{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RPWRNG5JWH4PZLW4CFVECORKB7","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":"36979cef4494d5aed208bdf55136c0b219c1bd7fc533c29a9c08f90e1f8fdad5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-07T17:59:56Z","title_canon_sha256":"a839c44d3b4004375cc8354fa5004a4b1bdc2b8c453c564d4139f0bacab7e988"},"schema_version":"1.0","source":{"id":"2507.05259","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.05259","created_at":"2026-07-05T11:33:11Z"},{"alias_kind":"arxiv_version","alias_value":"2507.05259v1","created_at":"2026-07-05T11:33:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05259","created_at":"2026-07-05T11:33:11Z"},{"alias_kind":"pith_short_12","alias_value":"RPWRNG5JWH4P","created_at":"2026-07-05T11:33:11Z"},{"alias_kind":"pith_short_16","alias_value":"RPWRNG5JWH4PZLW4","created_at":"2026-07-05T11:33:11Z"},{"alias_kind":"pith_short_8","alias_value":"RPWRNG5J","created_at":"2026-07-05T11:33:11Z"}],"graph_snapshots":[{"event_id":"sha256:aacd3ff0d574905f9c99afbea4cde4dbcf8c24f0bfe85c408dcd7be06d082051","target":"graph","created_at":"2026-07-05T11:33:11Z","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/2507.05259/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent diffusion-based image editing methods have significantly advanced text-guided tasks but often struggle to interpret complex, indirect instructions. Moreover, current models frequently suffer from poor identity preservation, unintended edits, or rely heavily on manual masks. To address these challenges, we introduce X-Planner, a Multimodal Large Language Model (MLLM)-based planning system that effectively bridges user intent with editing model capabilities. X-Planner employs chain-of-thought reasoning to systematically decompose complex instructions into simpler, clear sub-instructions. ","authors_text":"Chun-Hsiao Yeh, Krishna Kumar Singh, Nanxuan Zhao, Richard Zhang, Yilin Wang, Yi Ma, Yuheng Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-07T17:59:56Z","title":"Beyond Simple Edits: X-Planner for Complex Instruction-Based Image Editing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05259","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:ff4854b4f6cc78bfc6f9d388e7da709212453befa04751abfb174fedcbf9ec54","target":"record","created_at":"2026-07-05T11:33:11Z","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":"36979cef4494d5aed208bdf55136c0b219c1bd7fc533c29a9c08f90e1f8fdad5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-07-07T17:59:56Z","title_canon_sha256":"a839c44d3b4004375cc8354fa5004a4b1bdc2b8c453c564d4139f0bacab7e988"},"schema_version":"1.0","source":{"id":"2507.05259","kind":"arxiv","version":1}},"canonical_sha256":"8bed169ba9b1f8fcaedc116a413a2a0fc847e5b1f5fd03d9ee204678099bdb71","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8bed169ba9b1f8fcaedc116a413a2a0fc847e5b1f5fd03d9ee204678099bdb71","first_computed_at":"2026-07-05T11:33:11.377003Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:33:11.377003Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"DwO2uN0RVebCXBex7ke+Xt1fRBRsmfg+VixJWsZ4OBZTQwo5xFbhQm5TmbLq7351Do9qXF1WSgki84Ti4Sr2Dw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:33:11.377419Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.05259","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ff4854b4f6cc78bfc6f9d388e7da709212453befa04751abfb174fedcbf9ec54","sha256:aacd3ff0d574905f9c99afbea4cde4dbcf8c24f0bfe85c408dcd7be06d082051"],"state_sha256":"1a8fb095b13d65664c692180fd699f2d738038efde7fee2e48c31db201d31d85"}