{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:3HHETYAFWHWMKJPDNKEWBBDXBG","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":"b70c676d685a1f503dbcc4468eed8b274492571d1015ed24d48918e4ddddabba","cross_cats_sorted":["cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-15T18:51:18Z","title_canon_sha256":"edff315c1b5fb907ac89914284c98640c7cc2ee5bc9973511380bf667a7b19bf"},"schema_version":"1.0","source":{"id":"2409.09823","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.09823","created_at":"2026-07-05T09:07:15Z"},{"alias_kind":"arxiv_version","alias_value":"2409.09823v1","created_at":"2026-07-05T09:07:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.09823","created_at":"2026-07-05T09:07:15Z"},{"alias_kind":"pith_short_12","alias_value":"3HHETYAFWHWM","created_at":"2026-07-05T09:07:15Z"},{"alias_kind":"pith_short_16","alias_value":"3HHETYAFWHWMKJPD","created_at":"2026-07-05T09:07:15Z"},{"alias_kind":"pith_short_8","alias_value":"3HHETYAF","created_at":"2026-07-05T09:07:15Z"}],"graph_snapshots":[{"event_id":"sha256:684664de7cd7bba06290ea5c2de01c52cfdf5174cb74fcb7198b5ad905ea607b","target":"graph","created_at":"2026-07-05T09:07:15Z","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/2409.09823/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Video-to-audio (V2A) generation aims to produce corresponding audio given silent video inputs. This task is particularly challenging due to the cross-modality and sequential nature of the audio-visual features involved. Recent works have made significant progress in bridging the domain gap between video and audio, generating audio that is semantically aligned with the video content. However, a critical limitation of these approaches is their inability to effectively recognize and handle multiple scenes within a video, often leading to suboptimal audio generation in such cases. In this paper, w","authors_text":"Mingjing Yi, Ming Li","cross_cats":["cs.MM","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-15T18:51:18Z","title":"Efficient Video to Audio Mapper with Visual Scene Detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.09823","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":"sha256:98327f9d504d57140cda6c5d6a924229b664a1c93e4a7646018ce470dfe2f0fd","target":"record","created_at":"2026-07-05T09:07:15Z","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":"b70c676d685a1f503dbcc4468eed8b274492571d1015ed24d48918e4ddddabba","cross_cats_sorted":["cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-15T18:51:18Z","title_canon_sha256":"edff315c1b5fb907ac89914284c98640c7cc2ee5bc9973511380bf667a7b19bf"},"schema_version":"1.0","source":{"id":"2409.09823","kind":"arxiv","version":1}},"canonical_sha256":"d9ce49e005b1ecc525e36a8960847709a2d8e54b72cbb4ba9b3a19553f4aa981","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d9ce49e005b1ecc525e36a8960847709a2d8e54b72cbb4ba9b3a19553f4aa981","first_computed_at":"2026-07-05T09:07:15.311299Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:07:15.311299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LL8JLRX68a19y1uVAx3ssKSxKXWFa6uJzisrY1kThkZVCsvd/O7b+EBT1Ed8IIqpvDdbt5M5IL2aXrRBPdghAg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:07:15.311734Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.09823","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:98327f9d504d57140cda6c5d6a924229b664a1c93e4a7646018ce470dfe2f0fd","sha256:684664de7cd7bba06290ea5c2de01c52cfdf5174cb74fcb7198b5ad905ea607b"],"state_sha256":"11200ee5fe051251f06aa60adcfa8308303afe89d3dc99d151439b77cb8231eb"}