{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OBTD72IROXX4UH4POA3B3GGD54","short_pith_number":"pith:OBTD72IR","schema_version":"1.0","canonical_sha256":"70663fe91175efca1f8f70361d98c3ef3c14330370b457f3dd8fae9c41a08413","source":{"kind":"arxiv","id":"2506.23563","version":1},"attestation_state":"computed","paper":{"title":"MMReason: An Open-Ended Multi-Modal Multi-Step Reasoning Benchmark for MLLMs Toward AGI","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Dacheng Tao, Huanjin Yao, Jiaxing Huang, Jingyi Zhang, Michael K. Chen, Wei Zhang, Wenhao Wu, Wenjie Zeng, Wenzheng Liu, Xikun Zhang, Yawen Qiu, Yuxin Song","submitted_at":"2025-06-30T07:14:38Z","abstract_excerpt":"Reasoning plays a crucial role in advancing Multimodal Large Language Models (MLLMs) toward Artificial General Intelligence. However, existing MLLM benchmarks often fall short in precisely and comprehensively evaluating long-chain reasoning abilities from three key aspects: (1) lack of difficulty and diversity, (2) susceptibility to guessability and memorization, (3) inadequate assessment of intermediate reasoning steps. To fill this gap, we introduce MMReason, a new benchmark designed to precisely and comprehensively evaluate MLLM long-chain reasoning capability with diverse, open-ended, chal"},"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":"2506.23563","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-06-30T07:14:38Z","cross_cats_sorted":["cs.CL","cs.CV"],"title_canon_sha256":"7191b0d73478bef7dd764c31c6c3b26d0f111c7dac3ffe18abe0649958fd95be","abstract_canon_sha256":"ed0cb86fb7c7484e7a24286be8b712d5d6f68a2aaba83a7164b94f1ab771bdb2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:29:24.055538Z","signature_b64":"UQ0RoSAZG3RQFiIhqR4bba4dydS/8MA7Vo5MUEU/Z1cHjNfY4nZ9A/gVPB5FvpSAHeKD0gaPEQwnEXDupXKSDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"70663fe91175efca1f8f70361d98c3ef3c14330370b457f3dd8fae9c41a08413","last_reissued_at":"2026-07-05T11:29:24.055024Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:29:24.055024Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MMReason: An Open-Ended Multi-Modal Multi-Step Reasoning Benchmark for MLLMs Toward AGI","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL","cs.CV"],"primary_cat":"cs.AI","authors_text":"Dacheng Tao, Huanjin Yao, Jiaxing Huang, Jingyi Zhang, Michael K. Chen, Wei Zhang, Wenhao Wu, Wenjie Zeng, Wenzheng Liu, Xikun Zhang, Yawen Qiu, Yuxin Song","submitted_at":"2025-06-30T07:14:38Z","abstract_excerpt":"Reasoning plays a crucial role in advancing Multimodal Large Language Models (MLLMs) toward Artificial General Intelligence. However, existing MLLM benchmarks often fall short in precisely and comprehensively evaluating long-chain reasoning abilities from three key aspects: (1) lack of difficulty and diversity, (2) susceptibility to guessability and memorization, (3) inadequate assessment of intermediate reasoning steps. To fill this gap, we introduce MMReason, a new benchmark designed to precisely and comprehensively evaluate MLLM long-chain reasoning capability with diverse, open-ended, chal"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.23563","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/2506.23563/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":"2506.23563","created_at":"2026-07-05T11:29:24.055083+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.23563v1","created_at":"2026-07-05T11:29:24.055083+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.23563","created_at":"2026-07-05T11:29:24.055083+00:00"},{"alias_kind":"pith_short_12","alias_value":"OBTD72IROXX4","created_at":"2026-07-05T11:29:24.055083+00:00"},{"alias_kind":"pith_short_16","alias_value":"OBTD72IROXX4UH4P","created_at":"2026-07-05T11:29:24.055083+00:00"},{"alias_kind":"pith_short_8","alias_value":"OBTD72IR","created_at":"2026-07-05T11:29:24.055083+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.12937","citing_title":"R1-VL: Learning to Reason with Multimodal Large Language Models via Step-wise Group Relative Policy Optimization","ref_index":45,"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":66,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OBTD72IROXX4UH4POA3B3GGD54","json":"https://pith.science/pith/OBTD72IROXX4UH4POA3B3GGD54.json","graph_json":"https://pith.science/api/pith-number/OBTD72IROXX4UH4POA3B3GGD54/graph.json","events_json":"https://pith.science/api/pith-number/OBTD72IROXX4UH4POA3B3GGD54/events.json","paper":"https://pith.science/paper/OBTD72IR"},"agent_actions":{"view_html":"https://pith.science/pith/OBTD72IROXX4UH4POA3B3GGD54","download_json":"https://pith.science/pith/OBTD72IROXX4UH4POA3B3GGD54.json","view_paper":"https://pith.science/paper/OBTD72IR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.23563&json=true","fetch_graph":"https://pith.science/api/pith-number/OBTD72IROXX4UH4POA3B3GGD54/graph.json","fetch_events":"https://pith.science/api/pith-number/OBTD72IROXX4UH4POA3B3GGD54/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OBTD72IROXX4UH4POA3B3GGD54/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OBTD72IROXX4UH4POA3B3GGD54/action/storage_attestation","attest_author":"https://pith.science/pith/OBTD72IROXX4UH4POA3B3GGD54/action/author_attestation","sign_citation":"https://pith.science/pith/OBTD72IROXX4UH4POA3B3GGD54/action/citation_signature","submit_replication":"https://pith.science/pith/OBTD72IROXX4UH4POA3B3GGD54/action/replication_record"}},"created_at":"2026-07-05T11:29:24.055083+00:00","updated_at":"2026-07-05T11:29:24.055083+00:00"}