{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:STZV345FKEKWXIYROT6HWZWSYA","short_pith_number":"pith:STZV345F","schema_version":"1.0","canonical_sha256":"94f35df3a551156ba31174fc7b66d2c036e512b9f9f77873eb7d6e8793b20aea","source":{"kind":"arxiv","id":"2508.16930","version":1},"attestation_state":"computed","paper":{"title":"HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.SD"],"primary_cat":"eess.AS","authors_text":"Jin Zhou, Miles Yang, Qiulin Li, Qun Yang, Sizhe Shan, Yuehai Wang, Yutao Cui, Zhao Zhong","submitted_at":"2025-08-23T07:30:18Z","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"},"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":"2508.16930","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2025-08-23T07:30:18Z","cross_cats_sorted":["cs.CV","cs.SD"],"title_canon_sha256":"dfcf86467e1ad2d818d662307471f7207f38910ce04216b276d7b390970f31e3","abstract_canon_sha256":"dd0b21d1848de9cc250d1a568b505d6629b74ee5063de7a9cd7bc009b0f0477e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:58:06.582490Z","signature_b64":"5bdP1a6gve6BG7hv6aQL99ygnE8hMuNH3lJiDABLh175bOJ7w1E05LXbaA9u/uqzzZnPBZ88ZDq22QcWf3YvDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94f35df3a551156ba31174fc7b66d2c036e512b9f9f77873eb7d6e8793b20aea","last_reissued_at":"2026-07-05T11:58:06.582049Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:58:06.582049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HunyuanVideo-Foley: Multimodal Diffusion with Representation Alignment for High-Fidelity Foley Audio Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.SD"],"primary_cat":"eess.AS","authors_text":"Jin Zhou, Miles Yang, Qiulin Li, Qun Yang, Sizhe Shan, Yuehai Wang, Yutao Cui, Zhao Zhong","submitted_at":"2025-08-23T07:30:18Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.16930","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/2508.16930/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":"2508.16930","created_at":"2026-07-05T11:58:06.582110+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.16930v1","created_at":"2026-07-05T11:58:06.582110+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.16930","created_at":"2026-07-05T11:58:06.582110+00:00"},{"alias_kind":"pith_short_12","alias_value":"STZV345FKEKW","created_at":"2026-07-05T11:58:06.582110+00:00"},{"alias_kind":"pith_short_16","alias_value":"STZV345FKEKWXIYR","created_at":"2026-07-05T11:58:06.582110+00:00"},{"alias_kind":"pith_short_8","alias_value":"STZV345F","created_at":"2026-07-05T11:58:06.582110+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":22,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03672","citing_title":"Foley-Omni: A Unified Multimodal Generation Model from Task-Level Audio Synthesis to Complete Video Soundtrack Generation","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.03168","citing_title":"JAVEDIT: Joint Audio-Visual Instruction-Guided Video Editing with Agentic Data Curation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30965","citing_title":"ImmersiveTTS: Environment-Aware Text-to-Speech with Multimodal Diffusion Transformer and Domain-Specific Representation Alignment","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18916","citing_title":"CounterFlow: A Two-Phase Inference-Time Sampling for Counterfactual Video Foley Generation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24652","citing_title":"AVBench: Human-Aligned and Automated Evaluation Benchmark for Audio-Video Generative Models","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25193","citing_title":"SpongeBob: Sync-Aware Harmonious Audio-Visual Generative Editing","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29473","citing_title":"MAVIN: Multi-Shot Audio-Visual Generation with Narrative Control","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30339","citing_title":"Benchmarking Single-Factor Physical Video-to-Audio Generation","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2512.23994","citing_title":"PhyAVBench: A Challenging Audio Physics-Sensitivity Benchmark for Physically Grounded Text-to-Audio-Video Generation","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17488","citing_title":"Omni-Customizer: End-to-End MultiModal Customization for Joint Audio-Video Generation","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18749","citing_title":"WavFlow: Audio Generation in Waveform Space","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18916","citing_title":"CounterFlow: A Two-Phase Inference-Time Sampling for Counterfactual Video Foley Generation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2512.00336","citing_title":"MVAD: A Benchmark Dataset for Multimodal AI-Generated Video-Audio Detection","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2512.09299","citing_title":"VABench: A Comprehensive Benchmark for Audio-Video Generation","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2512.10571","citing_title":"AVI-Edit: Audio-sync Video Instance Editing with Granularity-Aware Mask Refiner","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2512.23994","citing_title":"PhyAVBench: A Challenging Audio Physics-Sensitivity Benchmark for Physically Grounded Text-to-Audio-Video Generation","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2601.02731","citing_title":"Omni2Sound: Towards Unified Video-Text-to-Audio Generation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01809","citing_title":"TMD-Bench: A Multi-Level Evaluation Paradigm for Music-Dance Co-Generation","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10542","citing_title":"VidAudio-Bench: Benchmarking V2A and VT2A Generation across Four Audio Categories","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09057","citing_title":"Tora3: Trajectory-Guided Audio-Video Generation with Physical Coherence","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04348","citing_title":"OmniSonic: Towards Universal and Holistic Audio Generation from Video and Text","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15086","citing_title":"ControlFoley: Unified and Controllable Video-to-Audio Generation with Cross-Modal Conflict Handling","ref_index":39,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/STZV345FKEKWXIYROT6HWZWSYA","json":"https://pith.science/pith/STZV345FKEKWXIYROT6HWZWSYA.json","graph_json":"https://pith.science/api/pith-number/STZV345FKEKWXIYROT6HWZWSYA/graph.json","events_json":"https://pith.science/api/pith-number/STZV345FKEKWXIYROT6HWZWSYA/events.json","paper":"https://pith.science/paper/STZV345F"},"agent_actions":{"view_html":"https://pith.science/pith/STZV345FKEKWXIYROT6HWZWSYA","download_json":"https://pith.science/pith/STZV345FKEKWXIYROT6HWZWSYA.json","view_paper":"https://pith.science/paper/STZV345F","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.16930&json=true","fetch_graph":"https://pith.science/api/pith-number/STZV345FKEKWXIYROT6HWZWSYA/graph.json","fetch_events":"https://pith.science/api/pith-number/STZV345FKEKWXIYROT6HWZWSYA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/STZV345FKEKWXIYROT6HWZWSYA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/STZV345FKEKWXIYROT6HWZWSYA/action/storage_attestation","attest_author":"https://pith.science/pith/STZV345FKEKWXIYROT6HWZWSYA/action/author_attestation","sign_citation":"https://pith.science/pith/STZV345FKEKWXIYROT6HWZWSYA/action/citation_signature","submit_replication":"https://pith.science/pith/STZV345FKEKWXIYROT6HWZWSYA/action/replication_record"}},"created_at":"2026-07-05T11:58:06.582110+00:00","updated_at":"2026-07-05T11:58:06.582110+00:00"}