{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:FMD3ZOFDZEA42D23TYGGOEEHEL","short_pith_number":"pith:FMD3ZOFD","canonical_record":{"source":{"id":"2407.07464","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-07-10T08:40:39Z","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"title_canon_sha256":"d08a263c71f663c40420cfc605ffabd8cec7c634f5da7d8211efb15d9b805566","abstract_canon_sha256":"851653390f3a15e440f1078f4a4f5b3a74425e2562c67018e23543f5cb8a5235"},"schema_version":"1.0"},"canonical_sha256":"2b07bcb8a3c901cd0f5b9e0c67108722f9d0d3f031c7f65d7e6a189d382cef99","source":{"kind":"arxiv","id":"2407.07464","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.07464","created_at":"2026-07-05T10:28:19Z"},{"alias_kind":"arxiv_version","alias_value":"2407.07464v3","created_at":"2026-07-05T10:28:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.07464","created_at":"2026-07-05T10:28:19Z"},{"alias_kind":"pith_short_12","alias_value":"FMD3ZOFDZEA4","created_at":"2026-07-05T10:28:19Z"},{"alias_kind":"pith_short_16","alias_value":"FMD3ZOFDZEA42D23","created_at":"2026-07-05T10:28:19Z"},{"alias_kind":"pith_short_8","alias_value":"FMD3ZOFD","created_at":"2026-07-05T10:28:19Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:FMD3ZOFDZEA42D23TYGGOEEHEL","target":"record","payload":{"canonical_record":{"source":{"id":"2407.07464","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-07-10T08:40:39Z","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"title_canon_sha256":"d08a263c71f663c40420cfc605ffabd8cec7c634f5da7d8211efb15d9b805566","abstract_canon_sha256":"851653390f3a15e440f1078f4a4f5b3a74425e2562c67018e23543f5cb8a5235"},"schema_version":"1.0"},"canonical_sha256":"2b07bcb8a3c901cd0f5b9e0c67108722f9d0d3f031c7f65d7e6a189d382cef99","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:28:19.046817Z","signature_b64":"IFb9mszeiSegBtmjpx1W2ORgT6nFCvR+BulVaZ7BeuBoRXd6GGfx3eh7t9jd0jmS2cVt6IXE+WwnP+Y2Ek5bDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b07bcb8a3c901cd0f5b9e0c67108722f9d0d3f031c7f65d7e6a189d382cef99","last_reissued_at":"2026-07-05T10:28:19.046327Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:28:19.046327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2407.07464","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":"2026-07-05T10:28:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Oz2Lw43x5NVj6Bq6Ko31p/XITRXSUm2EiuBp6XbXuSGSj8xKe6DrLSYc2MWo6K/7722rbH3xri0pjMQXuFawDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T04:51:13.305627Z"},"content_sha256":"d095cd8aeac40a7d663f245beee7c93cc4b49845ac73e84a01e336ed6860b6c7","schema_version":"1.0","event_id":"sha256:d095cd8aeac40a7d663f245beee7c93cc4b49845ac73e84a01e336ed6860b6c7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:FMD3ZOFDZEA42D23TYGGOEEHEL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Video-to-Audio Generation with Hidden Alignment","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.MM","eess.AS"],"primary_cat":"cs.SD","authors_text":"Chenxing Li, Dong Yu, Manjie Xu, Rilin Chen, Wei Liang, Xinyi Tu, Yong Ren, Yu Gu","submitted_at":"2024-07-10T08:40:39Z","abstract_excerpt":"Generating semantically and temporally aligned audio content in accordance with video input has become a focal point for researchers, particularly following the remarkable breakthrough in text-to-video generation. In this work, we aim to offer insights into the video-to-audio generation paradigm, focusing on three crucial aspects: vision encoders, auxiliary embeddings, and data augmentation techniques. Beginning with a foundational model built on a simple yet surprisingly effective intuition, we explore various vision encoders and auxiliary embeddings through ablation studies. Employing a comp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.07464","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/2407.07464/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":"2026-07-05T10:28:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P4YpeQZHiOrPTEQ37vD2FEmzbTlBUc3svrPdktT9xwrHYL4WJQQnBy8VR2VeVJCDnNpy3n0VHjVVWg/RtEdlBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T04:51:13.306116Z"},"content_sha256":"8b1cd0ca765fa8d6f63f29f36236569f08150d741d05d0c8568b0630eec93695","schema_version":"1.0","event_id":"sha256:8b1cd0ca765fa8d6f63f29f36236569f08150d741d05d0c8568b0630eec93695"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/FMD3ZOFDZEA42D23TYGGOEEHEL/bundle.json","state_url":"https://