A Survey of Methods for Explaining Black Box Models
Open accessThe DOI matches its Crossref record; 132 of the 132 references it cites were found in a registry or an index; 4 of the 59 sources its claims cite were checked for support.
Abstract
In recent years, many accurate decision support systems have been constructed as black boxes, that is as systems that hide their internal logic to the user. This lack of explanation constitutes both a practical and an ethical issue. The literature reports many approaches aimed at overcoming this crucial weakness, sometimes at the cost of sacrificing accuracy for interpretability. The applications in which black box decision systems can be used are various, and each approach is typically developed to provide a solution for a specific problem and, as a consequence, it explicitly or implicitly delineates its own definition of interpretability and explanation. The aim of this article is to provide a classification of the main problems addressed in the literature with respect to the notion of explanation and the type of black box system. Given a problem definition, a black box type, and a desired explanation, this survey should help the researcher to find the proposals more useful for his own work. The proposed classification of approaches to open black box models should also be useful for putting the many research open questions in perspective.
Overview
CoChat Summary
TL;DR
This survey classifies methods for explaining black-box machine learning models into four problem types: black box model explanation, black box outcome explanation, black box inspection, and transparent box design. It organizes the literature by problem, explanator, black-box type, and data type, and highlights open challenges around defining and measuring explanation and comprehensibility.
Key findings
- The paper identifies and formally defines four explanation problems: black box model explanation (global interpretable mimic), black box outcome explanation (local explanation for a prediction), black box inspection (visual/textual representation of behavior), and transparent box design (interpretable model by design).
- It classifies explanators into decision trees, decision rules, feature importance, saliency masks, sensitivity analysis, partial dependence plots, prototype selection, and neuron activation; black boxes into neural networks, tree ensembles, SVMs, deep neural networks, and agnostic black boxes; and data into tabular, image, and text.
- Many methods are specific to a problem or black-box type, while agnostic/generalizable approaches use reverse engineering by querying the black box as an oracle; examples include Trepan, inTrees, LIME, and PALM.
- Motivating cases cited include COMPAS ethnic bias (black non-reoffenders classified high risk twice as much as whites who did not re-offend; white repeat offenders classified low risk twice as much as black repeat offenders), credit scoring discordance (in 500,000 records, 29% of consumers received scores differing by at least fifty points among three major US banks), and the St. George’s Hospital screening program that discriminated via inferred ethnicity from surnames and place of birth.
Methods
- Literature survey/review; no primary empirical study. The paper formalizes the general classification problem and defines the four explanation problems as specific cases.
- The classification dimensions are: type of problem faced, type of explanator adopted, type of black box model opened, and type of data used as input by the black box. Table 1 summarizes methods with features including General, Random, Examples, Code, and Dataset.
- The common reverse-engineering approach queries the black box with a test dataset to create an oracle dataset, then trains a comprehensible predictor; approaches are distinguished as generalizable/pedagogical versus not generalizable/decompositional.
Limitations
- The paper states that there is no agreement on what an explanation is, no general/common formalism for defining explanations or properties such as soundness, completeness, compactness, and comprehensibility, and no serious work quantifying human comprehensibility; it also lists open questions on latent features, recommender systems, and learning predictors directly from explanations.
- The paper states it does not address whether the black box can be queried at will versus only a fixed dataset being available, or whether the complete feature set is known, because there is insufficient literature.
- Evident from the text: the survey scope is limited to tabular, image, and text data, with no work addressing interpretability for sequence, spatio-temporal, or complex network data; many reviewed methods are ad hoc or specific, only a few consider user expertise, and no work provides real experiments on the time required to understand an explanation.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
4 Valid · 13 Not valid · 38 Not checked · 49 Own results and interpretations
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“and no one provides real experiments about the time required to understand an explanation.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The paper states this without a source or data behind it here, so there is nothing to check it against. The quote shows it is in the paper.
In the paper
“The works reviewed in the literature only implicitly specify if their proposal is global or local.”
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: unclear — It is unclear why the paper says it holds.
None of the sources cited for this claim have been checked yet.
In the paper
“Just a few of them take into account the nature of user expertise [29,84,87]”
What the sources say
- Not checked yetcites [29] 29. R. D. Gibbons, G. Hooker, M. D. Finkelman, D. J. Weiss, P. A. Pilkonis, E. Frank, T. Moore, and D. J. Kupfer. The cad-mdd: a computerized adaptive diagnostic screening tool for depression. The Journal of clinical psychiatry , 74(7):669, 2013. source
- Not checked yetcites [84] 84. M. T. Ribeiro, S. Singh, and C. Guestrin. Why should i trust you?: Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining , pages 1135-1144. ACM, 2016. source
- Not checked yetcites [87] 87. V. Schetinin, J. E. Fieldsend, D. Partridge, T. J. Coats, W. J. Krzanowski, R. M. Everson, T. C. Bailey, and A. Hernandez. Confident interpretation of bayesian decision tree ensembles for clinical applications. IEEE Transactions on Information Technology in Biomedicine , 11(3):312-319, 2007. source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
In the paper
“In the following, we list all the black boxes opened in the reviewed papers. These black boxes are all supervised learning algorithm designed to solve a classification problem [95].”
What the sources say
- Not checked yetcites [95] 95. P.-N. Tan et al. Introduction to data mining . Pearson Education India, 2006.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
In the paper
“However, this is not always the case in practice [84].”
What the sources say
- Not checked yetcites [84] 84. M. T. Ribeiro, S. Singh, and C. Guestrin. Why should i trust you?: Explaining the predictions of any classifier. In Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining , pages 1135-1144. ACM, 2016. source
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
23 more claims
Create a free account to see all 104 claims and to verify the 46 references still open.
