Pith. sign in

REVIEW 6 cited by

FormalGeo: An Extensible Formalized Framework for Olympiad Geometric Problem Solving

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2310.18021 v6 pith:YRRB52D4 submitted 2023-10-27 cs.AI

FormalGeo: An Extensible Formalized Framework for Olympiad Geometric Problem Solving

classification cs.AI
keywords geometryformalproblemsimo-levelsystemfgpsplaneproblem
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

This is the first paper in a series of work we have accomplished over the past three years. In this paper, we have constructed a consistent formal plane geometry system. This will serve as a crucial bridge between IMO-level plane geometry challenges and readable AI automated reasoning. Within this formal framework, we have been able to seamlessly integrate modern AI models with our formal system. AI is now capable of providing deductive reasoning solutions to IMO-level plane geometry problems, just like handling other natural languages, and these proofs are readable, traceable, and verifiable. We propose the geometry formalization theory (GFT) to guide the development of the geometry formal system. Based on the GFT, we have established the FormalGeo, which consists of 88 geometric predicates and 196 theorems. It can represent, validate, and solve IMO-level geometry problems. we also have crafted the FGPS (formal geometry problem solver) in Python. It serves as both an interactive assistant for verifying problem-solving processes and an automated problem solver. We've annotated the formalgeo7k and formalgeo-imo datasets. The former contains 6,981 (expand to 133,818 through data augmentation) geometry problems, while the latter includes 18 (expand to 2,627 and continuously increasing) IMO-level challenging geometry problems. All annotated problems include detailed formal language descriptions and solutions. Implementation of the formal system and experiments validate the correctness and utility of the GFT. The backward depth-first search method only yields a 2.42% problem-solving failure rate, and we can incorporate deep learning techniques to achieve lower one. The source code of FGPS and datasets are available at https://github.com/BitSecret/FGPS.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 6 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Hilbert-Geo: Solving Solid Geometric Problems by Neural-Symbolic Reasoning

    cs.CV 2026-05 unverdicted novelty 8.0

    Hilbert-Geo creates the first unified formal language for solid geometry and a two-step parsing-then-reasoning method that reaches SOTA accuracy on solid geometry benchmarks.

  2. FormalAnalyticGeo: A Neural-Symbolic Based Framework for Multimodal Analytic Geometry Problem Generation

    cs.AI 2026-07 conditional novelty 7.0

    A neural-symbolic framework with a formal condition language and SDF rendering generates 7,043 multimodal analytic-geometry problems with visually measured ground truths at 0.70% median relative error.

  3. Hilbert-Geo: Solving Solid Geometric Problems by Neural-Symbolic Reasoning

    cs.CV 2026-05 unverdicted novelty 7.0

    Hilbert-Geo introduces a unified formal language framework with CDL predicates and theorem bank for solid geometry, using a Parse2Reason pipeline to achieve SOTA accuracy on new solid and plane geometry datasets.

  4. FormalAnalyticGeo: A Neural-Symbolic Based Framework for Multimodal Analytic Geometry Problem Generation

    cs.AI 2026-07 conditional novelty 6.0

    A four-LLM pipeline with CDL formalization and SDF rendering produces AnalyticGeo7K, over 7K verified multimodal analytic-geometry problems with 0.70% median relative error.

  5. Concise Geometric Description as a Bridge: Unleashing the Potential of LLM for Plane Geometry Problem Solving

    cs.AI 2026-01 unverdicted novelty 5.0

    An MLLM interpreter generates concise CDL descriptions from diagrams, enabling an off-the-shelf LLM to solve plane geometry problems competitively after training on only 5.5k examples.

  6. AI for Mathematics: Progress, Challenges, and Prospects

    math.HO 2026-01 unverdicted novelty 4.0

    AI for math combines task-specific architectures and general foundation models to support research and advance AI reasoning capabilities.