{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:ZOYC6GZLPFRL54KVMQ7BLYKVLZ","short_pith_number":"pith:ZOYC6GZL","canonical_record":{"source":{"id":"2605.25195","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-24T17:55:11Z","cross_cats_sorted":[],"title_canon_sha256":"86d13dabe16641e3b1fc2393653d570a47986321c274e377160ac9f00aba4fb2","abstract_canon_sha256":"39d55f88eb2cc2b6e20f5d1c07a8eec5965f6c10173ed03d6b84ac082348aa4a"},"schema_version":"1.0"},"canonical_sha256":"cbb02f1b2b7962bef155643e15e1555e7d5794046289fe539adc3d245984ecdc","source":{"kind":"arxiv","id":"2605.25195","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:ZOYC6GZLPFRL54KVMQ7BLYKVLZ","target":"record","payload":{"canonical_record":{"source":{"id":"2605.25195","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-24T17:55:11Z","cross_cats_sorted":[],"title_canon_sha256":"86d13dabe16641e3b1fc2393653d570a47986321c274e377160ac9f00aba4fb2","abstract_canon_sha256":"39d55f88eb2cc2b6e20f5d1c07a8eec5965f6c10173ed03d6b84ac082348aa4a"},"schema_version":"1.0"},"canonical_sha256":"cbb02f1b2b7962bef155643e15e1555e7d5794046289fe539adc3d245984ecdc","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:04:22.655276Z","signature_b64":"YGCojQr6W7dliRPhI/ZE6JgykVw49I6mtBUXD8YBQSsXavtvrrUxuP1FnRv1s6yK27TmzX/wdxUqRclzmBnaCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbb02f1b2b7962bef155643e15e1555e7d5794046289fe539adc3d245984ecdc","last_reissued_at":"2026-05-26T02:04:22.654507Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:04:22.654507Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.25195","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":"2026-05-26T02:04:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hnFa16LvskgCPD4mld2Ax/xWituScujiFp7MyPVFFrkKYHp5jcwoYhNHJNQlRyLtN+en0Z5+IbUO//Sr65ZYCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T16:21:20.885540Z"},"content_sha256":"4e1a6bffcec3004a9c31bff7bc1f1b7c0866fb597ab2dba8c4d1a79b82996c35","schema_version":"1.0","event_id":"sha256:4e1a6bffcec3004a9c31bff7bc1f1b7c0866fb597ab2dba8c4d1a79b82996c35"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:ZOYC6GZLPFRL54KVMQ7BLYKVLZ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Baton: Explicit Semantic Blueprints for Joint Video-Audio Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","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","submitted_at":"2026-05-24T17:55:11Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25195","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/2605.25195/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":"2026-05-26T02:04:22Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JxrXrtHwXbgId8EaBa1h8PLs4z1ALCI2nWqT8kNCjUjGgNrbbtuNtlTWN/Rzb1UgHDsXAx2u3LYfL3QjmGAlDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-28T16:21:20.885962Z"},"content_sha256":"fff8231bfcd8bd1e0d672af5c38def97886b54f7e0592b879ba8626bb5729655","schema_version":"1.0","event_id":"sha256:fff8231bfcd8bd1e0d672af5c38def97886b54f7e0592b879ba8626bb5729655"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZOYC6GZLPFRL54KVMQ7BLYKVLZ/bundle.json","state_url":"https://pith.science/pith/ZOYC6GZLPFRL54KVMQ7BLYKVLZ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZOYC6GZLPFRL54KVMQ7BLYKVLZ/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":"2026-05-28T16:21:20Z","links":{"resolver":"https://pith.science/pith/ZOYC6GZLPFRL54KVMQ7BLYKVLZ","bundle":"https://pith.science/pith/ZOYC6GZLPFRL54KVMQ7BLYKVLZ/bundle.json","state":"https://pith.science/pith/ZOYC6GZLPFRL54KVMQ7BLYKVLZ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZOYC6GZLPFRL54KVMQ7BLYKVLZ/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5P79p5bwTbGFFjRCuwjON8lUADLXEfaMyzp7+43jnmCp7EAD39WHflCNMS1YZx2b/mJhVH38ff5xn95wDjdVAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-28T16:21:20.888131Z","bundle_sha256":"facf58960342f4c590f857da8329c9c47abd3e63509390aec1e31c3cf5b2f2d6"}}