- It may state two separate claims as one. 37
- Probably not a substantial claim. 65
- The quote only partly states this claim. 1
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 source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“While “black‐box” algorithms raise complex opaqueness and interpretability challenges, simpler interpretable ML algorithms do not, but have generally also been regarded as less powerful (Guidotti et al. 2019; see however, Rudin 2019).”
From Accountable Artificial Intelligence: Holding Algorithms to Account (2021) · cites this paper as Guidotti et al. 2019
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Since we could not find a complete and recent overview of explanation types, we reviewed recent XAI surveys [14,58,167,280] and adapted and extended the categories identified by Guidotti et al. [86] with these insights.”
From From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AI (2023) · cites this paper as [86]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“However, there is no consensus on what a good XAD technique should be.”
From A Survey on Explainable Anomaly Detection (2024) · cites this paper as [76]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Among the main impediments prohibiting banking institutions from implementing their AI strategy is the ''black-box'' paradox [28].”
From A Review of Trustworthy and Explainable Artificial Intelligence (XAI) (2023) · cites this paper as [28]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The models are black boxes due to their significant non-linearity and intricacy, making it unfeasible for individuals to fathom their fundamental operational processes and judgment mechanisms [28].”
From A Review of Trustworthy and Explainable Artificial Intelligence (XAI) (2023) · cites this paper as [28]
Experimental — accuracy not yet measured
16 more claims about this paper
Create a free account to see every claim other papers make about this one.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
§ 4.1 Problem Formulation · p. 13
“for the comprehensible predictor c we get the set of predictions ¯ Y = ⋃ x ∈ X c ( x )”
§ 4.1 Problem Formulation · p. 13
“where as target value is used the prediction ¯ Y of the black box b instead of the real values Y”
Citations
Cites
"Why Should I Trust You?": Explaining the Predictions of Any Classifier
Ribeiro, M. T., Singh, S., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939778 · Cited by 17,555
Visualizing and understanding convolutional networks
Zeiler, M. D., & Fergus, R. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10590-1_53 · Cited by 15,839 · cited 2×
“elated to producing a certain prediction by realizing a sort of articial image prototype. There is a signicant amount of work in understanding the representation of DNN by means of artifact images, [41,100,105,111]. We conclude this section presenting how [25] deals with artifacts in DNNs. Finding a single representat…”
BackgroundLearning Deep Features for Discriminative Localization
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., & Torralba, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.319 · Cited by 11,428 · cited 5×
“al. 2017 Model Expl. DT AGN ANY X X X - [97] Tolomei et al. 2017 Model Expl. FI TE TAB X - [108] Xu et al. 2015 Outcome Expl. SM DNN IMG X X X - [25] Fong et al. 2017 Outcome Expl. SM DNN IMG X X CAM [113] Zhou et al. 2016 Outcome Expl. SM DNN IMG X X X Grad-CAM [89] Selvaraju et al. 2016 Outcome Expl. SM DNN IMG X X…”
BackgroundMethodInfluentialShow, Attend and Tell: Neural Image Caption Generation with Visual Attention
Xu, K., Ba, J., Kiros, R., Cho, K., Courville, A., Salakhutdinov, R., Zemel, R., & Bengio, Y. (2015) · arXiv · doi:10.48550/arxiv.1502.03044 · Cited by 8,248 · cited 2×
“Reference [134] introduces an attention-based model f , which automatically identifies the contents of an image.”
BackgroundIntriguing properties of neural networks
Szegedy, C., Zaremba, W., Sutskever, I., Bruna, J., Erhan, D., Goodfellow, I., & Fergus, R. (2013) · arXiv · doi:10.48550/arxiv.1312.6199 · Cited by 8,143 · cited 1×
“In Reference [116] it is shown the alteration of an image (e.”
Background(2008) · Data Mining and Market Intelligence for Optimal Marketing Returns · doi:10.4324/9780080878096-12 · Cited by 6,954
Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization
Selvaraju, R. R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., & Batra, D. (2020) · International Journal of Computer Vision · doi:10.1007/s11263-019-01228-7 · Cited by 6,909
Lipton, Z. C. (2018) · Queue · doi:10.1145/3236386.3241340 · Cited by 5,427 · cited 1×
“Existing works tend to provide just a general overview of the problem [68] highlighting unanswered questions and problems [28].”
BackgroundThe Mythos of Model Interpretability
Lipton, Z. C. (2016) · arXiv · doi:10.48550/arxiv.1606.03490 · Cited by 5,422 · cited 1×
“Existing works tend to provide just a general overview of the problem [68] highlighting unanswered questions and problems [28].”
BackgroundAdversarial examples in the physical world
Kurakin, A., Goodfellow, I. J., & Bengio, S. (2018) · Artificial Intelligence Safety and Security · doi:10.1201/9781351251389-8 · Cited by 5,375 · cited 1×
“For example, Reference [60] shows that a nearly-invisible image perturbation can lead a NN to classify an object for another; Reference [81] constructs abstract synthetic images that are classified arbitrarily; Reference [72] finds deconstructed versions of an image that are indistinguishable from the viewpoint of the…”
Background
Research works printed but not linked: 31
- 10.5555/645920.672836 · doi:10.5555/645920.672836
- Mariusz Bojarski, Anna Choromanska, Krzysztof Choromanski, Bernhard Firner, Larry Jackel, Urs Muller, and Karol Zieba. 2016. VisualBackProp: Visualizing CNNs for autonomous driving. CoRR, Vol. abs/1611.05418 (2016). · arXiv
- Leo Breiman, Jerome Friedman, Charles J. Stone, and Richard A. Olshen. 1984. Classification and Regression Trees. CRC Press.
