{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3FBY6TL6SRF5PZWI73D35QV2HT","short_pith_number":"pith:3FBY6TL6","schema_version":"1.0","canonical_sha256":"d9438f4d7e944bd7e6c8fec7bec2ba3cc00c6fa6d24db93468c5de9fd5c4876d","source":{"kind":"arxiv","id":"2605.25384","version":1},"attestation_state":"computed","paper":{"title":"GeoMathCode: Understanding Interleaved Math-Code Reasoning for Geometry Problem Solving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andr\\'e Freitas, Yingji Zhang, Yong Dai","submitted_at":"2026-05-25T03:21:12Z","abstract_excerpt":"Mathematical reasoning is a hallmark of human intelligence, requiring logical deduction, symbolic manipulation, and abstract thinking. Recent multimodal large language models (MLLMs) have demonstrated strong performance on geometry problems through multi-step reasoning. To better emulate human problem-solving, intermediate steps can incorporate auxiliary visual constructions, such as additional lines or points, which improve geometric interpretation and educational clarity. In this work, we introduce the GeoMathCode, where programmatic representations serve as intermediate visual outputs. We f"},"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":"2605.25384","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-05-25T03:21:12Z","cross_cats_sorted":[],"title_canon_sha256":"525fcfd579c9a8a99c2bceeacddd641db409cf90969b02d9a6f5c23b96c931bc","abstract_canon_sha256":"5a399b612ee96157b5c51e088f820739621e1866809224d3645b03431f72ab47"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:04:31.946239Z","signature_b64":"fTze79lbmEQSz1St9S/MACgx1IOxoG1VV3OtmPvvz2rLZp1o7U+62YQLNZmmN1mIFPZFLmS9Hlb2n7ZIMUvaBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d9438f4d7e944bd7e6c8fec7bec2ba3cc00c6fa6d24db93468c5de9fd5c4876d","last_reissued_at":"2026-05-26T02:04:31.945258Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:04:31.945258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GeoMathCode: Understanding Interleaved Math-Code Reasoning for Geometry Problem Solving","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andr\\'e Freitas, Yingji Zhang, Yong Dai","submitted_at":"2026-05-25T03:21:12Z","abstract_excerpt":"Mathematical reasoning is a hallmark of human intelligence, requiring logical deduction, symbolic manipulation, and abstract thinking. Recent multimodal large language models (MLLMs) have demonstrated strong performance on geometry problems through multi-step reasoning. To better emulate human problem-solving, intermediate steps can incorporate auxiliary visual constructions, such as additional lines or points, which improve geometric interpretation and educational clarity. In this work, we introduce the GeoMathCode, where programmatic representations serve as intermediate visual outputs. We f"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.25384","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/2605.25384/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":"2605.25384","created_at":"2026-05-26T02:04:31.945442+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.25384v1","created_at":"2026-05-26T02:04:31.945442+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.25384","created_at":"2026-05-26T02:04:31.945442+00:00"},{"alias_kind":"pith_short_12","alias_value":"3FBY6TL6SRF5","created_at":"2026-05-26T02:04:31.945442+00:00"},{"alias_kind":"pith_short_16","alias_value":"3FBY6TL6SRF5PZWI","created_at":"2026-05-26T02:04:31.945442+00:00"},{"alias_kind":"pith_short_8","alias_value":"3FBY6TL6","created_at":"2026-05-26T02:04:31.945442+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3FBY6TL6SRF5PZWI73D35QV2HT","json":"https://pith.science/pith/3FBY6TL6SRF5PZWI73D35QV2HT.json","graph_json":"https://pith.science/api/pith-number/3FBY6TL6SRF5PZWI73D35QV2HT/graph.json","events_json":"https://pith.science/api/pith-number/3FBY6TL6SRF5PZWI73D35QV2HT/events.json","paper":"https://pith.science/paper/3FBY6TL6"},"agent_actions":{"view_html":"https://pith.science/pith/3FBY6TL6SRF5PZWI73D35QV2HT","download_json":"https://pith.science/pith/3FBY6TL6SRF5PZWI73D35QV2HT.json","view_paper":"https://pith.science/paper/3FBY6TL6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.25384&json=true","fetch_graph":"https://pith.science/api/pith-number/3FBY6TL6SRF5PZWI73D35QV2HT/graph.json","fetch_events":"https://pith.science/api/pith-number/3FBY6TL6SRF5PZWI73D35QV2HT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3FBY6TL6SRF5PZWI73D35QV2HT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3FBY6TL6SRF5PZWI73D35QV2HT/action/storage_attestation","attest_author":"https://pith.science/pith/3FBY6TL6SRF5PZWI73D35QV2HT/action/author_attestation","sign_citation":"https://pith.science/pith/3FBY6TL6SRF5PZWI73D35QV2HT/action/citation_signature","submit_replication":"https://pith.science/pith/3FBY6TL6SRF5PZWI73D35QV2HT/action/replication_record"}},"created_at":"2026-05-26T02:04:31.945442+00:00","updated_at":"2026-05-26T02:04:31.945442+00:00"}