{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:2I2B5FEEXTKMDSILXDVNRV3CXA","short_pith_number":"pith:2I2B5FEE","canonical_record":{"source":{"id":"2607.23855","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-07-26T21:51:28Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"3405999f6555c4c5a3f438eb79a67ce70e05fdd76db5a70d093fe773e9e6a79e","abstract_canon_sha256":"a573928fac333daef26574457bfbd3379ccf6b64afc60f39743c0f3ba155c6d2"},"schema_version":"1.0"},"canonical_sha256":"d2341e9484bcd4c1c90bb8ead8d762b81fcf90a73f5809f9063436a98b5ba27f","source":{"kind":"arxiv","id":"2607.23855","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.23855","created_at":"2026-07-28T01:23:14Z"},{"alias_kind":"arxiv_version","alias_value":"2607.23855v1","created_at":"2026-07-28T01:23:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23855","created_at":"2026-07-28T01:23:14Z"},{"alias_kind":"pith_short_12","alias_value":"2I2B5FEEXTKM","created_at":"2026-07-28T01:23:14Z"},{"alias_kind":"pith_short_16","alias_value":"2I2B5FEEXTKMDSIL","created_at":"2026-07-28T01:23:14Z"},{"alias_kind":"pith_short_8","alias_value":"2I2B5FEE","created_at":"2026-07-28T01:23:14Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:2I2B5FEEXTKMDSILXDVNRV3CXA","target":"record","payload":{"canonical_record":{"source":{"id":"2607.23855","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-07-26T21:51:28Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"3405999f6555c4c5a3f438eb79a67ce70e05fdd76db5a70d093fe773e9e6a79e","abstract_canon_sha256":"a573928fac333daef26574457bfbd3379ccf6b64afc60f39743c0f3ba155c6d2"},"schema_version":"1.0"},"canonical_sha256":"d2341e9484bcd4c1c90bb8ead8d762b81fcf90a73f5809f9063436a98b5ba27f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:23:14.589711Z","signature_b64":"zwI5HGndew4ZzTbh0/j/tY/QVXwITGPo8K2N1c9rPHjlZP48SVa6SD5oDvGR4Eslm5yjr77IeKxlIM4BBM6UBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d2341e9484bcd4c1c90bb8ead8d762b81fcf90a73f5809f9063436a98b5ba27f","last_reissued_at":"2026-07-28T01:23:14.588817Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:23:14.588817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2607.23855","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-28T01:23:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"816xDtWeLO1NoU/u7JpKIyOjFQ62Ch8CsA0pza1y+kpFDdG5VpgftLuUftlvKiIvRQv8vWnklbLTPTF7NsSnAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:01:51.166237Z"},"content_sha256":"311f2da6669a3df128e87ef0a3438966db2c92fa5323582d0cd4f3fa77ef190a","schema_version":"1.0","event_id":"sha256:311f2da6669a3df128e87ef0a3438966db2c92fa5323582d0cd4f3fa77ef190a"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:2I2B5FEEXTKMDSILXDVNRV3CXA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"OmniVAE: An Audio-Video VAE with Cross-Modal Alignment for Joint Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.SD","authors_text":"Cheng Chang, Chen Yang, Donghua Yu, Jiasheng Ye, Jin Wang, Junqi Dai, Jun Zhan, Kexin Huang, Kuangwei Chen, Qi Chen, Qi Luo, Qinyuan Cheng, Shimin Li, Songlin Wang, Tengyue Zhang, Tianyi Liang, Wenbo Zhang, Xiangyu Peng, Xiaogui Yang, Xie Chen, Xinchi Chen, Xipeng Qiu, Ying Zhu, Yitian Gong, Zhaoye Fei, Zhe Xu","submitted_at":"2026-07-26T21:51:28Z","abstract_excerpt":"Recent generative models are moving beyond silent video or standalone audio synthesis toward the joint generation of synchronized audio and video. Despite this progress, jointly generating audio and video with fine-grained cross-modal correspondence remains challenging due to their fundamental structural differences. Most existing methods use audio and video VAEs trained separately. As a result, the two latent spaces lack cross-modal alignment, leaving the downstream generative model to learn cross-modal