- Carolyn Carter, Elizabeth Renuart, Margot Saunders, and Chi Chi Wu. 2006. The credit card market and regulation: In need of repair. NC Bank. Inst. 10 (2006), 23.
- H. A. Chipman, E. I. George, and R. E. McCulloh. 1998. Making sense of a forest of trees. In Proceedings of the 30th Symposium on the Interface, S. Weisberg (Ed.). Fairfax Station, VA: Interface Foundation of North America, 84--92.
- Paulo Cortez and Mark J. Embrechts. 2011. Opening black box data mining models using sensitivity analysis. In Proceedings of the IEEE Symposium on Computational Intelligence and Data Mining (CIDM’11). IEEE, 341--348.
- 10.5555/3091574.3091580 · doi:10.5555/3091574.3091580
- 10.5555/2998828.2998832 · doi:10.5555/2998828.2998832
- 10.5555/3000292.3000299 · doi:10.5555/3000292.3000299
- Bryce Goodman and Seth Flaxman. 2016. EU regulations on algorithmic decision-making and a “right to explanation.” In Proceedings of the ICML Workshop on Human Interpretability in Machine Learning (WHI’16). Retrieved from http://arxiv. org/abs/1606.08813 v1.
- Riccardo Guidotti, Anna Monreale, Salvatore Ruggieri, Dino Pedreschi, Franco Turini, and Fosca Giannotti. 2018. Local rule-based explanations of black box decision systems. arXiv preprint arXiv:1805.10820 (2018). · arXiv
- U. Johansson, R. König, and L. Niklasson. 2003. Rule extraction from trained neural networks using genetic programming. In Proceedings of the 13th International Conference on Artificial Neural Networks. 13--16.
- 10.5555/3157096.3157352 · doi:10.5555/3157096.3157352
- 10.5555/2969033.2969045 · doi:10.5555/2969033.2969045
- 10.5555/2969442.2969492 · doi:10.5555/2969442.2969492
- Joshua A. Kroll, Joanna Huey, Solon Barocas, Edward W. Felten, Joel R. Reidenberg, David G. Robinson, and Harlan Yu. 2017. Accountable algorithms. U. Penn. Law Rev. 165 (2017), 633--705.
- Will Landecker, Michael D. Thomure, Luís M. A. Bettencourt, Melanie Mitchell, Garrett T. Kenyon, and Steven P. Brumby. 2013. Interpreting individual classifications of hierarchical networks. In Proceedings of the IEEE Symposium on Computational Intelligence and Data Mining (CIDM’13). IEEE, 32--38.
- Dmitry M. Malioutov, Kush R. Varshney, Amin Emad, and Sanjeeb Dash. 2017. Learning interpretable classification rules with boolean compressed sensing. In Transparent Data Mining for Big and Small Data. Springer, 95--121.
- 10.5555/3091825.3091863 · doi:10.5555/3091825.3091863
- 10.5555/3157382.3157477 · doi:10.5555/3157382.3157477
- 10.5555/2717112 · doi:10.5555/2717112
- Michael J. Pazzani, S. Mani, William R. Shankle et al. 2001. Acceptance of rules generated by machine learning among medical experts. Methods Info. Med. 40, 5 (2001), 380--385.
- 10.5555/1597122.1597143 · doi:10.5555/1597122.1597143
- 10.5555/1625015.1625078 · doi:10.5555/1625015.1625078
- 10.5555/152181 · doi:10.5555/152181
- Sameer Singh, Marco Tulio Ribeiro, and Carlos Guestrin. 2016. Programs as black-box explanations. arXiv preprint arXiv:1611.07579 (2016). · arXiv
- Nava Tintarev and Judith Masthoff. 2015. Explaining recommendations: Design and evaluation. In Recommender Systems Handbook, Francesco Ricci, Lior Rokach, and Bracha Shapira (Eds.). Springer, 353--382.
- Marina M.-C. Vidovic, Nico Görnitz, Klaus-Robert Müller, and Marius Kloft. 2016. Feature importance measure for non-linear learning algorithms. arXiv preprint arXiv:1611.07567 (2016). · arXiv
- Tong Wang. 2017. Multi-value rule sets. arXiv preprint arXiv:1710.05257 (2017). · arXiv
- 10.5555/273530.273548 · doi:10.5555/273530.273548
- 10.5555/3045118.3045336 · doi:10.5555/3045118.3045336
Cited by
Items 301–400 of 400
Misztal-Radecka, J., & Indurkhya, B. (2021) · Information Processing & Management · doi:10.1016/j.ipm.2021.102519 · Cited by 29
“Providing intuitions behind the decisions of black-box models has become an active area of research (Guidotti et al., 2018), especially for recommender systems (Tintarev & Masthoff, 2011; Zhang & Chen, 2020).”
Unjustified Classification Regions and Counterfactual Explanations in Machine Learning
Laugel, T., Lesot, M.-J., Marsala, C., Renard, X., & Detyniecki, M. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-46147-8_3 · Cited by 28
“Interfaces for explanations in human-AI interaction: proposing a design evaluation approach,”
Mucha, H., Robert, S., Breitschwerdt, R., & Fellmann, M. (2021) · Extended Abstracts of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411763.3451759 · Cited by 30
“The notion of explaining algorithmic decision making to humans – generally referred to as eXplainable Artificial Intelligence (XAI) [8] [12] [28] [24] – is continuing to move into the scope of recent HCI research efforts.”
An explainable dual-mode convolutional neural network for multivariate time series classification
Cai, W., Zhu, X., Bai, K., Ye, A., & Zhang, R. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.112015 · Cited by 35
Axiomatic Foundations of Explainability
Leila Amgoud, A., & Ben-Naim, J. (2022) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2022/90 · Cited by 32
“This has generated a lot of effort, see [Cyras et al. , 2021; Guidotti et al. , 2019; Miller, 2019; Biran and Cotton, 2017] for surveys on explainers of machine learning models.”
