{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:22QOAOZJ4KEEGIMDSMWKCHWZT4","short_pith_number":"pith:22QOAOZJ","schema_version":"1.0","canonical_sha256":"d6a0e03b29e288432183932ca11ed99f13f77b0f17bbc91b4f4eb3aee3161acd","source":{"kind":"arxiv","id":"2510.05094","version":2},"attestation_state":"computed","paper":{"title":"VChain: Chain-of-Visual-Thought for Reasoning in Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gordon Chen, Haonan Qiu, Ning Yu, Paul Debevec, Ziqi Huang, Ziwei Liu","submitted_at":"2025-10-06T17:57:59Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2510.05094","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-10-06T17:57:59Z","cross_cats_sorted":[],"title_canon_sha256":"be8f7aecd3becdf931a558478f9db8d32187284f9729affc8053f084e6506fdd","abstract_canon_sha256":"1ac2bc82ac6e692290a0a1d3aab6968e3c1643bb557bff440ca6d320421aa8b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-22T01:03:47.699941Z","signature_b64":"UaxAi9Fgw/QnT5CYZuK7/flKDTLk1V3bi0A0IhQRX51icPJj2DlqVwsGWNGenTfcNNdJjXwjZULcEAHE1usxDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6a0e03b29e288432183932ca11ed99f13f77b0f17bbc91b4f4eb3aee3161acd","last_reissued_at":"2026-05-22T01:03:47.699067Z","signature_status":"signed_v1","first_computed_at":"2026-05-22T01:03:47.699067Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"VChain: Chain-of-Visual-Thought for Reasoning in Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Gordon Chen, Haonan Qiu, Ning Yu, Paul Debevec, Ziqi Huang, Ziwei Liu","submitted_at":"2025-10-06T17:57:59Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.05094","kind":"arxiv","version":2},"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/2510.05094/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2510.05094","created_at":"2026-05-22T01:03:47.699196+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.05094v2","created_at":"2026-05-22T01:03:47.699196+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.05094","created_at":"2026-05-22T01:03:47.699196+00:00"},{"alias_kind":"pith_short_12","alias_value":"22QOAOZJ4KEE","created_at":"2026-05-22T01:03:47.699196+00:00"},{"alias_kind":"pith_short_16","alias_value":"22QOAOZJ4KEEGIMD","created_at":"2026-05-22T01:03:47.699196+00:00"},{"alias_kind":"pith_short_8","alias_value":"22QOAOZJ","created_at":"2026-05-22T01:03:47.699196+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":6,"sample":[{"citing_arxiv_id":"2604.08503","citing_title":"Phantom: Physics-Infused Video Generation via Joint Modeling of Visual and Latent Physical Dynamics","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2605.15458","citing_title":"Video Models Can Reason with Verifiable Rewards","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08735","citing_title":"CollabVR: Collaborative Video Reasoning with Vision-Language and Video Generation Models","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2604.22748","citing_title":"Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond","ref_index":157,"is_internal_anchor":true},{"citing_arxiv_id":"2604.08503","citing_title":"Phantom: Physics-Infused Video Generation via Joint Modeling of Visual and Latent Physical Dynamics","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2604.06161","citing_title":"DiffHDR: Re-Exposing LDR Videos with Video Diffusion Models","ref_index":39,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/22QOAOZJ4KEEGIMDSMWKCHWZT4","json":"https://pith.science/pith/22QOAOZJ4KEEGIMDSMWKCHWZT4.json","graph_json":"https://pith.science/api/pith-number/22QOAOZJ4KEEGIMDSMWKCHWZT4/graph.json","events_json":"https://pith.science/api/pith-number/22QOAOZJ4KEEGIMDSMWKCHWZT4/events.json","paper":"https://pith.science/paper/22QOAOZJ"},"agent_actions":{"view_html":"https://pith.science/pith/22QOAOZJ4KEEGIMDSMWKCHWZT4","download_json":"https://pith.science/pith/22QOAOZJ4KEEGIMDSMWKCHWZT4.json","view_paper":"https://pith.science/paper/22QOAOZJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.05094&json=true","fetch_graph":"https://pith.science/api/pith-number/22QOAOZJ4KEEGIMDSMWKCHWZT4/graph.json","fetch_events":"https://pith.science/api/pith-number/22QOAOZJ4KEEGIMDSMWKCHWZT4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/22QOAOZJ4KEEGIMDSMWKCHWZT4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/22QOAOZJ4KEEGIMDSMWKCHWZT4/action/storage_attestation","attest_author":"https://pith.science/pith/22QOAOZJ4KEEGIMDSMWKCHWZT4/action/author_attestation","sign_citation":"https://pith.science/pith/22QOAOZJ4KEEGIMDSMWKCHWZT4/action/citation_signature","submit_replication":"https://pith.science/pith/22QOAOZJ4KEEGIMDSMWKCHWZT4/action/replication_record"}},"created_at":"2026-05-22T01:03:47.699196+00:00","updated_at":"2026-05-22T01:03:47.699196+00:00"}