{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ZOYC6GZLPFRL54KVMQ7BLYKVLZ","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":"39d55f88eb2cc2b6e20f5d1c07a8eec5965f6c10173ed03d6b84ac082348aa4a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-24T17:55:11Z","title_canon_sha256":"86d13dabe16641e3b1fc2393653d570a47986321c274e377160ac9f00aba4fb2"},"schema_version":"1.0","source":{"id":"2605.25195","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.25195","created_at":"2026-05-26T02:04:22Z"},{"alias_kind":"arxiv_version","alias_value":"2605.25195v1","created_at":"2026-05-26T02:04:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25195","created_at":"2026-05-26T02:04:22Z"},{"alias_kind":"pith_short_12","alias_value":"ZOYC6GZLPFRL","created_at":"2026-05-26T02:04:22Z"},{"alias_kind":"pith_short_16","alias_value":"ZOYC6GZLPFRL54KV","created_at":"2026-05-26T02:04:22Z"},{"alias_kind":"pith_short_8","alias_value":"ZOYC6GZL","created_at":"2026-05-26T02:04:22Z"}],"graph_snapshots":[{"event_id":"sha256:fff8231bfcd8bd1e0d672af5c38def97886b54f7e0592b879ba8626bb5729655","target":"graph","created_at":"2026-05-26T02:04:22Z","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/2605.25195/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current open-source diffusion models struggle to generate stable and synchronized audio-visual content, particularly in scenarios demanding complex semantic reasoning. The root cause is that existing methods rely on coarse text embeddings from off-the-shelf encoders to guide audio-video denoising, which discards fine-grained semantics and, critically, lacks a shared long-horizon plan, leading to uncoordinated denoising trajectories and fragile cross-modal alignment. We propose Baton, the first framework that introduces explicit semantic planning into joint video-audio generation. Our key insig","authors_text":"Jiangfeng Xiong, Jian-Wei Zhang, Liefeng Bo, Qi Tian, Shuyuan Tu, Weijie Kong, Xintong Han, Yue Wu, Yu-Gang Jiang, Zhao Zhong, Zihan Yang, Zuxuan Wu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-24T17:55:11Z","title":"Baton: Explicit Semantic Blueprints for Joint Video-Audio Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25195","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":"sha256:4e1a6bffcec3004a9c31bff7bc1f1b7c0866fb597ab2dba8c4d1a79b82996c35","target":"record","created_at":"2026-05-26T02:04:22Z","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":"39d55f88eb2cc2b6e20f5d1c07a8eec5965f6c10173ed03d6b84ac082348aa4a","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-24T17:55:11Z","title_canon_sha256":"86d13dabe16641e3b1fc2393653d570a47986321c274e377160ac9f00aba4fb2"},"schema_version":"1.0","source":{"id":"2605.25195","kind":"arxiv","version":1}},"canonical_sha256":"cbb02f1b2b7962bef155643e15e1555e7d5794046289fe539adc3d245984ecdc","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cbb02f1b2b7962bef155643e15e1555e7d5794046289fe539adc3d245984ecdc","first_computed_at":"2026-05-26T02:04:22.654507Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-26T02:04:22.654507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"YGCojQr6W7dliRPhI/ZE6JgykVw49I6mtBUXD8YBQSsXavtvrrUxuP1FnRv1s6yK27TmzX/wdxUqRclzmBnaCw==","signature_status":"signed_v1","signed_at":"2026-05-26T02:04:22.655276Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.25195","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4e1a6bffcec3004a9c31bff7bc1f1b7c0866fb597ab2dba8c4d1a79b82996c35","sha256:fff8231bfcd8bd1e0d672af5c38def97886b54f7e0592b879ba8626bb5729655"],"state_sha256":"bb4623cf7d3a8b2aa86d7fac7b75ff2d01ad243ed8998a2d594b643de13196bb"}