On the Existence of Simpler Machine Learning Models
Open accessThe DOI matches its Crossref record; 53 of the 55 references it cites were found in a registry or an index.
Abstract
It is almost always easier to find an accurate-but-complex model than an accurate-yet-simple model. Finding optimal, sparse, accurate models of various forms (linear models with integer coefficients, decision sets, rule lists, decision trees) is generally NP-hard. We often do not know whether the search for a simpler model will be worthwhile, and thus we do not go to the trouble of searching for one. In this work, we ask an important practical question: can accurate-yet-simple models be proven to exist, or shown likely to exist, before explicitly searching for them? We hypothesize that there is an important reason that simple-yet-accurate models often do exist. This hypothesis is that the size of the Rashomon set is often large, where the Rashomon set is the set of almost-equally-accurate models from a function class. If the Rashomon set is large, it contains numerous accurate models, and perhaps at least one of them is the simple model we desire. In this work, we formally present the Rashomon ratio as a new gauge of simplicity for a learning problem, depending on a function class and a data set. The Rashomon ratio is the ratio of the volume of the set of accurate models to the volume of the hypothesis space, and it is different from standard complexity measures from statistical learning theory. Insight from studying the Rashomon ratio provides an easy way to check whether a simpler model might exist for a problem before finding it, namely whether several different machine learning methods achieve similar performance on the data. In that sense, the Rashomon ratio is a powerful tool for understanding why and when an accurate-yet-simple model might exist. If, as we hypothesize in this work, many real-world data sets admit large Rashomon sets, the implications are vast: it means that simple or interpretable models may often be used for high-stakes decisions without losing accuracy.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“One recent theory suggests that when the prediction problem is heavily influenced by randomness (e.g., whether someone will commit a crime within 2 y could depend on any number of circumstances, and is a noisy process), there are many approximately equally predictive models, and in that case, it is likely that at least one of these models is interpretable (34).”
From Interpretable algorithmic forensics (2023) · cites this paper as [34]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Cortes, C., & Vapnik, V. (1995) · Machine Learning · doi:10.1007/bf00994018 · Cited by 59,421
The Nature of Statistical Learning Theory
Vapnik, V. N. (1995) · doi:10.1007/978-1-4757-2440-0 · Cited by 39,138
UCI Machine Learning Repository
Asuncion, A. (2007) · Medical Entomology and Zoology · Cited by 25,410
A Tutorial on Support Vector Machines for Pattern Recognition
Burges, C. J. C. (1998) · Data Mining and Knowledge Discovery · doi:10.1023/a:1009715923555 · Cited by 16,429 · cited 3×
“Then the margin d is a sum of these distances d = d+ + d− [7].”
BackgroundInfluentialRudin, C. (2019) · Nature Machine Intelligence · doi:10.1038/s42256-019-0048-x · Cited by 10,561 · cited 1×
“However, because simple models are essential for many high-stakes decisions (Rudin, 2019), perhaps we should return to the goal of aiming directly for simpler models.”
BackgroundSelf-citationProceedings of the 21st International Conference on Neural Information Processing Systems
Koller, D., Schuurmans, D., Bengio, Y., & Bottou, L. (2008) · Cited by 4,461
Statistical Modeling: The Two Cultures (with comments and a rejoinder by the author)
Breiman, L. (2001) · Statistical Science · doi:10.1214/ss/1009213726 · Cited by 4,340 · cited 3×
“We hypothesize that these three observations can all be explained by the same phenomenon: the “Rashomon effect,” which is the existence of many almost-equally-accurate models (Breiman et al., 2001).”
BackgroundMethodOn the Uniform Convergence of Relative Frequencies of Events to Their Probabilities
Vapnik, V. N., & Chervonenkis, A. Y. (2015) · Measures of Complexity · doi:10.1007/978-3-319-21852-6_3 · Cited by 3,105 · cited 6×
“The VC dimension [49] shows the expressive power of a hypothesis space for any data set including an extreme arrangement of data points and labels.”
