{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:42UWX46XUXYEDC4E4INOBOJJ3Q","short_pith_number":"pith:42UWX46X","schema_version":"1.0","canonical_sha256":"e6a96bf3d7a5f0418b84e21ae0b929dc2e0ab110a492e06fa4347464c90a6e5e","source":{"kind":"arxiv","id":"2507.02271","version":1},"attestation_state":"computed","paper":{"title":"Spotlighting Partially Visible Cinematic Language for Video-to-Audio Generation via Self-distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Bo Du, Feizhen Huang, Yutian Lin, Yu Wu","submitted_at":"2025-07-03T03:23:11Z","abstract_excerpt":"Video-to-Audio (V2A) Generation achieves significant progress and plays a crucial role in film and video post-production. However, current methods overlook the cinematic language, a critical component of artistic expression in filmmaking. As a result, their performance deteriorates in scenarios where Foley targets are only partially visible. To address this challenge, we propose a simple self-distillation approach to extend V2A models to cinematic language scenarios. By simulating the cinematic language variations, the student model learns to align the video features of training pairs with the"},"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":"2507.02271","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-03T03:23:11Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"d89592927535ffea53c97a8ce919e9bd7f1e16b9f63e49b7f94399f797e04fdd","abstract_canon_sha256":"564b0d83d58a103831ddb9de7eb980d60abb93b458431c0c1a82e40c719e159b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:31:14.874559Z","signature_b64":"BTTDhYRNQRtesrz5uAmGskO/NnmPAu/vg3bd+dJBSDwumWCICz2XQ6RQtCxUPOQ2lo8CUlnANkSShIdV86OIBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6a96bf3d7a5f0418b84e21ae0b929dc2e0ab110a492e06fa4347464c90a6e5e","last_reissued_at":"2026-07-05T11:31:14.874103Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:31:14.874103Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Spotlighting Partially Visible Cinematic Language for Video-to-Audio Generation via Self-distillation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Bo Du, Feizhen Huang, Yutian Lin, Yu Wu","submitted_at":"2025-07-03T03:23:11Z","abstract_excerpt":"Video-to-Audio (V2A) Generation achieves significant progress and plays a crucial role in film and video post-production. However, current methods overlook the cinematic language, a critical component of artistic expression in filmmaking. As a result, their performance deteriorates in scenarios where Foley targets are only partially visible. To address this challenge, we propose a simple self-distillation approach to extend V2A models to cinematic language scenarios. By simulating the cinematic language variations, the student model learns to align the video features of training pairs with the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02271","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/2507.02271/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":"2507.02271","created_at":"2026-07-05T11:31:14.874172+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.02271v1","created_at":"2026-07-05T11:31:14.874172+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02271","created_at":"2026-07-05T11:31:14.874172+00:00"},{"alias_kind":"pith_short_12","alias_value":"42UWX46XUXYE","created_at":"2026-07-05T11:31:14.874172+00:00"},{"alias_kind":"pith_short_16","alias_value":"42UWX46XUXYEDC4E","created_at":"2026-07-05T11:31:14.874172+00:00"},{"alias_kind":"pith_short_8","alias_value":"42UWX46X","created_at":"2026-07-05T11:31:14.874172+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/42UWX46XUXYEDC4E4INOBOJJ3Q","json":"https://pith.science/pith/42UWX46XUXYEDC4E4INOBOJJ3Q.json","graph_json":"https://pith.science/api/pith-number/42UWX46XUXYEDC4E4INOBOJJ3Q/graph.json","events_json":"https://pith.science/api/pith-number/42UWX46XUXYEDC4E4INOBOJJ3Q/events.json","paper":"https://pith.science/paper/42UWX46X"},"agent_actions":{"view_html":"https://pith.science/pith/42UWX46XUXYEDC4E4INOBOJJ3Q","download_json":"https://pith.science/pith/42UWX46XUXYEDC4E4INOBOJJ3Q.json","view_paper":"https://pith.science/paper/42UWX46X","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.02271&json=true","fetch_graph":"https://pith.science/api/pith-number/42UWX46XUXYEDC4E4INOBOJJ3Q/graph.json","fetch_events":"https://pith.science/api/pith-number/42UWX46XUXYEDC4E4INOBOJJ3Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/42UWX46XUXYEDC4E4INOBOJJ3Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/42UWX46XUXYEDC4E4INOBOJJ3Q/action/storage_attestation","attest_author":"https://pith.science/pith/42UWX46XUXYEDC4E4INOBOJJ3Q/action/author_attestation","sign_citation":"https://pith.science/pith/42UWX46XUXYEDC4E4INOBOJJ3Q/action/citation_signature","submit_replication":"https://pith.science/pith/42UWX46XUXYEDC4E4INOBOJJ3Q/action/replication_record"}},"created_at":"2026-07-05T11:31:14.874172+00:00","updated_at":"2026-07-05T11:31:14.874172+00:00"}