Research map / Learning theory and algorithms / Prediction and decision losses
MLFMF: Data Sets for Machine Learning for Mathematical Formalization
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use node2vec graph embeddings with a tree-bagging classifier instead of recommending by in-degree | Link prediction on MLFMF libraries · Agda stdlib | accuracy: 0.51 -> 0.96 | Helped |
| Use node2vec graph embeddings with a tree-bagging classifier instead of recommending by in-degree | Link prediction on MLFMF libraries · Agda unimath | accuracy: 0.53 -> 0.96 | Helped |
| Use node2vec graph embeddings with a tree-bagging classifier instead of recommending by in-degree | Link prediction on MLFMF libraries · Agda TypeTopology | accuracy: 0.50 -> 0.98 | Helped |
| Use node2vec graph embeddings with a tree-bagging classifier instead of recommending by in-degree | Link prediction on MLFMF libraries · Lean Mathlib4 | accuracy: 0.51 -> 0.95 | Helped |
| Use node2vec graph embeddings with a tree-bagging classifier instead of recommending by in-degree | Recommendation on MLFMF libraries · Agda stdlib | minRank: 218 -> 4.37 | Helped |
| Use node2vec graph embeddings with a tree-bagging classifier instead of recommending by in-degree | Recommendation on MLFMF libraries · Agda unimath | minRank: 2134 -> 3.24 | Helped |
| Use node2vec graph embeddings with a tree-bagging classifier instead of recommending by in-degree | Recommendation on MLFMF libraries · Agda TypeTopology | minRank: 4556 -> 5.81 | Helped |
| Use node2vec graph embeddings with a tree-bagging classifier instead of recommending by in-degree | Recommendation on MLFMF libraries · Lean Mathlib4 | minRank: 26065 -> 195 | Helped |
| Combine node2vec embeddings with TFIDF or fastText embeddings | node2vec link prediction and recommendation · MLFMF libraries | accuracy | Hurt |
| Combine node2vec embeddings with TFIDF or fastText embeddings | node2vec link prediction and recommendation · MLFMF libraries | minRank | Hurt |
| Use TFIDF representations rather than fastText embeddings | Content-based recommendation · Agda libraries | minRank | Mixed |
Closest papers by meaning
- Machine Learning meets Algebraic Combinatorics: A Suite of Datasets Capturing Research-level Conjecturing Ability in Pure Mathematics (ICML 2025 · similarity 0.89)
- REFACTOR: Learning to Extract Theorems from Proofs (ICLR 2024 · similarity 0.88)
- FaithSieve: Fine-Grained Evaluation of Math Proofs with Faithful Formal Evidence (NeurIPS 2026 · similarity 0.88)
- APOLLO: Automated LLM and Lean Collaboration for Advanced Formal Reasoning (NeurIPS 2025 · similarity 0.88)
- miniF2F-Lean Revisited: Reviewing Limitations and Charting a Path Forward (NeurIPS 2025 · similarity 0.87)
- Learning Structure-Aware Representations of Dependent Types (NeurIPS 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.