BackgroundInfluentialBoosting the margin: a new explanation for the effectiveness of voting methods
Bartlett, P., Freund, Y., Lee, W. S., & Schapire, R. E. (1998) · The Annals of Statistics · doi:10.1214/aos/1024691352 · Cited by 2,306
Meinshausen, N., & Bühlmann, P. (2010) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.1467-9868.2010.00740.x · Cited by 2,215 · cited 1×
“Rashomon sets: Rashomon sets have been used for various purposes (Breiman et al., 2001; Srebro et al., 2010; Fisher et al., 2019; Coker et al., 2021; Tulabandhula and Rudin, 2014b; Meinshausen and Bühlmann, 2010; Letham et al., 2016; Nevo and Ritov, 2017).”
Method
Research works printed but not linked: 9
- 10.1023/A:1022873112823 · doi:10.1023/a:1022873112823 · Paper page
- Olivier Bousquet and André Elisseeff. 2002. Stability and generalization. Journal of Machine Learning Research 2, Mar (2002), 499–526.
- Nitish Shirish Keskar, Dheevatsa Mudigere, Jorge Nocedal, Mikhail Smelyanskiy, and Ping Tak Peter Tang. 2016. On large-batch training for deep learning: Generalization gap and sharp minima. arXiv preprint arXiv:1609.04836 (appeared at ICLR 2017) (2016). · arXiv
- 10.5555/2968618.2968674 · doi:10.5555/2968618.2968674
- 10.5555/3524938.3525566 · doi:10.5555/3524938.3525566
- Nagarajan Natarajan, Inderjit S Dhillon, Pradeep K Ravikumar, and Ambuj Tewari. 2013. Learning with noisy labels. In Advances in Neural Information Processing Systems, C. J. C. Burges, L. Bottou, M. Welling, Z. Ghahramani, and K. Q. Weinberger (Eds.). Vol. 26. Curran Associates, Inc.
- Lesia Semenova Cynthia Rudin and Ronald Parr. 2019. A study in Rashomon curves and volumes: A new perspective on generalization and model simplicity in machine learning. arXiv preprint arXiv:abs/1908.01755(2019).
- 10.5555/2567709.2567726 · doi:10.5555/2567709.2567726
- 10.5555/211359 · doi:10.5555/211359
Cited by
Explainable Artificial Intelligence by Genetic Programming: A Survey
Mei, Y., Chen, Q., Lensen, A., Xue, B., & Zhang, M. (2023) · IEEE Transactions on Evolutionary Computation · doi:10.1109/tevc.2022.3225509 · Cited by 164
“This can be achieved when the different machine learning models perform similarly on the dataset (the Rashomon set is large [54]).”
MethodBock, K. W. D., Coussement, K., Caigny, A. D., Słowiński, R., Baesens, B., Boute, R. N., Choi, T., Delen, D., Kraus, M., Lessmann, S., et al. (2023) · European Journal of Operational Research · doi:10.1016/j.ejor.2023.09.026 · Cited by 211
“According to Semenova, Rudin, & Parr (2022), they also provide simple, accurate models that can be superior to accurate, more complex models in terms of understandability.”
BackgroundWhy black box machine learning should be avoided for high-stakes decisions, in brief
Rudin, C. D. (2022) · Nature Reviews Methods Primers · doi:10.1038/s43586-022-00172-0 · Cited by 127
“A hypothesis for this remarkable phenomenon is the Rashomon set theory, that datasets tend to admit many accurate models 10 , among which are simpler, more interpretable models.”
BackgroundSelf-citationModel Multiplicity: Opportunities, Concerns, and Solutions
Black, E., Raghavan, M., & Barocas, S. (2022) · 2022 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3531146.3533149 · Cited by 85
Picking on the Same Person: Does Algorithmic Monoculture lead to Outcome Homogenization?
