{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BQPXED4B2HKB2EDY7U6KCGNQ2F","short_pith_number":"pith:BQPXED4B","schema_version":"1.0","canonical_sha256":"0c1f720f81d1d41d1078fd3ca119b0d1421d9c13440ecfd6ec3e25945e899ac0","source":{"kind":"arxiv","id":"2605.16371","version":1},"attestation_state":"computed","paper":{"title":"GeoSym127K: Scalable Symbolically-verifiable Synthesis for Multimodal Geometric Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Benyou Wang, Jingjing Bai, Jing Yang, Jinhao Jing, Jinwei Liang, Lewei Lu, Por Lip Yee, Prayag Tiwari, Qiannian Zhao, Shawn Chen, Zhan Su, Zheng Ma","submitted_at":"2026-05-10T13:13:47Z","abstract_excerpt":"Large Multimodal Models (LMMs) often struggle with geometric reasoning due to visual hallucinations and a lack of mathematically precise Chain-of-Thought (CoT) data. To address this, we propose the GeoSym Engine, an automated and scalable neuro-symbolic framework. By leveraging a type-conditional grammar and an analytic SymGT Solver, it derives exact symbolic ground truths and seamlessly integrates with a robust rendering pipeline to produce high-precision geometric diagrams. Using this engine, we construct GeoSym127K, a difficulty-stratified dataset featuring 51K high-resolution images, 127K "},"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":"2605.16371","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-05-10T13:13:47Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"a48cf4710a74db0c9f7e76b8b8c33034a704aa08edc6bef2711006b228e32b54","abstract_canon_sha256":"73c671266f05ece5ad0829b0310a46b2e2b1fb25fc06d8ffce4dd1461f0414a9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:02:18.873080Z","signature_b64":"Qa0KwK20OK1CnRw/v7Tf9xecM8aOGCYrDyxJzdKjtDTxmeb0kemuayZiG7fiQ0P+L+BKwNHZ6mt5augXQlE1BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c1f720f81d1d41d1078fd3ca119b0d1421d9c13440ecfd6ec3e25945e899ac0","last_reissued_at":"2026-05-20T00:02:18.872386Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:02:18.872386Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GeoSym127K: Scalable Symbolically-verifiable Synthesis for Multimodal Geometric Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Benyou Wang, Jingjing Bai, Jing Yang, Jinhao Jing, Jinwei Liang, Lewei Lu, Por Lip Yee, Prayag Tiwari, Qiannian Zhao, Shawn Chen, Zhan Su, Zheng Ma","submitted_at":"2026-05-10T13:13:47Z","abstract_excerpt":"Large Multimodal Models (LMMs) often struggle with geometric reasoning due to visual hallucinations and a lack of mathematically precise Chain-of-Thought (CoT) data. To address this, we propose the GeoSym Engine, an automated and scalable neuro-symbolic framework. By leveraging a type-conditional grammar and an analytic SymGT Solver, it derives exact symbolic ground truths and seamlessly integrates with a robust rendering pipeline to produce high-precision geometric diagrams. Using this engine, we construct GeoSym127K, a difficulty-stratified dataset featuring 51K high-resolution images, 127K "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.16371","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/2605.16371/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T19:34:36.619523Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"be29637a3b4e29cd27989e8b0200e8ce78abc97be6a83c8c065215abea9ddff5"},"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":"2605.16371","created_at":"2026-05-20T00:02:18.872492+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.16371v1","created_at":"2026-05-20T00:02:18.872492+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.16371","created_at":"2026-05-20T00:02:18.872492+00:00"},{"alias_kind":"pith_short_12","alias_value":"BQPXED4B2HKB","created_at":"2026-05-20T00:02:18.872492+00:00"},{"alias_kind":"pith_short_16","alias_value":"BQPXED4B2HKB2EDY","created_at":"2026-05-20T00:02:18.872492+00:00"},{"alias_kind":"pith_short_8","alias_value":"BQPXED4B","created_at":"2026-05-20T00:02:18.872492+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/BQPXED4B2HKB2EDY7U6KCGNQ2F","json":"https://pith.science/pith/BQPXED4B2HKB2EDY7U6KCGNQ2F.json","graph_json":"https://pith.science/api/pith-number/BQPXED4B2HKB2EDY7U6KCGNQ2F/graph.json","events_json":"https://pith.science/api/pith-number/BQPXED4B2HKB2EDY7U6KCGNQ2F/events.json","paper":"https://pith.science/paper/BQPXED4B"},"agent_actions":{"view_html":"https://pith.science/pith/BQPXED4B2HKB2EDY7U6KCGNQ2F","download_json":"https://pith.science/pith/BQPXED4B2HKB2EDY7U6KCGNQ2F.json","view_paper":"https://pith.science/paper/BQPXED4B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.16371&json=true","fetch_graph":"https://pith.science/api/pith-number/BQPXED4B2HKB2EDY7U6KCGNQ2F/graph.json","fetch_events":"https://pith.science/api/pith-number/BQPXED4B2HKB2EDY7U6KCGNQ2F/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BQPXED4B2HKB2EDY7U6KCGNQ2F/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BQPXED4B2HKB2EDY7U6KCGNQ2F/action/storage_attestation","attest_author":"https://pith.science/pith/BQPXED4B2HKB2EDY7U6KCGNQ2F/action/author_attestation","sign_citation":"https://pith.science/pith/BQPXED4B2HKB2EDY7U6KCGNQ2F/action/citation_signature","submit_replication":"https://pith.science/pith/BQPXED4B2HKB2EDY7U6KCGNQ2F/action/replication_record"}},"created_at":"2026-05-20T00:02:18.872492+00:00","updated_at":"2026-05-20T00:02:18.872492+00:00"}