{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:UERJ7CEZLJ5YA5HUULGVO32ZJJ","short_pith_number":"pith:UERJ7CEZ","schema_version":"1.0","canonical_sha256":"a1229f88995a7b8074f4a2cd576f594a591c4debd6786a75eadb677c6cd1b94b","source":{"kind":"arxiv","id":"2311.11567","version":3},"attestation_state":"computed","paper":{"title":"InfiMM-Eval: Complex Open-Ended Reasoning Evaluation For Multi-Modal Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bohan Zhai, Heng Wang, Hongxia Yang, Huangjie Zheng, Jianbo Yuan, Khalil Mrini, Quanzeng You, Wentao Chen, Xiaotian Han, Xudong Lin, Yiqi Wang, Yongfei Liu","submitted_at":"2023-11-20T07:06:31Z","abstract_excerpt":"Multi-modal Large Language Models (MLLMs) are increasingly prominent in the field of artificial intelligence. These models not only excel in traditional vision-language tasks but also demonstrate impressive performance in contemporary multi-modal benchmarks. Although many of these benchmarks attempt to holistically evaluate MLLMs, they typically concentrate on basic reasoning tasks, often yielding only simple yes/no or multi-choice responses. These methods naturally lead to confusion and difficulties in conclusively determining the reasoning capabilities of MLLMs. To mitigate this issue, we ma"},"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":"2311.11567","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2023-11-20T07:06:31Z","cross_cats_sorted":[],"title_canon_sha256":"fb80f04fdb6373ae4d6f388631f343aac2eda122ec085e2ff34eaf6b0951fd4c","abstract_canon_sha256":"e36c68108a3b88a2f3143eca5a151bfc8aab352f69dc3677265eae8d0d4d744d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:20:12.483394Z","signature_b64":"DgQuQesZGf5Le2NY1461u9bI30JGHJMrysX9LJosJWAuV3+nsXGoB9LaOAy27/A9KmdqmAKaOttyzVPiYGsACg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1229f88995a7b8074f4a2cd576f594a591c4debd6786a75eadb677c6cd1b94b","last_reissued_at":"2026-07-05T07:20:12.482915Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:20:12.482915Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"InfiMM-Eval: Complex Open-Ended Reasoning Evaluation For Multi-Modal Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bohan Zhai, Heng Wang, Hongxia Yang, Huangjie Zheng, Jianbo Yuan, Khalil Mrini, Quanzeng You, Wentao Chen, Xiaotian Han, Xudong Lin, Yiqi Wang, Yongfei Liu","submitted_at":"2023-11-20T07:06:31Z","abstract_excerpt":"Multi-modal Large Language Models (MLLMs) are increasingly prominent in the field of artificial intelligence. These models not only excel in traditional vision-language tasks but also demonstrate impressive performance in contemporary multi-modal benchmarks. Although many of these benchmarks attempt to holistically evaluate MLLMs, they typically concentrate on basic reasoning tasks, often yielding only simple yes/no or multi-choice responses. These methods naturally lead to confusion and difficulties in conclusively determining the reasoning capabilities of MLLMs. To mitigate this issue, we ma"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.11567","kind":"arxiv","version":3},"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/2311.11567/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":"2311.11567","created_at":"2026-07-05T07:20:12.482998+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.11567v3","created_at":"2026-07-05T07:20:12.482998+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.11567","created_at":"2026-07-05T07:20:12.482998+00:00"},{"alias_kind":"pith_short_12","alias_value":"UERJ7CEZLJ5Y","created_at":"2026-07-05T07:20:12.482998+00:00"},{"alias_kind":"pith_short_16","alias_value":"UERJ7CEZLJ5YA5HU","created_at":"2026-07-05T07:20:12.482998+00:00"},{"alias_kind":"pith_short_8","alias_value":"UERJ7CEZ","created_at":"2026-07-05T07:20:12.482998+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.15000","citing_title":"Towards Spoken Mathematical Reasoning: Benchmarking Speech-based Models over Multi-faceted Math Problems","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UERJ7CEZLJ5YA5HUULGVO32ZJJ","json":"https://pith.science/pith/UERJ7CEZLJ5YA5HUULGVO32ZJJ.json","graph_json":"https://pith.science/api/pith-number/UERJ7CEZLJ5YA5HUULGVO32ZJJ/graph.json","events_json":"https://pith.science/api/pith-number/UERJ7CEZLJ5YA5HUULGVO32ZJJ/events.json","paper":"https://pith.science/paper/UERJ7CEZ"},"agent_actions":{"view_html":"https://pith.science/pith/UERJ7CEZLJ5YA5HUULGVO32ZJJ","download_json":"https://pith.science/pith/UERJ7CEZLJ5YA5HUULGVO32ZJJ.json","view_paper":"https://pith.science/paper/UERJ7CEZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.11567&json=true","fetch_graph":"https://pith.science/api/pith-number/UERJ7CEZLJ5YA5HUULGVO32ZJJ/graph.json","fetch_events":"https://pith.science/api/pith-number/UERJ7CEZLJ5YA5HUULGVO32ZJJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UERJ7CEZLJ5YA5HUULGVO32ZJJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UERJ7CEZLJ5YA5HUULGVO32ZJJ/action/storage_attestation","attest_author":"https://pith.science/pith/UERJ7CEZLJ5YA5HUULGVO32ZJJ/action/author_attestation","sign_citation":"https://pith.science/pith/UERJ7CEZLJ5YA5HUULGVO32ZJJ/action/citation_signature","submit_replication":"https://pith.science/pith/UERJ7CEZLJ5YA5HUULGVO32ZJJ/action/replication_record"}},"created_at":"2026-07-05T07:20:12.482998+00:00","updated_at":"2026-07-05T07:20:12.482998+00:00"}