BackgroundA Machine Learning Perspective on fNIRS Signal Quality Control Approaches
Bizzego, A., Neoh, M. J. Y., Gabrieli, G., & Esposito, G. (2022) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2022.3198110 · Cited by 34
“An open issue with DL approaches is the explainability and interpretability of models [52], [53].”
BackgroundA survey on methods and metrics for the assessment of explainability under the proposed AI Act
Sovrano, F., Sapienza, S., Palmirani, M., & Vitali, F. (2021) · Frontiers in Artificial Intelligence and Applications · doi:10.3233/faia210342 · Cited by 27
Explainable Artificial Intelligence Based Heat Recycler Fault Detection in Air Handling Unit
Madhikermi, M., Malhi, A. K., & Främling, K. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-30391-4_7 · Cited by 31
Exploring explainable AI features in the vocal biomarkers of lung disease
Chen, Z., Liang, N., Li, H., Zhang, H., Li, H., Yan, L., Hu, Z., Chen, Y., Zhang, Y., Wang, Y., et al. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.108844 · Cited by 26
Archivist in the machine: paradata for AI-based automation in the archives
Davet, J., Hamidzadeh, B., & Franks, P. (2023) · Archival Science · doi:10.1007/s10502-023-09408-8 · Cited by 26
“(Guidotti et al. 2019) The creation of these black-box solutions is primarily a consequence of the developmental strategies employed and the resultant complexity of modern AI.”
BackgroundCalibrating Human-AI Collaboration: Impact of Risk, Ambiguity and Transparency on Algorithmic Bias
Schmidt, P., & Biessmann, F. (2020) · Lecture Notes in Computer Science · doi:10.1007/978-3-030-57321-8_24 · Cited by 26
“Yet there appears to be no consensus in the community on how the impact of interpretability methods on human-AI interaction should be evaluated [14].”
Knowledge extraction from the learning of sequences in a long short term memory (LSTM) architecture
Kaadoud, I. C., Rougier, N. P., & Alexandre, F. (2021) · Knowledge-Based Systems · doi:10.1016/j.knosys.2021.107657 · Cited by 34
Pan, B., Yao, Z., Wang, M., Pan, H., Bu, L., Kumar, K. R., Gao, H., & Huang, X. (2018) · Advances in Space Research · doi:10.1016/j.asr.2018.07.004 · Cited by 24
“For reviews see the book “Interpretable Machine Learning” [33] and surveys [32, 34–36].”
BackgroundMirzaei, S., Mao, H., Al-Nima, R. R. O., & Woo, W. L. (2023) · Information · doi:10.3390/info15010004 · Cited by 25
“Robust explanations are desired because the user expects the model to behave consistently by generating similar explanations for similar instances [3,6,36,61].”
BackgroundInfluentialDemocratizing Knowledge Creation Through Human-AI Collaboration in Academic Peer Review
Sarker, S., University of Virginia, Susarla, A., Michigan State University, Gopal, R., University of Warwick, Thatcher, J. B., & University of Colorado / University of Manchester (2024) · Journal of the Association for Information Systems · doi:10.17705/1jais.00872 · Cited by 25
Counterfactual Explanation of Machine Learning Survival Models
Kovalev, M. S., Utkin, L. V., Coolen, F. P. A., & Konstantinov, A. V. (2021) · Informatica · doi:10.15388/21-infor468 · Cited by 32
“ver, the corresponding methods are computationally complex when samples are of the high dimensionality. A lot of explanation methods, their analysis, and critical review can be found in survey papers [1, 3, 10, 25, 55, 75]. Most explanation methods deal with the point-valued results produced by explainable black-box m…”
BackgroundMethodKirat, T., Tambou, O., Do, V., & Tsoukiàs, A. (2023) · EURO Journal on Decision Processes · doi:10.1016/j.ejdp.2023.100036 · Cited by 43
A survey of post-hoc xai methods from a visualization perspective: Challenges and opportunities
Bhati, D., Amiruzzaman, M., Zhao, Y., Guercio, A., & Le, T. (2025) · IEEE Access · doi:10.1109/access.2025.3581136 · Cited by 24
“Guidotti et al. [3] provided an early survey on methods for explaining closed box models, outlining various interpretability techniques across rule-based, model-agnostic, and perturbation-based approaches.”
Sarra, C. (2020) · Global Jurist · doi:10.1515/gj-2020-0003 · Cited by 24
Interpretability and Transparency in Artificial Intelligence
Mittelstadt, B. (2022) · Oxford University Press eBooks · doi:10.1093/oxfordhb/9780198857815.013.20 · Cited by 41
In-Time Explainability in Multi-Agent Systems: Challenges, Opportunities, and Roadmap
Alzetta, F., Giorgini, P., Najjar, A., Schumacher, M., & Calvaresi, D. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-51924-7_3 · Cited by 22
“This originated a fer-vent effort in the so-called eXplainable AI (XAI) community, whose priority is to tackle the opacity of behaviors and results stemming from ML-based systems [1,4,20,24,35].”
BackgroundMeasurable Counterfactual Local Explanations for Any Classifier
Adam, W., & Artur, D. G. (2020) · Frontiers in Artificial Intelligence and Applications · doi:10.3233/faia200387 · Cited by 68
Constitutional Rights in the Machine Learning State
Huq, A. Z. (2020) · doi:10.2139/ssrn.3613282 · Cited by 21
Interpretable Multimodal Deception Detection in Videos
Karimi, H. (2018) · INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION · doi:10.1145/3242969.3264967 · Cited by 22
“Interpretability of audio data is an untouched territory [13] and will be one of the integral parts of my Ph.D. research investigation.”
