{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PMYIN3OUYCFUBSBEPWZPT44VBS","short_pith_number":"pith:PMYIN3OU","schema_version":"1.0","canonical_sha256":"7b3086edd4c08b40c8247db2f9f3950c96f3dec701911fd35086ab0396cf4a86","source":{"kind":"arxiv","id":"2503.19839","version":2},"attestation_state":"computed","paper":{"title":"FireEdit: Fine-grained Instruction-based Image Editing via Region-aware Vision Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fa-Ting Hong, Hanhui Li, Jiahao Li, Jun Zhou, Qinglin Lu, Qin Lin, Xiaodan Liang, Yiji Cheng, Zunnan Xu","submitted_at":"2025-03-25T16:59:42Z","abstract_excerpt":"Currently, instruction-based image editing methods have made significant progress by leveraging the powerful cross-modal understanding capabilities of vision language models (VLMs). However, they still face challenges in three key areas: 1) complex scenarios; 2) semantic consistency; and 3) fine-grained editing. To address these issues, we propose FireEdit, an innovative Fine-grained Instruction-based image editing framework that exploits a REgion-aware VLM. FireEdit is designed to accurately comprehend user instructions and ensure effective control over the editing process. Specifically, we e"},"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":"2503.19839","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-25T16:59:42Z","cross_cats_sorted":[],"title_canon_sha256":"ad7324f9c74d28fa647501327824410b213f6be2b14b037987784222c52cef72","abstract_canon_sha256":"13587df092e4d64cea139e9563baf671559b801bd38b32864f2e3535d6420d56"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:41:22.968885Z","signature_b64":"29ljCsSYcU3AaYw0Q9xcTkW4F9Lba22/KID4mk88o1AuDog8tQfR4rxLsnltfkSXYOKhe3zCqrrtcWiSauWWBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b3086edd4c08b40c8247db2f9f3950c96f3dec701911fd35086ab0396cf4a86","last_reissued_at":"2026-07-05T10:41:22.968378Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:41:22.968378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FireEdit: Fine-grained Instruction-based Image Editing via Region-aware Vision Language Model","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Fa-Ting Hong, Hanhui Li, Jiahao Li, Jun Zhou, Qinglin Lu, Qin Lin, Xiaodan Liang, Yiji Cheng, Zunnan Xu","submitted_at":"2025-03-25T16:59:42Z","abstract_excerpt":"Currently, instruction-based image editing methods have made significant progress by leveraging the powerful cross-modal understanding capabilities of vision language models (VLMs). However, they still face challenges in three key areas: 1) complex scenarios; 2) semantic consistency; and 3) fine-grained editing. To address these issues, we propose FireEdit, an innovative Fine-grained Instruction-based image editing framework that exploits a REgion-aware VLM. FireEdit is designed to accurately comprehend user instructions and ensure effective control over the editing process. Specifically, we e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.19839","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/2503.19839/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":"2503.19839","created_at":"2026-07-05T10:41:22.968444+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.19839v2","created_at":"2026-07-05T10:41:22.968444+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.19839","created_at":"2026-07-05T10:41:22.968444+00:00"},{"alias_kind":"pith_short_12","alias_value":"PMYIN3OUYCFU","created_at":"2026-07-05T10:41:22.968444+00:00"},{"alias_kind":"pith_short_16","alias_value":"PMYIN3OUYCFUBSBE","created_at":"2026-07-05T10:41:22.968444+00:00"},{"alias_kind":"pith_short_8","alias_value":"PMYIN3OU","created_at":"2026-07-05T10:41:22.968444+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2507.01908","citing_title":"Reasoning to Edit: Hypothetical Instruction-Based Image Editing with Visual Reasoning","ref_index":23,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PMYIN3OUYCFUBSBEPWZPT44VBS","json":"https://pith.science/pith/PMYIN3OUYCFUBSBEPWZPT44VBS.json","graph_json":"https://pith.science/api/pith-number/PMYIN3OUYCFUBSBEPWZPT44VBS/graph.json","events_json":"https://pith.science/api/pith-number/PMYIN3OUYCFUBSBEPWZPT44VBS/events.json","paper":"https://pith.science/paper/PMYIN3OU"},"agent_actions":{"view_html":"https://pith.science/pith/PMYIN3OUYCFUBSBEPWZPT44VBS","download_json":"https://pith.science/pith/PMYIN3OUYCFUBSBEPWZPT44VBS.json","view_paper":"https://pith.science/paper/PMYIN3OU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.19839&json=true","fetch_graph":"https://pith.science/api/pith-number/PMYIN3OUYCFUBSBEPWZPT44VBS/graph.json","fetch_events":"https://pith.science/api/pith-number/PMYIN3OUYCFUBSBEPWZPT44VBS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PMYIN3OUYCFUBSBEPWZPT44VBS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PMYIN3OUYCFUBSBEPWZPT44VBS/action/storage_attestation","attest_author":"https://pith.science/pith/PMYIN3OUYCFUBSBEPWZPT44VBS/action/author_attestation","sign_citation":"https://pith.science/pith/PMYIN3OUYCFUBSBEPWZPT44VBS/action/citation_signature","submit_replication":"https://pith.science/pith/PMYIN3OUYCFUBSBEPWZPT44VBS/action/replication_record"}},"created_at":"2026-07-05T10:41:22.968444+00:00","updated_at":"2026-07-05T10:41:22.968444+00:00"}