Fetching the paper…
Reading the bibliography…
The most widely studied explainable AI (XAI) approaches are unsound.
The magical number seven, plus or minus two: Some limits on our capacity for processing information
G. A. Miller · 1956
Earlier work this paper cites.
The complexity of theorem-proving procedures
S. A. Cook · 1971
Earlier work this paper cites.
Pattern classification
R. O. Duda, P. E. Hart, and D. G. Stork · 1973
Earlier work this paper cites.
Classification and Regression Trees
L. Breiman, J. H. Friedman, R. A. Olshen, and C. J. Stone · 1984
Earlier work this paper cites.
A theory of the learnable
L. G. Valiant · 1984
Earlier work this paper cites.
Graph-based algorithms for boolean function manipulation
R. E. Bryant · 1986
Earlier work this paper cites.
Induction of decision trees
J. R. Quinlan · 1986
Earlier work this paper cites.
Multi-valued decision diagrams
T. Kam and R. K. Brayton · 1990
Earlier work this paper cites.
Algorithms for discrete function manipulation
A. Srinivasan, T. Ham, S. Malik, and R. K. Brayton · 1990
Earlier work this paper cites.
Decision graphs – an extension of decision trees
J. J. Oliver · 1992
Earlier work this paper cites.
Inferring decision graphs using the minimum message length principle
J. J. Oliver, D. L. Dowe, and C. S. Wallace · 1992
Earlier work this paper cites.
Bayesian network classifiers
N. Friedman, D. Geiger, and M. Goldszmidt · 1997
Earlier work this paper cites.
Decision tree induction based on efficient tree restructuring
P. E. Utgoff, N. C. Berkman, and J. A. Clouse · 1997
Earlier work this paper cites.
Decomposable negation normal form
A. Darwiche · 2001
Earlier work this paper cites.
On the tractable counting of theory models and its application to truth maintenance and belief revision
A. Darwiche · 2001
Earlier work this paper cites.
A knowledge compilation map
A. Darwiche and P. Marquis · 2002
Earlier work this paper cites.
Using weighted MAX-SAT engines to solve MPE
J. D. Park · 2002
Earlier work this paper cites.
Approximate counting by dynamic programming
M. E. Dyer · 2003
Earlier work this paper cites.
QUICKXPLAIN: preferred explanations and relaxations for over-constrained problems
U. Junker · 2004
Earlier work this paper cites.
Knapsack problems
H. Kellerer, U. Pferschy, and D. Pisinger · 2004
Earlier work this paper cites.
Z3: an efficient SMT solver
L. M. de Moura and N. S. Bjørner · 2008
Earlier work this paper cites.
Computational Complexity - A Modern Approach
S. Arora and B. Barak · 2009
Earlier work this paper cites.
Satisfiability modulo theories
C. W. Barrett, R. Sebastiani, S. A. Seshia, and C. Tinelli · 2009
Earlier work this paper cites.
SDD: A new canonical representation of propositional knowledge bases
A. Darwiche · 2011
Earlier work this paper cites.
An FPTAS for #knapsack and related counting problems
P. Gopalan, A. R. Klivans, R. Meka, D. Stefankovic, S. S. Vempala, and E. Vigoda · 2011
Earlier work this paper cites.
Bayesian reasoning and machine learning
D. Barber · 2012
Earlier work this paper cites.
Dsharp: Fast d-DNNF compilation with sharpSAT
C. J. Muise, S. A. McIlraith, J. C. Beck, and E. I. Hsu · 2012
Earlier work this paper cites.
Representing csps with set-labeled diagrams: A compilation map
A. Niveau, H. Fargier, and C. Pralet · 2012
Earlier work this paper cites.
Knowledge compilation for model counting: Affine decision trees
F. Koriche, J. Lagniez, P. Marquis, and S. Thomas · 2013
Earlier work this paper cites.
Minimal sets over monotone predicates in boolean formulae
J. Marques-Silva, M. Janota, and A. Belov · 2013
Earlier work this paper cites.
On computing preferred MUSes and MCSes
J. Marques-Silva and A. Previti · 2014
Earlier work this paper cites.
Deep inside convolutional networks: Visualising image classification models and saliency maps
K. Simonyan, A. Vedaldi, and A. Zisserman · 2014
Earlier work this paper cites.
On pixel-wise explanations for non-linear classifier decisions by layer-wise relevance propagation
S. Bach, A. Binder, G. Montavon, F. Klauschen, K.-R. Müller, and W. Samek · 2015
Earlier work this paper cites.
On the role of canonicity in knowledge compilation
G. Van den Broeck and A. Darwiche · 2015
Cited alongside, same era.
Learning abductive reasoning using random examples
B. Juba · 2016
Cited alongside, same era.
Fast, flexible MUS enumeration
M. H. Liffiton, A. Previti, A. Malik, and J. Marques-Silva · 2016
Cited alongside, same era.
“Why should I trust you?”: Explaining the predictions of any classifier
M. T. Ribeiro, S. Singh, and C. Guestrin · 2016
Cited alongside, same era.
Optimal classification trees
D. Bertsimas and J. Dunn · 2017
Cited alongside, same era.
A unified approach to interpreting model predictions
S. M. Lundberg and S. Lee · 2017
Cited alongside, same era.
Explaining naive bayes and other linear classifiers with polynomial time and delay
J. Marques-Silva, T. Gerspacher, M. C. Cooper, A. Ignatiev, and N. Narodytska · 2020
Later among the works it cites.
Interpretable Machine Learning
C. Molnar · 2020
Later among the works it cites.
