{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GQIT7JKFBOW3ICN5ETWVI3KAEK","short_pith_number":"pith:GQIT7JKF","schema_version":"1.0","canonical_sha256":"34113fa5450badb409bd24ed546d402282d067c1776575da577f45c33128fdae","source":{"kind":"arxiv","id":"2407.05600","version":2},"attestation_state":"computed","paper":{"title":"GenArtist: Multimodal LLM as an Agent for Unified Image Generation and Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aoxue Li, Xihui Liu, Zhenguo Li, Zhenyu Wang","submitted_at":"2024-07-08T04:30:53Z","abstract_excerpt":"Despite the success achieved by existing image generation and editing methods, current models still struggle with complex problems including intricate text prompts, and the absence of verification and self-correction mechanisms makes the generated images unreliable. Meanwhile, a single model tends to specialize in particular tasks and possess the corresponding capabilities, making it inadequate for fulfilling all user requirements. We propose GenArtist, a unified image generation and editing system, coordinated by a multimodal large language model (MLLM) agent. We integrate a comprehensive ran"},"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":"2407.05600","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-08T04:30:53Z","cross_cats_sorted":[],"title_canon_sha256":"9aa2fadfbb3f384b6d1b69bd6c6e9567aad5ca6178f0dda2c31fd7466cd3a2c8","abstract_canon_sha256":"cbbd46bbb606b7f9c71540536d0aa4ec1a632eaab94b162cbbf3e367ec398658"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:27:02.965351Z","signature_b64":"J4aS1BQC/r6PU9/1aaH+DYTVmmNdzq51x78lCwmQQKMgyEXUDKG17yjlcSG7j3xo8ZPXJxZTwdRD5SdmGNsUCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"34113fa5450badb409bd24ed546d402282d067c1776575da577f45c33128fdae","last_reissued_at":"2026-07-05T09:27:02.964899Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:27:02.964899Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GenArtist: Multimodal LLM as an Agent for Unified Image Generation and Editing","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aoxue Li, Xihui Liu, Zhenguo Li, Zhenyu Wang","submitted_at":"2024-07-08T04:30:53Z","abstract_excerpt":"Despite the success achieved by existing image generation and editing methods, current models still struggle with complex problems including intricate text prompts, and the absence of verification and self-correction mechanisms makes the generated images unreliable. Meanwhile, a single model tends to specialize in particular tasks and possess the corresponding capabilities, making it inadequate for fulfilling all user requirements. We propose GenArtist, a unified image generation and editing system, coordinated by a multimodal large language model (MLLM) agent. We integrate a comprehensive ran"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.05600","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/2407.05600/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":"2407.05600","created_at":"2026-07-05T09:27:02.964957+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.05600v2","created_at":"2026-07-05T09:27:02.964957+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.05600","created_at":"2026-07-05T09:27:02.964957+00:00"},{"alias_kind":"pith_short_12","alias_value":"GQIT7JKFBOW3","created_at":"2026-07-05T09:27:02.964957+00:00"},{"alias_kind":"pith_short_16","alias_value":"GQIT7JKFBOW3ICN5","created_at":"2026-07-05T09:27:02.964957+00:00"},{"alias_kind":"pith_short_8","alias_value":"GQIT7JKF","created_at":"2026-07-05T09:27:02.964957+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31392","citing_title":"ReGRPO: Reflection-Augmented Policy Optimization for Tool-Using Agents","ref_index":26,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GQIT7JKFBOW3ICN5ETWVI3KAEK","json":"https://pith.science/pith/GQIT7JKFBOW3ICN5ETWVI3KAEK.json","graph_json":"https://pith.science/api/pith-number/GQIT7JKFBOW3ICN5ETWVI3KAEK/graph.json","events_json":"https://pith.science/api/pith-number/GQIT7JKFBOW3ICN5ETWVI3KAEK/events.json","paper":"https://pith.science/paper/GQIT7JKF"},"agent_actions":{"view_html":"https://pith.science/pith/GQIT7JKFBOW3ICN5ETWVI3KAEK","download_json":"https://pith.science/pith/GQIT7JKFBOW3ICN5ETWVI3KAEK.json","view_paper":"https://pith.science/paper/GQIT7JKF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.05600&json=true","fetch_graph":"https://pith.science/api/pith-number/GQIT7JKFBOW3ICN5ETWVI3KAEK/graph.json","fetch_events":"https://pith.science/api/pith-number/GQIT7JKFBOW3ICN5ETWVI3KAEK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GQIT7JKFBOW3ICN5ETWVI3KAEK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GQIT7JKFBOW3ICN5ETWVI3KAEK/action/storage_attestation","attest_author":"https://pith.science/pith/GQIT7JKFBOW3ICN5ETWVI3KAEK/action/author_attestation","sign_citation":"https://pith.science/pith/GQIT7JKFBOW3ICN5ETWVI3KAEK/action/citation_signature","submit_replication":"https://pith.science/pith/GQIT7JKFBOW3ICN5ETWVI3KAEK/action/replication_record"}},"created_at":"2026-07-05T09:27:02.964957+00:00","updated_at":"2026-07-05T09:27:02.964957+00:00"}