{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:E3RERAZ7OLZYQZBBS2X4LP6DGZ","short_pith_number":"pith:E3RERAZ7","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"},"canonical_sha256":"26e248833f72f388642196afc5bfc3366b574fa6afc2905c1878dadc4e115070","source":{"kind":"arxiv","id":"2504.18283","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.18283","created_at":"2026-07-05T10:54:04Z"},{"alias_kind":"arxiv_version","alias_value":"2504.18283v1","created_at":"2026-07-05T10:54:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.18283","created_at":"2026-07-05T10:54:04Z"},{"alias_kind":"pith_short_12","alias_value":"E3RERAZ7OLZY","created_at":"2026-07-05T10:54:04Z"},{"alias_kind":"pith_short_16","alias_value":"E3RERAZ7OLZYQZBB","created_at":"2026-07-05T10:54:04Z"},{"alias_kind":"pith_short_8","alias_value":"E3RERAZ7","created_at":"2026-07-05T10:54:04Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:E3RERAZ7OLZYQZBBS2X4LP6DGZ","target":"record","payload":{"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"},"canonical_sha256":"26e248833f72f388642196afc5bfc3366b574fa6afc2905c1878dadc4e115070","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"},"source_kind":"arxiv","source_id":"2504.18283","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":"2026-07-05T10:54:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0qc/ziW7Z9GXR6dC47hhhAMwt/C9yPhNi0ENPxyd16hcUdh3UVHmKruzQhoWPn8s89lvOXubC20KGg+g9DlwBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:32:15.126091Z"},"content_sha256":"8946832f1749ff7cbc266cf04a1150ddcedbdcf24d84ee4f83511cc7a55890bb","schema_version":"1.0","event_id":"sha256:8946832f1749ff7cbc266cf04a1150ddcedbdcf24d84ee4f83511cc7a55890bb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:E3RERAZ7OLZYQZBBS2X4LP6DGZ","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:54:04Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rugMdLs+TBes2XrjyBNMYIeosgq/5etmPFZTrVqfHAn8GbW6yIILO1ps0k4Asb/EM3b0yr01AQLxwhZYxqzvDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-06T23:32:15.126508Z"},"content_sha256":"0bf71ccacb1bc6406641c6e2db13b26a5432f5bc1cc49c85cee7d5930124b5de","schema_version":"1.0","event_id":"sha256:0bf71ccacb1bc6406641c6e2db13b26a5432f5bc1cc49c85cee7d5930124b5de"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/E3RERAZ7OLZYQZBBS2X4LP6DGZ/bundle.json","state_url":"https://pith.science/pith/E3RERAZ7OLZYQZBBS2X4LP6DGZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/E3RERAZ7OLZYQZBBS2X4LP6DGZ/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":"2026-07-06T23:32:15Z","links":{"resolver":"https://pith.science/pith/E3RERAZ7OLZYQZBBS2X4LP6DGZ","bundle":"https://pith.science/pith/E3RERAZ7OLZYQZBBS2X4LP6DGZ/bundle.json","state":"https://pith.science/pith/E3RERAZ7OLZYQZBBS2X4LP6DGZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/E3RERAZ7OLZYQZBBS2X4LP6DGZ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:E3RERAZ7OLZYQZBBS2X4LP6DGZ","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":"62a0c9fb0d49de87432831a5eef4078fb8557e8c8b1fa51a3f2772455a39379e","cross_cats_sorted":["cs.AI","cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-25T11:51:04Z","title_canon_sha256":"93f635cb36fe795f43d156d6f760d1173ebb56ca76368ff1e654edd81b6dd795"},"schema_version":"1.0","source":{"id":"2504.18283","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.18283","created_at":"2026-07-05T10:54:04Z"},{"alias_kind":"arxiv_version","alias_value":"2504.18283v1","created_at":"2026-07-05T10:54:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.18283","created_at":"2026-07-05T10:54:04Z"},{"alias_kind":"pith_short_12","alias_value":"E3RERAZ7OLZY","created_at":"2026-07-05T10:54:04Z"},{"alias_kind":"pith_short_16","alias_value":"E3RERAZ7OLZYQZBB","created_at":"2026-07-05T10:54:04Z"},{"alias_kind":"pith_short_8","alias_value":"E3RERAZ7","created_at":"2026-07-05T10:54:04Z"}],"graph_snapshots":[{"event_id":"sha256:0bf71ccacb1bc6406641c6e2db13b26a5432f5bc1cc49c85cee7d5930124b5de","target":"graph","created_at":"2026-07-05T10:54:04Z","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/2504.18283/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Martim Brand\\~ao, Minjae Kang","cross_cats":["cs.AI","cs.MM","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-25T11:51:04Z","title":"Seeing Soundscapes: Audio-Visual Generation and Separation from Soundscapes Using Audio-Visual Separator"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.18283","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":"sha256:8946832f1749ff7cbc266cf04a1150ddcedbdcf24d84ee4f83511cc7a55890bb","target":"record","created_at":"2026-07-05T10:54:04Z","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":"62a0c9fb0d49de87432831a5eef4078fb8557e8c8b1fa51a3f2772455a39379e","cross_cats_sorted":["cs.AI","cs.MM","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-25T11:51:04Z","title_canon_sha256":"93f635cb36fe795f43d156d6f760d1173ebb56ca76368ff1e654edd81b6dd795"},"schema_version":"1.0","source":{"id":"2504.18283","kind":"arxiv","version":1}},"canonical_sha256":"26e248833f72f388642196afc5bfc3366b574fa6afc2905c1878dadc4e115070","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"26e248833f72f388642196afc5bfc3366b574fa6afc2905c1878dadc4e115070","first_computed_at":"2026-07-05T10:54:04.792294Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:54:04.792294Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jI1GqjHyCWnP9DNEYQAZ488l1jodBda/vKBQcnQRqZLYwpIf49ZzhdijKofw5W0ASkA6RMubZFUv55c9KUfMCw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:54:04.792709Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.18283","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8946832f1749ff7cbc266cf04a1150ddcedbdcf24d84ee4f83511cc7a55890bb","sha256:0bf71ccacb1bc6406641c6e2db13b26a5432f5bc1cc49c85cee7d5930124b5de"],"state_sha256":"2ebf639be1697b6d9ad1fde75644d8cc3fb628986f967d62dfd38ccec514350d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"omAO/GAULltBJuZQ7G+fLnVC+4TkzBkJCh97VxLFfM7R+nm70tWJeczKusAltv2ErRzJySArOU6r+Tqq2FFJCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-06T23:32:15.128517Z","bundle_sha256":"b5600e0a319bb8d036f3cea143e891a3fa51a053a5878d7f1f1022b87cb32c40"}}