{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5S3JFOXBQP7BN5XT7ASNNCYH36","short_pith_number":"pith:5S3JFOXB","schema_version":"1.0","canonical_sha256":"ecb692bae183fe16f6f3f824d68b07df82391c17bb0958cad63d65cda571516f","source":{"kind":"arxiv","id":"2406.11833","version":2},"attestation_state":"computed","paper":{"title":"MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dahua Lin, Jiaqi Wang, Pan Zhang, Tao Chu, Xiaoyi Dong, Xilin Wei, Yuanjun Xiong, Yuhang Zang, Yu Qiao, Zijian Liang, Ziyu Liu","submitted_at":"2024-06-17T17:59:47Z","abstract_excerpt":"Generating natural and meaningful responses to communicate with multi-modal human inputs is a fundamental capability of Large Vision-Language Models(LVLMs). While current open-source LVLMs demonstrate promising performance in simplified scenarios such as single-turn single-image input, they fall short in real-world conversation scenarios such as following instructions in a long context history with multi-turn and multi-images. Existing LVLM benchmarks primarily focus on single-choice questions or short-form responses, which do not adequately assess the capabilities of LVLMs in real-world human"},"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":"2406.11833","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T17:59:47Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"76e828b060e25a4e3536b4f547229952cd8e7529c88b255695f99154e5c29a9b","abstract_canon_sha256":"f4d64699b45efa5c5a279ddaaefd91482a67386b4469aaeab52e1259c6ab9429"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:27:55.608734Z","signature_b64":"axcteScCfFWXcNH1axFrNibKGt8auH9aBe8WDmg3LVQoamX4u6uAstySMYBotzgQrpyCj2EjQSBXIfDDzxgBBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ecb692bae183fe16f6f3f824d68b07df82391c17bb0958cad63d65cda571516f","last_reissued_at":"2026-07-05T09:27:55.608194Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:27:55.608194Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MMDU: A Multi-Turn Multi-Image Dialog Understanding Benchmark and Instruction-Tuning Dataset for LVLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Dahua Lin, Jiaqi Wang, Pan Zhang, Tao Chu, Xiaoyi Dong, Xilin Wei, Yuanjun Xiong, Yuhang Zang, Yu Qiao, Zijian Liang, Ziyu Liu","submitted_at":"2024-06-17T17:59:47Z","abstract_excerpt":"Generating natural and meaningful responses to communicate with multi-modal human inputs is a fundamental capability of Large Vision-Language Models(LVLMs). While current open-source LVLMs demonstrate promising performance in simplified scenarios such as single-turn single-image input, they fall short in real-world conversation scenarios such as following instructions in a long context history with multi-turn and multi-images. Existing LVLM benchmarks primarily focus on single-choice questions or short-form responses, which do not adequately assess the capabilities of LVLMs in real-world human"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11833","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/2406.11833/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":"2406.11833","created_at":"2026-07-05T09:27:55.608261+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.11833v2","created_at":"2026-07-05T09:27:55.608261+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11833","created_at":"2026-07-05T09:27:55.608261+00:00"},{"alias_kind":"pith_short_12","alias_value":"5S3JFOXBQP7B","created_at":"2026-07-05T09:27:55.608261+00:00"},{"alias_kind":"pith_short_16","alias_value":"5S3JFOXBQP7BN5XT","created_at":"2026-07-05T09:27:55.608261+00:00"},{"alias_kind":"pith_short_8","alias_value":"5S3JFOXB","created_at":"2026-07-05T09:27:55.608261+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.15128","citing_title":"MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2408.04840","citing_title":"mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models","ref_index":235,"is_internal_anchor":false},{"citing_arxiv_id":"2407.03320","citing_title":"InternLM-XComposer-2.5: A Versatile Large Vision Language Model Supporting Long-Contextual Input and Output","ref_index":93,"is_internal_anchor":false},{"citing_arxiv_id":"2502.04326","citing_title":"WorldSense: Evaluating Real-world Omnimodal Understanding for Multimodal LLMs","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2505.20275","citing_title":"ImgEdit: A Unified Image Editing Dataset and Benchmark","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05557","citing_title":"EpiBench: Benchmarking Multi-turn Research Workflows for Multimodal Agents","ref_index":13,"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":159,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18512","citing_title":"S2H-DPO: Hardness-Aware Preference Optimization for Vision-Language Models","ref_index":115,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5S3JFOXBQP7BN5XT7ASNNCYH36","json":"https://pith.science/pith/5S3JFOXBQP7BN5XT7ASNNCYH36.json","graph_json":"https://pith.science/api/pith-number/5S3JFOXBQP7BN5XT7ASNNCYH36/graph.json","events_json":"https://pith.science/api/pith-number/5S3JFOXBQP7BN5XT7ASNNCYH36/events.json","paper":"https://pith.science/paper/5S3JFOXB"},"agent_actions":{"view_html":"https://pith.science/pith/5S3JFOXBQP7BN5XT7ASNNCYH36","download_json":"https://pith.science/pith/5S3JFOXBQP7BN5XT7ASNNCYH36.json","view_paper":"https://pith.science/paper/5S3JFOXB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.11833&json=true","fetch_graph":"https://pith.science/api/pith-number/5S3JFOXBQP7BN5XT7ASNNCYH36/graph.json","fetch_events":"https://pith.science/api/pith-number/5S3JFOXBQP7BN5XT7ASNNCYH36/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5S3JFOXBQP7BN5XT7ASNNCYH36/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5S3JFOXBQP7BN5XT7ASNNCYH36/action/storage_attestation","attest_author":"https://pith.science/pith/5S3JFOXBQP7BN5XT7ASNNCYH36/action/author_attestation","sign_citation":"https://pith.science/pith/5S3JFOXBQP7BN5XT7ASNNCYH36/action/citation_signature","submit_replication":"https://pith.science/pith/5S3JFOXBQP7BN5XT7ASNNCYH36/action/replication_record"}},"created_at":"2026-07-05T09:27:55.608261+00:00","updated_at":"2026-07-05T09:27:55.608261+00:00"}