{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:5HQ33EOLQHXP5VYO3O3TCGJLKP","short_pith_number":"pith:5HQ33EOL","canonical_record":{"source":{"id":"2411.05679","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-08T16:29:07Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"8c56a1bf902af94edf896e4619acf0cc68ba36a63aaa9f54e198b16a5aa0490f","abstract_canon_sha256":"f4fb961b08c33479a5fb838e8881aaafe20b2d2cabb4bd89e672a91c24b3090e"},"schema_version":"1.0"},"canonical_sha256":"e9e1bd91cb81eefed70edbb731192b53e12b660fff1855136830fa2abe18b0b7","source":{"kind":"arxiv","id":"2411.05679","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.05679","created_at":"2026-07-05T10:44:41Z"},{"alias_kind":"arxiv_version","alias_value":"2411.05679v3","created_at":"2026-07-05T10:44:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.05679","created_at":"2026-07-05T10:44:41Z"},{"alias_kind":"pith_short_12","alias_value":"5HQ33EOLQHXP","created_at":"2026-07-05T10:44:41Z"},{"alias_kind":"pith_short_16","alias_value":"5HQ33EOLQHXP5VYO","created_at":"2026-07-05T10:44:41Z"},{"alias_kind":"pith_short_8","alias_value":"5HQ33EOL","created_at":"2026-07-05T10:44:41Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:5HQ33EOLQHXP5VYO3O3TCGJLKP","target":"record","payload":{"canonical_record":{"source":{"id":"2411.05679","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-08T16:29:07Z","cross_cats_sorted":["cs.AI","cs.LG","cs.SD","eess.AS"],"title_canon_sha256":"8c56a1bf902af94edf896e4619acf0cc68ba36a63aaa9f54e198b16a5aa0490f","abstract_canon_sha256":"f4fb961b08c33479a5fb838e8881aaafe20b2d2cabb4bd89e672a91c24b3090e"},"schema_version":"1.0"},"canonical_sha256":"e9e1bd91cb81eefed70edbb731192b53e12b660fff1855136830fa2abe18b0b7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:44:41.110750Z","signature_b64":"h1gBmpxPdBV2P1oc2HCD3FTlyOOw+YCA6usPoeW3cTMF5TYsGdOsqsBGW+GLUQSYqgKVdiimsZcSENQfjisTDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9e1bd91cb81eefed70edbb731192b53e12b660fff1855136830fa2abe18b0b7","last_reissued_at":"2026-07-05T10:44:41.110251Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:44:41.110251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2411.05679","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T10:44:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"pHzsY7R7zW6DTV7CLTvhnuEYMUfgZaZDJhGKy0GM18AgMOhou3HIN8rh8mWbyW5ba8i/3ouaR2Lng2sWm8KzDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T07:14:27.094772Z"},"content_sha256":"43bd9cdb4ef19e3459a93d0789b992a4f94159605361627bac4ab2fc20976516","schema_version":"1.0","event_id":"sha256:43bd9cdb4ef19e3459a93d0789b992a4f94159605361627bac4ab2fc20976516"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:5HQ33EOLQHXP5VYO3O3TCGJLKP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Tell What You Hear From What You See -- Video to Audio Generation Through Text","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG","cs.SD","eess.AS"],"primary_cat":"cs.CV","authors_text":"Eli Shlizerman, Kun Su, Xiulong Liu","submitted_at":"2024-11-08T16:29:07Z","abstract_excerpt":"The content of visual and audio scenes is multi-faceted such that a video can be paired with various audio and vice-versa. Thereby, in video-to-audio generation task, it is imperative to introduce steering approaches for controlling the generated audio. While Video-to-Audio generation is a well-established generative task, existing methods lack such controllability. In this work, we propose VATT, a multi-modal generative framework that takes a video and an optional text prompt as input, and generates audio and optional textual description of the audio. Such a framework has two advantages: i) V"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.05679","kind":"arxiv","version":3},"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/2411.05679/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":"2026-07-05T10:44:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DcK2gJtZmc//iBgG9dVlQQVYMDdchTfHxVdcVcBr2l9kd1iwuo0keDnJjLo5UF0q37wP+ImdypJFyJqWPcjVCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-17T07:14:27.095747Z"},"content_sha256":"11a05c476a08324e11a9438d8dcf73db89236c20375c67f2d3b5e132ccd79ee9","schema_version":"1.0","event_id":"sha256:11a05c476a08324e11a9438d8dcf73db89236c20375c67f2d3b5e132ccd79ee9"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5HQ33EOLQHXP5VYO3O3TCGJLKP/bundle.json","state_url":"https://pith.science/pith/5HQ33EOLQHXP5VYO3O3TCGJLKP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5HQ33EOLQHXP5VYO3O3TCGJLKP/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":"2026-08-17T07:14:27Z","links":{"resolver":"https://pith.science/pith/5HQ33EOLQHXP5VYO3O3TCGJLKP","bundle":"https://pith.science/pith/5HQ33EOLQHXP5VYO3O3TCGJLKP/bundle.json","state":"https://pith.science/pith/5HQ33EOLQHXP5VYO3O3TCGJLKP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5HQ33EOLQHXP5VYO3O3TCGJLKP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5HQ33EOLQHXP5VYO3O3TCGJLKP","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":"f4fb961b08c33479a5fb838e8881aaafe20b2d2cabb4bd89e672a91c24b3090e","cross_cats_sorted":["cs.AI","cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-08T16:29:07Z","title_canon_sha256":"8c56a1bf902af94edf896e4619acf0cc68ba36a63aaa9f54e198b16a5aa0490f"},"schema_version":"1.0","source":{"id":"2411.05679","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.05679","created_at":"2026-07-05T10:44:41Z"},{"alias_kind":"arxiv_version","alias_value":"2411.05679v3","created_at":"2026-07-05T10:44:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.05679","created_at":"2026-07-05T10:44:41Z"},{"alias_kind":"pith_short_12","alias_value":"5HQ33EOLQHXP","created_at":"2026-07-05T10:44:41Z"},{"alias_kind":"pith_short_16","alias_value":"5HQ33EOLQHXP5VYO","created_at":"2026-07-05T10:44:41Z"},{"alias_kind":"pith_short_8","alias_value":"5HQ33EOL","created_at":"2026-07-05T10:44:41Z"}],"graph_snapshots":[{"event_id":"sha256:11a05c476a08324e11a9438d8dcf73db89236c20375c67f2d3b5e132ccd79ee9","target":"graph","created_at":"2026-07-05T10:44:41Z","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/2411.05679/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The content of visual and audio scenes is multi-faceted such that a video can be paired with various audio and vice-versa. Thereby, in video-to-audio generation task, it is imperative to introduce steering approaches for controlling the generated audio. While Video-to-Audio generation is a well-established generative task, existing methods lack such controllability. In this work, we propose VATT, a multi-modal generative framework that takes a video and an optional text prompt as input, and generates audio and optional textual description of the audio. Such a framework has two advantages: i) V","authors_text":"Eli Shlizerman, Kun Su, Xiulong Liu","cross_cats":["cs.AI","cs.LG","cs.SD","eess.AS"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-08T16:29:07Z","title":"Tell What You Hear From What You See -- Video to Audio Generation Through Text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.05679","kind":"arxiv","version":3},"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":"sha256:43bd9cdb4ef19e3459a93d0789b992a4f94159605361627bac4ab2fc20976516","target":"record","created_at":"2026-07-05T10:44:41Z","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":"f4fb961b08c33479a5fb838e8881aaafe20b2d2cabb4bd89e672a91c24b3090e","cross_cats_sorted":["cs.AI","cs.LG","cs.SD","eess.AS"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-11-08T16:29:07Z","title_canon_sha256":"8c56a1bf902af94edf896e4619acf0cc68ba36a63aaa9f54e198b16a5aa0490f"},"schema_version":"1.0","source":{"id":"2411.05679","kind":"arxiv","version":3}},"canonical_sha256":"e9e1bd91cb81eefed70edbb731192b53e12b660fff1855136830fa2abe18b0b7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e9e1bd91cb81eefed70edbb731192b53e12b660fff1855136830fa2abe18b0b7","first_computed_at":"2026-07-05T10:44:41.110251Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:44:41.110251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"h1gBmpxPdBV2P1oc2HCD3FTlyOOw+YCA6usPoeW3cTMF5TYsGdOsqsBGW+GLUQSYqgKVdiimsZcSENQfjisTDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:44:41.110750Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.05679","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:43bd9cdb4ef19e3459a93d0789b992a4f94159605361627bac4ab2fc20976516","sha256:11a05c476a08324e11a9438d8dcf73db89236c20375c67f2d3b5e132ccd79ee9"],"state_sha256":"d3f7433f035e9ba5475d970b1509f7442c2019c1e9a7ebf867eb14915938614a"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Ii9aZvJVCaOrdQnmWzO3dBzJgnqvSudeiScwi1wAMJ/k9wionOz4J/bcQcKOw1z2TqMHO0aJXN+9FB0eV8rgCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-17T07:14:27.108225Z","bundle_sha256":"94483dd4fbf6dcce572a2315a796db7e29f87640ab2e38e76ddc719074678ac6"}}