Bommasani, R., Creel, K. A., Kumar, A., Jurafsky, D., & Liang, P. (2022) · arXiv · doi:10.48550/arxiv.2211.13972 · Cited by 60
“This demonstration is reminscent of work that demonstrates 28 the existence of models of (near) equal accuracy but that are simpler [Semenova et al., 2022] or more fair [Marx et al., 2020].”
MethodBoosting: Empowering Citizens with Behavioral Science
Herzog, S. M., & Hertwig, R. (2024) · Annual Review of Psychology · doi:10.1146/annurev-psych-020924-124753 · Cited by 93
Transparency of medical artificial intelligence systems
Kim, C., Gadgil, S. U., & Lee, S. (2025) · Nature Reviews Bioengineering · doi:10.1038/s44222-025-00363-w · Cited by 81
“When such models achieve performance comparable to that of complex models 161 , they are generally preferred owing to their transparency.”
Interpretable algorithmic forensics
Garrett, B. L., & Rudin, C. (2023) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2301842120 · Cited by 68
“, whether someone will commit a crime within 2 y could depend on any number of circumstances, and is a noisy process), there are many approximately equally predictive models, and in that case, it is likely that at least one of these models is interpretable (34).”
BackgroundSelf-citationLogic-Based Explainability in Machine Learning
Marques-Silva, J. P. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-31414-8_2 · Cited by 122
Revisiting the Performance-Explainability Trade-Off in Explainable Artificial Intelligence (XAI)
Crook, B., Schlüter, M., & Speith, T. (2023) · 2023 IEEE 31st International Requirements Engineering Conference Workshops (REW) · doi:10.1109/rew57809.2023.00060 · Cited by 36
An Empirical Evaluation of the Rashomon Effect in Explainable Machine Learning
Müller, S., Toborek, V., Beckh, K., Jakobs, M., Bauckhage, C., & Welke, P. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-43418-1_28 · Cited by 73
Zhang, J., Srivatsa, P., Ahmadzai, F. H., Liu, Y., Song, X., Karpatne, A., Kong, Z., & Johnson, B. N. (2023) · ACS Sensors · doi:10.1021/acssensors.3c01258 · Cited by 32
Learning Optimal Fair Decision Trees: Trade-offs Between Interpretability, Fairness, and Accuracy
Jo, N., Aghaei, S., Benson, J., Gómez, A., & Vayanos, P. (2023) · Proceedings of the AAAI/ACM Conference on AI Ethics and Society · doi:10.1145/3600211.3604664 · Cited by 63
“[51] allow for comparisons across various model classes by using Rashomon sets to gauge the likelihood of simpler models with competing accuracy performance existing within a hypothesis space.”
MethodIs Ockham’s razor losing its edge? New perspectives on the principle of model parsimony
Dubova, M., Chandramouli, S., Gigerenzer, G., Grünwald, P., Holmes, W. R., Lombrozo, T., Marelli, M., Musslick, S., Nicenboim, B., Ross, L. N., et al. (2025) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2401230121 · Cited by 68
Minimizing bias when using artificial intelligence in critical care medicine
Ranard, B. L., Park, S., Jia, Y., Zhang, Y., Alwan, F. S., Celi, L. A., & Lusczek, E. R. (2024) · Journal of Critical Care · doi:10.1016/j.jcrc.2024.154796 · Cited by 31
Exploring explainable AI in the tax domain
Górski, Ł., Kuźniacki, B., Almada, M., Tyliński, K., Calvo, M., Asnaghi, P. M., Almada, L., Iñiguez, H. I., Rubianes, F., Pera, O., et al. (2024) · Artificial Intelligence and Law · doi:10.1007/s10506-024-09395-w · Cited by 43
“If , on the one hand, there is no reason to believe black box models always perform better (Semenova et al. 2022), some empirical research has pointed out that inter-pretable models are not always more legible to humans in the decision-making loop, either (Bell et al. 2022).”
