{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:BS33F62ZL72WNUF7I47V3UC3ZU","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":"a5b3490a8ec77d1785d53d1a3f68555d1f35bed4457712b25b072778454eadcf","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-12T10:55:57Z","title_canon_sha256":"cae321376e82b8f1d7eaa40602cb7ab63dead1603f4f360b9ff6f7c9a9df5f1a"},"schema_version":"1.0","source":{"id":"2412.09168","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.09168","created_at":"2026-07-05T09:48:20Z"},{"alias_kind":"arxiv_version","alias_value":"2412.09168v1","created_at":"2026-07-05T09:48:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.09168","created_at":"2026-07-05T09:48:20Z"},{"alias_kind":"pith_short_12","alias_value":"BS33F62ZL72W","created_at":"2026-07-05T09:48:20Z"},{"alias_kind":"pith_short_16","alias_value":"BS33F62ZL72WNUF7","created_at":"2026-07-05T09:48:20Z"},{"alias_kind":"pith_short_8","alias_value":"BS33F62Z","created_at":"2026-07-05T09:48:20Z"}],"graph_snapshots":[{"event_id":"sha256:5f8408261fe5f972dd959629bab714152093eb75c6d0bed4cff5f49f84034189","target":"graph","created_at":"2026-07-05T09:48:20Z","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/2412.09168/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generating sound effects for product-level videos, where only a small amount of labeled data is available for diverse scenes, requires the production of high-quality sounds in few-shot settings. To tackle the challenge of limited labeled data in real-world scenes, we introduce YingSound, a foundation model designed for video-guided sound generation that supports high-quality audio generation in few-shot settings. Specifically, YingSound consists of two major modules. The first module uses a conditional flow matching transformer to achieve effective semantic alignment in sound generation across","authors_text":"Chaofan Ding, Haomin Zhang, Haoyu Wang, Junjie Zheng, Lei Xie, Sizhe Shan, Wenjie Tian, Xinfa Zhu, Xinhan Di, Yihan Fan, Yihua Wang, Yunming Liang, Zihao Chen","cross_cats":["cs.CV","cs.MM","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-12T10:55:57Z","title":"YingSound: Video-Guided Sound Effects Generation with Multi-modal Chain-of-Thought Controls"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.09168","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":"sha256:99bb5f9f6ad7f5f4c380438f9d845014a3ff65fe4147c45fdc4a2a4f0cab710b","target":"record","created_at":"2026-07-05T09:48:20Z","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":"a5b3490a8ec77d1785d53d1a3f68555d1f35bed4457712b25b072778454eadcf","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-12-12T10:55:57Z","title_canon_sha256":"cae321376e82b8f1d7eaa40602cb7ab63dead1603f4f360b9ff6f7c9a9df5f1a"},"schema_version":"1.0","source":{"id":"2412.09168","kind":"arxiv","version":1}},"canonical_sha256":"0cb7b2fb595ff566d0bf473f5dd05bcd2cdaa160696a781f31b7ad8d0d2efe30","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0cb7b2fb595ff566d0bf473f5dd05bcd2cdaa160696a781f31b7ad8d0d2efe30","first_computed_at":"2026-07-05T09:48:20.525503Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:48:20.525503Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MxCDd77N3kd/6s7oIHTG1Trnq0ZP+EOL+c1kcEpxeqAcZJW+tHTA9dda1PjmbeZfklSwtFXNr47YT5w1NGW5Aw==","signature_status":"signed_v1","signed_at":"2026-07-05T09:48:20.525921Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.09168","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:99bb5f9f6ad7f5f4c380438f9d845014a3ff65fe4147c45fdc4a2a4f0cab710b","sha256:5f8408261fe5f972dd959629bab714152093eb75c6d0bed4cff5f49f84034189"],"state_sha256":"bd907f37fc7bb61d209551f4f2a20b217a6a013be8599a7d1b0ca73dc4e52579"}