{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:22QOAOZJ4KEEGIMDSMWKCHWZT4","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":"1ac2bc82ac6e692290a0a1d3aab6968e3c1643bb557bff440ca6d320421aa8b7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-10-06T17:57:59Z","title_canon_sha256":"be8f7aecd3becdf931a558478f9db8d32187284f9729affc8053f084e6506fdd"},"schema_version":"1.0","source":{"id":"2510.05094","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2510.05094","created_at":"2026-05-22T01:03:47Z"},{"alias_kind":"arxiv_version","alias_value":"2510.05094v2","created_at":"2026-05-22T01:03:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.05094","created_at":"2026-05-22T01:03:47Z"},{"alias_kind":"pith_short_12","alias_value":"22QOAOZJ4KEE","created_at":"2026-05-22T01:03:47Z"},{"alias_kind":"pith_short_16","alias_value":"22QOAOZJ4KEEGIMD","created_at":"2026-05-22T01:03:47Z"},{"alias_kind":"pith_short_8","alias_value":"22QOAOZJ","created_at":"2026-05-22T01:03:47Z"}],"graph_snapshots":[{"event_id":"sha256:1f976168aa4937dca214dace3d7d7153c830ae0a5ca6a70f8046188b241a54b0","target":"graph","created_at":"2026-05-22T01:03:47Z","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/2510.05094/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent video generation models can produce smooth and visually appealing clips, but they often struggle to synthesize complex dynamics with a coherent chain of consequences. Accurately modeling visual outcomes and state transitions over time remains a core challenge. In contrast, large language and multimodal models (e.g., GPT-4o) exhibit strong visual state reasoning and future prediction capabilities. To bridge these strengths, we introduce VChain, a novel inference-time chain-of-visual-thought framework that injects visual reasoning signals from multimodal models into video generation. Spec","authors_text":"Gordon Chen, Haonan Qiu, Ning Yu, Paul Debevec, Ziqi Huang, Ziwei Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-10-06T17:57:59Z","title":"VChain: Chain-of-Visual-Thought for Reasoning in Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.05094","kind":"arxiv","version":2},"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:d58f8a38a07ddc408dacd97e5d30fc1befd3d7ac79ea8116d35f5ea9ed10ec8d","target":"record","created_at":"2026-05-22T01:03:47Z","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":"1ac2bc82ac6e692290a0a1d3aab6968e3c1643bb557bff440ca6d320421aa8b7","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-10-06T17:57:59Z","title_canon_sha256":"be8f7aecd3becdf931a558478f9db8d32187284f9729affc8053f084e6506fdd"},"schema_version":"1.0","source":{"id":"2510.05094","kind":"arxiv","version":2}},"canonical_sha256":"d6a0e03b29e288432183932ca11ed99f13f77b0f17bbc91b4f4eb3aee3161acd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d6a0e03b29e288432183932ca11ed99f13f77b0f17bbc91b4f4eb3aee3161acd","first_computed_at":"2026-05-22T01:03:47.699067Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-22T01:03:47.699067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"UaxAi9Fgw/QnT5CYZuK7/flKDTLk1V3bi0A0IhQRX51icPJj2DlqVwsGWNGenTfcNNdJjXwjZULcEAHE1usxDg==","signature_status":"signed_v1","signed_at":"2026-05-22T01:03:47.699941Z","signed_message":"canonical_sha256_bytes"},"source_id":"2510.05094","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d58f8a38a07ddc408dacd97e5d30fc1befd3d7ac79ea8116d35f5ea9ed10ec8d","sha256:1f976168aa4937dca214dace3d7d7153c830ae0a5ca6a70f8046188b241a54b0"],"state_sha256":"42c45fbd8581f78a1cd046f6e19bffffcfc91739cd9bf57906b78cc8410406aa"}