BackgroundContrastive Explanations with Local Foil TreesPreprint
van der Waa, J., Robeer, M., van Diggelen, J., Brinkhuis, M. J. S., & Neerincx, M. A. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1806.07470 · Cited by 81
“See for example for an overview the review papers of Guidotti et al. (2018) and Chakraborty et al. (2017).”
BackgroundRichet, J.-L. (2025) · Journal of Innovation & Knowledge · doi:10.1016/j.jik.2025.100835 · Cited by 20
Wikipedia Knowledge Graph for Explainable AI
Sarker, M. K., Schwartz, J., Hitzler, P., Zhou, L., Nadella, S., Minnery, B. S., Juvina, I., Raymer, M. L., & Aue, W. R. (2020) · Communications in computer and information science · doi:10.1007/978-3-030-65384-2_6 · Cited by 26
“The research area explainable AI (XAI) [8,7,16] investigates techniques to examine these decision processes.”
BackgroundExplainable AI applications in the Medical Domain: a systematic review
Prentzas, N., Kakas, A., & Pattichis, C. S. (2023) · arXiv · doi:10.48550/arxiv.2308.05411 · Cited by 19
Mehdiyev, N., Houy, C., Gutermuth, O., Mayer, L., & Fettke, P. (2021) · Lecture notes in information systems and organisation · doi:10.1007/978-3-030-86790-4_28 · Cited by 35
Explaining Multi-label Black-Box Classifiers for Health Applications
Panigutti, C., Guidotti, R., Monreale, A., & Pedreschi, D. (2019) · Studies in computational intelligence · doi:10.1007/978-3-030-24409-5_9 · Cited by 25
Self-citationInterpretability of Machine Learning Solutions in Industrial Decision Engineering
Kolyshkina, I., & Simoff, S. J. (2019) · Communications in computer and information science · doi:10.1007/978-981-15-1699-3_13 · Cited by 20
Explainability Pitfalls: Beyond Dark Patterns in Explainable AI
Ehsan, U., & Riedl, M. O. (2021) · arXiv · doi:10.48550/arxiv.2109.12480 · Cited by 99
Risk and Exposure of XAI in Persuasion and Argumentation: The case of Manipulation
Carli, R., Najjar, A., & Calvaresi, D. (2022) · Lecture Notes in Computer Science · doi:10.1007/978-3-031-15565-9_13 · Cited by 18
Question-Driven Design Process for Explainable AI User Experiences
Liao, Q. V., Pribić, M., Han, J., Miller, S., & Sow, D. (2021) · arXiv · doi:10.48550/arxiv.2104.03483 · Cited by 18
“More fine-grained classification methods consider the formats of the explanation, which could range from less than 10 [30] to more than 40 types [11], each of which could be implemented by multiple algorithms that differ in computational properties.”
InfluentialGridEx: An Algorithm for Knowledge Extraction from Black-Box Regressors
Sabbatini, F., Ciatto, G., & Omicini, A. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-82017-6_2 · Cited by 30
Actionable Interpretability through Optimizable Counterfactual Explanations for Tree Ensembles.Preprint
Lučić, A., Oosterhuis, H., Haned, H., & de Rijke, M. (2019) · arXiv (Cornell University) · Cited by 18
Lee, L. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4799209 · Cited by 57
Introduction to Explainable AI
Liao, Q. V., Singh, M., Zhang, Y., & Bellamy, R. (2020) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3334480.3375044 · Cited by 16
“We will discuss the core topics in the current XAI research field [3, 6], including different types of explanation, desiderata of explainability, and recent trends in the HCI field regarding user interaction and usability of AI explanations (e.g., [1, 4]).”
MethodProposed Guidelines for the Responsible Use of Explainable Machine Learning
Hall, P., Gill, N., & Schmidt, N. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1906.03533 · Cited by 15
“[17]), “The Mythos of Model Interpretability” (Lipton [24]), Interpretable Machine Learning (Molnar [27]), “Interpretable Machine Learning: Definitions, Methods, and Applications” (Murdoch et al.”
Data Science Methods for Real-World Evidence Generation in Real-World Data
Liu, F. (2024) · Annual Review of Biomedical Data Science · doi:10.1146/annurev-biodatasci-102423-113220 · Cited by 16
Distillation of weighted automata from recurrent neural networks using a spectral approach
Eyraud, R., & Ayache, S. (2021) · Machine Learning · doi:10.1007/s10994-021-05948-1 · Cited by 23
“One usual path followed to tackle this issue is called local interpretability [Guidotti et al., 2018].”
Towards Incorporating Human Knowledge in Fuzzy Pattern Tree Evolution
Murphy, A., Murphy, G., Amaral, J. L. M., Dias, D. M., Naredo, E., & Ryan, C. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-72812-0_5 · Cited by 14
“Papers and conference talks in the area of XAI and computer model interpretability has grown and is continuing to grow rapidly [1,13].”
BackgroundWhat Does It Mean to Explain? A User-Centered Study on AI Explainability
Yang, L., Wang, H., & Deleris, L. A. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-77772-2_8 · Cited by 20
Tang, X., Shen, X., Wang, Y., & Yu-juan, Y. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-63031-7_22 · Cited by 24
“Nowadays, a large amount of explanation methods [Guidotti et al.2018, Olah et al.2017, Ancona et al.2017, Koh and Liang2017,Ribeiro et al.2016] have been proposed to reveal the behavior of deep neural networks.”
