{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:P2TDLSYZWBXY72BQ3AFZIAEPET","short_pith_number":"pith:P2TDLSYZ","schema_version":"1.0","canonical_sha256":"7ea635cb19b06f8fe830d80b94008f24d0ed4711a907b633566564ed7b1d28ac","source":{"kind":"arxiv","id":"2306.17203","version":1},"attestation_state":"computed","paper":{"title":"Diff-Foley: Synchronized Video-to-Audio Synthesis with Latent Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chenxu Hu, Chuanhao Yan, Hang Zhao, Simian Luo","submitted_at":"2023-06-29T12:39:58Z","abstract_excerpt":"The Video-to-Audio (V2A) model has recently gained attention for its practical application in generating audio directly from silent videos, particularly in video/film production. However, previous methods in V2A have limited generation quality in terms of temporal synchronization and audio-visual relevance. We present Diff-Foley, a synchronized Video-to-Audio synthesis method with a latent diffusion model (LDM) that generates high-quality audio with improved synchronization and audio-visual relevance. We adopt contrastive audio-visual pretraining (CAVP) to learn more temporally and semanticall"},"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":"2306.17203","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2023-06-29T12:39:58Z","cross_cats_sorted":["cs.CV","cs.LG","eess.AS"],"title_canon_sha256":"738f6bd004be43b211f3ca083606e28b8845e72ee4701349c6ee5f2daee05b8b","abstract_canon_sha256":"5abb9bc6981dbad4a378869fdbf9a74bc54130277f2770be0ddb06e0929ac751"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:26:23.346485Z","signature_b64":"COgXOZb2BLlz32XFm0YLhvPsuu/URaE5HF8Bz8ofkiiCGJNlRQNp3UB8EikM3UXLkgSDuH9DCzQ5YUjZwZ3KCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ea635cb19b06f8fe830d80b94008f24d0ed4711a907b633566564ed7b1d28ac","last_reissued_at":"2026-07-05T06:26:23.345970Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:26:23.345970Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diff-Foley: Synchronized Video-to-Audio Synthesis with Latent Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chenxu Hu, Chuanhao Yan, Hang Zhao, Simian Luo","submitted_at":"2023-06-29T12:39:58Z","abstract_excerpt":"The Video-to-Audio (V2A) model has recently gained attention for its practical application in generating audio directly from silent videos, particularly in video/film production. However, previous methods in V2A have limited generation quality in terms of temporal synchronization and audio-visual relevance. We present Diff-Foley, a synchronized Video-to-Audio synthesis method with a latent diffusion model (LDM) that generates high-quality audio with improved synchronization and audio-visual relevance. We adopt contrastive audio-visual pretraining (CAVP) to learn more temporally and semanticall"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2306.17203","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/2306.17203/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":"2306.17203","created_at":"2026-07-05T06:26:23.346029+00:00"},{"alias_kind":"arxiv_version","alias_value":"2306.17203v1","created_at":"2026-07-05T06:26:23.346029+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2306.17203","created_at":"2026-07-05T06:26:23.346029+00:00"},{"alias_kind":"pith_short_12","alias_value":"P2TDLSYZWBXY","created_at":"2026-07-05T06:26:23.346029+00:00"},{"alias_kind":"pith_short_16","alias_value":"P2TDLSYZWBXY72BQ","created_at":"2026-07-05T06:26:23.346029+00:00"},{"alias_kind":"pith_short_8","alias_value":"P2TDLSYZ","created_at":"2026-07-05T06:26:23.346029+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.26244","citing_title":"LongAV-Compass: Towards Unified Evaluation of Minute-Scale Audio-Visual Generation Across T2AV, I2AV, and V2AV","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2601.02731","citing_title":"Omni2Sound: Towards Unified Video-Text-to-Audio Generation","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P2TDLSYZWBXY72BQ3AFZIAEPET","json":"https://pith.science/pith/P2TDLSYZWBXY72BQ3AFZIAEPET.json","graph_json":"https://pith.science/api/pith-number/P2TDLSYZWBXY72BQ3AFZIAEPET/graph.json","events_json":"https://pith.science/api/pith-number/P2TDLSYZWBXY72BQ3AFZIAEPET/events.json","paper":"https://pith.science/paper/P2TDLSYZ"},"agent_actions":{"view_html":"https://pith.science/pith/P2TDLSYZWBXY72BQ3AFZIAEPET","download_json":"https://pith.science/pith/P2TDLSYZWBXY72BQ3AFZIAEPET.json","view_paper":"https://pith.science/paper/P2TDLSYZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2306.17203&json=true","fetch_graph":"https://pith.science/api/pith-number/P2TDLSYZWBXY72BQ3AFZIAEPET/graph.json","fetch_events":"https://pith.science/api/pith-number/P2TDLSYZWBXY72BQ3AFZIAEPET/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P2TDLSYZWBXY72BQ3AFZIAEPET/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P2TDLSYZWBXY72BQ3AFZIAEPET/action/storage_attestation","attest_author":"https://pith.science/pith/P2TDLSYZWBXY72BQ3AFZIAEPET/action/author_attestation","sign_citation":"https://pith.science/pith/P2TDLSYZWBXY72BQ3AFZIAEPET/action/citation_signature","submit_replication":"https://pith.science/pith/P2TDLSYZWBXY72BQ3AFZIAEPET/action/replication_record"}},"created_at":"2026-07-05T06:26:23.346029+00:00","updated_at":"2026-07-05T06:26:23.346029+00:00"}