{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UD5SH2FVX5P6F4ZCVYEOI3ZD4X","short_pith_number":"pith:UD5SH2FV","schema_version":"1.0","canonical_sha256":"a0fb23e8b5bf5fe2f322ae08e46f23e5d14b5c1128738b8857750fb6a8ef87b4","source":{"kind":"arxiv","id":"2502.13383","version":1},"attestation_state":"computed","paper":{"title":"MM-Verify: Enhancing Multimodal Reasoning with Chain-of-Thought Verification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bihui Yu, Fan Yang, Hao Liang, Jingxuan Wei, Linzhuang Sun, Tianpeng Li, Wentao Zhang, Zenan Zhou","submitted_at":"2025-02-19T02:46:52Z","abstract_excerpt":"According to the Test-Time Scaling, the integration of External Slow-Thinking with the Verify mechanism has been demonstrated to enhance multi-round reasoning in large language models (LLMs). However, in the multimodal (MM) domain, there is still a lack of a strong MM-Verifier. In this paper, we introduce MM-Verifier and MM-Reasoner to enhance multimodal reasoning through longer inference and more robust verification. First, we propose a two-step MM verification data synthesis method, which combines a simulation-based tree search with verification and uses rejection sampling to generate high-q"},"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":"2502.13383","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-02-19T02:46:52Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"05f120f0b4e2e994402c7808ce52381082aeafd82e0607f468881e81e13a921c","abstract_canon_sha256":"f04951e8b25e9f23d178225a6e2be2408ba2339f8b0e80b1173fe068607f19d9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:16:46.388997Z","signature_b64":"riTiWJBsPXDzCFK7wvgIacPVQaxUq/sxwY2nxmDnfBJZwyiLQS7e7vLdCJlwNChVrfsy/KMNNDokBK+jQkIBDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a0fb23e8b5bf5fe2f322ae08e46f23e5d14b5c1128738b8857750fb6a8ef87b4","last_reissued_at":"2026-07-05T10:16:46.388522Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:16:46.388522Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MM-Verify: Enhancing Multimodal Reasoning with Chain-of-Thought Verification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bihui Yu, Fan Yang, Hao Liang, Jingxuan Wei, Linzhuang Sun, Tianpeng Li, Wentao Zhang, Zenan Zhou","submitted_at":"2025-02-19T02:46:52Z","abstract_excerpt":"According to the Test-Time Scaling, the integration of External Slow-Thinking with the Verify mechanism has been demonstrated to enhance multi-round reasoning in large language models (LLMs). However, in the multimodal (MM) domain, there is still a lack of a strong MM-Verifier. In this paper, we introduce MM-Verifier and MM-Reasoner to enhance multimodal reasoning through longer inference and more robust verification. First, we propose a two-step MM verification data synthesis method, which combines a simulation-based tree search with verification and uses rejection sampling to generate high-q"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.13383","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/2502.13383/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":"2502.13383","created_at":"2026-07-05T10:16:46.388573+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.13383v1","created_at":"2026-07-05T10:16:46.388573+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.13383","created_at":"2026-07-05T10:16:46.388573+00:00"},{"alias_kind":"pith_short_12","alias_value":"UD5SH2FVX5P6","created_at":"2026-07-05T10:16:46.388573+00:00"},{"alias_kind":"pith_short_16","alias_value":"UD5SH2FVX5P6F4ZC","created_at":"2026-07-05T10:16:46.388573+00:00"},{"alias_kind":"pith_short_8","alias_value":"UD5SH2FV","created_at":"2026-07-05T10:16:46.388573+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.20033","citing_title":"A Nash Equilibrium Framework For Training-Free Multimodal Step Verification","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2509.23322","citing_title":"Mitigating Visual Context Degradation in Large Multimodal Models: A Training-Free Decoupled Agentic Framework","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2512.14044","citing_title":"OmniDrive-R1: Reinforcement-driven Interleaved Multi-modal Chain-of-Thought for Trustworthy Vision-Language Autonomous Driving","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2503.12605","citing_title":"Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey","ref_index":257,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12620","citing_title":"Think Twice, Act Once: Verifier-Guided Action Selection For Embodied Agents","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07593","citing_title":"TraceAV-Bench: Benchmarking Multi-Hop Trajectory Reasoning over Long Audio-Visual Videos","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04707","citing_title":"OpenWorldLib: A Unified Codebase and Definition of Advanced World Models","ref_index":109,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UD5SH2FVX5P6F4ZCVYEOI3ZD4X","json":"https://pith.science/pith/UD5SH2FVX5P6F4ZCVYEOI3ZD4X.json","graph_json":"https://pith.science/api/pith-number/UD5SH2FVX5P6F4ZCVYEOI3ZD4X/graph.json","events_json":"https://pith.science/api/pith-number/UD5SH2FVX5P6F4ZCVYEOI3ZD4X/events.json","paper":"https://pith.science/paper/UD5SH2FV"},"agent_actions":{"view_html":"https://pith.science/pith/UD5SH2FVX5P6F4ZCVYEOI3ZD4X","download_json":"https://pith.science/pith/UD5SH2FVX5P6F4ZCVYEOI3ZD4X.json","view_paper":"https://pith.science/paper/UD5SH2FV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.13383&json=true","fetch_graph":"https://pith.science/api/pith-number/UD5SH2FVX5P6F4ZCVYEOI3ZD4X/graph.json","fetch_events":"https://pith.science/api/pith-number/UD5SH2FVX5P6F4ZCVYEOI3ZD4X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UD5SH2FVX5P6F4ZCVYEOI3ZD4X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UD5SH2FVX5P6F4ZCVYEOI3ZD4X/action/storage_attestation","attest_author":"https://pith.science/pith/UD5SH2FVX5P6F4ZCVYEOI3ZD4X/action/author_attestation","sign_citation":"https://pith.science/pith/UD5SH2FVX5P6F4ZCVYEOI3ZD4X/action/citation_signature","submit_replication":"https://pith.science/pith/UD5SH2FVX5P6F4ZCVYEOI3ZD4X/action/replication_record"}},"created_at":"2026-07-05T10:16:46.388573+00:00","updated_at":"2026-07-05T10:16:46.388573+00:00"}