{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RT3YGQU4PIXIW4QXIC2Q3KM45R","short_pith_number":"pith:RT3YGQU4","schema_version":"1.0","canonical_sha256":"8cf783429c7a2e8b721740b50da99cec660fb62d9a98a7378c1fed3a573e51cc","source":{"kind":"arxiv","id":"2505.17768","version":2},"attestation_state":"computed","paper":{"title":"R-Genie: Reasoning-Guided Generative Image Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dong Zhang, Fei Shen, Jinhui Tang, Lingfeng He, Rui Yan","submitted_at":"2025-05-23T11:41:26Z","abstract_excerpt":"While recent advances in image editing have enabled impressive visual synthesis capabilities, current methods remain constrained by explicit textual instructions and limited editing operations, lacking deep comprehension of implicit user intentions and contextual reasoning. In this work, we introduce a new image editing paradigm: reasoning-guided generative editing, which synthesizes images based on complex, multi-faceted textual queries accepting world knowledge and intention inference. To facilitate this task, we first construct a comprehensive dataset featuring over 1,000 image-instruction-"},"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":"2505.17768","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-23T11:41:26Z","cross_cats_sorted":[],"title_canon_sha256":"561dd2b897e0376159b5aa519cc49373c9de806c2753f0ebc9f13626262eaa33","abstract_canon_sha256":"b05894037de81d9fc4792f2c18af1481cce042c91305647ed5925c180bb8f77f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:39:54.170217Z","signature_b64":"SeCsBNUvD1VAu4iEIjY++GQJ8zy936aOi9BsfhYlYh9z6BiIQ0uoDggdfV77yjfhdnT+My/iRLh8CZXm8jOPDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8cf783429c7a2e8b721740b50da99cec660fb62d9a98a7378c1fed3a573e51cc","last_reissued_at":"2026-07-05T11:39:54.169720Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:39:54.169720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"R-Genie: Reasoning-Guided Generative Image Editing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Dong Zhang, Fei Shen, Jinhui Tang, Lingfeng He, Rui Yan","submitted_at":"2025-05-23T11:41:26Z","abstract_excerpt":"While recent advances in image editing have enabled impressive visual synthesis capabilities, current methods remain constrained by explicit textual instructions and limited editing operations, lacking deep comprehension of implicit user intentions and contextual reasoning. In this work, we introduce a new image editing paradigm: reasoning-guided generative editing, which synthesizes images based on complex, multi-faceted textual queries accepting world knowledge and intention inference. To facilitate this task, we first construct a comprehensive dataset featuring over 1,000 image-instruction-"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.17768","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/2505.17768/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":"2505.17768","created_at":"2026-07-05T11:39:54.169782+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.17768v2","created_at":"2026-07-05T11:39:54.169782+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.17768","created_at":"2026-07-05T11:39:54.169782+00:00"},{"alias_kind":"pith_short_12","alias_value":"RT3YGQU4PIXI","created_at":"2026-07-05T11:39:54.169782+00:00"},{"alias_kind":"pith_short_16","alias_value":"RT3YGQU4PIXIW4QX","created_at":"2026-07-05T11:39:54.169782+00:00"},{"alias_kind":"pith_short_8","alias_value":"RT3YGQU4","created_at":"2026-07-05T11:39:54.169782+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.19103","citing_title":"ProductConsistency: Improving Product Identity Preservation in Instruction-Based Image Editing via SFT and RL","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2510.01186","citing_title":"ASTRA: Let Arbitrary Subjects Transform in Video Editing","ref_index":28,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RT3YGQU4PIXIW4QXIC2Q3KM45R","json":"https://pith.science/pith/RT3YGQU4PIXIW4QXIC2Q3KM45R.json","graph_json":"https://pith.science/api/pith-number/RT3YGQU4PIXIW4QXIC2Q3KM45R/graph.json","events_json":"https://pith.science/api/pith-number/RT3YGQU4PIXIW4QXIC2Q3KM45R/events.json","paper":"https://pith.science/paper/RT3YGQU4"},"agent_actions":{"view_html":"https://pith.science/pith/RT3YGQU4PIXIW4QXIC2Q3KM45R","download_json":"https://pith.science/pith/RT3YGQU4PIXIW4QXIC2Q3KM45R.json","view_paper":"https://pith.science/paper/RT3YGQU4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.17768&json=true","fetch_graph":"https://pith.science/api/pith-number/RT3YGQU4PIXIW4QXIC2Q3KM45R/graph.json","fetch_events":"https://pith.science/api/pith-number/RT3YGQU4PIXIW4QXIC2Q3KM45R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RT3YGQU4PIXIW4QXIC2Q3KM45R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RT3YGQU4PIXIW4QXIC2Q3KM45R/action/storage_attestation","attest_author":"https://pith.science/pith/RT3YGQU4PIXIW4QXIC2Q3KM45R/action/author_attestation","sign_citation":"https://pith.science/pith/RT3YGQU4PIXIW4QXIC2Q3KM45R/action/citation_signature","submit_replication":"https://pith.science/pith/RT3YGQU4PIXIW4QXIC2Q3KM45R/action/replication_record"}},"created_at":"2026-07-05T11:39:54.169782+00:00","updated_at":"2026-07-05T11:39:54.169782+00:00"}