{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:J7S7F6B6B6V4LY7KQQFJCUCDVI","short_pith_number":"pith:J7S7F6B6","schema_version":"1.0","canonical_sha256":"4fe5f2f83e0fabc5e3ea840a915043aa016dde961d65a3e269841e7e7e46d1c8","source":{"kind":"arxiv","id":"2505.11493","version":3},"attestation_state":"computed","paper":{"title":"GIE-Bench: Towards Grounded Evaluation for Text-Guided Image Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Chen, Jiasen Lu, Tsu-Jui Fu, Wenze Hu, Xinze Wang, Yinfei Yang, Yusu Qian, Zhe Gan","submitted_at":"2025-05-16T17:55:54Z","abstract_excerpt":"Editing images using natural language instructions has become a natural and expressive way to modify visual content; yet, evaluating the performance of such models remains challenging. Existing evaluation approaches often rely on image-text similarity metrics like CLIP, which lack precision. In this work, we introduce a new benchmark designed to evaluate text-guided image editing models in a more grounded manner, along two critical dimensions: (i) functional correctness, assessed via automatically generated multiple-choice questions that verify whether the intended change was successfully appl"},"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":"2505.11493","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-16T17:55:54Z","cross_cats_sorted":[],"title_canon_sha256":"d01a83c82d3baab872781e6961f50e0fb2d99bce51b39929d8452db2e7cb58df","abstract_canon_sha256":"347f0534e8d5270a500a290d92a419ee0dc0aabdd4519a589dd557f9363a8779"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:43:11.917804Z","signature_b64":"lIYiI2TATbiq9m3DJJNmVX6LXmpuhjlf/wx4TAtMIwMgO5iDAunJWXfHEo0BWEoOAA8RVcspkaAocN1/lp6FAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4fe5f2f83e0fabc5e3ea840a915043aa016dde961d65a3e269841e7e7e46d1c8","last_reissued_at":"2026-07-05T11:43:11.917298Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:43:11.917298Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GIE-Bench: Towards Grounded Evaluation for Text-Guided Image Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chen Chen, Jiasen Lu, Tsu-Jui Fu, Wenze Hu, Xinze Wang, Yinfei Yang, Yusu Qian, Zhe Gan","submitted_at":"2025-05-16T17:55:54Z","abstract_excerpt":"Editing images using natural language instructions has become a natural and expressive way to modify visual content; yet, evaluating the performance of such models remains challenging. Existing evaluation approaches often rely on image-text similarity metrics like CLIP, which lack precision. In this work, we introduce a new benchmark designed to evaluate text-guided image editing models in a more grounded manner, along two critical dimensions: (i) functional correctness, assessed via automatically generated multiple-choice questions that verify whether the intended change was successfully appl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11493","kind":"arxiv","version":3},"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/2505.11493/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":"2505.11493","created_at":"2026-07-05T11:43:11.917365+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.11493v3","created_at":"2026-07-05T11:43:11.917365+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11493","created_at":"2026-07-05T11:43:11.917365+00:00"},{"alias_kind":"pith_short_12","alias_value":"J7S7F6B6B6V4","created_at":"2026-07-05T11:43:11.917365+00:00"},{"alias_kind":"pith_short_16","alias_value":"J7S7F6B6B6V4LY7K","created_at":"2026-07-05T11:43:11.917365+00:00"},{"alias_kind":"pith_short_8","alias_value":"J7S7F6B6","created_at":"2026-07-05T11:43:11.917365+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.07051","citing_title":"Making Implicit Preservation Intent Explicit in Conversational Image Editing","ref_index":26,"is_internal_anchor":true},{"citing_arxiv_id":"2606.13303","citing_title":"DuET: Dual Expert Trajectories for Diffusion Image Editing","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01804","citing_title":"SpeechEditBench: A Bilingual Multi-Attribute Benchmark for Instruction-Guided Speech Editing","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01985","citing_title":"MT-EditFlow: Reinforcement Learning for Multi-Turn Image Editing with Flow Matching","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14842","citing_title":"Editor's Choice: Evaluating Abstract Intent in Image Editing through Atomic Entity Analysis","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2602.23622","citing_title":"DLEBench: Evaluating Small-scale Object Editing Ability for Instruction-based Image Editing Model","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08163","citing_title":"MULTITEXTEDIT: Benchmarking Cross-Lingual Degradation in Text-in-Image Editing","ref_index":20,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/J7S7F6B6B6V4LY7KQQFJCUCDVI","json":"https://pith.science/pith/J7S7F6B6B6V4LY7KQQFJCUCDVI.json","graph_json":"https://pith.science/api/pith-number/J7S7F6B6B6V4LY7KQQFJCUCDVI/graph.json","events_json":"https://pith.science/api/pith-number/J7S7F6B6B6V4LY7KQQFJCUCDVI/events.json","paper":"https://pith.science/paper/J7S7F6B6"},"agent_actions":{"view_html":"https://pith.science/pith/J7S7F6B6B6V4LY7KQQFJCUCDVI","download_json":"https://pith.science/pith/J7S7F6B6B6V4LY7KQQFJCUCDVI.json","view_paper":"https://pith.science/paper/J7S7F6B6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.11493&json=true","fetch_graph":"https://pith.science/api/pith-number/J7S7F6B6B6V4LY7KQQFJCUCDVI/graph.json","fetch_events":"https://pith.science/api/pith-number/J7S7F6B6B6V4LY7KQQFJCUCDVI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/J7S7F6B6B6V4LY7KQQFJCUCDVI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/J7S7F6B6B6V4LY7KQQFJCUCDVI/action/storage_attestation","attest_author":"https://pith.science/pith/J7S7F6B6B6V4LY7KQQFJCUCDVI/action/author_attestation","sign_citation":"https://pith.science/pith/J7S7F6B6B6V4LY7KQQFJCUCDVI/action/citation_signature","submit_replication":"https://pith.science/pith/J7S7F6B6B6V4LY7KQQFJCUCDVI/action/replication_record"}},"created_at":"2026-07-05T11:43:11.917365+00:00","updated_at":"2026-07-05T11:43:11.917365+00:00"}