{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:DWUNFJGVWCKEDOUENIVXPBF4QZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"f20ccf90c78c0dd20d11316e3416cfb8a174808eaaae7ffd6ada2da1dab9bf5f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T17:59:02Z","title_canon_sha256":"2ccd320f7554ed9116db653a98a3c93d3e6fe8c286c74ab5306c5237910bd1c7"},"schema_version":"1.0","source":{"id":"2506.05331","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2506.05331","created_at":"2026-07-05T11:16:46Z"},{"alias_kind":"arxiv_version","alias_value":"2506.05331v1","created_at":"2026-07-05T11:16:46Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.05331","created_at":"2026-07-05T11:16:46Z"},{"alias_kind":"pith_short_12","alias_value":"DWUNFJGVWCKE","created_at":"2026-07-05T11:16:46Z"},{"alias_kind":"pith_short_16","alias_value":"DWUNFJGVWCKEDOUE","created_at":"2026-07-05T11:16:46Z"},{"alias_kind":"pith_short_8","alias_value":"DWUNFJGV","created_at":"2026-07-05T11:16:46Z"}],"graph_snapshots":[{"event_id":"sha256:2c188f60dee3f05a1298eb00a84a98119e4d28db1c51cef213b637db3f55fe2c","target":"graph","created_at":"2026-07-05T11:16:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2506.05331/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Aojun Zhou, Dongzhi Jiang, Hongsheng Li, Renrui Zhang, Shilin Yan, Weifeng Lin, Xinyan Chen","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T17:59:02Z","title":"MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.05331","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:c97f3b61356cb35800bee88c7ebfbfc0ed5e810557149931fbab8e4625d9ac4c","target":"record","created_at":"2026-07-05T11:16:46Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"f20ccf90c78c0dd20d11316e3416cfb8a174808eaaae7ffd6ada2da1dab9bf5f","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-06-05T17:59:02Z","title_canon_sha256":"2ccd320f7554ed9116db653a98a3c93d3e6fe8c286c74ab5306c5237910bd1c7"},"schema_version":"1.0","source":{"id":"2506.05331","kind":"arxiv","version":1}},"canonical_sha256":"1da8d2a4d5b09441ba846a2b7784bc867f0a8cf1a4ac566a6c65a04408f7037c","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1da8d2a4d5b09441ba846a2b7784bc867f0a8cf1a4ac566a6c65a04408f7037c","first_computed_at":"2026-07-05T11:16:46.167469Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:16:46.167469Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a3AHYGyJQ2Eju0jnZfkf6L7zWmn2oOvvdwBTIwk8a75GZNJRbQpomUoqmpozGkB87/Zyfelrq8ZwAM1U62ViBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:16:46.167965Z","signed_message":"canonical_sha256_bytes"},"source_id":"2506.05331","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c97f3b61356cb35800bee88c7ebfbfc0ed5e810557149931fbab8e4625d9ac4c","sha256:2c188f60dee3f05a1298eb00a84a98119e4d28db1c51cef213b637db3f55fe2c"],"state_sha256":"91d222cea3603b134b5244f07a6d1c67c41e02f258234b6b27bb572e1a691d66"}