{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:IZRENXWQ7T23X2U5KLXTT6ZQAT","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":"28a303144ae89f3786e49109319b0d584aa351d638dfa239852f0fd0b37f07c5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-26T12:29:34Z","title_canon_sha256":"b9078af984075128142eae5cd63984542577d17f3533465c569f6bd4715362f6"},"schema_version":"1.0","source":{"id":"2505.19901","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.19901","created_at":"2026-07-05T11:15:00Z"},{"alias_kind":"arxiv_version","alias_value":"2505.19901v3","created_at":"2026-07-05T11:15:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19901","created_at":"2026-07-05T11:15:00Z"},{"alias_kind":"pith_short_12","alias_value":"IZRENXWQ7T23","created_at":"2026-07-05T11:15:00Z"},{"alias_kind":"pith_short_16","alias_value":"IZRENXWQ7T23X2U5","created_at":"2026-07-05T11:15:00Z"},{"alias_kind":"pith_short_8","alias_value":"IZRENXWQ","created_at":"2026-07-05T11:15:00Z"}],"graph_snapshots":[{"event_id":"sha256:b4a8b676b1b25157b6bd5d0ca8b2e51f8028516c5243522253fd93f359fc4afa","target":"graph","created_at":"2026-07-05T11:15:00Z","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/2505.19901/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in image-to-video (I2V) generation have shown promising performance in conventional scenarios. However, these methods still encounter significant challenges when dealing with complex scenes that require a deep understanding of nuanced motion and intricate object-action relationships. To address these challenges, we present Dynamic-I2V, an innovative framework that integrates Multimodal Large Language Models (MLLMs) to jointly encode visual and textual conditions for a diffusion transformer (DiT) architecture. By leveraging the advanced multimodal understanding capabilities ","authors_text":"Fengkai Liu, Haonan Lu, Peng Liu, Qingsong Xie, Quanlong Zheng, Xiaoming Ren, Yanhao Zhang, Yujiu Yang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-26T12:29:34Z","title":"Dynamic-I2V: Exploring Image-to-Video Generation Models via Multimodal LLM"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19901","kind":"arxiv","version":3},"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:f476414fd76b5625e5ae54848572efd5ca9a68c880c898fef9e5462a4b1aca4e","target":"record","created_at":"2026-07-05T11:15:00Z","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":"28a303144ae89f3786e49109319b0d584aa351d638dfa239852f0fd0b37f07c5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-26T12:29:34Z","title_canon_sha256":"b9078af984075128142eae5cd63984542577d17f3533465c569f6bd4715362f6"},"schema_version":"1.0","source":{"id":"2505.19901","kind":"arxiv","version":3}},"canonical_sha256":"466246ded0fcf5bbea9d52ef39fb3004c4ee35f63652c96c46b8ef36a56167f4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"466246ded0fcf5bbea9d52ef39fb3004c4ee35f63652c96c46b8ef36a56167f4","first_computed_at":"2026-07-05T11:15:00.240249Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:15:00.240249Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"LDpfWNno3k52rWyOpPwO2hunj3gxcLCuGEF0ZqO15RNJ8wWw1A3Xqo6kHYAy8NJxoaZ/z5amyrzffgoBsD6PAg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:15:00.240681Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.19901","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f476414fd76b5625e5ae54848572efd5ca9a68c880c898fef9e5462a4b1aca4e","sha256:b4a8b676b1b25157b6bd5d0ca8b2e51f8028516c5243522253fd93f359fc4afa"],"state_sha256":"9b3c19f2f47529daa1ff09c4a7180a1021b77e7e3daf94bdb53b8b73efec6c4b"}