Rehill, P., & Biddle, N. (2024) · Data & Policy · doi:10.1017/dap.2024.35 · Cited by 25
Feature importance measures for flood forecasting system design
Cappelli, F., Tauro, F., Apollonio, C., Petroselli, A., Borgonovo, E., Volpi, E., & Grimaldi, S. (2024) · Hydrological Sciences Journal · doi:10.1080/02626667.2024.2321332 · Cited by 17
“For selecting the most appropriate ML tool, we investigate the behaviour of four models: a linear model (LM), a random forest (RF), a gradient-boosting (GB) machine, and an extreme gradient-boosting (XGB) machine (Breiman 2001, Friedman 2001, Chen and Guestrin 2016, Semenova et al .”
MethodResponsible machine learning for United States Air Force pilot candidate selection
Wasilefsky, D., Caballero, W. N., Johnstone, C., Gaw, N. B., & Jenkins, P. R. (2024) · Decision Support Systems · doi:10.1016/j.dss.2024.114198 · Cited by 19
Discovering interpretable models of scientific image data with deep learning
Soelistyo, C. J., & Lowe, A. R. (2024) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw63382.2024.00682 · Cited by 13
Designing deep neural networks for driver intention recognition
Vellenga, K., Steinhauer, H. J., Karlsson, A., Falkman, G., Rhodin, A., & Koppisetty, A. C. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.109574 · Cited by 11
“Despite advancements of onboard computing platforms in cars, the computational resources are still quite limited, which makes it crucial to investigate whether reducing the complexity of a DNN yields comparable performance (11).”
Model interpretability enhances domain generalization in the case of textual complexity modeling
van der Sluis, F., & van den Broek, E. L. (2025) · Patterns · doi:10.1016/j.patter.2025.101177 · Cited by 18
“Two aspects of the models are systematically varied for the embedding and feature representations: interaction depth (three levels) and model parameters (26–153,012 parameters).”
InfluentialThe Dataset Multiplicity Problem: How Unreliable Data Impacts Predictions
Meyer, A. P., Albarghouthi, A., & D’Antoni, L. (2023) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3593013.3593988 · Cited by 33
“Because of this multiplicity, models can often be selected to simultaneously achieve accuracy and also fairness, robustness, or other desirable model-level properties [6, 14, 51, 60, 67].”
BackgroundWaveSleepNet: An Interpretable Network for Expert-Like Sleep Staging
Pei, Y., Xu, J., Yu, F. N., Zhang, L., & Luo, W. (2024) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2024.3498871 · Cited by 15
Mahynski, N. A., Strojnik, L., Shen, V. K., & Ogrinc, N. (2025) · Food Chemistry · doi:10.1016/j.foodchem.2025.144569 · Cited by 9
Drought-sensitive targeting and child growth faltering in Southern Africa
Báez, J. E., Kshirsagar, V., & Skoufias, E. (2024) · World Development · doi:10.1016/j.worlddev.2024.106702 · Cited by 7
Understanding with Toy Surrogate Models in Machine Learning
Páez, A. (2024) · Minds and Machines · doi:10.1007/s11023-024-09700-1 · Cited by 16
“The existence of multiple equally accurate TSMs has been called the “Rashomon Effect” in ML (Breiman, 2001; Semenova et al., 2022).”
Who Are We Missing? : A Principled Approach to Characterizing the Underrepresented Population
Parikh, H., Ross, R. K., Stuart, E. A., & Rudolph, K. E. (2025) · Journal of the American Statistical Association · doi:10.1080/01621459.2025.2495319 · Cited by 20
“However, there are possibly other decision trees that are nearly as optimal as the learned tree and have an alternate interpretation (Xin et al. 2022; Semenova, Rudin, and Parr 2022).”
Model selection with bootstrap validation
Savvides, R., Mäkelä, J., & Puolamäki, K. (2023) · Statistical analysis and data mining · doi:10.1002/sam.11606 · Cited by 7
“The probability bounds given for the model output by our algorithm are similar to bounds in prior work, such as in Rashomon sets [33] (the set of almost-equally-accurate models for a given problem), and predictive multiplicity [23].”
