{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:PMYIN3OUYCFUBSBEPWZPT44VBS","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":"13587df092e4d64cea139e9563baf671559b801bd38b32864f2e3535d6420d56","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-25T16:59:42Z","title_canon_sha256":"ad7324f9c74d28fa647501327824410b213f6be2b14b037987784222c52cef72"},"schema_version":"1.0","source":{"id":"2503.19839","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.19839","created_at":"2026-07-05T10:41:22Z"},{"alias_kind":"arxiv_version","alias_value":"2503.19839v2","created_at":"2026-07-05T10:41:22Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.19839","created_at":"2026-07-05T10:41:22Z"},{"alias_kind":"pith_short_12","alias_value":"PMYIN3OUYCFU","created_at":"2026-07-05T10:41:22Z"},{"alias_kind":"pith_short_16","alias_value":"PMYIN3OUYCFUBSBE","created_at":"2026-07-05T10:41:22Z"},{"alias_kind":"pith_short_8","alias_value":"PMYIN3OU","created_at":"2026-07-05T10:41:22Z"}],"graph_snapshots":[{"event_id":"sha256:905a0318f10089a80f717e9a3d7c8a303ec75d7f239e70341f950c7be2557b87","target":"graph","created_at":"2026-07-05T10:41:22Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2503.19839/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Fa-Ting Hong, Hanhui Li, Jiahao Li, Jun Zhou, Qinglin Lu, Qin Lin, Xiaodan Liang, Yiji Cheng, Zunnan Xu","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-25T16:59:42Z","title":"FireEdit: Fine-grained Instruction-based Image Editing via Region-aware Vision Language Model"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.19839","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:1d86f0527864f2055b5b064609720a0edeca3dfbe27147289ff093940de6a872","target":"record","created_at":"2026-07-05T10:41:22Z","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":"13587df092e4d64cea139e9563baf671559b801bd38b32864f2e3535d6420d56","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-25T16:59:42Z","title_canon_sha256":"ad7324f9c74d28fa647501327824410b213f6be2b14b037987784222c52cef72"},"schema_version":"1.0","source":{"id":"2503.19839","kind":"arxiv","version":2}},"canonical_sha256":"7b3086edd4c08b40c8247db2f9f3950c96f3dec701911fd35086ab0396cf4a86","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7b3086edd4c08b40c8247db2f9f3950c96f3dec701911fd35086ab0396cf4a86","first_computed_at":"2026-07-05T10:41:22.968378Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:41:22.968378Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"29ljCsSYcU3AaYw0Q9xcTkW4F9Lba22/KID4mk88o1AuDog8tQfR4rxLsnltfkSXYOKhe3zCqrrtcWiSauWWBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T10:41:22.968885Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.19839","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1d86f0527864f2055b5b064609720a0edeca3dfbe27147289ff093940de6a872","sha256:905a0318f10089a80f717e9a3d7c8a303ec75d7f239e70341f950c7be2557b87"],"state_sha256":"4a7fdc10c8ff257e04d88ec85bc4552cba16cd2165a9f43e55e71de939074570"}