{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:TGT37NDHNV4GADII5GPDHZVS3W","short_pith_number":"pith:TGT37NDH","schema_version":"1.0","canonical_sha256":"99a7bfb4676d78600d08e99e33e6b2ddb3193ab1d11987583029ebf833ca261d","source":{"kind":"arxiv","id":"2105.04165","version":3},"attestation_state":"computed","paper":{"title":"Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.FL"],"primary_cat":"cs.CL","authors_text":"Liang Qiu, Pan Lu, Ran Gong, Shibiao Jiang, Siyuan Huang, Song-Chun Zhu, Xiaodan Liang","submitted_at":"2021-05-10T07:46:55Z","abstract_excerpt":"Geometry problem solving has attracted much attention in the NLP community recently. The task is challenging as it requires abstract problem understanding and symbolic reasoning with axiomatic knowledge. However, current datasets are either small in scale or not publicly available. Thus, we construct a new large-scale benchmark, Geometry3K, consisting of 3,002 geometry problems with dense annotation in formal language. We further propose a novel geometry solving approach with formal language and symbolic reasoning, called Interpretable Geometry Problem Solver (Inter-GPS). Inter-GPS first parse"},"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":"2105.04165","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-05-10T07:46:55Z","cross_cats_sorted":["cs.AI","cs.CV","cs.FL"],"title_canon_sha256":"d50611091f500b7d08f97cd7646a0e4454b4fd3a07c3cd05a552f09cc0b740ee","abstract_canon_sha256":"0e80ff4b409fd3142c015ff36aaff759489690ca52588c497fa5d1f86ea1ba2c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:59:37.426156Z","signature_b64":"xcTZ9DrlwU9rbhIJPpdATbOBKJn6VM9kUZXFIONqvlR7g/KBEymTGZudfB6sumBGqIBwduTWMa5L1sxi83tPAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"99a7bfb4676d78600d08e99e33e6b2ddb3193ab1d11987583029ebf833ca261d","last_reissued_at":"2026-07-05T02:59:37.425657Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:59:37.425657Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Inter-GPS: Interpretable Geometry Problem Solving with Formal Language and Symbolic Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","cs.FL"],"primary_cat":"cs.CL","authors_text":"Liang Qiu, Pan Lu, Ran Gong, Shibiao Jiang, Siyuan Huang, Song-Chun Zhu, Xiaodan Liang","submitted_at":"2021-05-10T07:46:55Z","abstract_excerpt":"Geometry problem solving has attracted much attention in the NLP community recently. The task is challenging as it requires abstract problem understanding and symbolic reasoning with axiomatic knowledge. However, current datasets are either small in scale or not publicly available. Thus, we construct a new large-scale benchmark, Geometry3K, consisting of 3,002 geometry problems with dense annotation in formal language. We further propose a novel geometry solving approach with formal language and symbolic reasoning, called Interpretable Geometry Problem Solver (Inter-GPS). Inter-GPS first parse"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.04165","kind":"arxiv","version":3},"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/2105.04165/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":"2105.04165","created_at":"2026-07-05T02:59:37.425717+00:00"},{"alias_kind":"arxiv_version","alias_value":"2105.04165v3","created_at":"2026-07-05T02:59:37.425717+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.04165","created_at":"2026-07-05T02:59:37.425717+00:00"},{"alias_kind":"pith_short_12","alias_value":"TGT37NDHNV4G","created_at":"2026-07-05T02:59:37.425717+00:00"},{"alias_kind":"pith_short_16","alias_value":"TGT37NDHNV4GADII","created_at":"2026-07-05T02:59:37.425717+00:00"},{"alias_kind":"pith_short_8","alias_value":"TGT37NDH","created_at":"2026-07-05T02:59:37.425717+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":23,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.17678","citing_title":"See First, Answer Later: Visual Evidence Pre-Alignment via Sufficiency-Driven RL","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08728","citing_title":"Artificial Intelligence for Mathematical Reasoning: An Integrated Survey of Language Models, Neuro-symbolic Systems, and Verified Discovery","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2502.02871","citing_title":"Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning","ref_index":115,"is_internal_anchor":false},{"citing_arxiv_id":"2504.16155","citing_title":"PRIMETIME : Limits of LLMs in Temporal Primitives","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2602.18600","citing_title":"MapTab: A Diagnostic Benchmark