{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:STZV345FKEKWXIYROT6HWZWSYA","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":"dd0b21d1848de9cc250d1a568b505d6629b74ee5063de7a9cd7bc009b0f0477e","cross_cats_sorted":["cs.CV","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-08-23T07:30:18Z","title_canon_sha256":"dfcf86467e1ad2d818d662307471f7207f38910ce04216b276d7b390970f31e3"},"schema_version":"1.0","source":{"id":"2508.16930","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.16930","created_at":"2026-07-05T11:58:06Z"},{"alias_kind":"arxiv_version","alias_value":"2508.16930v1","created_at":"2026-07-05T11:58:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.16930","created_at":"2026-07-05T11:58:06Z"},{"alias_kind":"pith_short_12","alias_value":"STZV345FKEKW","created_at":"2026-07-05T11:58:06Z"},{"alias_kind":"pith_short_16","alias_value":"STZV345FKEKWXIYR","created_at":"2026-07-05T11:58:06Z"},{"alias_kind":"pith_short_8","alias_value":"STZV345F","created_at":"2026-07-05T11:58:06Z"}],"graph_snapshots":[{"event_id":"sha256:2bf95a55f1b4fb4820e72ec011f366ee80c19a0aa7dc57d0333a8b2fa8d0055d","target":"graph","created_at":"2026-07-05T11:58:06Z","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/2508.16930/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advances in video generation produce visually realistic content, yet the absence of synchronized audio severely compromises immersion. To address key challenges in video-to-audio generation, including multimodal data scarcity, modality imbalance and limited audio quality in existing methods, we propose HunyuanVideo-Foley, an end-to-end text-video-to-audio framework that synthesizes high-fidelity audio precisely aligned with visual dynamics and semantic context. Our approach incorporates three core innovations: (1) a scalable data pipeline curating 100k-hour multimodal datasets through a","authors_text":"Jin Zhou, Miles Yang, Qiulin Li, Qun Yang, Sizhe Shan, Yuehai Wang, Yutao Cui, Zhao Zhong","cross_cats":["cs.CV","cs.SD"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-08-23T07:30:18Z","title":"HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.16930","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:fd6dba829e5cd558511686e92b0c3fc86fc3d4c7e3d16fdaa49c5df9669d5a2c","target":"record","created_at":"2026-07-05T11:58:06Z","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":"dd0b21d1848de9cc250d1a568b505d6629b74ee5063de7a9cd7bc009b0f0477e","cross_cats_sorted":["cs.CV","cs.SD"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-08-23T07:30:18Z","title_canon_sha256":"dfcf86467e1ad2d818d662307471f7207f38910ce04216b276d7b390970f31e3"},"schema_version":"1.0","source":{"id":"2508.16930","kind":"arxiv","version":1}},"canonical_sha256":"94f35df3a551156ba31174fc7b66d2c036e512b9f9f77873eb7d6e8793b20aea","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"94f35df3a551156ba31174fc7b66d2c036e512b9f9f77873eb7d6e8793b20aea","first_computed_at":"2026-07-05T11:58:06.582049Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:58:06.582049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"5bdP1a6gve6BG7hv6aQL99ygnE8hMuNH3lJiDABLh175bOJ7w1E05LXbaA9u/uqzzZnPBZ88ZDq22QcWf3YvDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:58:06.582490Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.16930","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fd6dba829e5cd558511686e92b0c3fc86fc3d4c7e3d16fdaa49c5df9669d5a2c","sha256:2bf95a55f1b4fb4820e72ec011f366ee80c19a0aa7dc57d0333a8b2fa8d0055d"],"state_sha256":"98ddc832a7301e30ef8972876418ec2a6bac0d4d26eaf0fb553abac7bfc0feae"}