{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:OSF2JBRT7FDUFKC5Y37TEER3UP","short_pith_number":"pith:OSF2JBRT","canonical_record":{"source":{"id":"2605.30073","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T15:21:45Z","cross_cats_sorted":[],"title_canon_sha256":"caaad93ad8583716fc6c1358d1b840d9cff0bbd24b55565115ffde3bd93fe989","abstract_canon_sha256":"8c2eac7477b6922d81b8a98982a2bc4fa619ed1d487ac4e79f6d4a13e8f265f6"},"schema_version":"1.0"},"canonical_sha256":"748ba48633f94742a85dc6ff32123ba3daea307e21e4022d3cd7422f198cec0e","source":{"kind":"arxiv","id":"2605.30073","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30073","created_at":"2026-05-29T02:06:09Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30073v1","created_at":"2026-05-29T02:06:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30073","created_at":"2026-05-29T02:06:09Z"},{"alias_kind":"pith_short_12","alias_value":"OSF2JBRT7FDU","created_at":"2026-05-29T02:06:09Z"},{"alias_kind":"pith_short_16","alias_value":"OSF2JBRT7FDUFKC5","created_at":"2026-05-29T02:06:09Z"},{"alias_kind":"pith_short_8","alias_value":"OSF2JBRT","created_at":"2026-05-29T02:06:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:OSF2JBRT7FDUFKC5Y37TEER3UP","target":"record","payload":{"canonical_record":{"source":{"id":"2605.30073","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T15:21:45Z","cross_cats_sorted":[],"title_canon_sha256":"caaad93ad8583716fc6c1358d1b840d9cff0bbd24b55565115ffde3bd93fe989","abstract_canon_sha256":"8c2eac7477b6922d81b8a98982a2bc4fa619ed1d487ac4e79f6d4a13e8f265f6"},"schema_version":"1.0"},"canonical_sha256":"748ba48633f94742a85dc6ff32123ba3daea307e21e4022d3cd7422f198cec0e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:06:09.237897Z","signature_b64":"rK2GXFtEUmUPZDHuGDgU8Qqcf3wHpPBGfD6sL/n3qIRuxxqPbhPxBDgxCaBEor6f0a8ws6OvlZW1wG1UKftoDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"748ba48633f94742a85dc6ff32123ba3daea307e21e4022d3cd7422f198cec0e","last_reissued_at":"2026-05-29T02:06:09.237377Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:06:09.237377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.30073","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":"2026-05-29T02:06:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"KT1ykZCMFLpfLf545aa10+pHom6Lw4tnoSKL8wU3IwTSMALCT+01ixlKQJyYmkIz6PlBLxtXQQiCDAqEZ/93BA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T16:28:35.724165Z"},"content_sha256":"9a1c4492fc4fd2c8fc0854bdeef8b46b18df4a50a459bbda6b5e5964aee939eb","schema_version":"1.0","event_id":"sha256:9a1c4492fc4fd2c8fc0854bdeef8b46b18df4a50a459bbda6b5e5964aee939eb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:OSF2JBRT7FDUFKC5Y37TEER3UP","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Native Audio-Visual Alignment for Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chenye Yang, Guan Wang, Jingzhou He, Longbin Ji, Shuohuan Wang, Xiangrui Liu, Xuan Wei, Yu Sun, Zhenyu Zhang","submitted_at":"2026-05-28T15:21:45Z","abstract_excerpt":"Joint audio-video generation aims to synthesize temporally synchronized and semantically coherent visual-acoustic content. However, existing open-source methods mainly rely on either dual-tower designs with posterior alignment or fully unified tri-modal designs that mix textual context, audio and video in one shared space. The former weakens fine-grained audio-video co-evolution, while the latter couples semantic conditioning with low-level synchronization. To address these limitations, we propose NAVA, a Native Audio-Visual Alignment framework for joint audio-video generation. NAVA is built u"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30073","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/2605.30073/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":"2026-05-29T02:06:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"STE2hSk8FJAwYo/lP1MB0RC5hzx330R+ZNjamLYvAX5KT3myJp/u+x7AaE4d/TrnOymha3IifRC3vV5HcUAbAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-06T16:28:35.724559Z"},"content_sha256":"476d4b50647e14e9d2423dbe25a9cce9948faf7f053792ea925e9c07603e93d2","schema_version":"1.0","event_id":"sha256:476d4b50647e14e9d2423dbe25a9cce9948faf7f053792ea925e9c07603e93d2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OSF2JBRT7FDUFKC5Y37TEER3UP/bundle.json","state_url":"https://pith.science