{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PCD5HDAMHQNRGSN6HDTVAQXYB2","short_pith_number":"pith:PCD5HDAM","schema_version":"1.0","canonical_sha256":"7887d38c0c3c1b1349be38e75042f80ea3c94cbdcd26ba31f32b57412691f7ea","source":{"kind":"arxiv","id":"2505.19415","version":2},"attestation_state":"computed","paper":{"title":"MMIG-Bench: Towards Comprehensive and Explainable Evaluation of Multi-Modal Image Generation Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daniel Aliaga, Hang Hua, Jiebo Luo, Liu He, Wei Xiong, Yizhi Song, Yunlong Tang, Ziyun Zeng","submitted_at":"2025-05-26T02:07:24Z","abstract_excerpt":"Recent multimodal image generators such as GPT-4o, Gemini 2.0 Flash, and Gemini 2.5 Pro excel at following complex instructions, editing images and maintaining concept consistency. However, they are still evaluated by disjoint toolkits: text-to-image (T2I) benchmarks that lacks multi-modal conditioning, and customized image generation benchmarks that overlook compositional semantics and common knowledge. We propose MMIG-Bench, a comprehensive Multi-Modal Image Generation Benchmark that unifies these tasks by pairing 4,850 richly annotated text prompts with 1,750 multi-view reference images acr"},"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":"2505.19415","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2025-05-26T02:07:24Z","cross_cats_sorted":[],"title_canon_sha256":"e48a8026a4677031f6382632ceda322e577865a1efbf6a7147b5145dc7e05948","abstract_canon_sha256":"aa63735d92c677e8ced76e2dbd5b3d24067d8e799ba4d2194aca679a620fe94c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:58.149127Z","signature_b64":"M5HVuoNL9AfE8hhE6+KBFMwY9zDfsw0rX4tT9z5HOk9GFvcoUlIyQE/z2k/SwGm6hmg3NuC/9fbO0GF51FQtAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7887d38c0c3c1b1349be38e75042f80ea3c94cbdcd26ba31f32b57412691f7ea","last_reissued_at":"2026-07-05T11:10:58.148701Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:58.148701Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MMIG-Bench: Towards Comprehensive and Explainable Evaluation of Multi-Modal Image Generation Models","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Daniel Aliaga, Hang Hua, Jiebo Luo, Liu He, Wei Xiong, Yizhi Song, Yunlong Tang, Ziyun Zeng","submitted_at":"2025-05-26T02:07:24Z","abstract_excerpt":"Recent multimodal image generators such as GPT-4o, Gemini 2.0 Flash, and Gemini 2.5 Pro excel at following complex instructions, editing images and maintaining concept consistency. However, they are still evaluated by disjoint toolkits: text-to-image (T2I) benchmarks that lacks multi-modal conditioning, and customized image generation benchmarks that overlook compositional semantics and common knowledge. We propose MMIG-Bench, a comprehensive Multi-Modal Image Generation Benchmark that unifies these tasks by pairing 4,850 richly annotated text prompts with 1,750 multi-view reference images acr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.19415","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/2505.19415/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":"2505.19415","created_at":"2026-07-05T11:10:58.148754+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.19415v2","created_at":"2026-07-05T11:10:58.148754+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.19415","created_at":"2026-07-05T11:10:58.148754+00:00"},{"alias_kind":"pith_short_12","alias_value":"PCD5HDAMHQNR","created_at":"2026-07-05T11:10:58.148754+00:00"},{"alias_kind":"pith_short_16","alias_value":"PCD5HDAMHQNRGSN6","created_at":"2026-07-05T11:10:58.148754+00:00"},{"alias_kind":"pith_short_8","alias_value":"PCD5HDAM","created_at":"2026-07-05T11:10:58.148754+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27537","citing_title":"MemoBench: Benchmarking World Modeling in Dynamically Changing Environments","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27537","citing_title":"MemoBench: Benchmarking World Modeling in Dynamically Changing Environments","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27537","citing_title":"MemoBench: Benchmarking World Modeling in Dynamically Changing Environments","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.27537","citing_title":"MemoBench: Benchmarking World Modeling in Dynamically Changing Environments","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01414","citing_title":"Agent Skills Should Go Beyond Text: The Case for Visual Skills","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18652","citing_title":"MementoGUI: Learning Agentic Multimodal Memory Control for Long-Horizon GUI Agents","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2603.27064","citing_title":"ChartNet: A Million-Scale, High-Quality Multimodal Dataset for Robust Chart Understanding","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13223","citing_title":"Skill-Aligned Annotation for Reliable Evaluation in Text-to-Image Generation","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PCD5HDAMHQNRGSN6HDTVAQXYB2","json":"https://pith.science/pith/PCD5HDAMHQNRGSN6HDTVAQXYB2.json","graph_json":"https://pith.science/api/pith-number/PCD5HDAMHQNRGSN6HDTVAQXYB2/graph.json","events_json":"https://pith.science/api/pith-number/PCD5HDAMHQNRGSN6HDTVAQXYB2/events.json","paper":"https://pith.science/paper/PCD5HDAM"},"agent_actions":{"view_html":"https://pith.science/pith/PCD5HDAMHQNRGSN6HDTVAQXYB2","download_json":"https://pith.science/pith/PCD5HDAMHQNRGSN6HDTVAQXYB2.json","view_paper":"https://pith.science/paper/PCD5HDAM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.19415&json=true","fetch_graph":"https://pith.science/api/pith-number/PCD5HDAMHQNRGSN6HDTVAQXYB2/graph.json","fetch_events":"https://pith.science/api/pith-number/PCD5HDAMHQNRGSN6HDTVAQXYB2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PCD5HDAMHQNRGSN6HDTVAQXYB2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PCD5HDAMHQNRGSN6HDTVAQXYB2/action/storage_attestation","attest_author":"https://pith.science/pith/PCD5HDAMHQNRGSN6HDTVAQXYB2/action/author_attestation","sign_citation":"https://pith.science/pith/PCD5HDAMHQNRGSN6HDTVAQXYB2/action/citation_signature","submit_replication":"https://pith.science/pith/PCD5HDAMHQNRGSN6HDTVAQXYB2/action/replication_record"}},"created_at":"2026-07-05T11:10:58.148754+00:00","updated_at":"2026-07-05T11:10:58.148754+00:00"}