MethodÇavuş, M., & Biecek, P. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103243 · Cited by 21
Broader Issues Surrounding Model Transparency in Criminal Justice Risk Scoring
Rudin, C. D., Wang, C., & Coker, B. (2020) · Harvard Data Science Review · doi:10.1162/99608f92.038c43fe · Cited by 17
Self-citationArbitrary Decisions are a Hidden Cost of Differentially Private Training
Kulynych, B., Hsu, H., Troncoso, C., & Calmon, F. P. (2023) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3593013.3594103 · Cited by 32
“In non-private training, the existence of many models that achieve comparable accuracy creates an opportunity for selecting a model which satisfies both an acceptable accuracy level and other useful properties beyond performance, such as fairness [9], interpretability [17], or generalizability [31].”
BackgroundMethodInfluentialLi, S., & Barnard, A. S. (2023) · Cell Reports Physical Science · doi:10.1016/j.xcrp.2023.101675 · Cited by 12
Exploration of the Rashomon Set Assists Trustworthy Explanations for Medical Data
Kobylińska, K., Krzyziński, M., Machowicz, R., Adamek, M., & Biecek, P. (2024) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2024.3443069 · Cited by 19
“Many studies have addressed the topic of Rashomon sets [5], [6], [7].”
BackgroundMethodOn the Inevitability of the Rashomon Effect
Paes, L. M., Cruz, R., Calmon, F. P., & Díaz, M. (2023) · IEEE International Symposium on Information Theory (ISIT) · doi:10.1109/isit54713.2023.10206657 · Cited by 8
“Semenova et al. [2] studied the volume of the Rashomon set to analyze the existence of simple ML models.”
BackgroundInfluentialWhy shallow networks struggle to approximate and learn high frequencies
Zhang, S., Zhao, H., Zhong, Y., & Zhou, H. (2025) · Information and Inference A Journal of the IMA · doi:10.1093/imaiai/iaaf022 · Cited by 33
Gasper, J. R., & Cahalan, J. A. (2025) · Fisheries Research · doi:10.1016/j.fishres.2024.107253 · Cited by 5
Concurrent Classifier Error Detection (CCED) in Large Scale Machine Learning Systems
Reviriego, P., Wang, Z., Alonso, Á., Gao, Z., Niknia, F., Liu, S., & Lombardi, F. (2024) · IEEE Transactions on Reliability · doi:10.1109/tr.2024.3355408 · Cited by 5
“Therefore, the concurrent classifier can be implemented using classical ML algorithms with low complexity, which in simple classification problems can achieve an accuracy like that of more complex models such as DNNs [39].”
Efficient Exploration of the Rashomon Set of Rule-Set Models
Ciaperoni, M., Xiao, H., & Gionis, A. (2024) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3637528.3671818 · Cited by 17
What Constitutes a Less Discriminatory Algorithm?
Laufer, B., Raghavan, M., & Barocas, S. (2025) · doi:10.1145/3709025.3712214 · Cited by 20
“In lending and employment contexts, labels (i.e., outcomes) are not reliably observed after a model is deployed [57].”
Discovering Diverse Top-K Characteristic Lists
Lopez-Martinez-Carrasco, A., Proença, H. M., Juárez, J. M., van Leeuwen, M., & Campos, M. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-30047-9_21 · Cited by 5
“In this context, di(cid:27)erent research has been carried out [12, 13].”
BackgroundAllocation Multiplicity: Evaluating the Promises of the Rashomon Set
Jain, S., Wang, M., Creel, K. A., & Wilson, A. (2025) · Conference on Fairness, Accountability and Transparency · doi:10.1145/3715275.3732138 · Cited by 8
Scalable Rule Lists Learning with Sampling
Pellegrina, L., & Vandin, F. (2024) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3637528.3671989 · Cited by 8
Simson, J., Draxler, F., Mehr, S. A., & Kern, C. A. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713482 · Cited by 6
Interpretable Classifier Models for Decision Support Using High Utility Gain Patterns
Krishnamoorthy, S. (2024) · IEEE Access · doi:10.1109/access.2024.3455563 · Cited by 7
“Many of the real-world datasets are found to exhibit Rashomon effect [6], [11], [12] and have large Rashomon sets i.e. multiple descriptions or models of the same dataset with similar performance results.”
