{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JLEXOMXL25OOJD4MG3UUZVYI2V","short_pith_number":"pith:JLEXOMXL","schema_version":"1.0","canonical_sha256":"4ac97732ebd75ce48f8c36e94cd708d552c91f9f74d45c0ded2279a7d3f4ae99","source":{"kind":"arxiv","id":"2409.14709","version":1},"attestation_state":"computed","paper":{"title":"Video-to-Audio Generation with Fine-grained Temporal Semantics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Chenxing Li, Dong Yu, Rilin Chen, Yuchen Hu, Yu Gu","submitted_at":"2024-09-23T05:05:47Z","abstract_excerpt":"With recent advances of AIGC, video generation have gained a surge of research interest in both academia and industry (e.g., Sora). However, it remains a challenge to produce temporally aligned audio to synchronize the generated video, considering the complicated semantic information included in the latter. In this work, inspired by the recent success of text-to-audio (TTA) generation, we first investigate the video-to-audio (VTA) generation framework based on latent diffusion model (LDM). Similar to latest pioneering exploration in VTA, our preliminary results also show great potentials of LD"},"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":"2409.14709","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.AS","submitted_at":"2024-09-23T05:05:47Z","cross_cats_sorted":["cs.SD"],"title_canon_sha256":"96c694f50a1a9c57098fc599a306c4eba4ac35c22e110606b8d33df8f6290f10","abstract_canon_sha256":"fb4401132932fe1a9ed88310b6f80b811256ac1b3605cd86f644743455441f0c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:10:20.465124Z","signature_b64":"0IWF7Xq6YpXWD2YBEh59v3swfCPCTG/hRu7Ksr3jNTnOGzxbDQn93BjU/YMOyEi81qJTrixifE6puwkfLdDyCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ac97732ebd75ce48f8c36e94cd708d552c91f9f74d45c0ded2279a7d3f4ae99","last_reissued_at":"2026-07-05T09:10:20.464651Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:10:20.464651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Video-to-Audio Generation with Fine-grained Temporal Semantics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD"],"primary_cat":"eess.AS","authors_text":"Chenxing Li, Dong Yu, Rilin Chen, Yuchen Hu, Yu Gu","submitted_at":"2024-09-23T05:05:47Z","abstract_excerpt":"With recent advances of AIGC, video generation have gained a surge of research interest in both academia and industry (e.g., Sora). However, it remains a challenge to produce temporally aligned audio to synchronize the generated video, considering the complicated semantic information included in the latter. In this work, inspired by the recent success of text-to-audio (TTA) generation, we first investigate the video-to-audio (VTA) generation framework based on latent diffusion model (LDM). Similar to latest pioneering exploration in VTA, our preliminary results also show great potentials of LD"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.14709","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/2409.14709/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":"2409.14709","created_at":"2026-07-05T09:10:20.464715+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.14709v1","created_at":"2026-07-05T09:10:20.464715+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.14709","created_at":"2026-07-05T09:10:20.464715+00:00"},{"alias_kind":"pith_short_12","alias_value":"JLEXOMXL25OO","created_at":"2026-07-05T09:10:20.464715+00:00"},{"alias_kind":"pith_short_16","alias_value":"JLEXOMXL25OOJD4M","created_at":"2026-07-05T09:10:20.464715+00:00"},{"alias_kind":"pith_short_8","alias_value":"JLEXOMXL","created_at":"2026-07-05T09:10:20.464715+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.30073","citing_title":"Native Audio-Visual Alignment for Generation","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2603.19857","citing_title":"FoleyDirector: Fine-Grained Temporal Steering for Video-to-Audio Generation via Structured Scripts","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12335","citing_title":"All in One: A Unified Synthetic Data Pipeline for Multimodal Video Understanding","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JLEXOMXL25OOJD4MG3UUZVYI2V","json":"https://pith.science/pith/JLEXOMXL25OOJD4MG3UUZVYI2V.json","graph_json":"https://pith.science/api/pith-number/JLEXOMXL25OOJD4MG3UUZVYI2V/graph.json","events_json":"https://pith.science/api/pith-number/JLEXOMXL25OOJD4MG3UUZVYI2V/events.json","paper":"https://pith.science/paper/JLEXOMXL"},"agent_actions":{"view_html":"https://pith.science/pith/JLEXOMXL25OOJD4MG3UUZVYI2V","download_json":"https://pith.science/pith/JLEXOMXL25OOJD4MG3UUZVYI2V.json","view_paper":"https://pith.science/paper/JLEXOMXL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.14709&json=true","fetch_graph":"https://pith.science/api/pith-number/JLEXOMXL25OOJD4MG3UUZVYI2V/graph.json","fetch_events":"https://pith.science/api/pith-number/JLEXOMXL25OOJD4MG3UUZVYI2V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JLEXOMXL25OOJD4MG3UUZVYI2V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JLEXOMXL25OOJD4MG3UUZVYI2V/action/storage_attestation","attest_author":"https://pith.science/pith/JLEXOMXL25OOJD4MG3UUZVYI2V/action/author_attestation","sign_citation":"https://pith.science/pith/JLEXOMXL25OOJD4MG3UUZVYI2V/action/citation_signature","submit_replication":"https://pith.science/pith/JLEXOMXL25OOJD4MG3UUZVYI2V/action/replication_record"}},"created_at":"2026-07-05T09:10:20.464715+00:00","updated_at":"2026-07-05T09:10:20.464715+00:00"}