LP Mining with LP2Graph: A Use Case for Railway Rescheduling
Quick Answer
This paper shows that LP Mining with LP2Graph introduces a method for extracting and structuring railway rescheduling models from existing LP and MILP formulations, creating a reproducible dataset and taxonomy.
Quick Take
LP Mining with LP2Graph introduces a method for extracting and structuring railway rescheduling models from existing LP and MILP formulations, creating a reproducible dataset and taxonomy. This approach enables automated development of railway-rescheduling models, validated through independent resolution against benchmarks from CBC, HiGHS, and Gurobi.
Key Points
- LP2Graph creates a structured representation of LP and MILP formulations.
- Models are validated by re-solving with CBC, HiGHS, and Gurobi.
- The taxonomy aids in automated railway-rescheduling model development.
- Clusters are labeled using a self-updating classifier for accuracy.
- The method addresses the fragmentation of modeling knowledge in railway rescheduling.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Like many optimization-driven domains, railway rescheduling relies on Mixed-Integer Linear Programming (MILP), yet the field's modeling knowledge is scattered across hundreds of papers in incompatible notations, and narrative surveys organize it subjectively: they classify models by vocabulary rather than by structure, and reproduce neither. We present LP Mining with LP2Graph, a method that mines the structure of published LP and MILP formulations into a reproducible dataset and an induced taxonomy. Its core, LP2Graph, represents each formulation admitted by its canonical grammar as a typed variable--equation graph derived from a single canonical model; once a source is extracted into that model, everything downstream is deterministic. Each source is parsed into this model, homologized, and clustered bottom-up (over variables, then constraints and the objective, then whole-model structure) and, separately, by application domain and solution approach; the resulting groups are labeled by a rule-seeded, self-updating classifier. We validate the representation rather than assume it: per-cluster representatives are regenerated as independent LaTeX and re-solved across CBC, HiGHS and Gurobi against the optimum reported in the source paper. The outcome is an objective, repeatable taxonomy of variables, constraints and model types: the principled foundation on which our raiLPminer line of automated railway-rescheduling model development builds.
| Comments: | 22 pages, 2 figures. Work in progress, not yet submitted to a journal; comments welcome. Companion preprint to a talk at IFORS 2026, Vienna |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2607.11980 [cs.AI] |
| (or arXiv:2607.11980v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2607.11980 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Jörn Maurischat [view email]
[v1]
Mon, 13 Jul 2026 07:25:02 UTC (56 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →The Emerging Paradigm of Geospatial Foundation Models: From Pre-Training to Agentic Reasoning
The paper introduces Geospatial Foundation Models (GeoFMs), AI/ML models pre-trained on extensive geospatial datasets, enabling domain experts to fine-tune them for specific tasks. This paradigm shift democratizes access to advanced AI/ML while ensuring security, and proposes a framework for cost-effective adaptation strategies. The vision of Agentic Geospatial Reasoning is also presented, where Large Language Models orchestrate GeoFMs to automate complex analytical workflows.