synchronization from scratch. We present OmniVAE, a jointly trained audio-video VAE that l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23855","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/2607.23855/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":"2026-07-28T01:23:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QI5PZ59StPq0kU4FeVu6lY2Bc42hiD6kGiUJGbQx6vwuwAhqalM6Jpb1ve2HR1Nu/kf9nNm+0lwU07pohSQZAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:01:51.167071Z"},"content_sha256":"45b285a532b45a4f440625c2ffeff855d33ee83469c76014b30a6a86c2d4429d","schema_version":"1.0","event_id":"sha256:45b285a532b45a4f440625c2ffeff855d33ee83469c76014b30a6a86c2d4429d"},{"event_type":"integrity_finding","subject_pith_number":"pith:2026:2I2B5FEEXTKMDSILXDVNRV3CXA","target":"integrity","payload":{"note":"DOI in the printed bibliography is fragmented by whitespace or line breaks. A longer candidate (10.1109/ICASSP.2017.7952261) was visible in the surrounding text but could not be confirmed against doi.org as printed.","snippet":"Jort F. Gemmeke, Daniel P. W. Ellis, Dylan Freedman, Aren Jansen, Wade Lawrence, R. Channing Moore, Manoj Plakal, and Marvin Ritter. Audio set: An ontology and human-labeled dataset for audio events. In2017 IEEE International Conference on ","arxiv_id":"2607.23855","detector":"doi_compliance","evidence":{"ref_index":40,"verdict_class":"incontrovertible","resolved_title":null,"printed_excerpt":"10.1109/icassp.2017","reconstructed_doi":"10.1109/ICASSP.2017.7952261"},"severity":"advisory","ref_index":40,"audited_at":"2026-07-30T10:42:09.296523Z","event_type":"pith.integrity.v1","detected_doi":"10.1109/ICASSP.2017.7952261","detector_url":"https://pith.science/pith-integrity-protocol#doi_compliance","external_url":null,"finding_type":"recoverable_identifier","evidence_hash":"f84aa5b90cd788227a0715c373a62fa403e45e68d58a1dd989b439a6b8a72f24","paper_version":1,"verdict_class":"incontrovertible","resolved_title":null,"detector_version":"1.1.0","detected_arxiv_id":null,"integrity_event_id":13874,"payload_sha256":"2f5d4e059667d1b74585fe66cffffe2db58dc047ddbb051f82493048e472b9e0","signature_b64":null,"signing_key_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-30T10:46:19Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ichlhJE/cwEMnUrgGc726Wb06DMwXe3HQceAhkqXp0hKWoPmP1Ngfr1CTme6W0b3yexveZV/WczlYAfr3phkBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T17:01:51.170393Z"},"content_sha256":"f7f85e3453b1a56b9f66baeade55f0b8831ec4737d842b03a8eeda0152514317","schema_version":"1.0","event_id":"sha256:f7f85e3453b1a56b9f66baeade55f0b8831ec4737d842b03a8eeda0152514317"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2I2B5FEEXTKMDSILXDVNRV3CXA/bundle.json","state_url":"https://pith.science/pith/2I2B5FEEXTKMDSILXDVNRV3CXA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2I2B5FEEXTKMDSILXDVNRV3CXA/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":"2026-08-03T17:01:51Z","links":{"resolver":"https://pith.science/pith/2I2B5FEEXTKMDSILXDVNRV3CXA","bundle":"https://pith.science/pith/2I2B5FEEXTKMDSILXDVNRV3CXA/bundle.json","state":"https://pith.science/pith/2I2B5FEEXTKMDSILXDVNRV3CXA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2I2B5FEEXTKMDSILXDVNRV3CXA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:2I2B5FEEXTKMDSILXDVNRV3CXA","merge_version":"pith-open-graph-merge-v1","event_count":3,"valid_event_count":3,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a573928fac333daef26574457bfbd3379ccf6b64afc60f39743c0f3ba155c6d2","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-07-26T21:51:28Z","title_canon_sha256":"3405999f6555c4c5a3f438eb79a67ce70e05fdd76db5a70d093fe773e9e6a79e"},"schema_version":"1.0","source":{"id":"2607.23855","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.23855","