for Long-Horizon Multi-Criteria Multimodal Reasoning on Heterogeneous Topological Graphs","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2505.19075","citing_title":"Universal Reasoner: A Single, Composable Plug-and-Play Reasoner for Frozen LLMs","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2605.16371","citing_title":"GeoSym127K: Scalable Symbolically-verifiable Synthesis for Multimodal Geometric Reasoning","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2508.06226","citing_title":"GeoLaux: A Benchmark for Evaluating MLLMs' Geometry Performance on Long-Step Problems Requiring Auxiliary Lines","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2510.10606","citing_title":"ViSurf: Visual Supervised-and-Reinforcement Fine-Tuning for Large Vision-and-Language Models","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2511.19972","citing_title":"Boosting Reasoning in Large Multimodal Models via Activation Replay","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2511.20814","citing_title":"SPHINX: A Synthetic Environment for Visual Perception and Reasoning","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2403.14624","citing_title":"MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2407.01284","citing_title":"We-Math: Does Your Large Multimodal Model Achieve Human-like Mathematical Reasoning?","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2411.10442","citing_title":"Enhancing the Reasoning Ability of Multimodal Large Language Models via Mixed Preference Optimization","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2602.11731","citing_title":"Thinking with Drafting: Optical Decompression via Logical Reconstruction","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2602.18600","citing_title":"MapTab: A Diagnostic Benchmark for Long-Horizon Multi-Criteria Multimodal Reasoning on Heterogeneous Topological Graphs","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03179","citing_title":"Understanding the Role of Hallucination in Reinforcement Post-Training of Multimodal Reasoning Models","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2404.16821","citing_title":"How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites","ref_index":72,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01327","citing_title":"Segment-Aligned Policy Optimization for Multi-Modal Reasoning","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20806","citing_title":"OMIBench: Benchmarking Olympiad-Level Multi-Image Reasoning in Large Vision-Language Model","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2604.10219","citing_title":"Cognitive Pivot Points and Visual Anchoring: Unveiling and Rectifying Hallucinations in Multimodal Reasoning Models","ref_index":99,"is_internal_anchor":false},{"citing_arxiv_id":"2504.10479","citing_title":"InternVL3: Exploring Advanced Training and Test-Time Recipes for Open-Source Multimodal Models","ref_index":81,"is_internal_anchor":false},{"citing_arxiv_id":"2412.05271","citing_title":"Expanding Performance Boundaries of Open-Source Multimodal Models with Model, Data, and Test-Time Scaling","ref_index":164,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TGT37NDHNV4GADII5GPDHZVS3W","json":"https://pith.science/pith/TGT37NDHNV4GADII5GPDHZVS3W.json","graph_json":"https://pith.science/api/pith-number/TGT37NDHNV4GADII5GPDHZVS3W/graph.json","events_json":"https://pith.science/api/pith-number/TGT37NDHNV4GADII5GPDHZVS3W/events.json","paper":"https://pith.science/paper/TGT37NDH"},"agent_actions":{"view_html":"https://pith.science/pith/TGT37NDHNV4GADII5GPDHZVS3W","download_json":"https://pith.science/pith/TGT37NDHNV4GADII5GPDHZVS3W.json","view_paper":"https://pith.science/paper/TGT37NDH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2105.04165&json=true","fetch_graph":"https://pith.science/api/pith-number/TGT37NDHNV4GADII5GPDHZVS3W/graph.json","fetch_events":"https://pith.science/api/pith-number/TGT37NDHNV4GADII5GPDHZVS3W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TGT37NDHNV4GADII5GPDHZVS3W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TGT37NDHNV4GADII5GPDHZVS3W/action/storage_attestation","attest_author":"https://pith.science/pith/TGT37NDHNV4GADII5GPDHZVS3W/action/author_attestation","sign_citation":"https://pith.science/pith/TGT37NDHNV4GADII5GPDHZVS3W/action/citation_signature","submit_replication":"https://pith.science/pith/TGT37NDHNV4GADII5GPDHZVS3W/action/replication_record"}},"created_at":"2026-07-05T02:59:37.425717+00:00","updated_at":"2026-07-05T02:59:37.425717+00:00"}