{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZRUTVQOYKHM5U66BAGRZJ2JNO7","short_pith_number":"pith:ZRUTVQOY","schema_version":"1.0","canonical_sha256":"cc693ac1d851d9da7bc101a394e92d77fcd64888e6e27ba4a9298315f776500d","source":{"kind":"arxiv","id":"2504.04903","version":2},"attestation_state":"computed","paper":{"title":"Lumina-OmniLV: A Unified Multimodal Framework for General Low-Level Vision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chao Dong, Kaiwen Zhu, Le Zhuo, Liangbin Xie, Peng Gao, Wenlong Zhang, Xiangyu Chen, Yihao Liu, Yuandong Pu, Yu Qiao","submitted_at":"2025-04-07T10:22:00Z","abstract_excerpt":"We present Lunima-OmniLV (abbreviated as OmniLV), a universal multimodal multi-task framework for low-level vision that addresses over 100 sub-tasks across four major categories: image restoration, image enhancement, weak-semantic dense prediction, and stylization. OmniLV leverages both textual and visual prompts to offer flexible and user-friendly interactions. Built on Diffusion Transformer (DiT)-based generative priors, our framework supports arbitrary resolutions -- achieving optimal performance at 1K resolution -- while preserving fine-grained details and high fidelity. Through extensive "},"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":"2504.04903","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-07T10:22:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"443e8aba08c859c226d375f7841ca01480563630d005f17f16e45b3c033bf4c6","abstract_canon_sha256":"82f5a6c44e14165641aab288565c50e343b2cae7c92bb295b5636c044d6b4624"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:46:04.898151Z","signature_b64":"sdpDavofR8C5BCbp7u6YLyN5Mbf/RdFBgMQN2qDz+uLL/l8ITrTyBFdsSE06zv38IIUNnmrYQSTq2DHBOXS1Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cc693ac1d851d9da7bc101a394e92d77fcd64888e6e27ba4a9298315f776500d","last_reissued_at":"2026-07-05T10:46:04.897670Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:46:04.897670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lumina-OmniLV: A Unified Multimodal Framework for General Low-Level Vision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Chao Dong, Kaiwen Zhu, Le Zhuo, Liangbin Xie, Peng Gao, Wenlong Zhang, Xiangyu Chen, Yihao Liu, Yuandong Pu, Yu Qiao","submitted_at":"2025-04-07T10:22:00Z","abstract_excerpt":"We present Lunima-OmniLV (abbreviated as OmniLV), a universal multimodal multi-task framework for low-level vision that addresses over 100 sub-tasks across four major categories: image restoration, image enhancement, weak-semantic dense prediction, and stylization. OmniLV leverages both textual and visual prompts to offer flexible and user-friendly interactions. Built on Diffusion Transformer (DiT)-based generative priors, our framework supports arbitrary resolutions -- achieving optimal performance at 1K resolution -- while preserving fine-grained details and high fidelity. Through extensive "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.04903","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/2504.04903/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":"2504.04903","created_at":"2026-07-05T10:46:04.897736+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.04903v2","created_at":"2026-07-05T10:46:04.897736+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.04903","created_at":"2026-07-05T10:46:04.897736+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZRUTVQOYKHM5","created_at":"2026-07-05T10:46:04.897736+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZRUTVQOYKHM5U66B","created_at":"2026-07-05T10:46:04.897736+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZRUTVQOY","created_at":"2026-07-05T10:46:04.897736+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17557","citing_title":"Universal Image Restoration via Internalized Chain-of-Thought Reasoning","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2504.17761","citing_title":"Step1X-Edit: A Practical Framework for General Image Editing","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20258","citing_title":"Rethinking Where to Edit: Task-Aware Localization for Instruction-Based Image Editing","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZRUTVQOYKHM5U66BAGRZJ2JNO7","json":"https://pith.science/pith/ZRUTVQOYKHM5U66BAGRZJ2JNO7.json","graph_json":"https://pith.science/api/pith-number/ZRUTVQOYKHM5U66BAGRZJ2JNO7/graph.json","events_json":"https://pith.science/api/pith-number/ZRUTVQOYKHM5U66BAGRZJ2JNO7/events.json","paper":"https://pith.science/paper/ZRUTVQOY"},"agent_actions":{"view_html":"https://pith.science/pith/ZRUTVQOYKHM5U66BAGRZJ2JNO7","download_json":"https://pith.science/pith/ZRUTVQOYKHM5U66BAGRZJ2JNO7.json","view_paper":"https://pith.science/paper/ZRUTVQOY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.04903&json=true","fetch_graph":"https://pith.science/api/pith-number/ZRUTVQOYKHM5U66BAGRZJ2JNO7/graph.json","fetch_events":"https://pith.science/api/pith-number/ZRUTVQOYKHM5U66BAGRZJ2JNO7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZRUTVQOYKHM5U66BAGRZJ2JNO7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZRUTVQOYKHM5U66BAGRZJ2JNO7/action/storage_attestation","attest_author":"https://pith.science/pith/ZRUTVQOYKHM5U66BAGRZJ2JNO7/action/author_attestation","sign_citation":"https://pith.science/pith/ZRUTVQOYKHM5U66BAGRZJ2JNO7/action/citation_signature","submit_replication":"https://pith.science/pith/ZRUTVQOYKHM5U66BAGRZJ2JNO7/action/replication_record"}},"created_at":"2026-07-05T10:46:04.897736+00:00","updated_at":"2026-07-05T10:46:04.897736+00:00"}