{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6SUYVLX4J35AZKMMY4GBT5VL46","short_pith_number":"pith:6SUYVLX4","schema_version":"1.0","canonical_sha256":"f4a98aaefc4efa0ca98cc70c19f6abe7bbdda0916f6d5e638eb057043506cf3c","source":{"kind":"arxiv","id":"2506.04158","version":1},"attestation_state":"computed","paper":{"title":"Image Editing As Programs with Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Songhua Liu, Xinchao Wang, Xingyi Yang, Yujia Hu, Zhenxiong Tan","submitted_at":"2025-06-04T16:57:24Z","abstract_excerpt":"While diffusion models have achieved remarkable success in text-to-image generation, they encounter significant challenges with instruction-driven image editing. Our research highlights a key challenge: these models particularly struggle with structurally inconsistent edits that involve substantial layout changes. To mitigate this gap, we introduce Image Editing As Programs (IEAP), a unified image editing framework built upon the Diffusion Transformer (DiT) architecture. At its core, IEAP approaches instructional editing through a reductionist lens, decomposing complex editing instructions int"},"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":"2506.04158","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-04T16:57:24Z","cross_cats_sorted":[],"title_canon_sha256":"ea7b78a9404e5e05d6805dbdb11277027009e52b49e3a9248822cddc2ae3aebc","abstract_canon_sha256":"fff3caf738d1e4d43941bcfc3ddffe5ae4ded362ae206649c6510d4b4c6553af"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:58.172909Z","signature_b64":"kH2aGY3A8s7jjA/dG/ediZU9zAC0unCvsRoaGzkvn59qVUslQGJIGG4st8IysbMIpYrBxWCrq/lSr1nitsoUBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f4a98aaefc4efa0ca98cc70c19f6abe7bbdda0916f6d5e638eb057043506cf3c","last_reissued_at":"2026-07-05T11:15:58.172454Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:58.172454Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Image Editing As Programs with Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Songhua Liu, Xinchao Wang, Xingyi Yang, Yujia Hu, Zhenxiong Tan","submitted_at":"2025-06-04T16:57:24Z","abstract_excerpt":"While diffusion models have achieved remarkable success in text-to-image generation, they encounter significant challenges with instruction-driven image editing. Our research highlights a key challenge: these models particularly struggle with structurally inconsistent edits that involve substantial layout changes. To mitigate this gap, we introduce Image Editing As Programs (IEAP), a unified image editing framework built upon the Diffusion Transformer (DiT) architecture. At its core, IEAP approaches instructional editing through a reductionist lens, decomposing complex editing instructions int"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.04158","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/2506.04158/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":"2506.04158","created_at":"2026-07-05T11:15:58.172509+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.04158v1","created_at":"2026-07-05T11:15:58.172509+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.04158","created_at":"2026-07-05T11:15:58.172509+00:00"},{"alias_kind":"pith_short_12","alias_value":"6SUYVLX4J35A","created_at":"2026-07-05T11:15:58.172509+00:00"},{"alias_kind":"pith_short_16","alias_value":"6SUYVLX4J35AZKMM","created_at":"2026-07-05T11:15:58.172509+00:00"},{"alias_kind":"pith_short_8","alias_value":"6SUYVLX4","created_at":"2026-07-05T11:15:58.172509+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.05071","citing_title":"InstantRetouch: Efficient and High-Fidelity Instruction-Guided Image Retouching with Bilateral Space","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21190","citing_title":"Semantic Granularity Navigation in Image Editing","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21190","citing_title":"Semantic Granularity Navigation in Image Editing","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24625","citing_title":"Meta-CoT: Enhancing Granularity and Generalization in Image Editing","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01789","citing_title":"DataEvolver: Let Your Data Build and Improve Itself via Goal-Driven Loop Agents","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6SUYVLX4J35AZKMMY4GBT5VL46","json":"https://pith.science/pith/6SUYVLX4J35AZKMMY4GBT5VL46.json","graph_json":"https://pith.science/api/pith-number/6SUYVLX4J35AZKMMY4GBT5VL46/graph.json","events_json":"https://pith.science/api/pith-number/6SUYVLX4J35AZKMMY4GBT5VL46/events.json","paper":"https://pith.science/paper/6SUYVLX4"},"agent_actions":{"view_html":"https://pith.science/pith/6SUYVLX4J35AZKMMY4GBT5VL46","download_json":"https://pith.science/pith/6SUYVLX4J35AZKMMY4GBT5VL46.json","view_paper":"https://pith.science/paper/6SUYVLX4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.04158&json=true","fetch_graph":"https://pith.science/api/pith-number/6SUYVLX4J35AZKMMY4GBT5VL46/graph.json","fetch_events":"https://pith.science/api/pith-number/6SUYVLX4J35AZKMMY4GBT5VL46/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6SUYVLX4J35AZKMMY4GBT5VL46/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6SUYVLX4J35AZKMMY4GBT5VL46/action/storage_attestation","attest_author":"https://pith.science/pith/6SUYVLX4J35AZKMMY4GBT5VL46/action/author_attestation","sign_citation":"https://pith.science/pith/6SUYVLX4J35AZKMMY4GBT5VL46/action/citation_signature","submit_replication":"https://pith.science/pith/6SUYVLX4J35AZKMMY4GBT5VL46/action/replication_record"}},"created_at":"2026-07-05T11:15:58.172509+00:00","updated_at":"2026-07-05T11:15:58.172509+00:00"}