{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OQGIEJN4Q2MTEYX7AJD5POTLKD","short_pith_number":"pith:OQGIEJN4","schema_version":"1.0","canonical_sha256":"740c8225bc86993262ff0247d7ba6b50f483670af948378d5bb0a2e4b13a2d90","source":{"kind":"arxiv","id":"2407.15272","version":2},"attestation_state":"computed","paper":{"title":"MIBench: Evaluating Multimodal Large Language Models over Multiple Images","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bing Li, Chaoya Jiang, Chunfeng Yuan, Fei Huang, Haiyang Xu, Haowei Liu, Ji Zhang, Ming Yan, Weiming Hu, Xi Zhang, Yaya Shi","submitted_at":"2024-07-21T21:22:58Z","abstract_excerpt":"Built on the power of LLMs, numerous multimodal large language models (MLLMs) have recently achieved remarkable performance on various vision-language tasks. However, most existing MLLMs and benchmarks primarily focus on single-image input scenarios, leaving the performance of MLLMs when handling realistic multiple images underexplored. Although a few benchmarks consider multiple images, their evaluation dimensions and samples are very limited. In this paper, we propose a new benchmark MIBench, to comprehensively evaluate fine-grained abilities of MLLMs in multi-image scenarios. Specifically, "},"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":"2407.15272","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-21T21:22:58Z","cross_cats_sorted":[],"title_canon_sha256":"5c2f5c3c1e9b8a2b5f38477053405e50a2362b770cf53bbd60617389b7d296b6","abstract_canon_sha256":"5d9f7c26f34ae4f644fa82d3ac09427ee9ca9c01acdc74a031ef6d6d6ccb119a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:17:14.676690Z","signature_b64":"/ssfbQ/DeSGeiG/Kn5rVGfFoWMSy6j61sCtSiRQHQmZzUJcM9eMgpw5iEtssDbSGkX4Lf9FtMdQF7EcitOXlDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"740c8225bc86993262ff0247d7ba6b50f483670af948378d5bb0a2e4b13a2d90","last_reissued_at":"2026-07-05T09:17:14.676131Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:17:14.676131Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MIBench: Evaluating Multimodal Large Language Models over Multiple Images","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bing Li, Chaoya Jiang, Chunfeng Yuan, Fei Huang, Haiyang Xu, Haowei Liu, Ji Zhang, Ming Yan, Weiming Hu, Xi Zhang, Yaya Shi","submitted_at":"2024-07-21T21:22:58Z","abstract_excerpt":"Built on the power of LLMs, numerous multimodal large language models (MLLMs) have recently achieved remarkable performance on various vision-language tasks. However, most existing MLLMs and benchmarks primarily focus on single-image input scenarios, leaving the performance of MLLMs when handling realistic multiple images underexplored. Although a few benchmarks consider multiple images, their evaluation dimensions and samples are very limited. In this paper, we propose a new benchmark MIBench, to comprehensively evaluate fine-grained abilities of MLLMs in multi-image scenarios. Specifically, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.15272","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/2407.15272/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":"2407.15272","created_at":"2026-07-05T09:17:14.676196+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.15272v2","created_at":"2026-07-05T09:17:14.676196+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.15272","created_at":"2026-07-05T09:17:14.676196+00:00"},{"alias_kind":"pith_short_12","alias_value":"OQGIEJN4Q2MT","created_at":"2026-07-05T09:17:14.676196+00:00"},{"alias_kind":"pith_short_16","alias_value":"OQGIEJN4Q2MTEYX7","created_at":"2026-07-05T09:17:14.676196+00:00"},{"alias_kind":"pith_short_8","alias_value":"OQGIEJN4","created_at":"2026-07-05T09:17:14.676196+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2408.04840","citing_title":"mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models","ref_index":233,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11591","citing_title":"Logit-Attention Divergence: Mitigating Position Bias in Multi-Image Retrieval via Attention-Guided Calibration","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22498","citing_title":"CGC: Compositional Grounded Contrast for Fine-Grained Multi-Image Understanding","ref_index":28,"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":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OQGIEJN4Q2MTEYX7AJD5POTLKD","json":"https://pith.science/pith/OQGIEJN4Q2MTEYX7AJD5POTLKD.json","graph_json":"https://pith.science/api/pith-number/OQGIEJN4Q2MTEYX7AJD5POTLKD/graph.json","events_json":"https://pith.science/api/pith-number/OQGIEJN4Q2MTEYX7AJD5POTLKD/events.json","paper":"https://pith.science/paper/OQGIEJN4"},"agent_actions":{"view_html":"https://pith.science/pith/OQGIEJN4Q2MTEYX7AJD5POTLKD","download_json":"https://pith.science/pith/OQGIEJN4Q2MTEYX7AJD5POTLKD.json","view_paper":"https://pith.science/paper/OQGIEJN4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.15272&json=true","fetch_graph":"https://pith.science/api/pith-number/OQGIEJN4Q2MTEYX7AJD5POTLKD/graph.json","fetch_events":"https://pith.science/api/pith-number/OQGIEJN4Q2MTEYX7AJD5POTLKD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OQGIEJN4Q2MTEYX7AJD5POTLKD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OQGIEJN4Q2MTEYX7AJD5POTLKD/action/storage_attestation","attest_author":"https://pith.science/pith/OQGIEJN4Q2MTEYX7AJD5POTLKD/action/author_attestation","sign_citation":"https://pith.science/pith/OQGIEJN4Q2MTEYX7AJD5POTLKD/action/citation_signature","submit_replication":"https://pith.science/pith/OQGIEJN4Q2MTEYX7AJD5POTLKD/action/replication_record"}},"created_at":"2026-07-05T09:17:14.676196+00:00","updated_at":"2026-07-05T09:17:14.676196+00:00"}