{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:Q34QCN3K5SMQN4KBDPQYDO3J44","short_pith_number":"pith:Q34QCN3K","canonical_record":{"source":{"id":"2309.17102","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-29T10:01:50Z","cross_cats_sorted":[],"title_canon_sha256":"554ed35fdd4b839a26c3e0dc7637b1fda9af7a7445939fc493e08d627befea42","abstract_canon_sha256":"ee9790f85fbbd9820aea9145d77703b56271ac8f64c364802760fb742b2a8b7a"},"schema_version":"1.0"},"canonical_sha256":"86f901376aec9906f1411be181bb69e70044e18bcced93defd8c767de81aa0f2","source":{"kind":"arxiv","id":"2309.17102","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.17102","created_at":"2026-07-05T07:40:57Z"},{"alias_kind":"arxiv_version","alias_value":"2309.17102v2","created_at":"2026-07-05T07:40:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.17102","created_at":"2026-07-05T07:40:57Z"},{"alias_kind":"pith_short_12","alias_value":"Q34QCN3K5SMQ","created_at":"2026-07-05T07:40:57Z"},{"alias_kind":"pith_short_16","alias_value":"Q34QCN3K5SMQN4KB","created_at":"2026-07-05T07:40:57Z"},{"alias_kind":"pith_short_8","alias_value":"Q34QCN3K","created_at":"2026-07-05T07:40:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:Q34QCN3K5SMQN4KBDPQYDO3J44","target":"record","payload":{"canonical_record":{"source":{"id":"2309.17102","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-29T10:01:50Z","cross_cats_sorted":[],"title_canon_sha256":"554ed35fdd4b839a26c3e0dc7637b1fda9af7a7445939fc493e08d627befea42","abstract_canon_sha256":"ee9790f85fbbd9820aea9145d77703b56271ac8f64c364802760fb742b2a8b7a"},"schema_version":"1.0"},"canonical_sha256":"86f901376aec9906f1411be181bb69e70044e18bcced93defd8c767de81aa0f2","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:40:57.595804Z","signature_b64":"eIU4VGfpnA1R0TXstq9IhToatRCvMXFKIaGgn5XQkrmlenyOFGMM59iYn5yrSOCqbAkfZ3twFGbT9jhQ1mbyCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86f901376aec9906f1411be181bb69e70044e18bcced93defd8c767de81aa0f2","last_reissued_at":"2026-07-05T07:40:57.595254Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:40:57.595254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2309.17102","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:40:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rQf9qXhD5b2UyLFX/5VLAIFOg81a+0EwhP2c6MHrxM/7JHSAL25V5mnw7uB79uvt1ztKyYxecv7EVRRd62FIAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:19:16.181862Z"},"content_sha256":"e842c2733ddde33448918ab99329697b97c1059c381bb079bda619e4660fde23","schema_version":"1.0","event_id":"sha256:e842c2733ddde33448918ab99329697b97c1059c381bb079bda619e4660fde23"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:Q34QCN3K5SMQN4KBDPQYDO3J44","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Guiding Instruction-based Image Editing via Multimodal Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Tsu-Jui Fu, Wenze Hu, William Yang Wang, Xianzhi Du, Yinfei Yang, Zhe Gan","submitted_at":"2023-09-29T10:01:50Z","abstract_excerpt":"Instruction-based image editing improves the controllability and flexibility of image manipulation via natural commands without elaborate descriptions or regional masks. However, human instructions are sometimes too brief for current methods to capture and follow. Multimodal large language models (MLLMs) show promising capabilities in cross-modal understanding and visual-aware response generation via LMs. We investigate how MLLMs facilitate edit instructions and present MLLM-Guided Image Editing (MGIE). MGIE learns to derive expressive instructions and provides explicit guidance. The editing m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.17102","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/2309.17102/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:40:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5B6Cyk4iuO86iNeKY5nQ6j4OPjfcAcdvF8ds7xOUxUA+LTJ6vvN7dhjggaG7uv/107d992JAM2txaXTFtcGnCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T09:19:16.182726Z"},"content_sha256":"af6671c2a05c66894bcff96167f083396f2be7f9ae0c3a5fdc7ac3642ffb15ba","schema_version":"1.0","event_id":"sha256:af6671c2a05c66894bcff96167f083396f2be7f9ae0c3a5fdc7ac3642ffb15ba"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/Q34QCN3K5SMQN4KBDPQYDO3J44/bundle.json","state_url":"https://pith.science/pith/Q34QCN3K5