{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VNN6J642KWHONVPK7C4D4W7TUI","short_pith_number":"pith:VNN6J642","schema_version":"1.0","canonical_sha256":"ab5be4fb9a558ee6d5eaf8b83e5bf3a236160b15675fa497403bf800ee7a992b","source":{"kind":"arxiv","id":"2511.01295","version":3},"attestation_state":"computed","paper":{"title":"UniREditBench: A Unified Reasoning-based Image Editing Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Gong, Cheng Jin, Chenglin Li, Dianyi Wang, Feng Han, Jiaqi Wang, Yang Jiao, Yibin Wang, Zheming Liang, Zhipeng Wei","submitted_at":"2025-11-03T07:24:57Z","abstract_excerpt":"Recent advances in multi-modal generative models have driven substantial improvements in image editing. However, current generative models still struggle with handling diverse and complex image editing tasks that require implicit reasoning, underscoring the need for a comprehensive benchmark to systematically assess their performance across various reasoning scenarios. Existing benchmarks primarily focus on single-object attribute transformation in realistic scenarios, which, while effective, encounter two key challenges: (1) they largely overlook multi-object interactions as well as game-worl"},"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":"2511.01295","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-11-03T07:24:57Z","cross_cats_sorted":[],"title_canon_sha256":"21e1bfdbf861c81a0bfedda80e893638eb7505ee54b448f96a7477a91723ef19","abstract_canon_sha256":"138078561ae38cd1c32218bd8e09e435c498b8fba2178a6f462428ba92d26e52"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-10T01:09:17.774512Z","signature_b64":"v5XhfIyqm550nkVscuOUpTboPBm89sapbJefom9gM23gpOSG69rzZSrowYghVyn/9FPTRCMa1svTLip6lH0gAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ab5be4fb9a558ee6d5eaf8b83e5bf3a236160b15675fa497403bf800ee7a992b","last_reissued_at":"2026-08-10T01:09:17.772011Z","signature_status":"signed_v1","first_computed_at":"2026-08-10T01:09:17.772011Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"UniREditBench: A Unified Reasoning-based Image Editing Benchmark","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Gong, Cheng Jin, Chenglin Li, Dianyi Wang, Feng Han, Jiaqi Wang, Yang Jiao, Yibin Wang, Zheming Liang, Zhipeng Wei","submitted_at":"2025-11-03T07:24:57Z","abstract_excerpt":"Recent advances in multi-modal generative models have driven substantial improvements in image editing. However, current generative models still struggle with handling diverse and complex image editing tasks that require implicit reasoning, underscoring the need for a comprehensive benchmark to systematically assess their performance across various reasoning scenarios. Existing benchmarks primarily focus on single-object attribute transformation in realistic scenarios, which, while effective, encounter two key challenges: (1) they largely overlook multi-object interactions as well as game-worl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.01295","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/2511.01295/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":"2511.01295","created_at":"2026-08-10T01:09:17.772863+00:00"},{"alias_kind":"arxiv_version","alias_value":"2511.01295v3","created_at":"2026-08-10T01:09:17.772863+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.01295","created_at":"2026-08-10T01:09:17.772863+00:00"},{"alias_kind":"pith_short_12","alias_value":"VNN6J642KWHO","created_at":"2026-08-10T01:09:17.772863+00:00"},{"alias_kind":"pith_short_16","alias_value":"VNN6J642KWHONVPK","created_at":"2026-08-10T01:09:17.772863+00:00"},{"alias_kind":"pith_short_8","alias_value":"VNN6J642","created_at":"2026-08-10T01:09:17.772863+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":11,"sample":[{"citing_arxiv_id":"2606.26551","citing_title":"PhyEditBench: A Real-World Multi-Stage Benchmark for Physics-Aware Image Editing","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2606.19073","citing_title":"Taming I2V models for Image HOI Editing: A Cognitive Benchmark and Agentic Self-Correcting Framework","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2606.26551","citing_title":"PhyEditBench: A Real-World Multi-Stage Benchmark for Physics-Aware Image Editing","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2606.00188","citing_title":"PaintBench: Deterministic Evaluation of Precise Visual Editing","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2605.22344","citing_title":"Bernini: Latent Semantic Planning for Video Diffusion","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2602.23622","citing_title":"DLEBench: Evaluating Small-scale Object Editing Ability for Instruction-based Image Editing Model","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12724","citing_title":"Inline Critic Steers Image Editing","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13062","citing_title":"Edit-Compass & EditReward-Compass: A Unified Benchmark for Image Editing and Reward Modeling","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08163","citing_title":"MULTITEXTEDIT: Benchmarking Cross-Lingual Degradation in Text-in-Image Editing","ref_index":51,"is_internal_anchor":true},{"citing_arxiv_id":"2605.01789","citing_title":"DataEvolver: Let Your Data Build and Improve Itself via Goal-Driven Loop Agents","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07477","citing_title":"ReasonEdit: Towards Interpretable Image Editing Evaluation via Reinforcement Learning","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VNN6J642KWHONVPK7C4D4W7TUI","json":"https://pith.science/pith/VNN6J642KWHONVPK7C4D4W7TUI.json","graph_json":"https://pith.science/api/pith-number/VNN6J642KWHONVPK7C4D4W7TUI/graph.json","events_json":"https://pith.science/api/pith-number/VNN6J642KWHONVPK7C4D4W7TUI/events.json","paper":"https://pith.science/paper/VNN6J642"},"agent_actions":{"view_html":"https://pith.science/pith/VNN6J642KWHONVPK7C4D4W7TUI","download_json":"https://pith.science/pith/VNN6J642KWHONVPK7C4D4W7TUI.json","view_paper":"https://pith.science/paper/VNN6J642","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2511.01295&json=true","fetch_graph":"https://pith.science/api/pith-number/VNN6J642KWHONVPK7C4D4W7TUI/graph.json","fetch_events":"https://pith.science/api/pith-number/VNN6J642KWHONVPK7C4D4W7TUI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VNN6J642KWHONVPK7C4D4W7TUI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VNN6J642KWHONVPK7C4D4W7TUI/action/storage_attestation","attest_author":"https://pith.science/pith/VNN6J642KWHONVPK7C4D4W7TUI/action/author_attestation","sign_citation":"https://pith.science/pith/VNN6J642KWHONVPK7C4D4W7TUI/action/citation_signature","submit_replication":"https://pith.science/pith/VNN6J642KWHONVPK7C4D4W7TUI/action/replication_record"}},"created_at":"2026-08-10T01:09:17.772863+00:00","updated_at":"2026-08-10T01:09:17.772863+00:00"}