{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:H6FQWMT2OVM4PJKLOHNKADWXQP","short_pith_number":"pith:H6FQWMT2","schema_version":"1.0","canonical_sha256":"3f8b0b327a7559c7a54b71daa00ed783cade0c075d6a8d45b8a19604a9c3acc9","source":{"kind":"arxiv","id":"2408.02718","version":1},"attestation_state":"computed","paper":{"title":"MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuanhao Li, Fanqing Meng, Hao Tian, Jiaqi Liao, Jifeng Dai, Jin Wang, Kaipeng Zhang, Ping Luo, Quanfeng Lu, Wenqi Shao, Xizhou Zhu, Yu Qiao","submitted_at":"2024-08-05T17:56:41Z","abstract_excerpt":"The capability to process multiple images is crucial for Large Vision-Language Models (LVLMs) to develop a more thorough and nuanced understanding of a scene. Recent multi-image LVLMs have begun to address this need. However, their evaluation has not kept pace with their development. To fill this gap, we introduce the Multimodal Multi-image Understanding (MMIU) benchmark, a comprehensive evaluation suite designed to assess LVLMs across a wide range of multi-image tasks. MMIU encompasses 7 types of multi-image relationships, 52 tasks, 77K images, and 11K meticulously curated multiple-choice que"},"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":"2408.02718","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-08-05T17:56:41Z","cross_cats_sorted":[],"title_canon_sha256":"3c749d4667e7a792e1306d7e725985f99ff2fddbc2d8f25e06cf8af7833f9aac","abstract_canon_sha256":"e9124228370bb93b8afb617127a0413d9477d3faf5d4a20d27178dc5d5a0d29e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:52:39.161063Z","signature_b64":"SOIV/LJ7GpIBjhryUGV3/8oG3RsaH39JM8uND435e1vl+xXMWq/x3n3TNPAujPkz8/wPCaC8R5Dxi7u7De4zBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f8b0b327a7559c7a54b71daa00ed783cade0c075d6a8d45b8a19604a9c3acc9","last_reissued_at":"2026-07-05T08:52:39.160572Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:52:39.160572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MMIU: Multimodal Multi-image Understanding for Evaluating Large Vision-Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chuanhao Li, Fanqing Meng, Hao Tian, Jiaqi Liao, Jifeng Dai, Jin Wang, Kaipeng Zhang, Ping Luo, Quanfeng Lu, Wenqi Shao, Xizhou Zhu, Yu Qiao","submitted_at":"2024-08-05T17:56:41Z","abstract_excerpt":"The capability to process multiple images is crucial for Large Vision-Language Models (LVLMs) to develop a more thorough and nuanced understanding of a scene. Recent multi-image LVLMs have begun to address this need. However, their evaluation has not kept pace with their development. To fill this gap, we introduce the Multimodal Multi-image Understanding (MMIU) benchmark, a comprehensive evaluation suite designed to assess LVLMs across a wide range of multi-image tasks. MMIU encompasses 7 types of multi-image relationships, 52 tasks, 77K images, and 11K meticulously curated multiple-choice que"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.02718","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/2408.02718/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":"2408.02718","created_at":"2026-07-05T08:52:39.160636+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.02718v1","created_at":"2026-07-05T08:52:39.160636+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.02718","created_at":"2026-07-05T08:52:39.160636+00:00"},{"alias_kind":"pith_short_12","alias_value":"H6FQWMT2OVM4","created_at":"2026-07-05T08:52:39.160636+00:00"},{"alias_kind":"pith_short_16","alias_value":"H6FQWMT2OVM4PJKL","created_at":"2026-07-05T08:52:39.160636+00:00"},{"alias_kind":"pith_short_8","alias_value":"H6FQWMT2","created_at":"2026-07-05T08:52:39.160636+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12195","citing_title":"InternVideo3: Agentify Foundation Models with Multimodal Contextual Reasoning","ref_index":189,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00576","citing_title":"Safe Alone, Unsafe Together: Safeguarding Against Implicit Toxicity When Benign Images Combine","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09883","citing_title":"The Cartesian Shortcut: Re-evaluate Vision Reasoning in Polar Coordinate Space","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2507.00748","citing_title":"Improving the Reasoning of Multi-Image Grounding in MLLMs via Reinforcement Learning","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2603.04676","citing_title":"Decoding the Pulse of Reasoning VLMs in Multi-Image Understanding Tasks","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09883","citing_title":"The Cartesian Shortcut: Re-evaluate Vision Reasoning in Polar Coordinate Space","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22498","citing_title":"CGC: Compositional Grounded Contrast for Fine-Grained Multi-Image Understanding","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20806","citing_title":"OMIBench: Benchmarking Olympiad-Level Multi-Image Reasoning in Large Vision-Language Model","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2504.10479","citing_title":"InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models","ref_index":95,"is_internal_anchor":false},{"citing_arxiv_id":"2412.05271","citing_title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","ref_index":186,"is_internal_anchor":false},{"citing_arxiv_id":"2508.18265","citing_title":"InternVL3.5: Advancing Open-Source Multimodal Models in Versatility, Reasoning, and Efficiency","ref_index":91,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/H6FQWMT2OVM4PJKLOHNKADWXQP","json":"https://pith.science/pith/H6FQWMT2OVM4PJKLOHNKADWXQP.json","graph_json":"https://pith.science/api/pith-number/H6FQWMT2OVM4PJKLOHNKADWXQP/graph.json","events_json":"https://pith.science/api/pith-number/H6FQWMT2OVM4PJKLOHNKADWXQP/events.json","paper":"https://pith.science/paper/H6FQWMT2"},"agent_actions":{"view_html":"https://pith.science/pith/H6FQWMT2OVM4PJKLOHNKADWXQP","download_json":"https://pith.science/pith/H6FQWMT2OVM4PJKLOHNKADWXQP.json","view_paper":"https://pith.science/paper/H6FQWMT2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.02718&json=true","fetch_graph":"https://pith.science/api/pith-number/H6FQWMT2OVM4PJKLOHNKADWXQP/graph.json","fetch_events":"https://pith.science/api/pith-number/H6FQWMT2OVM4PJKLOHNKADWXQP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H6FQWMT2OVM4PJKLOHNKADWXQP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H6FQWMT2OVM4PJKLOHNKADWXQP/action/storage_attestation","attest_author":"https://pith.science/pith/H6FQWMT2OVM4PJKLOHNKADWXQP/action/author_attestation","sign_citation":"https://pith.science/pith/H6FQWMT2OVM4PJKLOHNKADWXQP/action/citation_signature","submit_replication":"https://pith.science/pith/H6FQWMT2OVM4PJKLOHNKADWXQP/action/replication_record"}},"created_at":"2026-07-05T08:52:39.160636+00:00","updated_at":"2026-07-05T08:52:39.160636+00:00"}