{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3HHETYAFWHWMKJPDNKEWBBDXBG","short_pith_number":"pith:3HHETYAF","schema_version":"1.0","canonical_sha256":"d9ce49e005b1ecc525e36a8960847709a2d8e54b72cbb4ba9b3a19553f4aa981","source":{"kind":"arxiv","id":"2409.09823","version":1},"attestation_state":"computed","paper":{"title":"Efficient Video to Audio Mapper with Visual Scene Detection","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Mingjing Yi, Ming Li","submitted_at":"2024-09-15T18:51:18Z","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"},"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":"2409.09823","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.SD","submitted_at":"2024-09-15T18:51:18Z","cross_cats_sorted":["cs.MM","eess.AS"],"title_canon_sha256":"edff315c1b5fb907ac89914284c98640c7cc2ee5bc9973511380bf667a7b19bf","abstract_canon_sha256":"b70c676d685a1f503dbcc4468eed8b274492571d1015ed24d48918e4ddddabba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:07:15.311734Z","signature_b64":"LL8JLRX68a19y1uVAx3ssKSxKXWFa6uJzisrY1kThkZVCsvd/O7b+EBT1Ed8IIqpvDdbt5M5IL2aXrRBPdghAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9ce49e005b1ecc525e36a8960847709a2d8e54b72cbb4ba9b3a19553f4aa981","last_reissued_at":"2026-07-05T09:07:15.311299Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:07:15.311299Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient Video to Audio Mapper with Visual Scene Detection","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Mingjing Yi, Ming Li","submitted_at":"2024-09-15T18:51:18Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.09823","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/2409.09823/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":"2409.09823","created_at":"2026-07-05T09:07:15.311370+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.09823v1","created_at":"2026-07-05T09:07:15.311370+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.09823","created_at":"2026-07-05T09:07:15.311370+00:00"},{"alias_kind":"pith_short_12","alias_value":"3HHETYAFWHWM","created_at":"2026-07-05T09:07:15.311370+00:00"},{"alias_kind":"pith_short_16","alias_value":"3HHETYAFWHWMKJPD","created_at":"2026-07-05T09:07:15.311370+00:00"},{"alias_kind":"pith_short_8","alias_value":"3HHETYAF","created_at":"2026-07-05T09:07:15.311370+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.18314","citing_title":"AGAV-Rater: Adapting Large Multimodal Model for AI-Generated Audio-Visual Quality Assessment","ref_index":63,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3HHETYAFWHWMKJPDNKEWBBDXBG","json":"https://pith.science/pith/3HHETYAFWHWMKJPDNKEWBBDXBG.json","graph_json":"https://pith.science/api/pith-number/3HHETYAFWHWMKJPDNKEWBBDXBG/graph.json","events_json":"https://pith.science/api/pith-number/3HHETYAFWHWMKJPDNKEWBBDXBG/events.json","paper":"https://pith.science/paper/3HHETYAF"},"agent_actions":{"view_html":"https://pith.science/pith/3HHETYAFWHWMKJPDNKEWBBDXBG","download_json":"https://pith.science/pith/3HHETYAFWHWMKJPDNKEWBBDXBG.json","view_paper":"https://pith.science/paper/3HHETYAF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.09823&json=true","fetch_graph":"https://pith.science/api/pith-number/3HHETYAFWHWMKJPDNKEWBBDXBG/graph.json","fetch_events":"https://pith.science/api/pith-number/3HHETYAFWHWMKJPDNKEWBBDXBG/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3HHETYAFWHWMKJPDNKEWBBDXBG/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3HHETYAFWHWMKJPDNKEWBBDXBG/action/storage_attestation","attest_author":"https://pith.science/pith/3HHETYAFWHWMKJPDNKEWBBDXBG/action/author_attestation","sign_citation":"https://pith.science/pith/3HHETYAFWHWMKJPDNKEWBBDXBG/action/citation_signature","submit_replication":"https://pith.science/pith/3HHETYAFWHWMKJPDNKEWBBDXBG/action/replication_record"}},"created_at":"2026-07-05T09:07:15.311370+00:00","updated_at":"2026-07-05T09:07:15.311370+00:00"}