{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:FTXZOSBUV2ZSN4BPH4QHFOMXRS","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":"1428810ef164932898969c09dcbe04ef2e1d18a581821dbf96e640a9b3ebf470","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-22T06:16:29Z","title_canon_sha256":"5e9e6791d516987e9291850306e112b92d22b94f1ac123de0175e750c9ae2758"},"schema_version":"1.0","source":{"id":"2401.11708","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.11708","created_at":"2026-07-05T08:27:02Z"},{"alias_kind":"arxiv_version","alias_value":"2401.11708v3","created_at":"2026-07-05T08:27:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.11708","created_at":"2026-07-05T08:27:02Z"},{"alias_kind":"pith_short_12","alias_value":"FTXZOSBUV2ZS","created_at":"2026-07-05T08:27:02Z"},{"alias_kind":"pith_short_16","alias_value":"FTXZOSBUV2ZSN4BP","created_at":"2026-07-05T08:27:02Z"},{"alias_kind":"pith_short_8","alias_value":"FTXZOSBU","created_at":"2026-07-05T08:27:02Z"}],"graph_snapshots":[{"event_id":"sha256:4f120558658f5cef01a12c4704d3ec12adf1eac1b53694fd81a78ce28a839f1a","target":"graph","created_at":"2026-07-05T08:27:02Z","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/2401.11708/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Diffusion models have exhibit exceptional performance in text-to-image generation and editing. However, existing methods often face challenges when handling complex text prompts that involve multiple objects with multiple attributes and relationships. In this paper, we propose a brand new training-free text-to-image generation/editing framework, namely Recaption, Plan and Generate (RPG), harnessing the powerful chain-of-thought reasoning ability of multimodal LLMs to enhance the compositionality of text-to-image diffusion models. Our approach employs the MLLM as a global planner to decompose t","authors_text":"Bin Cui, Chenlin Meng, Ling Yang, Minkai Xu, Stefano Ermon, Zhaochen Yu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-22T06:16:29Z","title":"Mastering Text-to-Image Diffusion: Recaptioning, Planning, and Generating with Multimodal LLMs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.11708","kind":"arxiv","version":3},"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":"sha256:4a1d25f17a00ccea2de119e28062c6589f37c5cef8b79099c3e938ff79ebae34","target":"record","created_at":"2026-07-05T08:27:02Z","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":"1428810ef164932898969c09dcbe04ef2e1d18a581821dbf96e640a9b3ebf470","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-01-22T06:16:29Z","title_canon_sha256":"5e9e6791d516987e9291850306e112b92d22b94f1ac123de0175e750c9ae2758"},"schema_version":"1.0","source":{"id":"2401.11708","kind":"arxiv","version":3}},"canonical_sha256":"2cef974834aeb326f02f3f2072b9978cb84fa7a417a52f99949a46d0972ba729","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2cef974834aeb326f02f3f2072b9978cb84fa7a417a52f99949a46d0972ba729","first_computed_at":"2026-07-05T08:27:02.683477Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:27:02.683477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8IWE+L+AZ8IRqkqj7WqthtfLp1cQ/Lcm7xpeXBOvpM17BKb4mC8vExB/hoiKgytpQyPjBLlrii+cqnpwztB8CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:27:02.683946Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.11708","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4a1d25f17a00ccea2de119e28062c6589f37c5cef8b79099c3e938ff79ebae34","sha256:4f120558658f5cef01a12c4704d3ec12adf1eac1b53694fd81a78ce28a839f1a"],"state_sha256":"dc889a51d32d8da6e7bf9ffe2fc1f758bbd3a3af86c97cf4f764b2c1d3c04518"}