{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DWUNFJGVWCKEDOUENIVXPBF4QZ","short_pith_number":"pith:DWUNFJGV","schema_version":"1.0","canonical_sha256":"1da8d2a4d5b09441ba846a2b7784bc867f0a8cf1a4ac566a6c65a04408f7037c","source":{"kind":"arxiv","id":"2506.05331","version":1},"attestation_state":"computed","paper":{"title":"MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aojun Zhou, Dongzhi Jiang, Hongsheng Li, Renrui Zhang, Shilin Yan, Weifeng Lin, Xinyan Chen","submitted_at":"2025-06-05T17:59:02Z","abstract_excerpt":"Chain-of-Thought (CoT) has widely enhanced mathematical reasoning in Large Language Models (LLMs), but it still remains challenging for extending it to multimodal domains. Existing works either adopt a similar textual reasoning for image input, or seek to interleave visual signals into mathematical CoT. However, they face three key limitations for math problem-solving: reliance on coarse-grained box-shaped image regions, limited perception of vision encoders on math content, and dependence on external capabilities for visual modification. In this paper, we propose MINT-CoT, introducing Mathema"},"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":"2506.05331","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T17:59:02Z","cross_cats_sorted":[],"title_canon_sha256":"2ccd320f7554ed9116db653a98a3c93d3e6fe8c286c74ab5306c5237910bd1c7","abstract_canon_sha256":"f20ccf90c78c0dd20d11316e3416cfb8a174808eaaae7ffd6ada2da1dab9bf5f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:46.167965Z","signature_b64":"a3AHYGyJQ2Eju0jnZfkf6L7zWmn2oOvvdwBTIwk8a75GZNJRbQpomUoqmpozGkB87/Zyfelrq8ZwAM1U62ViBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1da8d2a4d5b09441ba846a2b7784bc867f0a8cf1a4ac566a6c65a04408f7037c","last_reissued_at":"2026-07-05T11:16:46.167469Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:46.167469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aojun Zhou, Dongzhi Jiang, Hongsheng Li, Renrui Zhang, Shilin Yan, Weifeng Lin, Xinyan Chen","submitted_at":"2025-06-05T17:59:02Z","abstract_excerpt":"Chain-of-Thought (CoT) has widely enhanced mathematical reasoning in Large Language Models (LLMs), but it still remains challenging for extending it to multimodal domains. Existing works either adopt a similar textual reasoning for image input, or seek to interleave visual signals into mathematical CoT. However, they face three key limitations for math problem-solving: reliance on coarse-grained box-shaped image regions, limited perception of vision encoders on math content, and dependence on external capabilities for visual modification. In this paper, we propose MINT-CoT, introducing Mathema"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05331","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/2506.05331/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":"2506.05331","created_at":"2026-07-05T11:16:46.167529+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.05331v1","created_at":"2026-07-05T11:16:46.167529+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05331","created_at":"2026-07-05T11:16:46.167529+00:00"},{"alias_kind":"pith_short_12","alias_value":"DWUNFJGVWCKE","created_at":"2026-07-05T11:16:46.167529+00:00"},{"alias_kind":"pith_short_16","alias_value":"DWUNFJGVWCKEDOUE","created_at":"2026-07-05T11:16:46.167529+00:00"},{"alias_kind":"pith_short_8","alias_value":"DWUNFJGV","created_at":"2026-07-05T11:16:46.167529+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08763","citing_title":"OpenCoF: Learning to Reason Through Video Generation","ref_index":4,"is_internal_anchor":true},{"citing_arxiv_id":"2606.24233","citing_title":"Latent Visual States for Efficient Multimodal Reasoning","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17888","citing_title":"MathVis-Fine: Aligning Visual Supervision with Necessity via Progressive Dependency-Guided Training for Multimodal Mathematical Reasoning","ref_index":110,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11740","citing_title":"UniReason-Med: A Shared Grounded Reasoning Interface for 2D-to-3D Transfer in Medical VQA","ref_index":135,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09585","citing_title":"Optical Reasoning: Rethinking Images as an Expressive Reasoning Medium Beyond Text","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08728","citing_title":"Artificial Intelligence for Mathematical Reasoning: An Integrated Survey of Language Models, Neuro-symbolic Systems, and Verified Discovery","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2607.00461","citing_title":"Multimodal Continuous Reasoning via Asymmetric Mutual Variational Learning","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30168","citing_title":"Latent Noise Mask for Reducing Visual Redundancy in Multimodal Large Language Models","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25842","citing_title":"MuCRASP: Multimodal Chain-of-thought Reasoning aware Structured Pruning","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.27959","citing_title":"ROVER: Routing Object-Centric Visual Evidence for Grounded Multi-Image Reasoning","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2510.04978","citing_title":"Aligning Perception, Reasoning, Modeling and Interaction: A Survey on Physical AI","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2601.09536","citing_title":"Omni-R1: Towards the Unified Generative Paradigm for Multimodal Reasoning","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DWUNFJGVWCKEDOUENIVXPBF4QZ","json":"https://pith.science/pith/DWUNFJGVWCKEDOUENIVXPBF4QZ.json","graph_json":"https://pith.science/api/pith-number/DWUNFJGVWCKEDOUENIVXPBF4QZ/graph.json","events_json":"https://pith.science/api/pith-number/DWUNFJGVWCKEDOUENIVXPBF4QZ/events.json","paper":"https://pith.science/paper/DWUNFJGV"},"agent_actions":{"view_html":"https://pith.science/pith/DWUNFJGVWCKEDOUENIVXPBF4QZ","download_json":"https://pith.science/pith/DWUNFJGVWCKEDOUENIVXPBF4QZ.json","view_paper":"https://pith.science/paper/DWUNFJGV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.05331&json=true","fetch_graph":"https://pith.science/api/pith-number/DWUNFJGVWCKEDOUENIVXPBF4QZ/graph.json","fetch_events":"https://pith.science/api/pith-number/DWUNFJGVWCKEDOUENIVXPBF4QZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DWUNFJGVWCKEDOUENIVXPBF4QZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DWUNFJGVWCKEDOUENIVXPBF4QZ/action/storage_attestation","attest_author":"https://pith.science/pith/DWUNFJGVWCKEDOUENIVXPBF4QZ/action/author_attestation","sign_citation":"https://pith.science/pith/DWUNFJGVWCKEDOUENIVXPBF4QZ/action/citation_signature","submit_replication":"https://pith.science/pith/DWUNFJGVWCKEDOUENIVXPBF4QZ/action/replication_record"}},"created_at":"2026-07-05T11:16:46.167529+00:00","updated_at":"2026-07-05T11:16:46.167529+00:00"}