00"},{"alias_kind":"pith_short_12","alias_value":"GWPCHKSLWPUP","created_at":"2026-07-05T11:42:57.202854+00:00"},{"alias_kind":"pith_short_16","alias_value":"GWPCHKSLWPUPYRLF","created_at":"2026-07-05T11:42:57.202854+00:00"},{"alias_kind":"pith_short_8","alias_value":"GWPCHKSL","created_at":"2026-07-05T11:42:57.202854+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GWPCHKSLWPUPYRLFAGNFRH3NHC","json":"https://pith.science/pith/GWPCHKSLWPUPYRLFAGNFRH3NHC.json","graph_json":"https://pith.science/api/pith-number/GWPCHKSLWPUPYRLFAGNFRH3NHC/graph.json","events_json":"https://pith.science/api/pith-number/GWPCHKSLWPUPYRLFAGNFRH3NHC/events.json","paper":"https://pith.science/paper/GWPCHKSL"},"agent_actions":{"view_html":"https://pith.science/pith/GWPCHKSLWPUPYRLFAGNFRH3NHC","download_json":"https://pith.science/pith/GWPCHKSLWPUPYRLFAGNFRH3NHC.json","view_paper":"https://pith.science/paper/GWPCHKSL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.18750&json=true","fetch_graph":"https://pith.science/api/pith-number/GWPCHKSLWPUPYRLFAGNFRH3NHC/graph.json","fetch_events":"https://pith.science/api/pith-number/GWPCHKSLWPUPYRLFAGNFRH3NHC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GWPCHKSLWPUPYRLFAGNFRH3NHC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GWPCHKSLWPUPYRLFAGNFRH3NHC/action/storage_attestation","attest_author":"https://pith.science/pith/GWPCHKSLWPUPYRLFAGNFRH3NHC/action/author_attestation","sign_citation":"https://pith.science/pith/GWPCHKSLWPUPYRLFAGNFRH3NHC/action/citation_signature","submit_replication":"https://pith.science/pith/GWPCHKSLWPUPYRLFAGNFRH3NHC/action/replication_record"}},"created_at":"2026-07-05T11:42:57.202854+00:00","updated_at":"2026-07-05T11:42:57.202854+00:00"}