{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:YGRVTMJSD3EXBV6Z2ZHFOTQFZH","short_pith_number":"pith:YGRVTMJS","schema_version":"1.0","canonical_sha256":"c1a359b1321ec970d7d9d64e574e05c9f5825d096dce886861214470b7b27e70","source":{"kind":"arxiv","id":"2605.21487","version":1},"attestation_state":"computed","paper":{"title":"Uni-Edit: Intelligent Editing Is A General Task For Unified Model Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dian Zheng, Hongbo Liu, Hongsheng Li, Hongyu Li, Kaituo Feng, Kai Zou, Manyuan Zhang","submitted_at":"2026-05-20T17:59:42Z","abstract_excerpt":"Currently, enhancing Unified Multimodal Models (UMMs) with image understanding, generation, and editing capabilities mainly relies on mixed multi-task training. Due to inherent task conflicts, such strategy requires complex multi-stage pipelines, massive data mixing, and balancing tricks, merely resulting in a performance trade-off rather than true mutual reinforcement. To break this paradigm, we propose Uni-Edit, an intelligent image editing task that serves as the first general task for UMM tuning. Unlike complex mixed pipelines, Uni-Edit improves performance across all three abilities at on"},"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":"2605.21487","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-20T17:59:42Z","cross_cats_sorted":[],"title_canon_sha256":"243f118a518546fef080b000cb6836718c9abe803a4a5f98913c7dcdb8221420","abstract_canon_sha256":"2644b0da0554a5ffa43aadb36e932e6b75f3b0cd371e1eb169a47791e8e83436"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T02:05:39.629864Z","signature_b64":"jycqjCXw1ZRkJcVsjT49MMQ6bi+H9RDYbP4955ppgbbdsYhJDbQxHo/N6z1rxCzCnWCTBe5q0wOEBne9ozT0AA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c1a359b1321ec970d7d9d64e574e05c9f5825d096dce886861214470b7b27e70","last_reissued_at":"2026-05-21T02:05:39.629122Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T02:05:39.629122Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uni-Edit: Intelligent Editing Is A General Task For Unified Model Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dian Zheng, Hongbo Liu, Hongsheng Li, Hongyu Li, Kaituo Feng, Kai Zou, Manyuan Zhang","submitted_at":"2026-05-20T17:59:42Z","abstract_excerpt":"Currently, enhancing Unified Multimodal Models (UMMs) with image understanding, generation, and editing capabilities mainly relies on mixed multi-task training. Due to inherent task conflicts, such strategy requires complex multi-stage pipelines, massive data mixing, and balancing tricks, merely resulting in a performance trade-off rather than true mutual reinforcement. To break this paradigm, we propose Uni-Edit, an intelligent image editing task that serves as the first general task for UMM tuning. Unlike complex mixed pipelines, Uni-Edit improves performance across all three abilities at on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21487","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/2605.21487/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":"2605.21487","created_at":"2026-05-21T02:05:39.629231+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.21487v1","created_at":"2026-05-21T02:05:39.629231+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21487","created_at":"2026-05-21T02:05:39.629231+00:00"},{"alias_kind":"pith_short_12","alias_value":"YGRVTMJSD3EX","created_at":"2026-05-21T02:05:39.629231+00:00"},{"alias_kind":"pith_short_16","alias_value":"YGRVTMJSD3EXBV6Z","created_at":"2026-05-21T02:05:39.629231+00:00"},{"alias_kind":"pith_short_8","alias_value":"YGRVTMJS","created_at":"2026-05-21T02:05:39.629231+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YGRVTMJSD3EXBV6Z2ZHFOTQFZH","json":"https://pith.science/pith/YGRVTMJSD3EXBV6Z2ZHFOTQFZH.json","graph_json":"https://pith.science/api/pith-number/YGRVTMJSD3EXBV6Z2ZHFOTQFZH/graph.json","events_json":"https://pith.science/api/pith-number/YGRVTMJSD3EXBV6Z2ZHFOTQFZH/events.json","paper":"https://pith.science/paper/YGRVTMJS"},"agent_actions":{"view_html":"https://pith.science/pith/YGRVTMJSD3EXBV6Z2ZHFOTQFZH","download_json":"https://pith.science/pith/YGRVTMJSD3EXBV6Z2ZHFOTQFZH.json","view_paper":"https://pith.science/paper/YGRVTMJS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.21487&json=true","fetch_graph":"https://pith.science/api/pith-number/YGRVTMJSD3EXBV6Z2ZHFOTQFZH/graph.json","fetch_events":"https://pith.science/api/pith-number/YGRVTMJSD3EXBV6Z2ZHFOTQFZH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YGRVTMJSD3EXBV6Z2ZHFOTQFZH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YGRVTMJSD3EXBV6Z2ZHFOTQFZH/action/storage_attestation","attest_author":"https://pith.science/pith/YGRVTMJSD3EXBV6Z2ZHFOTQFZH/action/author_attestation","sign_citation":"https://pith.science/pith/YGRVTMJSD3EXBV6Z2ZHFOTQFZH/action/citation_signature","submit_replication":"https://pith.science/pith/YGRVTMJSD3EXBV6Z2ZHFOTQFZH/action/replication_record"}},"created_at":"2026-05-21T02:05:39.629231+00:00","updated_at":"2026-05-21T02:05:39.629231+00:00"}