pith.science/pith/FMD3ZOFDZEA42D23TYGGOEEHEL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/FMD3ZOFDZEA42D23TYGGOEEHEL/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":"2026-08-10T04:51:13Z","links":{"resolver":"https://pith.science/pith/FMD3ZOFDZEA42D23TYGGOEEHEL","bundle":"https://pith.science/pith/FMD3ZOFDZEA42D23TYGGOEEHEL/bundle.json","state":"https://pith.science/pith/FMD3ZOFDZEA42D23TYGGOEEHEL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/FMD3ZOFDZEA42D23TYGGOEEHEL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FMD3ZOFDZEA42D23TYGGOEEHEL","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":"851653390f3a15e440f1078f4a4f5b3a74425e2562c67018e23543f5cb8a5235","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-07-10T08:40:39Z","title_canon_sha256":"d08a263c71f663c40420cfc605ffabd8cec7c634f5da7d8211efb15d9b805566"},"schema_version":"1.0","source":{"id":"2407.07464","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.07464","created_at":"2026-07-05T10:28:19Z"},{"alias_kind":"arxiv_version","alias_value":"2407.07464v3","created_at":"2026-07-05T10:28:19Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.07464","created_at":"2026-07-05T10:28:19Z"},{"alias_kind":"pith_short_12","alias_value":"FMD3ZOFDZEA4","created_at":"2026-07-05T10:28:19Z"},{"alias_kind":"pith_short_16","alias_value":"FMD3ZOFDZEA42D23","created_at":"2026-07-05T10:28:19Z"},{"alias_kind":"pith_short_8","alias_value":"FMD3ZOFD","created_at":"2026-07-05T10:28:19Z"}],"graph_snapshots":[{"event_id":"sha256:8b1cd0ca765fa8d6f63f29f36236569f08150d741d05d0c8568b0630eec93695","target":"graph","created_at":"2026-07-05T10:28:19Z","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/2407.07464/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generating semantically and temporally aligned audio content in accordance with video input has become a focal point for researchers, particularly following the remarkable breakthrough in text-to-video generation. In this work, we aim to offer insights into the video-to-audio generation paradigm, focusing on three crucial aspects: vision encoders, auxiliary embeddings, and data augmentation techniques. Beginning with a foundational model built on a simple yet surprisingly effective intuition, we explore various vision encoders and auxiliary embeddings through ablation studies. Employing a comp","authors_text":"Chenxing Li, Dong Yu, Manjie Xu, Rilin Chen, Wei Liang, Xinyi Tu, Yong Ren, Yu Gu","cross_cats":["cs.CV","cs.MM","eess.AS"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-07-10T08:40:39Z","title":"Video-to-Audio Generation with Hidden Alignment"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.07464","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:d095cd8aeac40a7d663f245beee7c93cc4b49845ac73e84a01e336ed6860b6c7","target":"record","created_at":"2026-07-05T10:28:19Z","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":"851653390f3a15e440f1078f4a4f5b3a74425e2562c67018e23543f5cb8a5235","cross_cats_sorted":["cs.CV","cs.MM","eess.AS"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.SD","submitted_at":"2024-07-10T08:40:39Z","title_canon_sha256":"d08a263c71f663c40420cfc605ffabd8cec7c634f5da7d8211efb15d9b805566"},"schema_version":"1.0","source":{"id":"2407.07464","kind":"arxiv","version":3}},"canonical_sha256":"2b07bcb8a3c901cd0f5b9e0c67108722f9d0d3f031c7f65d7e6a189d382cef99","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2b07bcb8a3c901cd0f5b9e0c67108722f9d0d3f031c7f65d7e6a189d382cef99","first_computed_at":"2026-07-05T10:28:19.046327Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:28:19.046327Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"IFb9mszeiSegBtmjpx1W2ORgT6nFCvR+BulVaZ7BeuBoRXd6GGfx3eh7t9jd0jmS2cVt6IXE+WwnP+Y2Ek5bDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:28:19.046817Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.07464","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d095cd8aeac40a7d663f245beee7c93cc4b49845ac73e84a01e336ed6860b6c7","sha256:8b1cd0ca765fa8d6f63f29f36236569f08150d741d05d0c8568b0630eec93695"],"state_sha256":"bbd46ea86a50131f76349b36e3a60da565931a7b619a4e0d37074b10052dcd11"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vwJJrd7+J057lf9rpVqfeTy6ynocvfTT3XthFbgfncVWJ9kiYHW9ixMaoLASozRQJcW+XQ5FcA+tYWCXSGbbDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T04:51:13.309639Z","bundle_sha256":"531f0c868c02fbd9843ea924d7182dc92578a3d5786f4b9e6f26a4f198e5ca68"}}