ResultImperfect physics-guided neural networks
Carter, A., Imtiaz, S. A., & Naterer, G. F. (2024) · Chemical Engineering Science · doi:10.1016/j.ces.2024.121153 · Cited by 6
Early-Stage Sensor Data Fusion Pipeline Exploration Framework for Agriculture and Animal Welfare
Martin, D., Roberts, D. L., & Bozkurt, A. Y. (2025) · AgriEngineering · doi:10.3390/agriengineering7070215 · Cited by 3
Be Intentional About Fairness!: Fairness, Size, and Multiplicity in the Rashomon Set
Dai, G., Ravishankar, P., Yuan, R., Black, E., & Neill, D. B. (2025) · ACM Conference on Equity and Access in Algorithms, Mechanisms, and Optimization (EAAMO) · doi:10.1145/3757887.3763011 · Cited by 18
Death After Liver Transplantation: Mining Interpretable Risk Factors for Survival Prediction
Guidetti, V., Dolci, G., Franceschini, E., Bacca, E., Burastero, G. J., Ferrari, D., Serra, V., Benedetto, F. D., Mussini, C., & Mandreoli, F. (2023) · IEEE International Conference on Data Science and Advanced Analytics (DSAA) · doi:10.1109/dsaa60987.2023.10302622 · Cited by 3
Tian, X., Todorovic, J., & Todorovic, Z. W. (2023) · Journal of Applied Business and Economics · doi:10.33423/jabe.v25i6.6639 · Cited by 9
“The simple and interpretable models can be used for high-stakes decisions without losing accuracy (Semenova et al., 2022).”
MethodÇavuş, M., van Rijn, J. N., & Biecek, P. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-05461-6_29 · Cited by 2
“Two common metrics used to characterize this set are Rashomon set size and Rashomon ratio [26].”
Nativism and empiricism in artificial intelligence
Long, R. (2024) · Philosophical Studies · doi:10.1007/s11098-024-02122-w · Cited by 7
“They find that in many cases there will be more and less interpretable models within this set (Semenova et al., 2022).”
Fairness in Machine Learning for National Statistical Organizations
Schenk, P. O., Kern, C. A., & Kreuter, F. (2025) · Society, environment and statistics · doi:10.1007/978-3-032-10004-7_6 · Cited by 2
Automatic Coherence-Driven Inference on Arguments
Huntsman, S. (2025) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw69685.2025.00090 · Cited by 2
“2 There is always at least one assignment of truth values that is optimal, though near-optimal assignments are of interest in the spirit of Rashomon [23].”
Benchmarking Graph Construction by Large Language Models for Coherence-Driven Inference
Huntsman, S., & Thomas, J. (2025) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw69685.2025.00116 · Cited by 3
Coherence-Driven Inference for Cybersecurity
Huntsman, S. (2025) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw69685.2025.00144 · Cited by 2
“This accounting of near-optimal Rashomon solutions [28] can be done in a more principled way by averaging over a Gibbs measure instead of a counting measure.”
Virtual perturbations to assess explainability of deep-learning based cell fate predictors
Soelistyo, C. J., Charras, G., & Lowe, A. R. (2023) · IEEE International Conference on Computer Vision Workshops · doi:10.1109/iccvw60793.2023.00429 · Cited by 2
“2 we introduced the notion of an equal-performance “Rashomon” set G [2].”