When explanations lie: Why many modified BP attributions fail
L. Sixt, M. Granz, and T. Landgraf · 2020
Later among the works it cites.
Fooling LIME and SHAP: adversarial attacks on post hoc explanation methods
D. Slack, S. Hilgard, E. Jia, S. Singh, and H. Lakkaraju · 2020
Later among the works it cites.
Non-monotonic explanation functions
L. Amgoud · 2021
Later among the works it cites.
On the computational intelligibility of boolean classifiers
G. Audemard, S. Bellart, L. Bounia, F. Koriche, J. Lagniez, and P. Marquis · 2021
Later among the works it cites.
alphaXiv searches the wider corpus for related work and actual follow-ups.
alphaXiv is searching for related work…
J. Marques-Silva, M. Janota, and C. Mencía · 2017
Cited alongside, same era.
Sanity checks for saliency maps
J. Adebayo, J. Gilmer, M. Muelly, I. J. Goodfellow, M. Hardt, and B. Kim · 2018
Cited alongside, same era.
A faster FPTAS for #knapsack
P. Gawrychowski, L. Markin, and O. Weimann · 2018
Cited alongside, same era.
Methods for interpreting and understanding deep neural networks
G. Montavon, W. Samek, and K. Müller · 2018
Cited alongside, same era.
Anchors: High-precision model-agnostic explanations
M. T. Ribeiro, S. Singh, and C. Guestrin · 2018
Cited alongside, same era.
A symbolic approach to explaining bayesian network classifiers
A. Shih, A. Choi, and A. Darwiche · 2018
Cited alongside, same era.
Handbook of Satisfiability
A. Biere, M. Heule, H. van Maaren, and T. Walsh, editors · 2021
Later among the works it cites.
ASTERYX: A model-agnostic sat-based approach for symbolic and score-based explanations
R. Boumazouza, F. C. Alili, B. Mazure, and K. Tabia · 2021
Later among the works it cites.
On the tractability of explaining decisions of classifiers
M. C. Cooper and J. Marques-Silva · 2021
Later among the works it cites.
Artificial Intelligence Act
EU · 2021
Later among the works it cites.
On efficiently explaining graph-based classifiers
X. Huang, Y. Izza, A. Ignatiev, and J. Marques-Silva · 2021
Later among the works it cites.
On efficiently explaining graph-based classifiers
X. Huang, Y. Izza, A. Ignatiev, and J. Marques-Silva · 2021
Later among the works it cites.
SAT-based rigorous explanations for decision lists
A. Ignatiev and J. Marques-Silva · 2021
Later among the works it cites.
Efficient explanations with relevant sets
Y. Izza, A. Ignatiev, N. Narodytska, M. C. Cooper, and J. Marques-Silva · 2021
Later among the works it cites.
On explaining random forests with SAT
Y. Izza and J. Marques-Silva · 2021
Later among the works it cites.
A logic for binary classifiers and their explanation
X. Liu and E. Lorini · 2021
Later among the works it cites.
On guaranteed optimal robust explanations for NLP models
E. L. Malfa, R. Michelmore, A. M. Zbrzezny, N. Paoletti, and M. Kwiatkowska · 2021
Later among the works it cites.
Explanations for monotonic classifiers
J. Marques-Silva, T. Gerspacher, M. C. Cooper, A. Ignatiev, and N. Narodytska · 2021
Later among the works it cites.
Explaining deep neural networks and beyond: A review of methods and applications
W. Samek, G. Montavon, S. Lapuschkin, C. J. Anders, and K. Müller · 2021
Later among the works it cites.
The computational complexity of understanding binary classifier decisions
S. Wäldchen, J. MacDonald, S. Hauch, and G. Kutyniok · 2021
Later among the works it cites.
Probabilistic Sufficient Explanations
E. Wang, P. Khosravi, and G. V. den Broeck · 2021
Later among the works it cites.
On computing probabilistic explanations for decision trees
M. Arenas, P. Barceló, M. Romero, and B. Subercaseaux · 2022
Closest in time.
On computing probabilistic explanations for decision trees
M. Arenas, P. Barceló, M. Romero, and B. Subercaseaux · 2022
Closest in time.
Sufficient reasons for classifier decisions in the presence of domain constraints
N. Gorji and S. Rubin · 2022
Closest in time.
Tractable explanations for d-DNNF classifiers
X. Huang, Y. Izza, A. Ignatiev, M. C. Cooper, N. Asher, and J. Marques-Silva · 2022
Closest in time.
On deciding feature membership in explanations of SDD & related classifiers
X. Huang and J. Marques-Silva · 2022
Closest in time.
Using MaxSAT for efficient explanations of tree ensembles
A. Ignatiev, Y. Izza, P. Stuckey, and J. Marques-Silva · 2022
Closest in time.
On tackling explanation redundancy in decision trees
Y. Izza, A. Ignatiev, and J. Marques-Silva · 2022
Closest in time.
Provably precise, succinct and efficient explanations for decision trees
Y. Izza, A. Ignatiev, N. Narodytska, M. C. Cooper, and J. Marques-Silva · 2022
Closest in time.
On computing relevant features for explaining NBCs
Y. Izza and J. Marques-Silva · 2022
Closest in time.
Delivering trustworthy AI through formal XAI
J. Marques-Silva and A. Ignatiev · 2022
Closest in time.
Towards Explainable Artificial Intelligence – Interpreting Neural Network Classifiers with Probabilistic Prime Implicants
S. Wäldchen · 2022
Closest in time.
Eliminating the impossible, whatever remains must be true
J. Yu, A. Ignatiev, P. J. Stuckey, N. Narodytska, and J. Marques-Silva · 2022
Closest in time.