{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:42UWX46XUXYEDC4E4INOBOJJ3Q","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"564b0d83d58a103831ddb9de7eb980d60abb93b458431c0c1a82e40c719e159b","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-03T03:23:11Z","title_canon_sha256":"d89592927535ffea53c97a8ce919e9bd7f1e16b9f63e49b7f94399f797e04fdd"},"schema_version":"1.0","source":{"id":"2507.02271","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.02271","created_at":"2026-07-05T11:31:14Z"},{"alias_kind":"arxiv_version","alias_value":"2507.02271v1","created_at":"2026-07-05T11:31:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.02271","created_at":"2026-07-05T11:31:14Z"},{"alias_kind":"pith_short_12","alias_value":"42UWX46XUXYE","created_at":"2026-07-05T11:31:14Z"},{"alias_kind":"pith_short_16","alias_value":"42UWX46XUXYEDC4E","created_at":"2026-07-05T11:31:14Z"},{"alias_kind":"pith_short_8","alias_value":"42UWX46X","created_at":"2026-07-05T11:31:14Z"}],"graph_snapshots":[{"event_id":"sha256:cec4b345aba47446cfe855102f809ac969c315460c382614220bab72961466a1","target":"graph","created_at":"2026-07-05T11:31:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2507.02271/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Bo Du, Feizhen Huang, Yutian Lin, Yu Wu","cross_cats":["cs.AI","cs.MM"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-03T03:23:11Z","title":"Spotlighting Partially Visible Cinematic Language for Video-to-Audio Generation via Self-distillation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.02271","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:66a6bc56676d5bdb587776f4214e0450f6f998762e146c0dba8ab04de348adcb","target":"record","created_at":"2026-07-05T11:31:14Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"564b0d83d58a103831ddb9de7eb980d60abb93b458431c0c1a82e40c719e159b","cross_cats_sorted":["cs.AI","cs.MM"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-03T03:23:11Z","title_canon_sha256":"d89592927535ffea53c97a8ce919e9bd7f1e16b9f63e49b7f94399f797e04fdd"},"schema_version":"1.0","source":{"id":"2507.02271","kind":"arxiv","version":1}},"canonical_sha256":"e6a96bf3d7a5f0418b84e21ae0b929dc2e0ab110a492e06fa4347464c90a6e5e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e6a96bf3d7a5f0418b84e21ae0b929dc2e0ab110a492e06fa4347464c90a6e5e","first_computed_at":"2026-07-05T11:31:14.874103Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:31:14.874103Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BTTDhYRNQRtesrz5uAmGskO/NnmPAu/vg3bd+dJBSDwumWCICz2XQ6RQtCxUPOQ2lo8CUlnANkSShIdV86OIBw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:31:14.874559Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.02271","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:66a6bc56676d5bdb587776f4214e0450f6f998762e146c0dba8ab04de348adcb","sha256:cec4b345aba47446cfe855102f809ac969c315460c382614220bab72961466a1"],"state_sha256":"4ed095a78c9b33eb25a761a5f7632f49aab341173b2f58db03a47745f524e941"}