Vetter, J., Lim, K., Dijkstra, T. M. H., Dargaville, P. A., Kohlbacher, O., Macke, J. H., & Poets, C. F. (2023) · medRxiv · doi:10.1101/2023.03.14.23287021 · Cited by 2
Hug-Iml: Interpretable Machine Learning for Decision Support Using High Utility Gain PatternsPreprint
Krishnamoorthy, S. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4785680 · Cited by 2
“A 6 or a 9?”: Ensemble Learning through the Multiplicity of Performant Models and Explanations
Zuin, G. L., & Veloso, A. (2025) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/3767735 · Cited by 1
An interpretable deep learning model for EEG emotion recognition using the Rashomon effect
Gangolu, R., & Kadambari, K. V. (2026) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2026.110140 · Cited by 1
Rosende‐Pereiro, A., & Corgos, A. (2026) · Diversity · doi:10.3390/d18040232 · Cited by 1
Gosciak, J., Boyce, L., Wang, A., & Koenecke, A. (2026) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3805689.3812405 · Cited by 2
Machine Learning and IRB Capital Requirements: Advantages, Risks, and RecommendationsPreprint
Hurlin, C., & Pérignon, C. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4483793 · Cited by 3
Ragodos, R., Wang, T., Feng, L., & Hu, Y. J. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4915307 · Cited by 5
Recent advances in formal explainability
Huang, X. (2023) · theses.fr (ABES) · doi:10.70675/1b6e4710z8c13z4f84zbb0az80e114bebb07 · Cited by 2
Wang, Y., Banerjee, C., Chucri, S., & Chen, M. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4930677 · Cited by 1
Vetter, J., Lim, K., Dijkstra, T. M. H., Dargaville, P. A., Kohlbacher, O., Macke, J. H., & Poets, C. F. (2024) · PLOS Digital Health · doi:10.1371/journal.pdig.0000678
“Creating such models is often possible without a drop in model performance [15].”
Watershed‐Scale Runoff Efficiency Response to Climate Variability
Erikson, C. M., Renshaw, C. E., Dethier, E. N., & Magilligan, F. J. (2025) · Hydrological Processes · doi:10.1002/hyp.70086
“Among the possible statistical models, there can be multiple models of a similar accuracy across a range of complexity, known as the ‘Rashomon Effect’ (Breiman 2001; Rudin 2019; Semenova et al. 2022).”
Why it Works: Can LLM Hypotheses Improve AI Generated Marketing Content?Preprint
Wang, T., Sudhir, K., & Zhou, H. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5437276
Intelligence artificielle et marché du crédit : opportunités et acceptabilité
Christophe Hurlin, Y., & Pérignon, C. (2025) · Revue d économie financière · doi:10.3917/ecofi.159.0105
Vellenga, K. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5804595
Optimization based ensemble methods for music genre classification
Atsiz, E., Albey, E., & Kayış, E. (2026) · IISE Transactions · doi:10.1080/24725854.2026.2638451
CASHomon Sets: Efficient Rashomon Sets Across Multiple Model Classes and Their Hyperparameters
Ewald, F. K., Binder, M., Feurer, M., Bischl, B., & Casalicchio, G. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37667-1_19 · Cited by 2
Stability and robustness of minimal majority vote interpretable ensembles
Li, Q., Huang, Z., & Pan, M. (2026) · Scientific Reports · doi:10.1038/s41598-026-45289-4 · Cited by 1
Dong, H., Dong, Z., & Fu, L. (2026) · Neurological Sciences · doi:10.1007/s10072-026-09022-3
Kim, M. (2026) · Research Square · doi:10.21203/rs.3.rs-9501010/v1
Perturbation-Based Error Tolerance for Large-Scale Networks
Wang, Z., Reviriego, P., Liu, S., Niknia, F., Alonso, Á., Gao, Z., & Lombardi, F. (2026) · Springer eBooks · doi:10.1007/978-3-032-17948-7_8
Metamorphic Testing with the Rashomon Set: Explanation Faithfulness in Machine Learning
Spieker, H., Betten, J. E., & Arnaud Gotlieb, B. (2026) · IEEE Annual International Computer Software and Applications Conference (COMPSAC) · doi:10.1109/compsac69091.2026.00371
“Its existence has significant implications for model selection, variable importance analysis, and the scientific conclusions drawn from data [6]–[8].”