SMQN4KBDPQYDO3J44/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/Q34QCN3K5SMQN4KBDPQYDO3J44/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-04T09:19:16Z","links":{"resolver":"https://pith.science/pith/Q34QCN3K5SMQN4KBDPQYDO3J44","bundle":"https://pith.science/pith/Q34QCN3K5SMQN4KBDPQYDO3J44/bundle.json","state":"https://pith.science/pith/Q34QCN3K5SMQN4KBDPQYDO3J44/state.json","well_known_bundle":"https://pith.science/.well-known/pith/Q34QCN3K5SMQN4KBDPQYDO3J44/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:Q34QCN3K5SMQN4KBDPQYDO3J44","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":"ee9790f85fbbd9820aea9145d77703b56271ac8f64c364802760fb742b2a8b7a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-29T10:01:50Z","title_canon_sha256":"554ed35fdd4b839a26c3e0dc7637b1fda9af7a7445939fc493e08d627befea42"},"schema_version":"1.0","source":{"id":"2309.17102","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2309.17102","created_at":"2026-07-05T07:40:57Z"},{"alias_kind":"arxiv_version","alias_value":"2309.17102v2","created_at":"2026-07-05T07:40:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.17102","created_at":"2026-07-05T07:40:57Z"},{"alias_kind":"pith_short_12","alias_value":"Q34QCN3K5SMQ","created_at":"2026-07-05T07:40:57Z"},{"alias_kind":"pith_short_16","alias_value":"Q34QCN3K5SMQN4KB","created_at":"2026-07-05T07:40:57Z"},{"alias_kind":"pith_short_8","alias_value":"Q34QCN3K","created_at":"2026-07-05T07:40:57Z"}],"graph_snapshots":[{"event_id":"sha256:af6671c2a05c66894bcff96167f083396f2be7f9ae0c3a5fdc7ac3642ffb15ba","target":"graph","created_at":"2026-07-05T07:40:57Z","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/2309.17102/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Instruction-based image editing improves the controllability and flexibility of image manipulation via natural commands without elaborate descriptions or regional masks. However, human instructions are sometimes too brief for current methods to capture and follow. Multimodal large language models (MLLMs) show promising capabilities in cross-modal understanding and visual-aware response generation via LMs. We investigate how MLLMs facilitate edit instructions and present MLLM-Guided Image Editing (MGIE). MGIE learns to derive expressive instructions and provides explicit guidance. The editing m","authors_text":"Tsu-Jui Fu, Wenze Hu, William Yang Wang, Xianzhi Du, Yinfei Yang, Zhe Gan","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-29T10:01:50Z","title":"Guiding Instruction-based Image Editing via Multimodal Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.17102","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:e842c2733ddde33448918ab99329697b97c1059c381bb079bda619e4660fde23","target":"record","created_at":"2026-07-05T07:40:57Z","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":"ee9790f85fbbd9820aea9145d77703b56271ac8f64c364802760fb742b2a8b7a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-09-29T10:01:50Z","title_canon_sha256":"554ed35fdd4b839a26c3e0dc7637b1fda9af7a7445939fc493e08d627befea42"},"schema_version":"1.0","source":{"id":"2309.17102","kind":"arxiv","version":2}},"canonical_sha256":"86f901376aec9906f1411be181bb69e70044e18bcced93defd8c767de81aa0f2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"86f901376aec9906f1411be181bb69e70044e18bcced93defd8c767de81aa0f2","first_computed_at":"2026-07-05T07:40:57.595254Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:40:57.595254Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"eIU4VGfpnA1R0TXstq9IhToatRCvMXFKIaGgn5XQkrmlenyOFGMM59iYn5yrSOCqbAkfZ3twFGbT9jhQ1mbyCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:40:57.595804Z","signed_message":"canonical_sha256_bytes"},"source_id":"2309.17102","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e842c2733ddde33448918ab99329697b97c1059c381bb079bda619e4660fde23","sha256:af6671c2a05c66894bcff96167f083396f2be7f9ae0c3a5fdc7ac3642ffb15ba"],"state_sha256":"ce83581c75e4739bc93b02587327ca366cae5ad59a058adec4517b0df6024ce4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y0BviiR41GqhDROhz/cXUmgcOakClxJO01iiCFY/x5J0tSwN4Ov4ea2MOtx5TOQKIDpgavIyJO/Km6qO2NFeDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T09:19:16.187708Z","bundle_sha256":"1d4506bfeee0f9a01ae99d7be61a874a8ca54c714f4ceaa6a9fc389a7b88ff3a"}}