{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:QX77AURYJKXWETQM72ZHDMZ3CR","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":"3dd0d98e3c1e90ce186f703400b2dac663880fde686900bbee43199fd6a9e964","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-06T19:08:18Z","title_canon_sha256":"ef73612f2fe36cf070955695b2bd98177c9786a14ed11c7b3bd1a81a6ec87ba6"},"schema_version":"1.0","source":{"id":"2402.04324","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.04324","created_at":"2026-07-05T08:38:05Z"},{"alias_kind":"arxiv_version","alias_value":"2402.04324v2","created_at":"2026-07-05T08:38:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.04324","created_at":"2026-07-05T08:38:05Z"},{"alias_kind":"pith_short_12","alias_value":"QX77AURYJKXW","created_at":"2026-07-05T08:38:05Z"},{"alias_kind":"pith_short_16","alias_value":"QX77AURYJKXWETQM","created_at":"2026-07-05T08:38:05Z"},{"alias_kind":"pith_short_8","alias_value":"QX77AURY","created_at":"2026-07-05T08:38:05Z"}],"graph_snapshots":[{"event_id":"sha256:d5523cd6595b89450b5c508fb72ea9e9173ac7936d65da76896a559becf1ef22","target":"graph","created_at":"2026-07-05T08:38:05Z","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/2402.04324/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Image-to-video (I2V) generation aims to use the initial frame (alongside a text prompt) to create a video sequence. A grand challenge in I2V generation is to maintain visual consistency throughout the video: existing methods often struggle to preserve the integrity of the subject, background, and style from the first frame, as well as ensure a fluid and logical progression within the video narrative. To mitigate these issues, we propose ConsistI2V, a diffusion-based method to enhance visual consistency for I2V generation. Specifically, we introduce (1) spatiotemporal attention over the first f","authors_text":"Cong Wei, Ge Zhang, Huan Yang, Weiming Ren, Wenhao Huang, Wenhu Chen, Xinrun Du","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-06T19:08:18Z","title":"ConsistI2V: Enhancing Visual Consistency for Image-to-Video Generation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.04324","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:fce2b1077c5490959c32b1dada0fe75ba3b26cdfff2603bef82687bddfb132ce","target":"record","created_at":"2026-07-05T08:38:05Z","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":"3dd0d98e3c1e90ce186f703400b2dac663880fde686900bbee43199fd6a9e964","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-02-06T19:08:18Z","title_canon_sha256":"ef73612f2fe36cf070955695b2bd98177c9786a14ed11c7b3bd1a81a6ec87ba6"},"schema_version":"1.0","source":{"id":"2402.04324","kind":"arxiv","version":2}},"canonical_sha256":"85fff052384aaf624e0cfeb271b33b14679bc02b2a144f278b67d2ac3125a6a2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"85fff052384aaf624e0cfeb271b33b14679bc02b2a144f278b67d2ac3125a6a2","first_computed_at":"2026-07-05T08:38:05.906134Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:38:05.906134Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"J3a2U4+IL0V5ZlPrjgHOW6C7McBS+v847ixvjRmrhgZsXeRKvlD639MRKOx+MbO2uxF4m2OO9SRw522f+vKVBA==","signature_status":"signed_v1","signed_at":"2026-07-05T08:38:05.906716Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.04324","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fce2b1077c5490959c32b1dada0fe75ba3b26cdfff2603bef82687bddfb132ce","sha256:d5523cd6595b89450b5c508fb72ea9e9173ac7936d65da76896a559becf1ef22"],"state_sha256":"adfbd5fd239ae06e4c177f0faaaed8cca68e35dfa798748aa3dd1e393829e8dd"}