Explainability and Interpretability in Machine Learning and Artificial Intelligence
Rowat, C. (2026) · Oxford University Press eBooks · doi:10.1093/9780197851418.003.0994
Conformal Prediction and the Many-Worlds of Fairness
Brodén, J., Simson, J., & Kern, C. A. (2026) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3805689.3812391 · Cited by 1
Rashomon Sets and Model Multiplicity in Federated Learning
Heilmann, X., Corbucci, L., & Cerrato, M. (2026) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3805689.3812290
Fast Rashomon Sets of Sparse Rule Sets
Molero-Río, C., Li, B., Wang, T., & Rudin, C. D. (2026) · Machine Learning · doi:10.1007/s10994-026-07108-9 · Cited by 1
“The set of optimal and near-optimal models is called the Rashomon set (Semenova et al. 2022 ; Fisher et al. 2019 ).”
Self-citationAlkhnbashi, O. S., Mohammad, R., Khyriem, C., Hauns, S., Singh, A., Khan, I., Gomez, R. L., Ramachandran, R., Albedwawi, M. H., AbdulRahim, M. M., et al. (2026) · Artificial Intelligence Review · doi:10.1007/s10462-026-11634-2
SiTe: A Statistical Significance-aware Framework for Robust XAIPreprint
Akintande, O. J., & Pokojovy, M. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7101578
Huang, M., Liu, M., & Li, X. (2026) · Research Square · doi:10.21203/rs.3.rs-10524572/v1
The Impact of Stochasticity on the Rashomon Effect in Machine LearningPreprint
Apicella, A., Isgrò, F., Pollastro, A., & Prevete, R. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7306682
Aydoğan, Y., & Cantürk, İ. (2026) · Journal of Voice · doi:10.1016/j.jvoice.2026.08.044
Lifting the radiomics performance ceiling: how preprocessing leakage amplifies model multiplicity
García-Hidalgo, C., Hernández, J. A. C., & Espí, J. V. C. (2026) · European Radiology · doi:10.1007/s00330-026-12932-7
Solano, R. P., Berlanga, A., Molina, J. M., & Julio, Y. R. (2026) · Machine Learning and Knowledge Extraction · doi:10.3390/make8100319
From Accuracy to Understanding: Rashomon Ensembles for Alzheimer’s Disease Classification
Borsani, T., Rosani, A., & Fatta, G. D. (2026) · International Conference on Advanced Machine Learning and Data Science (AMLDS) · doi:10.1109/amlds69611.2026.11723594
“The Rashomon effect gives rise to simpler and yet accurate models [5], [6].”
Dalal, S., & Akbar, M. (2026) · Journal of Artificial Intelligence Machine Learning and Neural Network · doi:10.55529/jaimlnn.62.15.31
Metadata
- Authors
- Semenova, L., Rudin, C., & Parr, R.
- Affiliations
- Duke University (US)
- Venue
- 2022 ACM Conference on Fairness Accountability and Transparency
- Publisher
- ACM
- Published
- 2022-06-20
- Pages
- 1827-1858
- OpenAlex
- W4283168572
- Cited by
- 90
- References
- 55
- Citations by year
- 2026: 23 · 2025: 23 · 2024: 22 · 2023: 19 · 2022: 2
- FWCI
- 9.12
- Type
- conference paper
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- ACM Conference on Fairness, Accountability, and Transparency (FAccT) (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Algorithms
- Physical Sciences › Computer Science › Artificial Intelligence › Machine Learning and Data Classification
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Keywords
- Rashomon set, model simplicity, sparse models, interpretable models, hypothesis space, model complexity, decision tree, decision sets, NP-hardness, statistical learning theory
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.