created_at":"2026-07-28T01:23:14Z"},{"alias_kind":"arxiv_version","alias_value":"2607.23855v1","created_at":"2026-07-28T01:23:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.23855","created_at":"2026-07-28T01:23:14Z"},{"alias_kind":"pith_short_12","alias_value":"2I2B5FEEXTKM","created_at":"2026-07-28T01:23:14Z"},{"alias_kind":"pith_short_16","alias_value":"2I2B5FEEXTKMDSIL","created_at":"2026-07-28T01:23:14Z"},{"alias_kind":"pith_short_8","alias_value":"2I2B5FEE","created_at":"2026-07-28T01:23:14Z"}],"graph_snapshots":[{"event_id":"sha256:45b285a532b45a4f440625c2ffeff855d33ee83469c76014b30a6a86c2d4429d","target":"graph","created_at":"2026-07-28T01:23:14Z","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/2607.23855/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent generative models are moving beyond silent video or standalone audio synthesis toward the joint generation of synchronized audio and video. Despite this progress, jointly generating audio and video with fine-grained cross-modal correspondence remains challenging due to their fundamental structural differences. Most existing methods use audio and video VAEs trained separately. As a result, the two latent spaces lack cross-modal alignment, leaving the downstream generative model to learn cross-modal synchronization from scratch. We present OmniVAE, a jointly trained audio-video VAE that l","authors_text":"Cheng Chang, Chen Yang, Donghua Yu, Jiasheng Ye, Jin Wang, Junqi Dai, Jun Zhan, Kexin Huang, Kuangwei Chen, Qi Chen, Qi Luo, Qinyuan Cheng, Shimin Li, Songlin Wang, Tengyue Zhang, Tianyi Liang, Wenbo Zhang, Xiangyu Peng, Xiaogui Yang, Xie Chen, Xinchi Chen, Xipeng Qiu, Ying Zhu, Yitian Gong, Zhaoye Fei, Zhe Xu","cross_cats":["cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-07-26T21:51:28Z","title":"OmniVAE: An Audio-Video VAE with Cross-Modal Alignment for Joint Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.23855","kind":"arxiv","version":1},"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":"sha256:311f2da6669a3df128e87ef0a3438966db2c92fa5323582d0cd4f3fa77ef190a","target":"record","created_at":"2026-07-28T01:23:14Z","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":"a573928fac333daef26574457bfbd3379ccf6b64afc60f39743c0f3ba155c6d2","cross_cats_sorted":["cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SD","submitted_at":"2026-07-26T21:51:28Z","title_canon_sha256":"3405999f6555c4c5a3f438eb79a67ce70e05fdd76db5a70d093fe773e9e6a79e"},"schema_version":"1.0","source":{"id":"2607.23855","kind":"arxiv","version":1}},"canonical_sha256":"d2341e9484bcd4c1c90bb8ead8d762b81fcf90a73f5809f9063436a98b5ba27f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d2341e9484bcd4c1c90bb8ead8d762b81fcf90a73f5809f9063436a98b5ba27f","first_computed_at":"2026-07-28T01:23:14.588817Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-28T01:23:14.588817Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"zwI5HGndew4ZzTbh0/j/tY/QVXwITGPo8K2N1c9rPHjlZP48SVa6SD5oDvGR4Eslm5yjr77IeKxlIM4BBM6UBw==","signature_status":"signed_v1","signed_at":"2026-07-28T01:23:14.589711Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.23855","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:311f2da6669a3df128e87ef0a3438966db2c92fa5323582d0cd4f3fa77ef190a","sha256:45b285a532b45a4f440625c2ffeff855d33ee83469c76014b30a6a86c2d4429d","sha256:f7f85e3453b1a56b9f66baeade55f0b8831ec4737d842b03a8eeda0152514317"],"state_sha256":"c25e742d98eabde59dd0628de8bc8d1ae961a214eab74d729a606900912ee50e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5wfm5NWbk/ZmNPuD3DvnTpXybYgKhaYvvbBNb05VfbaEXGwrzi+m6Wn+ioYNdG5J1S6YlghdnO9qMNraXlJNCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T17:01:51.172870Z","bundle_sha256":"db02a8639995c47ee488110d670b12979dc1b1f783cc1aae1c25d1c14ddd6659"}}