{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GVXUZCURDCKSJMCISHU42UOAAJ","short_pith_number":"pith:GVXUZCUR","canonical_record":{"source":{"id":"2411.15447","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2024-11-23T04:27:19Z","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"title_canon_sha256":"394763737d51fd08112693e28c691f743a921367f8363168d0174e0902d66a17","abstract_canon_sha256":"49549cab21a47c4073ed74a66e622f741de8fd29787ac85a78c2b4cae678064e"},"schema_version":"1.0"},"canonical_sha256":"356f4c8a91189524b04891e9cd51c002730737b4da671b7499739bbb117469fc","source":{"kind":"arxiv","id":"2411.15447","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.15447","created_at":"2026-07-05T11:52:16Z"},{"alias_kind":"arxiv_version","alias_value":"2411.15447v4","created_at":"2026-07-05T11:52:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15447","created_at":"2026-07-05T11:52:16Z"},{"alias_kind":"pith_short_12","alias_value":"GVXUZCURDCKS","created_at":"2026-07-05T11:52:16Z"},{"alias_kind":"pith_short_16","alias_value":"GVXUZCURDCKSJMCI","created_at":"2026-07-05T11:52:16Z"},{"alias_kind":"pith_short_8","alias_value":"GVXUZCUR","created_at":"2026-07-05T11:52:16Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GVXUZCURDCKSJMCISHU42UOAAJ","target":"record","payload":{"canonical_record":{"source":{"id":"2411.15447","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2024-11-23T04:27:19Z","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"title_canon_sha256":"394763737d51fd08112693e28c691f743a921367f8363168d0174e0902d66a17","abstract_canon_sha256":"49549cab21a47c4073ed74a66e622f741de8fd29787ac85a78c2b4cae678064e"},"schema_version":"1.0"},"canonical_sha256":"356f4c8a91189524b04891e9cd51c002730737b4da671b7499739bbb117469fc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:52:16.174325Z","signature_b64":"uQXc4E2SisyDUCl9eUnsttP34pCzyZ1K2AKwE+yoRvSmSifld94OurFa5cJnSk393KKOdoFU3FLsXxLeeyGgAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"356f4c8a91189524b04891e9cd51c002730737b4da671b7499739bbb117469fc","last_reissued_at":"2026-07-05T11:52:16.173852Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:52:16.173852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.15447","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:52:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"SBK9lwd5Fi+Q7yzSVKUEPq3zxpHG7aaPvAQpZTazCh430Jfnwt0Y/e5a4QulC0nrqqIcascyCBivQISUp14OAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:37:36.173302Z"},"content_sha256":"0b9b3335d683eeca702f7d746c6ff1735cf5cd1cb8dd30a9fe126b936fc9d13c","schema_version":"1.0","event_id":"sha256:0b9b3335d683eeca702f7d746c6ff1735cf5cd1cb8dd30a9fe126b936fc9d13c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GVXUZCURDCKSJMCISHU42UOAAJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Gotta Hear Them All: Towards Sound Source Aware Audio Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Heng Wang, Jianbo Ma, Weidong Cai, Wei Guo","submitted_at":"2024-11-23T04:27:19Z","abstract_excerpt":"Audio synthesis has broad applications in multimedia. Recent advancements have made it possible to generate relevant audios from inputs describing an audio scene, such as images or texts. However, the immersiveness and expressiveness of the generation are limited. One possible problem is that existing methods solely rely on the global scene and overlook details of local sounding objects (i.e., sound sources). To address this issue, we propose a Sound Source-Aware Audio (SS2A) generator. SS2A is able to locally perceive multimodal sound sources from a scene with visual detection and cross-modal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15447","kind":"arxiv","version":4},"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/2411.15447/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":"2026-07-05T11:52:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3jWNi78KuhV5B7hj6rovPuRvn9VtVd7ScHD74SVh3001euZVp8XBe2XxLdOAZYc0Ae8oCFDGzkkQAI86vs1MAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T14:37:36.173909Z"},"content_sha256":"d711d40d4ec9701b2e7e893b6413fac509012e190278fca41ecc57aa2ce43e7c","schema_version":"1.0","event_id":"sha256:d711d40d4ec9701b2e7e893b6413fac509012e190278fca41ecc57aa2ce43e7c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GVXUZCURDCKSJMCISHU42UOAAJ/bundle.json","state_url":"https://pith.science/pith/GVXUZCURDCKSJMCISHU42UOAAJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GVXUZCURDCKSJMCISHU42UOAAJ/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":"2026-08-09T14:37:36Z","links":{"resolver":"https://pith.science/pith/GVXUZCURDCKSJMCISHU42UOAAJ","bundle":"https://pith.science/pith/GVXUZCURDCKSJMCISHU42UOAAJ/bundle.json","state":"https://pith.science/pith/GVXUZCURDCKSJMCISHU42UOAAJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GVXUZCURDCKSJMCISHU42UOAAJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GVXUZCURDCKSJMCISHU42UOAAJ","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":"49549cab21a47c4073ed74a66e622f741de8fd29787ac85a78c2b4cae678064e","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2024-11-23T04:27:19Z","title_canon_sha256":"394763737d51fd08112693e28c691f743a921367f8363168d0174e0902d66a17"},"schema_version":"1.0","source":{"id":"2411.15447","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.15447","created_at":"2026-07-05T11:52:16Z"},{"alias_kind":"arxiv_version","alias_value":"2411.15447v4","created_at":"2026-07-05T11:52:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.15447","created_at":"2026-07-05T11:52:16Z"},{"alias_kind":"pith_short_12","alias_value":"GVXUZCURDCKS","created_at":"2026-07-05T11:52:16Z"},{"alias_kind":"pith_short_16","alias_value":"GVXUZCURDCKSJMCI","created_at":"2026-07-05T11:52:16Z"},{"alias_kind":"pith_short_8","alias_value":"GVXUZCUR","created_at":"2026-07-05T11:52:16Z"}],"graph_snapshots":[{"event_id":"sha256:d711d40d4ec9701b2e7e893b6413fac509012e190278fca41ecc57aa2ce43e7c","target":"graph","created_at":"2026-07-05T11:52:16Z","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/2411.15447/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Audio synthesis has broad applications in multimedia. Recent advancements have made it possible to generate relevant audios from inputs describing an audio scene, such as images or texts. However, the immersiveness and expressiveness of the generation are limited. One possible problem is that existing methods solely rely on the global scene and overlook details of local sounding objects (i.e., sound sources). To address this issue, we propose a Sound Source-Aware Audio (SS2A) generator. SS2A is able to locally perceive multimodal sound sources from a scene with visual detection and cross-modal","authors_text":"Heng Wang, Jianbo Ma, Weidong Cai, Wei Guo","cross_cats":["cs.CV","cs.SD","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2024-11-23T04:27:19Z","title":"Gotta Hear Them All: Towards Sound Source Aware Audio Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.15447","kind":"arxiv","version":4},"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":"sha256:0b9b3335d683eeca702f7d746c6ff1735cf5cd1cb8dd30a9fe126b936fc9d13c","target":"record","created_at":"2026-07-05T11:52:16Z","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":"49549cab21a47c4073ed74a66e622f741de8fd29787ac85a78c2b4cae678064e","cross_cats_sorted":["cs.CV","cs.SD","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.MM","submitted_at":"2024-11-23T04:27:19Z","title_canon_sha256":"394763737d51fd08112693e28c691f743a921367f8363168d0174e0902d66a17"},"schema_version":"1.0","source":{"id":"2411.15447","kind":"arxiv","version":4}},"canonical_sha256":"356f4c8a91189524b04891e9cd51c002730737b4da671b7499739bbb117469fc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"356f4c8a91189524b04891e9cd51c002730737b4da671b7499739bbb117469fc","first_computed_at":"2026-07-05T11:52:16.173852Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:52:16.173852Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uQXc4E2SisyDUCl9eUnsttP34pCzyZ1K2AKwE+yoRvSmSifld94OurFa5cJnSk393KKOdoFU3FLsXxLeeyGgAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:52:16.174325Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.15447","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0b9b3335d683eeca702f7d746c6ff1735cf5cd1cb8dd30a9fe126b936fc9d13c","sha256:d711d40d4ec9701b2e7e893b6413fac509012e190278fca41ecc57aa2ce43e7c"],"state_sha256":"551870c29c32ff77d934c3a6901b28764abc8ed8b75792f4ea5d679d1bd2acc9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aFR8uY997cT4ZYNCf0lhJoTevhBZ1B+f5ICcw3rM4JPp13a6T9Qz2ZoMv8F/B9sOA6QG+wQfuIFdwPqInXcfBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T14:37:36.179406Z","bundle_sha256":"93b7ab5fe6cb0467a43e190e590889e1d0c47b7ff59892fb64fc08fa1e8463ae"}}