{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RPHYWWJOKIZPSBNGZOLH4YIWNZ","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":"a9cb400b24d709337b03a923f6900cdd3ebbb8564e096a321938f82758175fbb","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-15T17:59:21Z","title_canon_sha256":"30fe0471da12a6865af66b9928c27ea523b605cc0bfb36f47c91d750d086f3d9"},"schema_version":"1.0","source":{"id":"2505.10557","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.10557","created_at":"2026-07-05T11:03:45Z"},{"alias_kind":"arxiv_version","alias_value":"2505.10557v1","created_at":"2026-07-05T11:03:45Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.10557","created_at":"2026-07-05T11:03:45Z"},{"alias_kind":"pith_short_12","alias_value":"RPHYWWJOKIZP","created_at":"2026-07-05T11:03:45Z"},{"alias_kind":"pith_short_16","alias_value":"RPHYWWJOKIZPSBNG","created_at":"2026-07-05T11:03:45Z"},{"alias_kind":"pith_short_8","alias_value":"RPHYWWJO","created_at":"2026-07-05T11:03:45Z"}],"graph_snapshots":[{"event_id":"sha256:7d133065f3a18d1bb0d54dc4230ccaf7f6ab44b3e305be56a10c66447d0a7f6d","target":"graph","created_at":"2026-07-05T11:03:45Z","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/2505.10557/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Natural language image-caption datasets, widely used for training Large Multimodal Models, mainly focus on natural scenarios and overlook the intricate details of mathematical figures that are critical for problem-solving, hindering the advancement of current LMMs in multimodal mathematical reasoning. To this end, we propose leveraging code as supervision for cross-modal alignment, since code inherently encodes all information needed to generate corresponding figures, establishing a precise connection between the two modalities. Specifically, we co-develop our image-to-code model and dataset w","authors_text":"Aojun Zhou, Han Xiao, Hongsheng Li, Houxing Ren, Junting Pan, Ke Wang, Linda Wei, Mingjie Zhan, Weikang Shi, Yunqiao Yang, Zimu Lu","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-15T17:59:21Z","title":"MathCoder-VL: Bridging Vision and Code for Enhanced Multimodal Mathematical Reasoning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.10557","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":"sha256:3e0efb9b87bc0975e7931ac37b8985bd9cf803fdd2934a42906f4c83e250315b","target":"record","created_at":"2026-07-05T11:03:45Z","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":"a9cb400b24d709337b03a923f6900cdd3ebbb8564e096a321938f82758175fbb","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-15T17:59:21Z","title_canon_sha256":"30fe0471da12a6865af66b9928c27ea523b605cc0bfb36f47c91d750d086f3d9"},"schema_version":"1.0","source":{"id":"2505.10557","kind":"arxiv","version":1}},"canonical_sha256":"8bcf8b592e5232f905a6cb967e61166e60a312cb2a4934b334e7811a153b5a96","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8bcf8b592e5232f905a6cb967e61166e60a312cb2a4934b334e7811a153b5a96","first_computed_at":"2026-07-05T11:03:45.612171Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:03:45.612171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aqqPTImz1vKa+YqheluqyLYW9btcd5u7/nu3KQqaUuyrXn+x42133rdmmJQk+xvACHHH9Q/fJ3eNwSPiGe8RCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:03:45.612671Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.10557","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3e0efb9b87bc0975e7931ac37b8985bd9cf803fdd2934a42906f4c83e250315b","sha256:7d133065f3a18d1bb0d54dc4230ccaf7f6ab44b3e305be56a10c66447d0a7f6d"],"state_sha256":"8f255b35433dba444c24e67f74f23ed7c9fc8c26d8c47911f8959f76d4936db5"}