{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZFN2O7BMEHMKVZK4MDTTTO35ZE","short_pith_number":"pith:ZFN2O7BM","schema_version":"1.0","canonical_sha256":"c95ba77c2c21d8aae55c60e739bb7dc922e5de7e7cac581ac76223fb0b4c011a","source":{"kind":"arxiv","id":"2512.16864","version":2},"attestation_state":"computed","paper":{"title":"RePlan: Reasoning-guided Region Planning for Complex Instruction-based Image Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bei Yu, Bohao Peng, Dong Yu, Jiaya Jia, Lei Ke, Longxiang Tang, Tianyuan Qu, Xiaohang Zhan, Yuqi Liu","submitted_at":"2025-12-18T18:34:23Z","abstract_excerpt":"Instruction-based image editing enables natural-language control over visual modifications, yet existing models falter under Instruction-Visual Complexity (IV-Complexity), where intricate instructions meet cluttered or ambiguous scenes. We introduce RePlan (Region-aligned Planning), a plan-then-execute framework that couples a vision-language planner with a diffusion editor. The planner decomposes instructions via step-by-step reasoning and explicitly grounds them to target regions; the editor then applies changes using a training-free attention-region injection mechanism, enabling precise, pa"},"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":"2512.16864","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-12-18T18:34:23Z","cross_cats_sorted":[],"title_canon_sha256":"16a503c8b57d39e188b1634ae7af9bf4bce106b2dfeab27b531a08aa701bd08d","abstract_canon_sha256":"626049b84ec1613db5353590a0a82b0bb1852bfec5708c14cf9fc59a7e60aff4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-17T01:20:42.037933Z","signature_b64":"uCvqvoHst3M6NnSZpSV0yPdl5QZcMeFmY6xBL5V6+nqNmFyGMraHTl4yhdKkA7lkxRNALMH5nWYyBT5ShguEBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c95ba77c2c21d8aae55c60e739bb7dc922e5de7e7cac581ac76223fb0b4c011a","last_reissued_at":"2026-07-17T01:20:42.036935Z","signature_status":"signed_v1","first_computed_at":"2026-07-17T01:20:42.036935Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RePlan: Reasoning-guided Region Planning for Complex Instruction-based Image Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bei Yu, Bohao Peng, Dong Yu, Jiaya Jia, Lei Ke, Longxiang Tang, Tianyuan Qu, Xiaohang Zhan, Yuqi Liu","submitted_at":"2025-12-18T18:34:23Z","abstract_excerpt":"Instruction-based image editing enables natural-language control over visual modifications, yet existing models falter under Instruction-Visual Complexity (IV-Complexity), where intricate instructions meet cluttered or ambiguous scenes. We introduce RePlan (Region-aligned Planning), a plan-then-execute framework that couples a vision-language planner with a diffusion editor. The planner decomposes instructions via step-by-step reasoning and explicitly grounds them to target regions; the editor then applies changes using a training-free attention-region injection mechanism, enabling precise, pa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.16864","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/2512.16864/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":"2512.16864","created_at":"2026-07-17T01:20:42.037385+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.16864v2","created_at":"2026-07-17T01:20:42.037385+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.16864","created_at":"2026-07-17T01:20:42.037385+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZFN2O7BMEHMK","created_at":"2026-07-17T01:20:42.037385+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZFN2O7BMEHMKVZK4","created_at":"2026-07-17T01:20:42.037385+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZFN2O7BM","created_at":"2026-07-17T01:20:42.037385+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":7,"sample":[{"citing_arxiv_id":"2606.19103","citing_title":"ProductConsistency: Improving Product Identity Preservation in Instruction-Based Image Editing via SFT and RL","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2607.00920","citing_title":"GMO-E$^2$DIT: Grounded Multi-Operation Editing for E-Commerce Images","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2607.00920","citing_title":"GMO-E$^2$DIT: Grounded Multi-Operation Editing for E-Commerce Images","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2605.25568","citing_title":"Rethinking Scribble-Guided Image Editing: Generalization, Instruction Adherence, and Multi-Tasking","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2605.28805","citing_title":"OmniVerifier-M1: Multimodal Meta-Verifier with Explicit Structured Recalibration","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2604.25477","citing_title":"DDA-Thinker: Decoupled Dual-Atomic Reinforcement Learning for Reasoning-Driven Image Editing","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2604.15917","citing_title":"Making Image Editing Easier via Adaptive Task Reformulation with Agentic Executions","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZFN2O7BMEHMKVZK4MDTTTO35ZE","json":"https://pith.science/pith/ZFN2O7BMEHMKVZK4MDTTTO35ZE.json","graph_json":"https://pith.science/api/pith-number/ZFN2O7BMEHMKVZK4MDTTTO35ZE/graph.json","events_json":"https://pith.science/api/pith-number/ZFN2O7BMEHMKVZK4MDTTTO35ZE/events.json","paper":"https://pith.science/paper/ZFN2O7BM"},"agent_actions":{"view_html":"https://pith.science/pith/ZFN2O7BMEHMKVZK4MDTTTO35ZE","download_json":"https://pith.science/pith/ZFN2O7BMEHMKVZK4MDTTTO35ZE.json","view_paper":"https://pith.science/paper/ZFN2O7BM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.16864&json=true","fetch_graph":"https://pith.science/api/pith-number/ZFN2O7BMEHMKVZK4MDTTTO35ZE/graph.json","fetch_events":"https://pith.science/api/pith-number/ZFN2O7BMEHMKVZK4MDTTTO35ZE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZFN2O7BMEHMKVZK4MDTTTO35ZE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZFN2O7BMEHMKVZK4MDTTTO35ZE/action/storage_attestation","attest_author":"https://pith.science/pith/ZFN2O7BMEHMKVZK4MDTTTO35ZE/action/author_attestation","sign_citation":"https://pith.science/pith/ZFN2O7BMEHMKVZK4MDTTTO35ZE/action/citation_signature","submit_replication":"https://pith.science/pith/ZFN2O7BMEHMKVZK4MDTTTO35ZE/action/replication_record"}},"created_at":"2026-07-17T01:20:42.037385+00:00","updated_at":"2026-07-17T01:20:42.037385+00:00"}