{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:STNIQL5J73H2TTIXLADLG7HZJL","short_pith_number":"pith:STNIQL5J","schema_version":"1.0","canonical_sha256":"94da882fa9fecfa9cd175806b37cf94ae2369d16f9a353661a94af1518e74d7f","source":{"kind":"arxiv","id":"2410.07133","version":2},"attestation_state":"computed","paper":{"title":"EvolveDirector: Approaching Advanced Text-to-Image Generation with Large Vision-Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hangjie Yuan, Junhao Zhang, Lingmin Ran, Mike Zheng Shou, Rui Zhao, Shiwei Zhang, Xiang Wang, Yingya Zhang, Yuchao Gu, Yujie Wei, Zhangjie Wu","submitted_at":"2024-10-09T17:52:28Z","abstract_excerpt":"Recent advancements in generation models have showcased remarkable capabilities in generating fantastic content. However, most of them are trained on proprietary high-quality data, and some models withhold their parameters and only provide accessible application programming interfaces (APIs), limiting their benefits for downstream tasks. To explore the feasibility of training a text-to-image generation model comparable to advanced models using publicly available resources, we introduce EvolveDirector. This framework interacts with advanced models through their public APIs to obtain text-image "},"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":"2410.07133","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-09T17:52:28Z","cross_cats_sorted":[],"title_canon_sha256":"1e00cd9146cb9dc0448ba3bc50eb0f19d36a6251b8659e4e2fad5001e99ec1d8","abstract_canon_sha256":"0597dc9f11dfcc40cad72ea325c0a679045682eb7143bee64dcc71930aba71ba"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:32.328057Z","signature_b64":"wztKpT2sHG2yeW2eIVwja2XZeJUW1+Favb0GZh9wpBNKlSBjQTE+X8IHsFs+ZlRG6nZjPjidbBzhY57PjrfUAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94da882fa9fecfa9cd175806b37cf94ae2369d16f9a353661a94af1518e74d7f","last_reissued_at":"2026-07-05T09:18:32.327498Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:32.327498Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EvolveDirector: Approaching Advanced Text-to-Image Generation with Large Vision-Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hangjie Yuan, Junhao Zhang, Lingmin Ran, Mike Zheng Shou, Rui Zhao, Shiwei Zhang, Xiang Wang, Yingya Zhang, Yuchao Gu, Yujie Wei, Zhangjie Wu","submitted_at":"2024-10-09T17:52:28Z","abstract_excerpt":"Recent advancements in generation models have showcased remarkable capabilities in generating fantastic content. However, most of them are trained on proprietary high-quality data, and some models withhold their parameters and only provide accessible application programming interfaces (APIs), limiting their benefits for downstream tasks. To explore the feasibility of training a text-to-image generation model comparable to advanced models using publicly available resources, we introduce EvolveDirector. This framework interacts with advanced models through their public APIs to obtain text-image "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.07133","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/2410.07133/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":"2410.07133","created_at":"2026-07-05T09:18:32.327555+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.07133v2","created_at":"2026-07-05T09:18:32.327555+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.07133","created_at":"2026-07-05T09:18:32.327555+00:00"},{"alias_kind":"pith_short_12","alias_value":"STNIQL5J73H2","created_at":"2026-07-05T09:18:32.327555+00:00"},{"alias_kind":"pith_short_16","alias_value":"STNIQL5J73H2TTIX","created_at":"2026-07-05T09:18:32.327555+00:00"},{"alias_kind":"pith_short_8","alias_value":"STNIQL5J","created_at":"2026-07-05T09:18:32.327555+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/STNIQL5J73H2TTIXLADLG7HZJL","json":"https://pith.science/pith/STNIQL5J73H2TTIXLADLG7HZJL.json","graph_json":"https://pith.science/api/pith-number/STNIQL5J73H2TTIXLADLG7HZJL/graph.json","events_json":"https://pith.science/api/pith-number/STNIQL5J73H2TTIXLADLG7HZJL/events.json","paper":"https://pith.science/paper/STNIQL5J"},"agent_actions":{"view_html":"https://pith.science/pith/STNIQL5J73H2TTIXLADLG7HZJL","download_json":"https://pith.science/pith/STNIQL5J73H2TTIXLADLG7HZJL.json","view_paper":"https://pith.science/paper/STNIQL5J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.07133&json=true","fetch_graph":"https://pith.science/api/pith-number/STNIQL5J73H2TTIXLADLG7HZJL/graph.json","fetch_events":"https://pith.science/api/pith-number/STNIQL5J73H2TTIXLADLG7HZJL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/STNIQL5J73H2TTIXLADLG7HZJL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/STNIQL5J73H2TTIXLADLG7HZJL/action/storage_attestation","attest_author":"https://pith.science/pith/STNIQL5J73H2TTIXLADLG7HZJL/action/author_attestation","sign_citation":"https://pith.science/pith/STNIQL5J73H2TTIXLADLG7HZJL/action/citation_signature","submit_replication":"https://pith.science/pith/STNIQL5J73H2TTIXLADLG7HZJL/action/replication_record"}},"created_at":"2026-07-05T09:18:32.327555+00:00","updated_at":"2026-07-05T09:18:32.327555+00:00"}