{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:FMD3ZOFDZEA42D23TYGGOEEHEL","short_pith_number":"pith:FMD3ZOFD","schema_version":"1.0","canonical_sha256":"2b07bcb8a3c901cd0f5b9e0c67108722f9d0d3f031c7f65d7e6a189d382cef99","source":{"kind":"arxiv","id":"2407.07464","version":3},"attestation_state":"computed","paper":{"title":"Video-to-Audio Generation with Hidden Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chenxing Li, Dong Yu, Manjie Xu, Rilin Chen, Wei Liang, Xinyi Tu, Yong Ren, Yu Gu","submitted_at":"2024-07-10T08:40:39Z","abstract_excerpt":"Generating semantically and temporally aligned audio content in accordance with video input has become a focal point for researchers, particularly following the remarkable breakthrough in text-to-video generation. In this work, we aim to offer insights into the video-to-audio generation paradigm, focusing on three crucial aspects: vision encoders, auxiliary embeddings, and data augmentation techniques. Beginning with a foundational model built on a simple yet surprisingly effective intuition, we explore various vision encoders and auxiliary embeddings through ablation studies. Employing a comp"},"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":"2407.07464","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-07-10T08:40:39Z","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"title_canon_sha256":"d08a263c71f663c40420cfc605ffabd8cec7c634f5da7d8211efb15d9b805566","abstract_canon_sha256":"851653390f3a15e440f1078f4a4f5b3a74425e2562c67018e23543f5cb8a5235"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:19.046817Z","signature_b64":"IFb9mszeiSegBtmjpx1W2ORgT6nFCvR+BulVaZ7BeuBoRXd6GGfx3eh7t9jd0jmS2cVt6IXE+WwnP+Y2Ek5bDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b07bcb8a3c901cd0f5b9e0c67108722f9d0d3f031c7f65d7e6a189d382cef99","last_reissued_at":"2026-07-05T10:28:19.046327Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:19.046327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Video-to-Audio Generation with Hidden Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chenxing Li, Dong Yu, Manjie Xu, Rilin Chen, Wei Liang, Xinyi Tu, Yong Ren, Yu Gu","submitted_at":"2024-07-10T08:40:39Z","abstract_excerpt":"Generating semantically and temporally aligned audio content in accordance with video input has become a focal point for researchers, particularly following the remarkable breakthrough in text-to-video generation. In this work, we aim to offer insights into the video-to-audio generation paradigm, focusing on three crucial aspects: vision encoders, auxiliary embeddings, and data augmentation techniques. Beginning with a foundational model built on a simple yet surprisingly effective intuition, we explore various vision encoders and auxiliary embeddings through ablation studies. Employing a comp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.07464","kind":"arxiv","version":3},"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/2407.07464/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":"2407.07464","created_at":"2026-07-05T10:28:19.046386+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.07464v3","created_at":"2026-07-05T10:28:19.046386+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.07464","created_at":"2026-07-05T10:28:19.046386+00:00"},{"alias_kind":"pith_short_12","alias_value":"FMD3ZOFDZEA4","created_at":"2026-07-05T10:28:19.046386+00:00"},{"alias_kind":"pith_short_16","alias_value":"FMD3ZOFDZEA42D23","created_at":"2026-07-05T10:28:19.046386+00:00"},{"alias_kind":"pith_short_8","alias_value":"FMD3ZOFD","created_at":"2026-07-05T10:28:19.046386+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"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":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30940","citing_title":"Towards Streaming Synchronized Spatial Audio Generation via Autoregressive Diffusion Transformer","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30339","citing_title":"Benchmarking Single-Factor Physical Video-to-Audio Generation","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2509.23727","citing_title":"AudioMoG: Guiding Audio Generation with Mixture-of-Guidance","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23909","citing_title":"AMAVA: Adaptive Motion-Aware Video-to-Audio Framework for Visually-Impaired Assistance","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2410.13720","citing_title":"Movie Gen: A Cast of Media Foundation Models","ref_index":76,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FMD3ZOFDZEA42D23TYGGOEEHEL","json":"https://pith.science/pith/FMD3ZOFDZEA42D23TYGGOEEHEL.json","graph_json":"https://pith.science/api/pith-number/FMD3ZOFDZEA42D23TYGGOEEHEL/graph.json","events_json":"https://pith.science/api/pith-number/FMD3ZOFDZEA42D23TYGGOEEHEL/events.json","paper":"https://pith.science/paper/FMD3ZOFD"},"agent_actions":{"view_html":"https://pith.science/pith/FMD3ZOFDZEA42D23TYGGOEEHEL","download_json":"https://pith.science/pith/FMD3ZOFDZEA42D23TYGGOEEHEL.json","view_paper":"https://pith.science/paper/FMD3ZOFD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.07464&json=true","fetch_graph":"https://pith.science/api/pith-number/FMD3ZOFDZEA42D23TYGGOEEHEL/graph.json","fetch_events":"https://pith.science/api/pith-number/FMD3ZOFDZEA42D23TYGGOEEHEL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FMD3ZOFDZEA42D23TYGGOEEHEL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FMD3ZOFDZEA42D23TYGGOEEHEL/action/storage_attestation","attest_author":"https://pith.science/pith/FMD3ZOFDZEA42D23TYGGOEEHEL/action/author_attestation","sign_citation":"https://pith.science/pith/FMD3ZOFDZEA42D23TYGGOEEHEL/action/citation_signature","submit_replication":"https://pith.science/pith/FMD3ZOFDZEA42D23TYGGOEEHEL/action/replication_record"}},"created_at":"2026-07-05T10:28:19.046386+00:00","updated_at":"2026-07-05T10:28:19.046386+00:00"}