{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:ZLKKDHNLLDDPETBBTQD7QJ33MB","short_pith_number":"pith:ZLKKDHNL","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"},"canonical_sha256":"cad4a19dab58c6f24c219c07f8277b60508251e748377d2673240f2cd7156644","source":{"kind":"arxiv","id":"2404.16305","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.16305","created_at":"2026-07-05T08:12:32Z"},{"alias_kind":"arxiv_version","alias_value":"2404.16305v2","created_at":"2026-07-05T08:12:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.16305","created_at":"2026-07-05T08:12:32Z"},{"alias_kind":"pith_short_12","alias_value":"ZLKKDHNLLDDP","created_at":"2026-07-05T08:12:32Z"},{"alias_kind":"pith_short_16","alias_value":"ZLKKDHNLLDDPETBB","created_at":"2026-07-05T08:12:32Z"},{"alias_kind":"pith_short_8","alias_value":"ZLKKDHNL","created_at":"2026-07-05T08:12:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:ZLKKDHNLLDDPETBBTQD7QJ33MB","target":"record","payload":{"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"},"canonical_sha256":"cad4a19dab58c6f24c219c07f8277b60508251e748377d2673240f2cd7156644","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"},"source_kind":"arxiv","source_id":"2404.16305","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:12:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fP1mFbCZDivrCrMqlMGinowMVSFbwXQrPS0SccGS9pyeqFfx4LNahThvbnBZxoZlVqOiIkR8jQJonMW0dmZWBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:27:06.074011Z"},"content_sha256":"a766167c0d39aff7d3050e6a476dea65d76e27e105b8650190dc29ca04410fdf","schema_version":"1.0","event_id":"sha256:a766167c0d39aff7d3050e6a476dea65d76e27e105b8650190dc29ca04410fdf"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:ZLKKDHNLLDDPETBBTQD7QJ33MB","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:12:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zuMkTo9b6ta2x9hbbyfdBs223SeYmFxwTWaj/06xPpTxn+swzKuiJy23FnEYMbC0TYMh8UpsvVshxT3M8cdODQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T23:27:06.074931Z"},"content_sha256":"14a1614b3af26971a17f06292d528a569d42f4ecf84da33f4d4d723176c28927","schema_version":"1.0","event_id":"sha256:14a1614b3af26971a17f06292d528a569d42f4ecf84da33f4d4d723176c28927"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZLKKDHNLLDDPETBBTQD7QJ33MB/bundle.json","state_url":"https://pith.science/pith/ZLKKDHNLLDDPETBBTQD7QJ33MB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZLKKDHNLLDDPETBBTQD7QJ33MB/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-07T23:27:06Z","links":{"resolver":"https://pith.science/pith/ZLKKDHNLLDDPETBBTQD7QJ33MB","bundle":"https://pith.science/pith/ZLKKDHNLLDDPETBBTQD7QJ33MB/bundle.json","state":"https://pith.science/pith/ZLKKDHNLLDDPETBBTQD7QJ33MB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZLKKDHNLLDDPETBBTQD7QJ33MB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:ZLKKDHNLLDDPETBBTQD7QJ33MB","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":"869bdf60a2eea298a3540936c394a2b127e7683a0633e45d6856f625aba0848e","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-04-25T03:14:49Z","title_canon_sha256":"94777d0c434c783fa812d3ca64974046e02176737c13ecface79295db5912ace"},"schema_version":"1.0","source":{"id":"2404.16305","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.16305","created_at":"2026-07-05T08:12:32Z"},{"alias_kind":"arxiv_version","alias_value":"2404.16305v2","created_at":"2026-07-05T08:12:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.16305","created_at":"2026-07-05T08:12:32Z"},{"alias_kind":"pith_short_12","alias_value":"ZLKKDHNLLDDP","created_at":"2026-07-05T08:12:32Z"},{"alias_kind":"pith_short_16","alias_value":"ZLKKDHNLLDDPETBB","created_at":"2026-07-05T08:12:32Z"},{"alias_kind":"pith_short_8","alias_value":"ZLKKDHNL","created_at":"2026-07-05T08:12:32Z"}],"graph_snapshots":[{"event_id":"sha256:14a1614b3af26971a17f06292d528a569d42f4ecf84da33f4d4d723176c28927","target":"graph","created_at":"2026-07-05T08:12:32Z","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/2404.16305/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Gehui Chen, Guan'an Wang, Jitao Sang, Xiaowen Huang","cross_cats":["cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-04-25T03:14:49Z","title":"Semantically consistent Video-to-Audio Generation using Multimodal Language Large Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.16305","kind":"arxiv","version":2},"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:a766167c0d39aff7d3050e6a476dea65d76e27e105b8650190dc29ca04410fdf","target":"record","created_at":"2026-07-05T08:12:32Z","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":"869bdf60a2eea298a3540936c394a2b127e7683a0633e45d6856f625aba0848e","cross_cats_sorted":["cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-04-25T03:14:49Z","title_canon_sha256":"94777d0c434c783fa812d3ca64974046e02176737c13ecface79295db5912ace"},"schema_version":"1.0","source":{"id":"2404.16305","kind":"arxiv","version":2}},"canonical_sha256":"cad4a19dab58c6f24c219c07f8277b60508251e748377d2673240f2cd7156644","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cad4a19dab58c6f24c219c07f8277b60508251e748377d2673240f2cd7156644","first_computed_at":"2026-07-05T08:12:32.511445Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:12:32.511445Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"iabPAnsQSzE2LuinpBT2sRNO9T1yADU412sYQNw4Qm9bxY/Vnwj0S7K9PQYVSToBEFHxzImOgTBGztocrZ+lBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:12:32.511927Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.16305","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a766167c0d39aff7d3050e6a476dea65d76e27e105b8650190dc29ca04410fdf","sha256:14a1614b3af26971a17f06292d528a569d42f4ecf84da33f4d4d723176c28927"],"state_sha256":"78e15b83e1f961e24bc479988ef1b4bf14f8e9d6d9b2baf1ac20a50ccae8aad5"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sq37vvc9bj9BiqwZ35S95Opt3/bNeTTY4iqfN+GWdrOQJEuAMoSn2FOYWQ/YGlN7mel16f0TUxhPGeaITFOIDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T23:27:06.082081Z","bundle_sha256":"932705934a44a1477db863d2782a8aa30268e7958e7e1a87150fa5b26eb193fc"}}