{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DOFPGUK7VYF3IGXNK2SCIVNV24","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":"27f135510bace5cb08e2ba0a9e557b96faf6fe276a8db9d900404f50a20aae43","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-29T12:14:47Z","title_canon_sha256":"b09eff2550cbfc815651eabd97454b4c5a2dcb6fefbfffce677bfa8d2eea2896"},"schema_version":"1.0","source":{"id":"2504.20690","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2504.20690","created_at":"2026-05-17T23:38:47Z"},{"alias_kind":"arxiv_version","alias_value":"2504.20690v3","created_at":"2026-05-17T23:38:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.20690","created_at":"2026-05-17T23:38:47Z"},{"alias_kind":"pith_short_12","alias_value":"DOFPGUK7VYF3","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"DOFPGUK7VYF3IGXN","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"DOFPGUK7","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:4c7d6564b0e1f4b311511c6950ceeedd7287dd797bc64c989b7e52473e016416","target":"graph","created_at":"2026-05-17T23:38:47Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"ICEdit achieves state-of-the-art editing performance with only 0.1% of the training data and 1% trainable parameters compared to previous methods."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That the inherent comprehension and generation abilities of large-scale Diffusion Transformers can be effectively leveraged for precise instructional editing through an in-context paradigm without any architectural modifications."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"ICEdit achieves state-of-the-art instructional image editing in Diffusion Transformers via in-context generation, requiring only 0.1% of prior training data and 1% trainable parameters."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Large Diffusion Transformers perform precise instructional image editing via in-context generation without major retraining."}],"snapshot_sha256":"a30c54734c9e7ab2952e1db28f3caff75a0a24a0b731dd6cdb0869296cde5e7a"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"76fb4d9e70ba5fd058da1aa94c524198b6a56a3e291d4193f52fbbaab528c58e"},"paper":{"abstract_excerpt":"Instruction-based image editing enables precise modifications via natural language prompts, but existing methods face a precision-efficiency tradeoff: fine-tuning demands massive datasets (>10M) and computational resources, while training-free approaches suffer from weak instruction comprehension. We address this by proposing ICEdit, which leverages the inherent comprehension and generation abilities of large-scale Diffusion Transformers (DiTs) through three key innovations: (1) An in-context editing paradigm without architectural modifications; (2) Minimal parameter-efficient fine-tuning for ","authors_text":"Ji Xie, Yi Yang, Yu Lu, Zechuan Zhang, Zongxin Yang","cross_cats":[],"headline":"Large Diffusion Transformers perform precise instructional image editing via in-context generation without major retraining.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-29T12:14:47Z","title":"In-Context Edit: Enabling Instructional Image Editing with In-Context Generation in Large Scale Diffusion Transformer"},"references":{"count":60,"internal_anchors":13,"resolved_work":60,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Instructpix2pix: Learning to follow image editing instructions","work_id":"fd7a4946-0389-427a-bb45-c75d5e7c48c3","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Magicbrush: A manually annotated dataset for instruction-guided image editing.Advances in Neural Information Processing Systems, 36, 2024","work_id":"da65b41a-11ec-470b-8042-e8459a3c6095","year":2024},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Emu edit: Precise image editing via recognition and generation tasks","work_id":"041fd7a8-5b0e-41c8-9dd4-1750ebee5c81","year":2023},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"Ultraedit: Instruction-based fine-grained image editing at scale.Advances in Neural Information Processing Systems, 37:3058–3093, 2025","work_id":"63911165-3afc-4d06-8929-abf84f29ab58","year":2025},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"arXiv preprint arXiv:2309.17102 (2023)","work_id":"2bb3b94c-6b63-43cc-8c25-25ed4a0de29c","year":2023}],"snapshot_sha256":"8df2c86e799a633ea6a0b76f35c0d47ce4df2644664e872c963ef45ccd0c2e84"},"source":{"id":"2504.20690","kind":"arxiv","version":3},"verdict":{"created_at":"2026-05-16T16:04:06.609653Z","id":"1e73ec36-2161-4fe0-b2f0-207517cbbcb5","model_set":{"reader":"grok-4.3"},"one_line_summary":"ICEdit achieves state-of-the-art instructional image editing in Diffusion Transformers via in-context generation, requiring only 0.1% of prior training data and 1% trainable parameters.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Large Diffusion Transformers perform precise instructional image editing via in-context generation without major retraining.","strongest_claim":"ICEdit achieves state-of-the-art editing performance with only 0.1% of the training data and 1% trainable parameters compared to previous methods.","weakest_assumption":"That the inherent comprehension and generation abilities of large-scale Diffusion Transformers can be effectively leveraged for precise instructional editing through an in-context paradigm without any architectural modifications."}},"verdict_id":"1e73ec36-2161-4fe0-b2f0-207517cbbcb5"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:08c5c1d1c4a714992f884cb2715ec2f1f4138568c717698e388cc0889c0c39aa","target":"record","created_at":"2026-05-17T23:38:47Z","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":"27f135510bace5cb08e2ba0a9e557b96faf6fe276a8db9d900404f50a20aae43","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-29T12:14:47Z","title_canon_sha256":"b09eff2550cbfc815651eabd97454b4c5a2dcb6fefbfffce677bfa8d2eea2896"},"schema_version":"1.0","source":{"id":"2504.20690","kind":"arxiv","version":3}},"canonical_sha256":"1b8af3515fae0bb41aed56a42455b5d715a7b16f51b8b63ee579750d58984a0d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1b8af3515fae0bb41aed56a42455b5d715a7b16f51b8b63ee579750d58984a0d","first_computed_at":"2026-05-17T23:38:47.348564Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:38:47.348564Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RXPP073Ltu9/+s7/+Xz5VEBuZk2GVwYAsd0N58aporuHInlasDw8xbEyQhZ7ucWdZ0lrIPlFpt2M3Bm8tOJhBA==","signature_status":"signed_v1","signed_at":"2026-05-17T23:38:47.349279Z","signed_message":"canonical_sha256_bytes"},"source_id":"2504.20690","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:08c5c1d1c4a714992f884cb2715ec2f1f4138568c717698e388cc0889c0c39aa","sha256:4c7d6564b0e1f4b311511c6950ceeedd7287dd797bc64c989b7e52473e016416"],"state_sha256":"83e8ec9654b6075ef6efd2b12c6a56e30ae87623c21f1b736f2447f6bf4f84f2"}