{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VETHRTUXH6F5WAEXRNDUQYWXT3","short_pith_number":"pith:VETHRTUX","schema_version":"1.0","canonical_sha256":"a92678ce973f8bdb00978b474862d79ed71d2c1f339b04b6140fc9ef342324d4","source":{"kind":"arxiv","id":"2503.19907","version":1},"attestation_state":"computed","paper":{"title":"FullDiT: Multi-Task Video Generative Foundation Model with Full Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Di Zhang, Kun Gai, Pengfei Wan, Qiang Xu, Qiulin Wang, Quande Liu, Weicai Ye, Xintao Wang, Xuan Ju","submitted_at":"2025-03-25T17:59:06Z","abstract_excerpt":"Current video generative foundation models primarily focus on text-to-video tasks, providing limited control for fine-grained video content creation. Although adapter-based approaches (e.g., ControlNet) enable additional controls with minimal fine-tuning, they encounter challenges when integrating multiple conditions, including: branch conflicts between independently trained adapters, parameter redundancy leading to increased computational cost, and suboptimal performance compared to full fine-tuning. To address these challenges, we introduce FullDiT, a unified foundation model for video gener"},"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":"2503.19907","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-03-25T17:59:06Z","cross_cats_sorted":[],"title_canon_sha256":"e7fd43f771ebf4329ec8e2ef81e41c3e7378c370a94b1537ac569d8a9b741208","abstract_canon_sha256":"1bdb346c03a26f17ee6d4a0471f3aff518a64ddbb7485eb0bae20dd64cf4bc9e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:39:03.397240Z","signature_b64":"QvFzhPZW6hBFPbN5nk7a3TMAAcxb7/iwCKwFYtENIZySHr9kGBcFxYa0eLFGbhnTn4IUJB4CzXSvCAIuIhONAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a92678ce973f8bdb00978b474862d79ed71d2c1f339b04b6140fc9ef342324d4","last_reissued_at":"2026-07-05T10:39:03.396785Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:39:03.396785Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FullDiT: Multi-Task Video Generative Foundation Model with Full Attention","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Di Zhang, Kun Gai, Pengfei Wan, Qiang Xu, Qiulin Wang, Quande Liu, Weicai Ye, Xintao Wang, Xuan Ju","submitted_at":"2025-03-25T17:59:06Z","abstract_excerpt":"Current video generative foundation models primarily focus on text-to-video tasks, providing limited control for fine-grained video content creation. Although adapter-based approaches (e.g., ControlNet) enable additional controls with minimal fine-tuning, they encounter challenges when integrating multiple conditions, including: branch conflicts between independently trained adapters, parameter redundancy leading to increased computational cost, and suboptimal performance compared to full fine-tuning. To address these challenges, we introduce FullDiT, a unified foundation model for video gener"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.19907","kind":"arxiv","version":1},"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/2503.19907/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":"2503.19907","created_at":"2026-07-05T10:39:03.396843+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.19907v1","created_at":"2026-07-05T10:39:03.396843+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.19907","created_at":"2026-07-05T10:39:03.396843+00:00"},{"alias_kind":"pith_short_12","alias_value":"VETHRTUXH6F5","created_at":"2026-07-05T10:39:03.396843+00:00"},{"alias_kind":"pith_short_16","alias_value":"VETHRTUXH6F5WAEX","created_at":"2026-07-05T10:39:03.396843+00:00"},{"alias_kind":"pith_short_8","alias_value":"VETHRTUX","created_at":"2026-07-05T10:39:03.396843+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01677","citing_title":"ICDepth: Taming Video Diffusion Models for Video Depth Estimation via In-Context Conditioning","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.07326","citing_title":"AnchorWorld: Embodied Egocentric World Simulation with View-based Evolution Customization","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23891","citing_title":"Smart-Insertion-V: Photorealistic Video Insertion via a Closed-Loop Feedback Dual-Stream Framework","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18678","citing_title":"Lance: Unified Multimodal Modeling by Multi-Task Synergy","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18678","citing_title":"Lance: Unified Multimodal Modeling by Multi-Task Synergy","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2512.07469","citing_title":"VideoCoF: Unified Video Editing with Temporal Reasoner","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13857","citing_title":"MoZoo:Unleashing Video Diffusion power in animal fur and muscle simulation","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09442","citing_title":"SWIFT: Prompt-Adaptive Memory for Efficient Interactive Long Video Generation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19193","citing_title":"How Far Are Video Models from True Multimodal Reasoning?","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07966","citing_title":"Lighting-grounded Video Generation with Renderer-based Agent Reasoning","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VETHRTUXH6F5WAEXRNDUQYWXT3","json":"https://pith.science/pith/VETHRTUXH6F5WAEXRNDUQYWXT3.json","graph_json":"https://pith.science/api/pith-number/VETHRTUXH6F5WAEXRNDUQYWXT3/graph.json","events_json":"https://pith.science/api/pith-number/VETHRTUXH6F5WAEXRNDUQYWXT3/events.json","paper":"https://pith.science/paper/VETHRTUX"},"agent_actions":{"view_html":"https://pith.science/pith/VETHRTUXH6F5WAEXRNDUQYWXT3","download_json":"https://pith.science/pith/VETHRTUXH6F5WAEXRNDUQYWXT3.json","view_paper":"https://pith.science/paper/VETHRTUX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.19907&json=true","fetch_graph":"https://pith.science/api/pith-number/VETHRTUXH6F5WAEXRNDUQYWXT3/graph.json","fetch_events":"https://pith.science/api/pith-number/VETHRTUXH6F5WAEXRNDUQYWXT3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VETHRTUXH6F5WAEXRNDUQYWXT3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VETHRTUXH6F5WAEXRNDUQYWXT3/action/storage_attestation","attest_author":"https://pith.science/pith/VETHRTUXH6F5WAEXRNDUQYWXT3/action/author_attestation","sign_citation":"https://pith.science/pith/VETHRTUXH6F5WAEXRNDUQYWXT3/action/citation_signature","submit_replication":"https://pith.science/pith/VETHRTUXH6F5WAEXRNDUQYWXT3/action/replication_record"}},"created_at":"2026-07-05T10:39:03.396843+00:00","updated_at":"2026-07-05T10:39:03.396843+00:00"}