{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ZLKKDHNLLDDPETBBTQD7QJ33MB","short_pith_number":"pith:ZLKKDHNL","schema_version":"1.0","canonical_sha256":"cad4a19dab58c6f24c219c07f8277b60508251e748377d2673240f2cd7156644","source":{"kind":"arxiv","id":"2404.16305","version":2},"attestation_state":"computed","paper":{"title":"Semantically consistent Video-to-Audio Generation using Multimodal Language Large Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Gehui Chen, Guan'an Wang, Jitao Sang, Xiaowen Huang","submitted_at":"2024-04-25T03:14:49Z","abstract_excerpt":"Existing works have made strides in video generation, but the lack of sound effects (SFX) and background music (BGM) hinders a complete and immersive viewer experience. We introduce a novel semantically consistent v ideo-to-audio generation framework, namely SVA, which automatically generates audio semantically consistent with the given video content. The framework harnesses the power of multimodal large language model (MLLM) to understand video semantics from a key frame and generate creative audio schemes, which are then utilized as prompts for text-to-audio models, resulting in video-to-aud"},"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":"2404.16305","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-04-25T03:14:49Z","cross_cats_sorted":["cs.SD","eess.AS"],"title_canon_sha256":"94777d0c434c783fa812d3ca64974046e02176737c13ecface79295db5912ace","abstract_canon_sha256":"869bdf60a2eea298a3540936c394a2b127e7683a0633e45d6856f625aba0848e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:12:32.511927Z","signature_b64":"iabPAnsQSzE2LuinpBT2sRNO9T1yADU412sYQNw4Qm9bxY/Vnwj0S7K9PQYVSToBEFHxzImOgTBGztocrZ+lBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cad4a19dab58c6f24c219c07f8277b60508251e748377d2673240f2cd7156644","last_reissued_at":"2026-07-05T08:12:32.511445Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:12:32.511445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Semantically consistent Video-to-Audio Generation using Multimodal Language Large Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.SD","eess.AS"],"primary_cat":"cs.MM","authors_text":"Gehui Chen, Guan'an Wang, Jitao Sang, Xiaowen Huang","submitted_at":"2024-04-25T03:14:49Z","abstract_excerpt":"Existing works have made strides in video generation, but the lack of sound effects (SFX) and background music (BGM) hinders a complete and immersive viewer experience. We introduce a novel semantically consistent v ideo-to-audio generation framework, namely SVA, which automatically generates audio semantically consistent with the given video content. The framework harnesses the power of multimodal large language model (MLLM) to understand video semantics from a key frame and generate creative audio schemes, which are then utilized as prompts for text-to-audio models, resulting in video-to-aud"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.16305","kind":"arxiv","version":2},"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/2404.16305/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":"2404.16305","created_at":"2026-07-05T08:12:32.511504+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.16305v2","created_at":"2026-07-05T08:12:32.511504+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.16305","created_at":"2026-07-05T08:12:32.511504+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZLKKDHNLLDDP","created_at":"2026-07-05T08:12:32.511504+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZLKKDHNLLDDPETBB","created_at":"2026-07-05T08:12:32.511504+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZLKKDHNL","created_at":"2026-07-05T08:12:32.511504+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2510.01284","citing_title":"Ovi: Twin Backbone Cross-Modal Fusion for Audio-Video Generation","ref_index":2,"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":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZLKKDHNLLDDPETBBTQD7QJ33MB","json":"https://pith.science/pith/ZLKKDHNLLDDPETBBTQD7QJ33MB.json","graph_json":"https://pith.science/api/pith-number/ZLKKDHNLLDDPETBBTQD7QJ33MB/graph.json","events_json":"https://pith.science/api/pith-number/ZLKKDHNLLDDPETBBTQD7QJ33MB/events.json","paper":"https://pith.science/paper/ZLKKDHNL"},"agent_actions":{"view_html":"https://pith.science/pith/ZLKKDHNLLDDPETBBTQD7QJ33MB","download_json":"https://pith.science/pith/ZLKKDHNLLDDPETBBTQD7QJ33MB.json","view_paper":"https://pith.science/paper/ZLKKDHNL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.16305&json=true","fetch_graph":"https://pith.science/api/pith-number/ZLKKDHNLLDDPETBBTQD7QJ33MB/graph.json","fetch_events":"https://pith.science/api/pith-number/ZLKKDHNLLDDPETBBTQD7QJ33MB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZLKKDHNLLDDPETBBTQD7QJ33MB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZLKKDHNLLDDPETBBTQD7QJ33MB/action/storage_attestation","attest_author":"https://pith.science/pith/ZLKKDHNLLDDPETBBTQD7QJ33MB/action/author_attestation","sign_citation":"https://pith.science/pith/ZLKKDHNLLDDPETBBTQD7QJ33MB/action/citation_signature","submit_replication":"https://pith.science/pith/ZLKKDHNLLDDPETBBTQD7QJ33MB/action/replication_record"}},"created_at":"2026-07-05T08:12:32.511504+00:00","updated_at":"2026-07-05T08:12:32.511504+00:00"}