{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WMP6B73ROXNIOYGS6LW6XMQ5QQ","short_pith_number":"pith:WMP6B73R","schema_version":"1.0","canonical_sha256":"b31fe0ff7175da8760d2f2edebb21d8426dc9e07ffe9b39b04d0ee99d8b1a839","source":{"kind":"arxiv","id":"2608.04436","version":1},"attestation_state":"computed","paper":{"title":"ToolArtist: Tool-Using Unified Multimodal Models for Agentic Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengwei Qin, Fengwei Teng, Jiahao Zhao, Jun Xu, Shuicheng Yan, Xiaobin Hu, Xiaomin Yu, Zhongxiang Sun","submitted_at":"2026-08-05T04:26:19Z","abstract_excerpt":"Text-to-image (T2I) models can produce visually compelling images, yet they remain limited on open-world tasks that require complex semantic understanding, multi-step reasoning, and the integration of external world knowledge. Existing efforts introduce agent capabilities into image generation, but they either prescribe a fixed workflow or place only a subset of the open-world image generation process under agent control. Consequently, reasoning, tool invocation, and image generation are not coordinated by a single policy. We propose ToolArtist, a fully agentic image generation model obtained "},"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":"2608.04436","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-08-05T04:26:19Z","cross_cats_sorted":[],"title_canon_sha256":"33c46cc1747b2a599de1d682fc72fd01856ca5c99bb0f550cd04b6333a231b35","abstract_canon_sha256":"584298a9c68f945ef5ae15718ea919bd0dcd51c8658fad9fb30170aa85260290"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-06T01:35:26.202644Z","signature_b64":"Au737lROI2oiYGooda2rV2+RaN4H7HIBzbQLfKNz20kGFe3lJux+3zFtN4Lv00dPOYn6j3oS5fltmBPmGli0Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b31fe0ff7175da8760d2f2edebb21d8426dc9e07ffe9b39b04d0ee99d8b1a839","last_reissued_at":"2026-08-06T01:35:26.201258Z","signature_status":"signed_v1","first_computed_at":"2026-08-06T01:35:26.201258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ToolArtist: Tool-Using Unified Multimodal Models for Agentic Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chengwei Qin, Fengwei Teng, Jiahao Zhao, Jun Xu, Shuicheng Yan, Xiaobin Hu, Xiaomin Yu, Zhongxiang Sun","submitted_at":"2026-08-05T04:26:19Z","abstract_excerpt":"Text-to-image (T2I) models can produce visually compelling images, yet they remain limited on open-world tasks that require complex semantic understanding, multi-step reasoning, and the integration of external world knowledge. Existing efforts introduce agent capabilities into image generation, but they either prescribe a fixed workflow or place only a subset of the open-world image generation process under agent control. Consequently, reasoning, tool invocation, and image generation are not coordinated by a single policy. We propose ToolArtist, a fully agentic image generation model obtained "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.04436","kind":"arxiv","version":1},"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/2608.04436/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":"2608.04436","created_at":"2026-08-06T01:35:26.203048+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.04436v1","created_at":"2026-08-06T01:35:26.203048+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.04436","created_at":"2026-08-06T01:35:26.203048+00:00"},{"alias_kind":"pith_short_12","alias_value":"WMP6B73ROXNI","created_at":"2026-08-06T01:35:26.203048+00:00"},{"alias_kind":"pith_short_16","alias_value":"WMP6B73ROXNIOYGS","created_at":"2026-08-06T01:35:26.203048+00:00"},{"alias_kind":"pith_short_8","alias_value":"WMP6B73R","created_at":"2026-08-06T01:35:26.203048+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WMP6B73ROXNIOYGS6LW6XMQ5QQ","json":"https://pith.science/pith/WMP6B73ROXNIOYGS6LW6XMQ5QQ.json","graph_json":"https://pith.science/api/pith-number/WMP6B73ROXNIOYGS6LW6XMQ5QQ/graph.json","events_json":"https://pith.science/api/pith-number/WMP6B73ROXNIOYGS6LW6XMQ5QQ/events.json","paper":"https://pith.science/paper/WMP6B73R"},"agent_actions":{"view_html":"https://pith.science/pith/WMP6B73ROXNIOYGS6LW6XMQ5QQ","download_json":"https://pith.science/pith/WMP6B73ROXNIOYGS6LW6XMQ5QQ.json","view_paper":"https://pith.science/paper/WMP6B73R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.04436&json=true","fetch_graph":"https://pith.science/api/pith-number/WMP6B73ROXNIOYGS6LW6XMQ5QQ/graph.json","fetch_events":"https://pith.science/api/pith-number/WMP6B73ROXNIOYGS6LW6XMQ5QQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WMP6B73ROXNIOYGS6LW6XMQ5QQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WMP6B73ROXNIOYGS6LW6XMQ5QQ/action/storage_attestation","attest_author":"https://pith.science/pith/WMP6B73ROXNIOYGS6LW6XMQ5QQ/action/author_attestation","sign_citation":"https://pith.science/pith/WMP6B73ROXNIOYGS6LW6XMQ5QQ/action/citation_signature","submit_replication":"https://pith.science/pith/WMP6B73ROXNIOYGS6LW6XMQ5QQ/action/replication_record"}},"created_at":"2026-08-06T01:35:26.203048+00:00","updated_at":"2026-08-06T01:35:26.203048+00:00"}