{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QILZTKZRXNVCHE3TPDN7UTFZYQ","short_pith_number":"pith:QILZTKZR","schema_version":"1.0","canonical_sha256":"821799ab31bb6a23937378dbfa4cb9c41506a77aaee1d770aaa39b30e5c2b0bc","source":{"kind":"arxiv","id":"2406.11503","version":1},"attestation_state":"computed","paper":{"title":"GeoGPT4V: Towards Geometric Multi-modal Large Language Models with Geometric Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Bo Zheng, Hangyu Guo, Jizhi Zhang, Jun Song, Keqin Bao, Shihao Cai","submitted_at":"2024-06-17T13:04:27Z","abstract_excerpt":"Large language models have seen widespread adoption in math problem-solving. However, in geometry problems that usually require visual aids for better understanding, even the most advanced multi-modal models currently still face challenges in effectively using image information. High-quality data is crucial for enhancing the geometric capabilities of multi-modal models, yet existing open-source datasets and related efforts are either too challenging for direct model learning or suffer from misalignment between text and images. To overcome this issue, we introduce a novel pipeline that leverage"},"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":"2406.11503","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-17T13:04:27Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"7a580a218f6f3f8f75ac52851ba9a4b1a679d7b495e6c62948331dae5f668480","abstract_canon_sha256":"6e4de822d8cd6799385eb79419af069b1551c70b70a91bc521dbbd779f23dac4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:32:54.209041Z","signature_b64":"BGfQ0RGAVXuYmRXOKS8TEhLLZKD3RqWbG5zraQqUmh+WlemEpmqBx0huavHVlFK9uzjLdXXJTEb/zz55dermCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"821799ab31bb6a23937378dbfa4cb9c41506a77aaee1d770aaa39b30e5c2b0bc","last_reissued_at":"2026-07-05T08:32:54.208563Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:32:54.208563Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GeoGPT4V: Towards Geometric Multi-modal Large Language Models with Geometric Image Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.CV","authors_text":"Bo Zheng, Hangyu Guo, Jizhi Zhang, Jun Song, Keqin Bao, Shihao Cai","submitted_at":"2024-06-17T13:04:27Z","abstract_excerpt":"Large language models have seen widespread adoption in math problem-solving. However, in geometry problems that usually require visual aids for better understanding, even the most advanced multi-modal models currently still face challenges in effectively using image information. High-quality data is crucial for enhancing the geometric capabilities of multi-modal models, yet existing open-source datasets and related efforts are either too challenging for direct model learning or suffer from misalignment between text and images. To overcome this issue, we introduce a novel pipeline that leverage"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.11503","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/2406.11503/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":"2406.11503","created_at":"2026-07-05T08:32:54.208622+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.11503v1","created_at":"2026-07-05T08:32:54.208622+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.11503","created_at":"2026-07-05T08:32:54.208622+00:00"},{"alias_kind":"pith_short_12","alias_value":"QILZTKZRXNVC","created_at":"2026-07-05T08:32:54.208622+00:00"},{"alias_kind":"pith_short_16","alias_value":"QILZTKZRXNVCHE3T","created_at":"2026-07-05T08:32:54.208622+00:00"},{"alias_kind":"pith_short_8","alias_value":"QILZTKZR","created_at":"2026-07-05T08:32:54.208622+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2503.16549","citing_title":"MathFlow: Enhancing the Perceptual Flow of MLLMs for Visual Mathematical Problems","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16371","citing_title":"GeoSym127K: Scalable Symbolically-verifiable Synthesis for Multimodal Geometric Reasoning","ref_index":3,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QILZTKZRXNVCHE3TPDN7UTFZYQ","json":"https://pith.science/pith/QILZTKZRXNVCHE3TPDN7UTFZYQ.json","graph_json":"https://pith.science/api/pith-number/QILZTKZRXNVCHE3TPDN7UTFZYQ/graph.json","events_json":"https://pith.science/api/pith-number/QILZTKZRXNVCHE3TPDN7UTFZYQ/events.json","paper":"https://pith.science/paper/QILZTKZR"},"agent_actions":{"view_html":"https://pith.science/pith/QILZTKZRXNVCHE3TPDN7UTFZYQ","download_json":"https://pith.science/pith/QILZTKZRXNVCHE3TPDN7UTFZYQ.json","view_paper":"https://pith.science/paper/QILZTKZR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.11503&json=true","fetch_graph":"https://pith.science/api/pith-number/QILZTKZRXNVCHE3TPDN7UTFZYQ/graph.json","fetch_events":"https://pith.science/api/pith-number/QILZTKZRXNVCHE3TPDN7UTFZYQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QILZTKZRXNVCHE3TPDN7UTFZYQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QILZTKZRXNVCHE3TPDN7UTFZYQ/action/storage_attestation","attest_author":"https://pith.science/pith/QILZTKZRXNVCHE3TPDN7UTFZYQ/action/author_attestation","sign_citation":"https://pith.science/pith/QILZTKZRXNVCHE3TPDN7UTFZYQ/action/citation_signature","submit_replication":"https://pith.science/pith/QILZTKZRXNVCHE3TPDN7UTFZYQ/action/replication_record"}},"created_at":"2026-07-05T08:32:54.208622+00:00","updated_at":"2026-07-05T08:32:54.208622+00:00"}