{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:I6ISXV4WS3GPQLNOTXJF6DMY56","short_pith_number":"pith:I6ISXV4W","schema_version":"1.0","canonical_sha256":"47912bd79696ccf82dae9dd25f0d98efaf1ebbc3d649d99aab5fa2d50604da4e","source":{"kind":"arxiv","id":"2505.21327","version":1},"attestation_state":"computed","paper":{"title":"MME-Reasoning: A Comprehensive Benchmark for Logical Reasoning in MLLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Bo Zhang, Chaoyou Fu, Jiakang Yuan, Kaituo Feng, Lei Bai, Renrui Zhang, Tao Chen, Tianshuo Peng, Xiangyu Yue, Yilei Jiang, Yiting Lu","submitted_at":"2025-05-27T15:23:23Z","abstract_excerpt":"Logical reasoning is a fundamental aspect of human intelligence and an essential capability for multimodal large language models (MLLMs). Despite the significant advancement in multimodal reasoning, existing benchmarks fail to comprehensively evaluate their reasoning abilities due to the lack of explicit categorization for logical reasoning types and an unclear understanding of reasoning. To address these issues, we introduce MME-Reasoning, a comprehensive benchmark designed to evaluate the reasoning ability of MLLMs, which covers all three types of reasoning (i.e., inductive, deductive, and a"},"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":"2505.21327","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-27T15:23:23Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"dd4196e133e2965a4c27b71d33498289789ba8800e0a2145dd306c315d7f52a5","abstract_canon_sha256":"0d05f6888610f26f083d1f9c1d769c91a85d36911c7be3578b693ea2b785e5f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:10:40.336049Z","signature_b64":"IfOX0b5WqbHJ+4I3O1mA8ufF14Y29ASh3k5/T42mh0ry5B9UEJa7OFRB4sa2HA8aGee9ypMwYBpMrQBw+lQACg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47912bd79696ccf82dae9dd25f0d98efaf1ebbc3d649d99aab5fa2d50604da4e","last_reissued_at":"2026-07-05T11:10:40.335532Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:10:40.335532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MME-Reasoning: A Comprehensive Benchmark for Logical Reasoning in MLLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.AI","authors_text":"Bo Zhang, Chaoyou Fu, Jiakang Yuan, Kaituo Feng, Lei Bai, Renrui Zhang, Tao Chen, Tianshuo Peng, Xiangyu Yue, Yilei Jiang, Yiting Lu","submitted_at":"2025-05-27T15:23:23Z","abstract_excerpt":"Logical reasoning is a fundamental aspect of human intelligence and an essential capability for multimodal large language models (MLLMs). Despite the significant advancement in multimodal reasoning, existing benchmarks fail to comprehensively evaluate their reasoning abilities due to the lack of explicit categorization for logical reasoning types and an unclear understanding of reasoning. To address these issues, we introduce MME-Reasoning, a comprehensive benchmark designed to evaluate the reasoning ability of MLLMs, which covers all three types of reasoning (i.e., inductive, deductive, and a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.21327","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/2505.21327/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":"2505.21327","created_at":"2026-07-05T11:10:40.335594+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.21327v1","created_at":"2026-07-05T11:10:40.335594+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.21327","created_at":"2026-07-05T11:10:40.335594+00:00"},{"alias_kind":"pith_short_12","alias_value":"I6ISXV4WS3GP","created_at":"2026-07-05T11:10:40.335594+00:00"},{"alias_kind":"pith_short_16","alias_value":"I6ISXV4WS3GPQLNO","created_at":"2026-07-05T11:10:40.335594+00:00"},{"alias_kind":"pith_short_8","alias_value":"I6ISXV4W","created_at":"2026-07-05T11:10:40.335594+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2607.08317","citing_title":"Blind-Spots-Bench: Evaluating Blind Spots in Multimodal Models","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2607.05992","citing_title":"PluraMath: Extending Mathematical Reasoning Evaluation Beyond High-Resource Languages","ref_index":11,"is_internal_anchor":true},{"citing_arxiv_id":"2606.19120","citing_title":"Seeing Before Reasoning: Decoupling Perception and Reasoning for Shortcut-Resilient Multimodal On-Policy Self-Distillation","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01599","citing_title":"TRON: Targeted Rule-Verifiable Online Environments for Visual Reasoning RL","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2603.11689","citing_title":"Explicit Logic Channel for Validation and Enhancement of MLLMs on Zero-Shot Tasks","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04970","citing_title":"Skill Neologisms: Towards Skill-based Continual Learning","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2512.03043","citing_title":"OneThinker: All-in-one Reasoning Model for Image and Video","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2512.16918","citing_title":"AdaTooler-V: Adaptive Tool-Use for Images and Videos","ref_index":77,"is_internal_anchor":false},{"citing_arxiv_id":"2503.21776","citing_title":"Video-R1: Reinforcing Video Reasoning in MLLMs","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04970","citing_title":"Skill Neologisms: Towards Skill-based Continual Learning","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02378","citing_title":"Enhancing Multimodal In-Context Learning via Inductive-Deductive Reasoning","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I6ISXV4WS3GPQLNOTXJF6DMY56","json":"https://pith.science/pith/I6ISXV4WS3GPQLNOTXJF6DMY56.json","graph_json":"https://pith.science/api/pith-number/I6ISXV4WS3GPQLNOTXJF6DMY56/graph.json","events_json":"https://pith.science/api/pith-number/I6ISXV4WS3GPQLNOTXJF6DMY56/events.json","paper":"https://pith.science/paper/I6ISXV4W"},"agent_actions":{"view_html":"https://pith.science/pith/I6ISXV4WS3GPQLNOTXJF6DMY56","download_json":"https://pith.science/pith/I6ISXV4WS3GPQLNOTXJF6DMY56.json","view_paper":"https://pith.science/paper/I6ISXV4W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.21327&json=true","fetch_graph":"https://pith.science/api/pith-number/I6ISXV4WS3GPQLNOTXJF6DMY56/graph.json","fetch_events":"https://pith.science/api/pith-number/I6ISXV4WS3GPQLNOTXJF6DMY56/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I6ISXV4WS3GPQLNOTXJF6DMY56/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I6ISXV4WS3GPQLNOTXJF6DMY56/action/storage_attestation","attest_author":"https://pith.science/pith/I6ISXV4WS3GPQLNOTXJF6DMY56/action/author_attestation","sign_citation":"https://pith.science/pith/I6ISXV4WS3GPQLNOTXJF6DMY56/action/citation_signature","submit_replication":"https://pith.science/pith/I6ISXV4WS3GPQLNOTXJF6DMY56/action/replication_record"}},"created_at":"2026-07-05T11:10:40.335594+00:00","updated_at":"2026-07-05T11:10:40.335594+00:00"}