{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:S3V7PKUKW4SJSE5E3HSVM7TVSM","short_pith_number":"pith:S3V7PKUK","schema_version":"1.0","canonical_sha256":"96ebf7aa8ab7249913a4d9e5567e75933cbf345b26ed34ffe76877f4b8909a75","source":{"kind":"arxiv","id":"2504.07046","version":1},"attestation_state":"computed","paper":{"title":"A Unified Agentic Framework for Evaluating Conditional Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Baotian Hu, Jifang Wang, Kaifu Zhang, Longyue Wang, Min Zhang, Weihua Luo, Xue Yang, Yaowei Wang, Yiyu Wang, Zhenran Xu","submitted_at":"2025-04-09T17:04:14Z","abstract_excerpt":"Conditional image generation has gained significant attention for its ability to personalize content. However, the field faces challenges in developing task-agnostic, reliable, and explainable evaluation metrics. This paper introduces CIGEval, a unified agentic framework for comprehensive evaluation of conditional image generation tasks. CIGEval utilizes large multimodal models (LMMs) as its core, integrating a multi-functional toolbox and establishing a fine-grained evaluation framework. Additionally, we synthesize evaluation trajectories for fine-tuning, empowering smaller LMMs to autonomous"},"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":"2504.07046","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-04-09T17:04:14Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"4bca8c9749669a7bf0072c5bc05b856b84f5efdb5efb0b38140291edd5424c0d","abstract_canon_sha256":"14cc983b104e5bb8c2517dc31cb00ca709d4945e3e20d6f437815f9f5bfff1fe"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:46:50.309892Z","signature_b64":"q26QPF3TRcY5zXxTZTtA/kPKfvUDi8G6eqF5iZRgytEKk1Qw1zMCsbbXh8Ov1aqUvJFbhZLF2VBMS2+h2tM+Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"96ebf7aa8ab7249913a4d9e5567e75933cbf345b26ed34ffe76877f4b8909a75","last_reissued_at":"2026-07-05T10:46:50.309434Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:46:50.309434Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Unified Agentic Framework for Evaluating Conditional Image Generation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Baotian Hu, Jifang Wang, Kaifu Zhang, Longyue Wang, Min Zhang, Weihua Luo, Xue Yang, Yaowei Wang, Yiyu Wang, Zhenran Xu","submitted_at":"2025-04-09T17:04:14Z","abstract_excerpt":"Conditional image generation has gained significant attention for its ability to personalize content. However, the field faces challenges in developing task-agnostic, reliable, and explainable evaluation metrics. This paper introduces CIGEval, a unified agentic framework for comprehensive evaluation of conditional image generation tasks. CIGEval utilizes large multimodal models (LMMs) as its core, integrating a multi-functional toolbox and establishing a fine-grained evaluation framework. Additionally, we synthesize evaluation trajectories for fine-tuning, empowering smaller LMMs to autonomous"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.07046","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/2504.07046/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":"2504.07046","created_at":"2026-07-05T10:46:50.309506+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.07046v1","created_at":"2026-07-05T10:46:50.309506+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.07046","created_at":"2026-07-05T10:46:50.309506+00:00"},{"alias_kind":"pith_short_12","alias_value":"S3V7PKUKW4SJ","created_at":"2026-07-05T10:46:50.309506+00:00"},{"alias_kind":"pith_short_16","alias_value":"S3V7PKUKW4SJSE5E","created_at":"2026-07-05T10:46:50.309506+00:00"},{"alias_kind":"pith_short_8","alias_value":"S3V7PKUK","created_at":"2026-07-05T10:46:50.309506+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.03385","citing_title":"Human Preference-Aligned Concept Customization Benchmark via Decomposed Evaluation","ref_index":52,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/S3V7PKUKW4SJSE5E3HSVM7TVSM","json":"https://pith.science/pith/S3V7PKUKW4SJSE5E3HSVM7TVSM.json","graph_json":"https://pith.science/api/pith-number/S3V7PKUKW4SJSE5E3HSVM7TVSM/graph.json","events_json":"https://pith.science/api/pith-number/S3V7PKUKW4SJSE5E3HSVM7TVSM/events.json","paper":"https://pith.science/paper/S3V7PKUK"},"agent_actions":{"view_html":"https://pith.science/pith/S3V7PKUKW4SJSE5E3HSVM7TVSM","download_json":"https://pith.science/pith/S3V7PKUKW4SJSE5E3HSVM7TVSM.json","view_paper":"https://pith.science/paper/S3V7PKUK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.07046&json=true","fetch_graph":"https://pith.science/api/pith-number/S3V7PKUKW4SJSE5E3HSVM7TVSM/graph.json","fetch_events":"https://pith.science/api/pith-number/S3V7PKUKW4SJSE5E3HSVM7TVSM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/S3V7PKUKW4SJSE5E3HSVM7TVSM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/S3V7PKUKW4SJSE5E3HSVM7TVSM/action/storage_attestation","attest_author":"https://pith.science/pith/S3V7PKUKW4SJSE5E3HSVM7TVSM/action/author_attestation","sign_citation":"https://pith.science/pith/S3V7PKUKW4SJSE5E3HSVM7TVSM/action/citation_signature","submit_replication":"https://pith.science/pith/S3V7PKUKW4SJSE5E3HSVM7TVSM/action/replication_record"}},"created_at":"2026-07-05T10:46:50.309506+00:00","updated_at":"2026-07-05T10:46:50.309506+00:00"}