/pith/OSF2JBRT7FDUFKC5Y37TEER3UP/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OSF2JBRT7FDUFKC5Y37TEER3UP/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":"2026-06-06T16:28:35Z","links":{"resolver":"https://pith.science/pith/OSF2JBRT7FDUFKC5Y37TEER3UP","bundle":"https://pith.science/pith/OSF2JBRT7FDUFKC5Y37TEER3UP/bundle.json","state":"https://pith.science/pith/OSF2JBRT7FDUFKC5Y37TEER3UP/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OSF2JBRT7FDUFKC5Y37TEER3UP/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:OSF2JBRT7FDUFKC5Y37TEER3UP","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":"8c2eac7477b6922d81b8a98982a2bc4fa619ed1d487ac4e79f6d4a13e8f265f6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T15:21:45Z","title_canon_sha256":"caaad93ad8583716fc6c1358d1b840d9cff0bbd24b55565115ffde3bd93fe989"},"schema_version":"1.0","source":{"id":"2605.30073","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.30073","created_at":"2026-05-29T02:06:09Z"},{"alias_kind":"arxiv_version","alias_value":"2605.30073v1","created_at":"2026-05-29T02:06:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.30073","created_at":"2026-05-29T02:06:09Z"},{"alias_kind":"pith_short_12","alias_value":"OSF2JBRT7FDU","created_at":"2026-05-29T02:06:09Z"},{"alias_kind":"pith_short_16","alias_value":"OSF2JBRT7FDUFKC5","created_at":"2026-05-29T02:06:09Z"},{"alias_kind":"pith_short_8","alias_value":"OSF2JBRT","created_at":"2026-05-29T02:06:09Z"}],"graph_snapshots":[{"event_id":"sha256:476d4b50647e14e9d2423dbe25a9cce9948faf7f053792ea925e9c07603e93d2","target":"graph","created_at":"2026-05-29T02:06:09Z","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/2605.30073/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Joint audio-video generation aims to synthesize temporally synchronized and semantically coherent visual-acoustic content. However, existing open-source methods mainly rely on either dual-tower designs with posterior alignment or fully unified tri-modal designs that mix textual context, audio and video in one shared space. The former weakens fine-grained audio-video co-evolution, while the latter couples semantic conditioning with low-level synchronization. To address these limitations, we propose NAVA, a Native Audio-Visual Alignment framework for joint audio-video generation. NAVA is built u","authors_text":"Chenye Yang, Guan Wang, Jingzhou He, Longbin Ji, Shuohuan Wang, Xiangrui Liu, Xuan Wei, Yu Sun, Zhenyu Zhang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T15:21:45Z","title":"Native Audio-Visual Alignment for Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.30073","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":"sha256:9a1c4492fc4fd2c8fc0854bdeef8b46b18df4a50a459bbda6b5e5964aee939eb","target":"record","created_at":"2026-05-29T02:06:09Z","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":"8c2eac7477b6922d81b8a98982a2bc4fa619ed1d487ac4e79f6d4a13e8f265f6","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-28T15:21:45Z","title_canon_sha256":"caaad93ad8583716fc6c1358d1b840d9cff0bbd24b55565115ffde3bd93fe989"},"schema_version":"1.0","source":{"id":"2605.30073","kind":"arxiv","version":1}},"canonical_sha256":"748ba48633f94742a85dc6ff32123ba3daea307e21e4022d3cd7422f198cec0e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"748ba48633f94742a85dc6ff32123ba3daea307e21e4022d3cd7422f198cec0e","first_computed_at":"2026-05-29T02:06:09.237377Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T02:06:09.237377Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rK2GXFtEUmUPZDHuGDgU8Qqcf3wHpPBGfD6sL/n3qIRuxxqPbhPxBDgxCaBEor6f0a8ws6OvlZW1wG1UKftoDA==","signature_status":"signed_v1","signed_at":"2026-05-29T02:06:09.237897Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.30073","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a1c4492fc4fd2c8fc0854bdeef8b46b18df4a50a459bbda6b5e5964aee939eb","sha256:476d4b50647e14e9d2423dbe25a9cce9948faf7f053792ea925e9c07603e93d2"],"state_sha256":"f0b94e333b3cc4fbc811cb439f9ecdb6ece7e00e7d72e387f244a5b3484de442"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vKYXJpHn6FApEfT6aTnBe0xEEJBaiAtRXe6baXX7G0LwtR9QqGZEUM2/IjxmLdDYPI8tCG/p/x0vM4vNMVjyAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-06T16:28:35.727019Z","bundle_sha256":"a11994b81e3a5e42e88dca83ea5fa7d766fa7219dc88140e757b95468416bb00"}}