{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:P6OAI6UG4LAXAJF6N2OCAMLV5A","short_pith_number":"pith:P6OAI6UG","schema_version":"1.0","canonical_sha256":"7f9c047a86e2c17024be6e9c203175e823dc68e6b6a457ae291d9eb6ee56a1a6","source":{"kind":"arxiv","id":"2506.11080","version":1},"attestation_state":"computed","paper":{"title":"MANBench: Is Your Multimodal Model Smarter than Human?","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Han Zhou, Qitong Xu, Xin Yang, Yiheng Dong","submitted_at":"2025-06-04T08:42:14Z","abstract_excerpt":"The rapid advancement of Multimodal Large Language Models (MLLMs) has ignited discussions regarding their potential to surpass human performance in multimodal tasks. In response, we introduce MANBench (Multimodal Ability Norms Benchmark), a bilingual benchmark (English and Chinese) comprising 1,314 questions across nine tasks, spanning knowledge-based and non-knowledge-based domains. MANBench emphasizes intuitive reasoning, seamless cross-modal integration, and real-world complexity, providing a rigorous evaluation framework.\n  Through extensive human experiments involving diverse participants"},"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":"2506.11080","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-04T08:42:14Z","cross_cats_sorted":[],"title_canon_sha256":"6b498b838382bec9a1ebfcf8aea703e8425a841dbe11ebcc9db477b61402d043","abstract_canon_sha256":"3920c84cc87757c76a137a79e8de675810f7c80084b3749be24e08d3d3c88471"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:59.130919Z","signature_b64":"vs7GRb7sCnOqb6Sr2e5eDsPyChHtN1MdoFH5FJMkx1vKMhDtqUlEVvGwWlNa1RTvrVgOOaJVk5osZ9qdUfU1Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f9c047a86e2c17024be6e9c203175e823dc68e6b6a457ae291d9eb6ee56a1a6","last_reissued_at":"2026-07-05T11:20:59.130531Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:59.130531Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MANBench: Is Your Multimodal Model Smarter than Human?","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Han Zhou, Qitong Xu, Xin Yang, Yiheng Dong","submitted_at":"2025-06-04T08:42:14Z","abstract_excerpt":"The rapid advancement of Multimodal Large Language Models (MLLMs) has ignited discussions regarding their potential to surpass human performance in multimodal tasks. In response, we introduce MANBench (Multimodal Ability Norms Benchmark), a bilingual benchmark (English and Chinese) comprising 1,314 questions across nine tasks, spanning knowledge-based and non-knowledge-based domains. MANBench emphasizes intuitive reasoning, seamless cross-modal integration, and real-world complexity, providing a rigorous evaluation framework.\n  Through extensive human experiments involving diverse participants"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.11080","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/2506.11080/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":"2506.11080","created_at":"2026-07-05T11:20:59.130588+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.11080v1","created_at":"2026-07-05T11:20:59.130588+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.11080","created_at":"2026-07-05T11:20:59.130588+00:00"},{"alias_kind":"pith_short_12","alias_value":"P6OAI6UG4LAX","created_at":"2026-07-05T11:20:59.130588+00:00"},{"alias_kind":"pith_short_16","alias_value":"P6OAI6UG4LAXAJF6","created_at":"2026-07-05T11:20:59.130588+00:00"},{"alias_kind":"pith_short_8","alias_value":"P6OAI6UG","created_at":"2026-07-05T11:20:59.130588+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P6OAI6UG4LAXAJF6N2OCAMLV5A","json":"https://pith.science/pith/P6OAI6UG4LAXAJF6N2OCAMLV5A.json","graph_json":"https://pith.science/api/pith-number/P6OAI6UG4LAXAJF6N2OCAMLV5A/graph.json","events_json":"https://pith.science/api/pith-number/P6OAI6UG4LAXAJF6N2OCAMLV5A/events.json","paper":"https://pith.science/paper/P6OAI6UG"},"agent_actions":{"view_html":"https://pith.science/pith/P6OAI6UG4LAXAJF6N2OCAMLV5A","download_json":"https://pith.science/pith/P6OAI6UG4LAXAJF6N2OCAMLV5A.json","view_paper":"https://pith.science/paper/P6OAI6UG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.11080&json=true","fetch_graph":"https://pith.science/api/pith-number/P6OAI6UG4LAXAJF6N2OCAMLV5A/graph.json","fetch_events":"https://pith.science/api/pith-number/P6OAI6UG4LAXAJF6N2OCAMLV5A/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P6OAI6UG4LAXAJF6N2OCAMLV5A/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P6OAI6UG4LAXAJF6N2OCAMLV5A/action/storage_attestation","attest_author":"https://pith.science/pith/P6OAI6UG4LAXAJF6N2OCAMLV5A/action/author_attestation","sign_citation":"https://pith.science/pith/P6OAI6UG4LAXAJF6N2OCAMLV5A/action/citation_signature","submit_replication":"https://pith.science/pith/P6OAI6UG4LAXAJF6N2OCAMLV5A/action/replication_record"}},"created_at":"2026-07-05T11:20:59.130588+00:00","updated_at":"2026-07-05T11:20:59.130588+00:00"}