BackgroundAdvancing financial risk management: A transparent framework for effective fraud detection
Li, W., Liu, X., Su, J., & Cui, T. (2025) · Finance research letters · doi:10.1016/j.frl.2025.106865 · Cited by 29
Risk mitigation in algorithmic accountability: The role of machine learning copies
Unceta, I., Nin, J., & Pujol, O. (2020) · PLoS ONE · doi:10.1371/journal.pone.0241286 · Cited by 15
“The problem of copying can also be understood as a form of reverse engineering, as discussed in [83], where observations about the input and the output of a blackbox are used to infer its inner working.”
BackgroundMethodWhy Should I Trust This Item? Explaining the Recommendations of any Model
Lonjarret, C., Robardet, C., Plantevit, M., Auburtin, R., & Atzmueller, M. (2020) · IEEE International Conference on Data Science and Advanced Analytics (DSAA) · doi:10.1109/dsaa49011.2020.00067 · Cited by 13
“Recently, the concept of transparent and explainable models has gained a strong focus and momentum in the data mining and machine learning community, specifically regarding model-agnostic explanations e. g., [4], [9], [15], [23].”
BackgroundJeon, Y., Jeon, S. G., & Han, K. (2020) · User Modeling and User-Adapted Interaction · doi:10.1007/s11257-020-09260-w · Cited by 17
“While some have tried to understand and explain DNN (Montavon et al. 2018; Guidotti et al. 2018), the process to understand the interpretability of DNN is in relation to identifying the importance of its layers (filters).”
BackgroundContrastive Explanations to Classification Systems Using Sparse Dictionaries
Apicella, A., Isgrò, F., Prevete, R., & Tamburrini, G. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-30642-7_19 · Cited by 17
DOME: recommendations for supervised machine learning validation in biology
Walsh, I., Fishman, D., Garcia-Gasulla, D., Titma, T., Pollastri, G., ELIXIR Machine Learning Focus Group, Capriotti, E., Casadio, R., Capella-Gutierrez, S., Cirillo, D., et al. (2021) · Nature Methods · doi:10.1038/s41592-021-01205-4 · Cited by 282
Transparency and Explainability for Public Policy
Vredenburgh, K. (2024) · LSE Public Policy Review · doi:10.31389/lseppr.111 · Cited by 20
Even If Explanations: Prior Work, Desiderata & Benchmarks for Semi-Factual XAI
Aryal, S., & Keane, M. T. (2023) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2023/732 · Cited by 34
Human-in-the-loop machine learning with applications for population health
Chen, L., Wang, J., Guo, B., & Chen, L. (2022) · CCF Transactions on Pervasive Computing and Interaction · doi:10.1007/s42486-022-00115-4 · Cited by 38
“More extensive review can be found in the survey (Riccardo et al. 2019).”
BackgroundFreitas, A. A. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-29726-8_4 · Cited by 32
“Note that it is possible to extract interpretable knowledge from a black box model [9],”
BackgroundAn Empirical Comparison of Interpretable Models to Post-Hoc Explanations
Mahya, P., & Fürnkranz, J. (2023) · AI · doi:10.3390/ai4020023 · Cited by 17
“The necessity of having some explanations to understand how the model works led to substantial research on explaining learned models [1].”
BackgroundInterpretable Knowledge Tracing via Response Influence-based Counterfactual Reasoning
Cui, J., Yu, M., Jiang, B., Zhou, A., Wang, J., & Zhang, W. (2024) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde60146.2024.00090 · Cited by 33
“Nevertheless, researchers have continued to propose new machine learning-based KT methods that achieve comparable performance to DLKT methods.”
BackgroundHauser, J. R., Li, Z., & Mao, C. (2023) · Emerald Group Publishing Limited eBooks · doi:10.1108/s1548-643520230000020007 · Cited by 12
Model Doctor: A Simple Gradient Aggregation Strategy for Diagnosing and Treating CNN Classifiers
Feng, Z., Hu, J., Wu, S., Yu, X., Song, J., & Song, M. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i1.19941 · Cited by 17
Coarse ethics: how to ethically assess explainable artificial intelligence
Izumo, T., & Weng, Y.-H. (2021) · AI and Ethics · doi:10.1007/s43681-021-00091-y · Cited by 14
“Thereafter, diverse models were proposed as surveyed by Arrieta et al. [2], Guidotti et al. [17], Hall [20] and Molnar [36].”
Ensemble of Counterfactual Explainers
Guidotti, R., & Ruggieri, S. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-88942-5_28 · Cited by 20
Self-citationGlobal Explanations with Local Scoring
Setzu, M., Guidotti, R., Monreale, A., & Turini, F. (2020) · Communications in computer and information science · doi:10.1007/978-3-030-43823-4_14 · Cited by 20
Self-citationKanakaris, N., Karacapilidis, N. I., Κουρνέτας, Γ., et al. (2019) · Communications in computer and information science · doi:10.1007/978-3-030-37584-3_7 · Cited by 11
A Historical Perspective on Cognitive Science and Its Influence on XAI Research
Westberg, M., Zelvelder, A. E., & Najjar, A. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-30391-4_12 · Cited by 17
An Explainable Machine Learning Model for Early Prediction of Sepsis Using ICU Data
Nesaragi, N., & Patidar, S. (2021) · Infections and Sepsis Development · doi:10.5772/intechopen.98957 · Cited by 11
Explaining the Suspicion: Design of an XAI-Based User-Focused Anti-Phishing Measure
Kluge, K., & Eckhardt, R. (2021) · Lecture notes in information systems and organisation · doi:10.1007/978-3-030-86797-3_17 · Cited by 14
ALEEDSA: Augmented Reality for Interactive Machine Learning
Ferrario, A., Weibel, R. P., & Feuerriegel, S. (2020) · CHI Conference Extended Abstracts on Human Factors in Computing Systems (CHI EA) · doi:10.1145/3334480.3382937 · Cited by 10
“There have been a few attempts to extend these visualizations via interactive elements [8, 7], and yet the potential of AR has remained untapped.”
