{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:E3RERAZ7OLZYQZBBS2X4LP6DGZ","short_pith_number":"pith:E3RERAZ7","schema_version":"1.0","canonical_sha256":"26e248833f72f388642196afc5bfc3366b574fa6afc2905c1878dadc4e115070","source":{"kind":"arxiv","id":"2504.18283","version":1},"attestation_state":"computed","paper":{"title":"Seeing Soundscapes: Audio-Visual Generation and Separation from Soundscapes Using Audio-Visual Separator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Martim Brand\\~ao, Minjae Kang","submitted_at":"2025-04-25T11:51:04Z","abstract_excerpt":"Recent audio-visual generative models have made substantial progress in generating images from audio. However, existing approaches focus on generating images from single-class audio and fail to generate images from mixed audio. To address this, we propose an Audio-Visual Generation and Separation model (AV-GAS) for generating images from soundscapes (mixed audio containing multiple classes). Our contribution is threefold: First, we propose a new challenge in the audio-visual generation task, which is to generate an image given a multi-class audio input, and we propose a method that solves this"},"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":"2504.18283","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-25T11:51:04Z","cross_cats_sorted":["cs.AI","cs.MM","cs.SD","eess.AS"],"title_canon_sha256":"93f635cb36fe795f43d156d6f760d1173ebb56ca76368ff1e654edd81b6dd795","abstract_canon_sha256":"62a0c9fb0d49de87432831a5eef4078fb8557e8c8b1fa51a3f2772455a39379e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:54:04.792709Z","signature_b64":"jI1GqjHyCWnP9DNEYQAZ488l1jodBda/vKBQcnQRqZLYwpIf49ZzhdijKofw5W0ASkA6RMubZFUv55c9KUfMCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"26e248833f72f388642196afc5bfc3366b574fa6afc2905c1878dadc4e115070","last_reissued_at":"2026-07-05T10:54:04.792294Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:54:04.792294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Seeing Soundscapes: Audio-Visual Generation and Separation from Soundscapes Using Audio-Visual Separator","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Martim Brand\\~ao, Minjae Kang","submitted_at":"2025-04-25T11:51:04Z","abstract_excerpt":"Recent audio-visual generative models have made substantial progress in generating images from audio. However, existing approaches focus on generating images from single-class audio and fail to generate images from mixed audio. To address this, we propose an Audio-Visual Generation and Separation model (AV-GAS) for generating images from soundscapes (mixed audio containing multiple classes). Our contribution is threefold: First, we propose a new challenge in the audio-visual generation task, which is to generate an image given a multi-class audio input, and we propose a method that solves this"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.18283","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/2504.18283/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":"2504.18283","created_at":"2026-07-05T10:54:04.792356+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.18283v1","created_at":"2026-07-05T10:54:04.792356+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.18283","created_at":"2026-07-05T10:54:04.792356+00:00"},{"alias_kind":"pith_short_12","alias_value":"E3RERAZ7OLZY","created_at":"2026-07-05T10:54:04.792356+00:00"},{"alias_kind":"pith_short_16","alias_value":"E3RERAZ7OLZYQZBB","created_at":"2026-07-05T10:54:04.792356+00:00"},{"alias_kind":"pith_short_8","alias_value":"E3RERAZ7","created_at":"2026-07-05T10:54:04.792356+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/E3RERAZ7OLZYQZBBS2X4LP6DGZ","json":"https://pith.science/pith/E3RERAZ7OLZYQZBBS2X4LP6DGZ.json","graph_json":"https://pith.science/api/pith-number/E3RERAZ7OLZYQZBBS2X4LP6DGZ/graph.json","events_json":"https://pith.science/api/pith-number/E3RERAZ7OLZYQZBBS2X4LP6DGZ/events.json","paper":"https://pith.science/paper/E3RERAZ7"},"agent_actions":{"view_html":"https://pith.science/pith/E3RERAZ7OLZYQZBBS2X4LP6DGZ","download_json":"https://pith.science/pith/E3RERAZ7OLZYQZBBS2X4LP6DGZ.json","view_paper":"https://pith.science/paper/E3RERAZ7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.18283&json=true","fetch_graph":"https://pith.science/api/pith-number/E3RERAZ7OLZYQZBBS2X4LP6DGZ/graph.json","fetch_events":"https://pith.science/api/pith-number/E3RERAZ7OLZYQZBBS2X4LP6DGZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/E3RERAZ7OLZYQZBBS2X4LP6DGZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/E3RERAZ7OLZYQZBBS2X4LP6DGZ/action/storage_attestation","attest_author":"https://pith.science/pith/E3RERAZ7OLZYQZBBS2X4LP6DGZ/action/author_attestation","sign_citation":"https://pith.science/pith/E3RERAZ7OLZYQZBBS2X4LP6DGZ/action/citation_signature","submit_replication":"https://pith.science/pith/E3RERAZ7OLZYQZBBS2X4LP6DGZ/action/replication_record"}},"created_at":"2026-07-05T10:54:04.792356+00:00","updated_at":"2026-07-05T10:54:04.792356+00:00"}