{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7APMQMQT366NALU32WBPELKDG7","short_pith_number":"pith:7APMQMQT","schema_version":"1.0","canonical_sha256":"f81ec83213dfbcd02e9bd582f22d4337ef99d8dd71c4c7d1c5cb5a53ab331b69","source":{"kind":"arxiv","id":"2412.07774","version":2},"attestation_state":"computed","paper":{"title":"UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hengshuang Zhao, He Zhang, Hui Ding, Jianming Zhang, Nanxuan Zhao, Qing Liu, Soo Ye Kim, Xi Chen, Yijun Li, Yilin Wang, Yuqian Zhou, Zhe Lin, Zhifei Zhang","submitted_at":"2024-12-10T18:59:55Z","abstract_excerpt":"We introduce UniReal, a unified framework designed to address various image generation and editing tasks. Existing solutions often vary by tasks, yet share fundamental principles: preserving consistency between inputs and outputs while capturing visual variations. Inspired by recent video generation models that effectively balance consistency and variation across frames, we propose a unifying approach that treats image-level tasks as discontinuous video generation. Specifically, we treat varying numbers of input and output images as frames, enabling seamless support for tasks such as image gen"},"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":"2412.07774","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-10T18:59:55Z","cross_cats_sorted":[],"title_canon_sha256":"bbc5262b7c4c38acd257fc30b3610f839548c070308c9ea27caffcab23050b3e","abstract_canon_sha256":"8f7180ae42a3fc092d068e1f8f66b8976051fb1f777ed3d9a755ec2b5ba122e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:47:58.387062Z","signature_b64":"ULKwZCYAFie6N6KdL+LjGaFeQNtRMnoRUC6g16ZIBp3ara8AR9hy4udc2/Ux4W6WF+/d/M2u0vSo7vLsUtMrBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f81ec83213dfbcd02e9bd582f22d4337ef99d8dd71c4c7d1c5cb5a53ab331b69","last_reissued_at":"2026-07-05T09:47:58.386615Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:47:58.386615Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniReal: Universal Image Generation and Editing via Learning Real-world Dynamics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hengshuang Zhao, He Zhang, Hui Ding, Jianming Zhang, Nanxuan Zhao, Qing Liu, Soo Ye Kim, Xi Chen, Yijun Li, Yilin Wang, Yuqian Zhou, Zhe Lin, Zhifei Zhang","submitted_at":"2024-12-10T18:59:55Z","abstract_excerpt":"We introduce UniReal, a unified framework designed to address various image generation and editing tasks. Existing solutions often vary by tasks, yet share fundamental principles: preserving consistency between inputs and outputs while capturing visual variations. Inspired by recent video generation models that effectively balance consistency and variation across frames, we propose a unifying approach that treats image-level tasks as discontinuous video generation. Specifically, we treat varying numbers of input and output images as frames, enabling seamless support for tasks such as image gen"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.07774","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/2412.07774/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":"2412.07774","created_at":"2026-07-05T09:47:58.386672+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.07774v2","created_at":"2026-07-05T09:47:58.386672+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.07774","created_at":"2026-07-05T09:47:58.386672+00:00"},{"alias_kind":"pith_short_12","alias_value":"7APMQMQT366N","created_at":"2026-07-05T09:47:58.386672+00:00"},{"alias_kind":"pith_short_16","alias_value":"7APMQMQT366NALU3","created_at":"2026-07-05T09:47:58.386672+00:00"},{"alias_kind":"pith_short_8","alias_value":"7APMQMQT","created_at":"2026-07-05T09:47:58.386672+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21337","citing_title":"DataClaw0: Agentic Tailoring Multimodal Data from Raw Streams","ref_index":53,"is_internal_anchor":false},{"citing_arxiv_id":"2503.07598","citing_title":"VACE: All-in-One Video Creation and Editing","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10859","citing_title":"Masked Generative Transformer Is What You Need for Image Editing","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23763","citing_title":"Edit Where You Mean: Region-Aware Adapter Injection for Mask-Free Local Image Editing","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00707","citing_title":"PhysEdit: Physically-Consistent Region-Aware Image Editing via Adaptive Spatio-Temporal Reasoning","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7APMQMQT366NALU32WBPELKDG7","json":"https://pith.science/pith/7APMQMQT366NALU32WBPELKDG7.json","graph_json":"https://pith.science/api/pith-number/7APMQMQT366NALU32WBPELKDG7/graph.json","events_json":"https://pith.science/api/pith-number/7APMQMQT366NALU32WBPELKDG7/events.json","paper":"https://pith.science/paper/7APMQMQT"},"agent_actions":{"view_html":"https://pith.science/pith/7APMQMQT366NALU32WBPELKDG7","download_json":"https://pith.science/pith/7APMQMQT366NALU32WBPELKDG7.json","view_paper":"https://pith.science/paper/7APMQMQT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.07774&json=true","fetch_graph":"https://pith.science/api/pith-number/7APMQMQT366NALU32WBPELKDG7/graph.json","fetch_events":"https://pith.science/api/pith-number/7APMQMQT366NALU32WBPELKDG7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7APMQMQT366NALU32WBPELKDG7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7APMQMQT366NALU32WBPELKDG7/action/storage_attestation","attest_author":"https://pith.science/pith/7APMQMQT366NALU32WBPELKDG7/action/author_attestation","sign_citation":"https://pith.science/pith/7APMQMQT366NALU32WBPELKDG7/action/citation_signature","submit_replication":"https://pith.science/pith/7APMQMQT366NALU32WBPELKDG7/action/replication_record"}},"created_at":"2026-07-05T09:47:58.386672+00:00","updated_at":"2026-07-05T09:47:58.386672+00:00"}