{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:KKJKI3VSNEP2I7EZFCBOG2KTTC","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":"7f65865e9044cb851d09a57d59b87501674e75327e1887badf9494c9778877f5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-19T18:06:15Z","title_canon_sha256":"14fb3815666f101204bd8e4f4537c56d63e0af665e1c388d0b94fb9175d47970"},"schema_version":"1.0","source":{"id":"2606.21661","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.21661","created_at":"2026-06-23T01:13:18Z"},{"alias_kind":"arxiv_version","alias_value":"2606.21661v1","created_at":"2026-06-23T01:13:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21661","created_at":"2026-06-23T01:13:18Z"},{"alias_kind":"pith_short_12","alias_value":"KKJKI3VSNEP2","created_at":"2026-06-23T01:13:18Z"},{"alias_kind":"pith_short_16","alias_value":"KKJKI3VSNEP2I7EZ","created_at":"2026-06-23T01:13:18Z"},{"alias_kind":"pith_short_8","alias_value":"KKJKI3VS","created_at":"2026-06-23T01:13:18Z"}],"graph_snapshots":[{"event_id":"sha256:c8cb257cd8e5804c100b28a3246e8b4132c42b065c8b293fb3e26b29d02ccf08","target":"graph","created_at":"2026-06-23T01:13:18Z","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/2606.21661/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Generating a coherent multi-shot video requires structured cross-shot memory. Subject appearance, scene context, and speaker identity must persist across cuts. Existing approaches either train end-to-end over fixed-length sequences and cannot scale, generate shot-by-shot with memory banks that grow linearly, or orchestrate pretrained generators under an LLM planner without a multi-shot-aware backbone. We present UnityShots, a memory-driven multi-shot audio-video generation system built on LTX-2.3, trained on annotated cinematic and music-video shots. The video stream maintains two fixed-size s","authors_text":"Bin Xia, Jiahao Wang, Jiaya Jia, Jiehui Huang, Meng Chu, Pengfei Wan, Xin Tao, Xu He, Yuechen Zhang, Zhenchao Tang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-19T18:06:15Z","title":"UnityShots: Memory-Driven Multi-Shot Audio-Video Generation with Boundary-Aware Gating"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21661","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":"sha256:633d07b8b97f25dc0d088de90b4340316e0ea9281c2cfe3aba9b62d4bdacc805","target":"record","created_at":"2026-06-23T01:13:18Z","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":"7f65865e9044cb851d09a57d59b87501674e75327e1887badf9494c9778877f5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-06-19T18:06:15Z","title_canon_sha256":"14fb3815666f101204bd8e4f4537c56d63e0af665e1c388d0b94fb9175d47970"},"schema_version":"1.0","source":{"id":"2606.21661","kind":"arxiv","version":1}},"canonical_sha256":"5292a46eb2691fa47c992882e36953989322d9d3ff03a528bcb547d1ab21a148","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5292a46eb2691fa47c992882e36953989322d9d3ff03a528bcb547d1ab21a148","first_computed_at":"2026-06-23T01:13:18.263833Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T01:13:18.263833Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"O4W9fgu+h53nKqdZ+R/JMKCq8URTs0z79CXstCCi2uDEckBzaFWuiUBjWnQrEOJW44bwVese9Z2JWZCMprukDw==","signature_status":"signed_v1","signed_at":"2026-06-23T01:13:18.264293Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.21661","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:633d07b8b97f25dc0d088de90b4340316e0ea9281c2cfe3aba9b62d4bdacc805","sha256:c8cb257cd8e5804c100b28a3246e8b4132c42b065c8b293fb3e26b29d02ccf08"],"state_sha256":"0c382ee307cd63fdf489be219ede2862cabbf07431de9d8ab3466add5b8624ac"}