BackgroundAn Argumentation-Based Approach to Generate Domain-Specific Explanations
Kökciyan, N., Parsons, S., Sassoon, I. K., et al. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-66412-1_20 · Cited by 10
Sparse Robust Regression for Explaining Classifiers
Björklund, A., Henelius, A., Oikarinen, E., Kallonen, K. T. S., & Puolamäki, K. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-33778-0_27 · Cited by 10
Meaningful Data Sampling for a Faithful Local Explanation Method
Rasouli, P., & Yu, I. C. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-33607-3_4 · Cited by 17
Adversarial NLI for Factual Correctness in Text Summarisation Models
Barrantes, M., Herudek, B., & Wang, R. (2020) · arXiv · doi:10.48550/arxiv.2005.11739 · Cited by 10
“There is a body of research about interpreting neural networks (Doshi-Velez and Kim, 2017), (Molnar, 2019), (Guidotti et al., 2018).”
BackgroundSevillano-García, I., Luengo, J., & Herrera, F. (2023) · International Journal of Intelligent Systems · doi:10.1155/2023/8068569 · Cited by 10
Iudicium ex Machinae: The Ethical Challenges of ADM at Sentencing
Thomsen, F. K. (2022) · Oxford University Press eBooks · doi:10.1093/oso/9780197539538.003.0013 · Cited by 11
Revina, A., Búza, K., & Meister, V. G. (2021) · Studies in computational intelligence · doi:10.1007/978-3-030-64949-4_10 · Cited by 14
Quality estimation of magnetotelluric impedance tensors using neural networks
Imamura, N., & Schultz, A. (2020) · The Leading Edge · doi:10.1190/tle39100702.1 · Cited by 9
Visualization of Convolutional Neural Networks for Monocular Depth EstimationPreprint
Hu, J., Zhang, Y., & Okatani, T. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1904.03380 · Cited by 9
“However, there are only a few methods that have been recognized to be practically useful in the community [11, 20, 21].”
BackgroundConceptual Explanations of Neural Network Prediction for Time Series
Kusters, F., Schichtel, P., Ahmed, S., & Dengel, A. (2020) · 2020 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn48605.2020.9207341 · Cited by 8
“Explainability of DNNs is an active field of research and a variety of interpretation methods have been proposed [3].”
BackgroundKlüver, C., Greisbach, A., Kindermann, M., & Püttmann, B. (2024) · Security and Safety · doi:10.1051/sands/2024020 · Cited by 8
“It can refer to the functioning of the entire model ( global xAI ) or to the explanation of the background of a specific decision ( local xAI ) [47–49].”
Raees, M., Khan, V.-J., Lykourentzou, I., & Papangelis, K. (2026) · Proceedings of the 2026 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3772318.3791467 · Cited by 5
“The literature on human-centered explainable AI (XAI) either advocates for transparent models or enhancing the interpretations of opaque models [50, 56].”
InfluentialWang, C., & An, P. (2021) · Extended Abstracts of the 2021 Annual Symposium on Computer-Human Interaction in Play · doi:10.1145/3450337.3483487 · Cited by 6
“Regarding the HOW in XAI, Guidotti et al [7] and Arrieta et al [3] suggested a general distinction between transparent models and post-hoc explainability.”
MethodKarahan, S. N., Güllü, M., Karhan, D., Çimen, S., Osmanca, M. S., & Barışçı, N. (2025) · Electronics · doi:10.3390/electronics14193841 · Cited by 6
A Risk Evaluation Framework in System Control Subject to Sensor Degradation and Failure
Yuan, T., Xu, W., Adjallah, K. H., Wang, H., Liu, L., & Xu, J. (2024) · Sensors · doi:10.3390/s24051550 · Cited by 6
“In particular, when decision models are developed by third parties, users are unable to understand the specific operational mechanisms inside the box, leading to low interpretability and a lack of trust from users [5].”
BackgroundAI-driven data governance for smart cities: balancing privacy, efficiency, and public trust
Mastrogiovanni, S. (2025) · South Florida Journal of Development · doi:10.46932/sfjdv6n9-029 · Cited by 5
Understanding the Interpretability of Search Result Summaries
Mi, S., & Jiang, J. (2019) · Proceedings of the 42nd International ACM SIGIR Conference on Research and Development in Information Retrieval · doi:10.1145/3331184.3331306 · Cited by 5
“Despite many discussions of explainable AI and machine learning recently [3, 4, 9, 11, 13], few previous work explicitly examined the interpretability of search results.”
ResultDe la Torre-Trillo, J., Yáñez Castillo, Y., Melgarejo Segura, M. T., Carmona Sánchez, E., Zambudio Munuera, A., Mora-Delgado, J., & López Luque, A. (2026) · Journal of Clinical Medicine · doi:10.3390/jcm15062130 · Cited by 5
“First, ChatGPT’s internal logic and data sources remain opaque, precluding transparent verification of its clinical reasoning (the “black box” issue) [29,30].”
Porębski, A. (2023) · Research Handbook on Law and Technology · doi:10.4337/9781803921327.00037 · Cited by 4
A bias detection tree approach for detecting disparities in a recommendation model’s errors
Misztal-Radecka, J., & Indurkhya, B. (2023) · User Modeling and User-Adapted Interaction · doi:10.1007/s11257-022-09334-x · Cited by 4
“In such cases, the exact functioning of the algorithm remains unknown, and it is not possible to use a transparent-box design approach to provide explainability (Guidotti et al. 2018).”
