{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CREQPQGX2AJK5V4AE4VFPCXDLN","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":"9f3bf13b53a4c50b8670738bbe28c2a7158be2f52ea12cecb9ae23d7067ae8bb","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-07T14:47:32Z","title_canon_sha256":"a6582e40a423f8f223a60d01c99b27462e266a3836faa34e9aab57c9f3a2d23e"},"schema_version":"1.0","source":{"id":"2509.06079","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2509.06079","created_at":"2026-07-05T12:06:29Z"},{"alias_kind":"arxiv_version","alias_value":"2509.06079v1","created_at":"2026-07-05T12:06:29Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.06079","created_at":"2026-07-05T12:06:29Z"},{"alias_kind":"pith_short_12","alias_value":"CREQPQGX2AJK","created_at":"2026-07-05T12:06:29Z"},{"alias_kind":"pith_short_16","alias_value":"CREQPQGX2AJK5V4A","created_at":"2026-07-05T12:06:29Z"},{"alias_kind":"pith_short_8","alias_value":"CREQPQGX","created_at":"2026-07-05T12:06:29Z"}],"graph_snapshots":[{"event_id":"sha256:787ffb1f373f01e6290765ec0415280259e689c41661183e22a2bf783fb90914","target":"graph","created_at":"2026-07-05T12:06:29Z","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/2509.06079/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Multimodal reasoning remains a fundamental challenge in artificial intelligence. Despite substantial advances in text-based reasoning, even state-of-the-art models such as GPT-o3 struggle to maintain strong performance in multimodal scenarios. To address this gap, we introduce a caption-assisted reasoning framework that effectively bridges visual and textual modalities. Our approach achieved 1st place in the ICML 2025 AI for Math Workshop \\& Challenge 2: SeePhys, highlighting its effectiveness and robustness. Furthermore, we validate its generalization on the MathVerse benchmark for geometric ","authors_text":"Bin Dong, Bohan Zeng, Hao Liang, Junbo Niu, Ruitao Wu, Wentao Zhang","cross_cats":["cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-07T14:47:32Z","title":"Multimodal Reasoning for Science: Technical Report and 1st Place Solution to the ICML 2025 SeePhys Challenge"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.06079","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":"sha256:9a7906cd4d76752590ba36216f97dba45ebcdf2921a6a67764cd688e108f69b9","target":"record","created_at":"2026-07-05T12:06:29Z","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":"9f3bf13b53a4c50b8670738bbe28c2a7158be2f52ea12cecb9ae23d7067ae8bb","cross_cats_sorted":["cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-09-07T14:47:32Z","title_canon_sha256":"a6582e40a423f8f223a60d01c99b27462e266a3836faa34e9aab57c9f3a2d23e"},"schema_version":"1.0","source":{"id":"2509.06079","kind":"arxiv","version":1}},"canonical_sha256":"144907c0d7d012aed780272a578ae35b49a1486daea2da07c333ba642e6112b9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"144907c0d7d012aed780272a578ae35b49a1486daea2da07c333ba642e6112b9","first_computed_at":"2026-07-05T12:06:29.634744Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T12:06:29.634744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7AdhHbrx+t9wTQ4svCl4cEeAh2RFq4rdGPqEYRxOzyWHJ/0EMOz8XNCbh8q2BqdD44RtmUlth991cxgkUg+uAA==","signature_status":"signed_v1","signed_at":"2026-07-05T12:06:29.635300Z","signed_message":"canonical_sha256_bytes"},"source_id":"2509.06079","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9a7906cd4d76752590ba36216f97dba45ebcdf2921a6a67764cd688e108f69b9","sha256:787ffb1f373f01e6290765ec0415280259e689c41661183e22a2bf783fb90914"],"state_sha256":"c7e864792ba94d755e459dfda69cafb836898b457aecd45567150106a781bd70"}