{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:IO27BK4LUQOOUQXHGVW6ZRJJDT","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":"5ac438cd42f8891cf3086078872e1aa361a04170651b02a3c86c0406a566c287","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-11T17:54:11Z","title_canon_sha256":"7e6d84131ebfffc84d6d4fa81f5ec0cd6aa0c1be1c810b89d82ae253c6db6268"},"schema_version":"1.0","source":{"id":"2312.06739","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.06739","created_at":"2026-07-05T07:22:52Z"},{"alias_kind":"arxiv_version","alias_value":"2312.06739v1","created_at":"2026-07-05T07:22:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.06739","created_at":"2026-07-05T07:22:52Z"},{"alias_kind":"pith_short_12","alias_value":"IO27BK4LUQOO","created_at":"2026-07-05T07:22:52Z"},{"alias_kind":"pith_short_16","alias_value":"IO27BK4LUQOOUQXH","created_at":"2026-07-05T07:22:52Z"},{"alias_kind":"pith_short_8","alias_value":"IO27BK4L","created_at":"2026-07-05T07:22:52Z"}],"graph_snapshots":[{"event_id":"sha256:00d87220cf8b97d4d31f3ccbf7caabe15104ab5bb9277bcbd7f9e42aaf133480","target":"graph","created_at":"2026-07-05T07:22:52Z","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/2312.06739/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current instruction-based editing methods, such as InstructPix2Pix, often fail to produce satisfactory results in complex scenarios due to their dependence on the simple CLIP text encoder in diffusion models. To rectify this, this paper introduces SmartEdit, a novel approach to instruction-based image editing that leverages Multimodal Large Language Models (MLLMs) to enhance their understanding and reasoning capabilities. However, direct integration of these elements still faces challenges in situations requiring complex reasoning. To mitigate this, we propose a Bidirectional Interaction Modul","authors_text":"Chao Dong, Jiantao Zhou, Liangbin Xie, Rui Huang, Ruimao Zhang, Xiaodong Cun, Xintao Wang, Ying Shan, Yixiao Ge, Yuzhou Huang, Ziyang Yuan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-11T17:54:11Z","title":"SmartEdit: Exploring Complex Instruction-based Image Editing with Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.06739","kind":"arxiv","version":1},"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":"sha256:4fe65cfb0c05999c067671370c79bb31c3d900094e2930cc4ad92ed746bc37ff","target":"record","created_at":"2026-07-05T07:22:52Z","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":"5ac438cd42f8891cf3086078872e1aa361a04170651b02a3c86c0406a566c287","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-11T17:54:11Z","title_canon_sha256":"7e6d84131ebfffc84d6d4fa81f5ec0cd6aa0c1be1c810b89d82ae253c6db6268"},"schema_version":"1.0","source":{"id":"2312.06739","kind":"arxiv","version":1}},"canonical_sha256":"43b5f0ab8ba41cea42e7356decc5291cdd7b94a419bf05ea95c222ad75ee71d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"43b5f0ab8ba41cea42e7356decc5291cdd7b94a419bf05ea95c222ad75ee71d2","first_computed_at":"2026-07-05T07:22:52.204278Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:22:52.204278Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ds2I1fZEPZyrvitVYqByWgFNBeUj8Agb08Jsx7qDn6+czxAJmZOXW3rPKaxbgPLqNVZ6dCb8sB6t80nNeRCmCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:22:52.204696Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.06739","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4fe65cfb0c05999c067671370c79bb31c3d900094e2930cc4ad92ed746bc37ff","sha256:00d87220cf8b97d4d31f3ccbf7caabe15104ab5bb9277bcbd7f9e42aaf133480"],"state_sha256":"4e17c3fc563c17bfa7282f2f24c16465ed5fcccca2015851e4898fd18df30775"}