BackgroundMethodInfluentialExploring the impact of classification probabilities on users' trust in ambiguous instances
Dos Santos Ribeiro, D., Barbosa, G. D. J., Do Carmo Silva, M., Lopes, H., & Barbosa, S. D. J. (2021) · 2021 IEEE Symposium on Visual Languages and Human-Centric Computing (VL/HCC) · doi:10.1109/vl/hcc51201.2021.9576291 · Cited by 4
Benchmarking Trust: A Metric for Trustworthy Machine Learning
Rutinowski, J., Klüttermann, S., Endendyk, J., Reining, C., & Müller, E. (2024) · Communications in Computer and Information Science · doi:10.1007/978-3-031-63787-2_15 · Cited by 4
“Researchers agree that its use is quite ambiguous and that the term is often used synonymously with other terms such as transparency, intelligibility, comprehensibility, and interpretability [1,6,16,42,48].”
(2019) · Cited by 3
Are numerical or verbal explanations of AI the key to appropriate user reliance and error detection?
Papenkordt, J., Ngonga Ngomo, A.-C., & Thommes, K. (2026) · Behaviour & Information Technology · doi:10.1080/0144929x.2025.2568928 · Cited by 2
“However, even after decades of research, we still do not know what constitutes an accurate and understandable explanation for users (Guidotti et al. 2018; Rohlfing et al. 2021; Vilone and Longo 2021).”
InfluentialDíaz-Rodríguez, N., Lamas, A., Sanchez, J., Franchi, G., Donadello, I., Tabik, S., Filliat, D., Cruz, P., Montes, R., & Herrera, F. (2022) · Information Fusion · doi:10.1016/j.inffus.2021.09.022 · Cited by 2
A brief Review on the Role of Context in Explainable AI
Baruah, R. D., & Organero, M. M. (2024) · 2024 IEEE International Conference on Evolving and Adaptive Intelligent Systems (EAIS) · doi:10.1109/eais58494.2024.10570037 · Cited by 2
“Broadly, the existing literature [7], [8] provides two perspectives on explainability: • The first perspective focuses on understanding the inner workings and functionality of black-box models.”
BackgroundAnomaly detection and root-cause identification in microservices: a survey
Barata, L. M., Sequeira, S., Lopes, E., Inácio, P. R. M., & Freire, M. M. (2026) · Cluster Computing · doi:10.1007/s10586-026-06095-9 · Cited by 4
“Prior research in anomaly detection [22], interpretable machine learning [242, 244, 245], robustness evaluation [53], and causal inference [52, 246] provides conceptual foundations for operationalizing trust in intelligent systems.”
Outlining Traceability: A Principle for Operationalizing Accountability in Computing Systems
Kroll, J. A. (2021) · Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3442188.3445937 · Cited by 2
“This requires thinking beyond the current focus on explainability and causality in AI [77, 78, 109, 117, 174] and a push toward ty-”
BackgroundPe, S., Bergomi, L., Nicora, G., Simonelli, C. A., Kour, P., Diaz, E., Alendal, G., Hernáiz Ferrer, A. I., Corso, V., Bortolotto, C., et al. (2026) · Machine Learning and Knowledge Extraction · doi:10.3390/make8070216
“A natural response to these concerns has been the growing adoption of explainable AI methods [7,8].”
L'acte administratif algorithmique
Stepanov, A. (2026) · doi:10.70675/adc05be3za62ez4b4fz81e7zabf744e60dbf
Explainable and Interpretable AI for Voice and Speech Analysis in Clinical Care: Systematic Review
Ebraheem, M., Toghranegar, J., Bridge2AI-Voice Consortium, Bensoussan, Y., & Templeton, J. M. (2026) · Journal of Medical Internet Research · doi:10.2196/83790
“As existing surveys of XAI demonstrate a lack of consensus on a unified XAI taxonomy, we adopted a set of commonly used XAI method categories reported across prior surveys and taxonomy literature, including work in medical XAI [77-79].”
Santana-Velásquez, A., & Salazar-Sánchez, M. B. (2026) · Computers · doi:10.3390/computers15080506
Explainable AI for employee turnover prediction: a SHAP-based intelligent analytics approach
Jia, H. (2026) · Scientific Reports · doi:10.1038/s41598-026-60901-3
AI in Control: Rethinking Cybersecurity Compliance and Auditing
Loumachi, F. Y., Lacerda, M., Ouazzane, K., Adnane, A., & Adamyk, O. (2025) · doi:10.2139/ssrn.5731707
Metadata
- Authors
- Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., & Pedreschi, D.
- Affiliations
- University of Pisa (IT)
- Istituto di Scienza e Tecnologie dell'Informazione "Alessandro Faedo" (IT)
- Venue
- ACM Computing Surveys
- Published
- 2018-08-22
- Volume
- 51
- Issue
- 5
- Pages
- 1-42
- ISSN
- 0360-0300 (ISSN-L)
- 1557-7341
- OpenAlex
- W2786715987
- Cited by
- 629
- References
- 121
- Citations by year
- 2026: 3 · 2025: 62 · 2024: 82 · 2023: 86 · 2022: 92 · 2021: 145 · 2020: 105 · 2019: 40 · 2018: 13
- FWCI
- 42.69
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Locations
- ACM Computing Surveys (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- CINECA IRIS Institutial research information system (University of Pisa) (submittedVersion, other-oa)
- Scuola Normale Superiore di Pisa (submittedVersion, public-domain)
- arXiv (Cornell University)
- Funders
- Horizon 2020 Framework Programme (-2014-2015, 654024)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Software › Software Testing and Debugging Techniques
- Physical Sciences › Computer Science › Information Systems › Data Mining Algorithms and Applications
- Keywords
- explainable AI, black-box models, interpretability, decision support system, explanation methods, model transparency
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.
A language model drew the claims from the paper on 2026-10-04, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-04 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
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.