{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:MBVH4NYNAR5MDLTY7RTCS32F3W","short_pith_number":"pith:MBVH4NYN","schema_version":"1.0","canonical_sha256":"606a7e370d047ac1ae78fc66296f45ddb5f42c7c7502c1fe6eb1375795962a54","source":{"kind":"arxiv","id":"2502.11903","version":2},"attestation_state":"computed","paper":{"title":"MMRC: A Large-Scale Benchmark for Understanding Multimodal Large Language Model in Real-World Conversation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chengzhi Liu, Chong Zhang, Chun-Mei Feng, Feilong Tang, Haochen Xue, Imran Razzak, Jionglong Su, Junjun He, Ming Hu, Qidong Huang, Yexin Liu, Yulong Li, Yu Qiao, Yutong Xie, Zhongxing Xu, Zongyuan Ge","submitted_at":"2025-02-17T15:24:49Z","abstract_excerpt":"Recent multimodal large language models (MLLMs) have demonstrated significant potential in open-ended conversation, generating more accurate and personalized responses. However, their abilities to memorize, recall, and reason in sustained interactions within real-world scenarios remain underexplored. This paper introduces MMRC, a Multi-Modal Real-world Conversation benchmark for evaluating six core open-ended abilities of MLLMs: information extraction, multi-turn reasoning, information update, image management, memory recall, and answer refusal. With data collected from real-world scenarios, M"},"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":"2502.11903","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-17T15:24:49Z","cross_cats_sorted":[],"title_canon_sha256":"cefdc65ac988bf40a32e8c9f24dd5430f981942f01659b89bd50d9f41ce2e0c3","abstract_canon_sha256":"35dd7d3886c642aba26a713285a257129e2ab261475b8f71ebc49e1b98b05e3e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:26:43.790355Z","signature_b64":"pxlHzLCjlM3cpcDvsyWn1rvCGVIQqPBHSHY+XyeO7v2z6H5qScXLBWY8Xu7gvZPOOWqMEjHkFmSZ6dMHwWvrBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"606a7e370d047ac1ae78fc66296f45ddb5f42c7c7502c1fe6eb1375795962a54","last_reissued_at":"2026-07-05T10:26:43.789432Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:26:43.789432Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MMRC: A Large-Scale Benchmark for Understanding Multimodal Large Language Model in Real-World Conversation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chengzhi Liu, Chong Zhang, Chun-Mei Feng, Feilong Tang, Haochen Xue, Imran Razzak, Jionglong Su, Junjun He, Ming Hu, Qidong Huang, Yexin Liu, Yulong Li, Yu Qiao, Yutong Xie, Zhongxing Xu, Zongyuan Ge","submitted_at":"2025-02-17T15:24:49Z","abstract_excerpt":"Recent multimodal large language models (MLLMs) have demonstrated significant potential in open-ended conversation, generating more accurate and personalized responses. However, their abilities to memorize, recall, and reason in sustained interactions within real-world scenarios remain underexplored. This paper introduces MMRC, a Multi-Modal Real-world Conversation benchmark for evaluating six core open-ended abilities of MLLMs: information extraction, multi-turn reasoning, information update, image management, memory recall, and answer refusal. With data collected from real-world scenarios, M"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11903","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/2502.11903/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":"2502.11903","created_at":"2026-07-05T10:26:43.789570+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.11903v2","created_at":"2026-07-05T10:26:43.789570+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11903","created_at":"2026-07-05T10:26:43.789570+00:00"},{"alias_kind":"pith_short_12","alias_value":"MBVH4NYNAR5M","created_at":"2026-07-05T10:26:43.789570+00:00"},{"alias_kind":"pith_short_16","alias_value":"MBVH4NYNAR5MDLTY","created_at":"2026-07-05T10:26:43.789570+00:00"},{"alias_kind":"pith_short_8","alias_value":"MBVH4NYN","created_at":"2026-07-05T10:26:43.789570+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2504.15965","citing_title":"From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMs","ref_index":79,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MBVH4NYNAR5MDLTY7RTCS32F3W","json":"https://pith.science/pith/MBVH4NYNAR5MDLTY7RTCS32F3W.json","graph_json":"https://pith.science/api/pith-number/MBVH4NYNAR5MDLTY7RTCS32F3W/graph.json","events_json":"https://pith.science/api/pith-number/MBVH4NYNAR5MDLTY7RTCS32F3W/events.json","paper":"https://pith.science/paper/MBVH4NYN"},"agent_actions":{"view_html":"https://pith.science/pith/MBVH4NYNAR5MDLTY7RTCS32F3W","download_json":"https://pith.science/pith/MBVH4NYNAR5MDLTY7RTCS32F3W.json","view_paper":"https://pith.science/paper/MBVH4NYN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.11903&json=true","fetch_graph":"https://pith.science/api/pith-number/MBVH4NYNAR5MDLTY7RTCS32F3W/graph.json","fetch_events":"https://pith.science/api/pith-number/MBVH4NYNAR5MDLTY7RTCS32F3W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MBVH4NYNAR5MDLTY7RTCS32F3W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MBVH4NYNAR5MDLTY7RTCS32F3W/action/storage_attestation","attest_author":"https://pith.science/pith/MBVH4NYNAR5MDLTY7RTCS32F3W/action/author_attestation","sign_citation":"https://pith.science/pith/MBVH4NYNAR5MDLTY7RTCS32F3W/action/citation_signature","submit_replication":"https://pith.science/pith/MBVH4NYNAR5MDLTY7RTCS32F3W/action/replication_record"}},"created_at":"2026-07-05T10:26:43.789570+00:00","updated_at":"2026-07-05T10:26:43.789570+00:00"}