SAT-based rigorous explanations for decision lists
From MaRDI portal
Publication:2118305
DOI10.1007/978-3-030-80223-3_18OpenAlexW3184339776MaRDI QIDQ2118305
Alexey Ignatiev, João P. Marques-Silva
Publication date: 22 March 2022
Full work available at URL: https://arxiv.org/abs/2105.06782
Analysis of algorithms and problem complexity (68Q25) Problem solving in the context of artificial intelligence (heuristics, search strategies, etc.) (68T20) Computational aspects of satisfiability (68R07)
Related Items (4)
On Tackling Explanation Redundancy in Decision Trees ⋮ Tractability of explaining classifier decisions ⋮ Explaining black-box classifiers: properties and functions ⋮ On computing probabilistic abductive explanations
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Learning Certifiably Optimal Rule Lists for Categorical Data
- Fast, flexible MUS enumeration
- Quantified maximum satisfiability
- A branch and bound algorithm for extracting smallest minimal unsatisfiable subformulas
- A theory of diagnosis from first principles
- PySAT: a Python toolkit for prototyping with SAT oracles
- Learning customized and optimized lists of rules with mathematical programming
- A SAT-based approach to learn explainable decision sets
- Assessing heuristic machine learning explanations with model counting
- Explanation in artificial intelligence: insights from the social sciences
- Algorithms for computing minimal unsatisfiable subsets of constraints
- MCS Extraction with Sublinear Oracle Queries
- On Improving MUS Extraction Algorithms
- Towards efficient MUS extraction
- Consistent subsets of inconsistent systems: structure and behaviour
- Enumerating Infeasibility: Finding Multiple MUSes Quickly
- RC2: an Efficient MaxSAT Solver
- Improving Glucose for Incremental SAT Solving with Assumptions: Application to MUS Extraction
- Theory and Applications of Satisfiability Testing
This page was built for publication: SAT-based rigorous explanations for decision lists
