CoChat
Sign Up
Cited by 87Explainable Artificial Intelligence (XAI)Philosophy of Biology and Scientific ExplanationEthics and Social Impacts of AI

The DOI matches its Crossref record; 27 of the 27 references it cites were found in a registry or an index.

Conceptual challenges for interpretable machine learning

Open access
Watson, David S.·2022·Synthese
DOI 10.1007/s11229-022-03485-5
Open this paper in CoChat — free accountOpen PDF

Abstract

As machine learning has gradually entered into ever more sectors of public and private life, there has been a growing demand for algorithmic explainability. How can we make the predictions of complex statistical models more intelligible to end users? A subdiscipline of computer science known as interpretable machine learning (IML) has emerged to address this urgent question. Numerous influential methods have been proposed, from local linear approximations to rule lists and counterfactuals. In this article, I highlight three conceptual challenges that are largely overlooked by authors in this area. I argue that the vast majority of IML algorithms are plagued by (1) ambiguity with respect to their true target; (2) a disregard for error rates and severe testing; and (3) an emphasis on product over process. Each point is developed at length, drawing on relevant debates in epistemology and philosophy of science. Examples and counterexamples from IML are considered, demonstrating how failure to acknowledge these problems can result in counterintuitive and potentially misleading explanations. Without greater care for the conceptual foundations of IML, future work in this area is doomed to repeat the same mistakes.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1007/s11229-022-03485-5

Cites

27 of 27 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

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?

  • On a theoretical level, many gradient-based attribution methods identify only a first-order approximation of the ideal attribution, which is sometimes a poor approximation.

    “However, on a theoretical level, many gradientbased methods identify only a first-order approximation of the ideal attribution, which is sometimes a poor approximation (Watson, 2022).”

    From Open Problems in Mechanistic Interpretability (2025) · cites this paper as Watson, 2022

    Section 4.2.1 (“How local is ‘local’?”; page unavailable) says local linear approximations can become unreliable when the model is highly nonlinear. It discusses approximators such as LIME and SHAP, but does not establish that many gradient-based attribution methods provide only a first-order approximation of an ideal attribution. (LLM, conf=0.84)

    Experimental — accuracy not yet measured

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

Flagged first, then by citations

Research works printed but not linked: 134

  1. Aas, K., Jullum, M., & Løland, A. (2021). Explaining individual predictions when features are dependent: More accurate approximations to Shapley values. Artificial Intelligence, 298, 103502. · DOI
  2. Achinstein, P. (1983). The nature of explanation. Oxford University Press.
  3. Akula, R. A., Todorovic, S., Chai, Y. J., & Zhu, S.-C. (2019). Natural language interaction with explainable ai models. In: Proceedings of the IEEE/CVF conference on computer vision and pattern recognition (CVPR) workshops.
  4. Altmann, A., Toloşi, L., Sander, O., & Lengauer, T. (2010). Permutation importance: A corrected feature importance measure. Bioinformatics, 26(10), 1340–1347. · DOI
  5. Austin, J. L. (1961). Philosophical papers (J. O. Urmson & G. J. Warnock, Eds.). Oxford: Clarendon Press.
  6. Bandyopadhyay, P. S., & Forster, M. R. (Eds.). (2011). Philosophy of statistics. Elsevier.
  7. Berger, J. (2006). The case for objective Bayesian analysis. Bayesian Analysis, 1(3), 385–402.
  8. Berkeley, G. (1979). Three dialogues between hylas and philonous (R. M. Adams, Ed.). Indianapolis: Hackett.
  9. Bhatt, U., Xiang, A., Sharma, S., Weller, A., Taly, A., Jia, Y., Eckersley, P. (2020). Explainable machine learning in deployment. In: Proceedings of the conference on fairness, accountability, and transparency (pp. 648–657). · DOI · Paper page
  10. Breiman, L. (2001). Statistical modeling: The two cultures. Statistical Science, 16(3), 199–231. · DOI · Paper page
  11. Bromberger, S. (1966). Why questions. In R. Colodny (Ed.), Mind and cosmos: Essays in contemporary science and philosophy. Pittsburgh: University of Pittsburgh Press.
  12. Canetti, R., Cohen, A., Dikkala, N., Ramnarayan, G., Scheffler, S., & Smith, A. (2019). From soft classifiers to hard decisions: How fair can we be? In: Proceedings of the conference on fairness, accountability, and transparency (pp. 309–318). · DOI
  13. Creel, K. A. (2020). Transparency in complex computational systems. Phil. Sci., 87(4), 568–589. · DOI
  14. Das, A., & Rad, P. (2020). Opportunities and challenges in explainable artificial intelligence (XAI): A survey. arXiv preprint, 2006.11371. · arXiv
  15. Datta, A., Sen, S., & Zick, Y. (2016). Algorithmic transparency via quantitative input influence: Theory and experiments with learning systems. In: Proceedings of the IEEE symposium on security and privacy (pp. 598–617). · DOI · Paper page
  16. Datta, A., Fredrikson, M., Ko, G., Mardziel, P., & Sen, S. (2017). Proxy non-discrimination in data-driven systems. arXiv preprint, 1707.08120. · DOI
  17. Dawid, A. P. (2000). Causal inference without counterfactuals. Journal of American Statistical Association, 95(450), 407–424. · DOI
  18. Deaton, A., & Cartwright, N. (2018). Understanding and misunderstanding randomized controlled trials. Social Science and Medicine, 210, 2–21. · DOI · Paper page
  19. Doran, G., Muandet, K., Zhang, K., & Schölkopf, B. (2014). A Permutation-based kernel conditional independence test. In: Proceedings of the 13th conference on uncertainty in artificial intelligence, (pp. 132–141).
  20. Dowe, P. (2000). Physical causation. Cambridge University Press. · DOI
  21. Duhem, P. (1954). The aim and structure of physical theory (P. W. Wiener, Ed.). Princeton, NJ: Princeton University Press. · DOI · Paper page
  22. Earman, J. (1992). Bayes or Bust? A critical examination of bayesian confirmation theory. The MIT Press.
  23. Eberhardt, F. (2010). Causal discovery as a game. In: Proceedings of NIPS workshop on causality (pp. 87–96).
  24. Efron, B. (2010). Large-scale inference: Empirical bayes methods for estimation, testing, and prediction. Cambridge University Press. · DOI
  25. Feyerabend, P. (1975). Against Method. New Left Books.
  26. Fisher, A., Rudin, C., & Dominici, F. (2019). All models are wrong, but many are useful: Learning a variable’s importance by studying an entire class of prediction models simultaneously. Journal of Machine Learning Research, 20(177), 1–81.
  27. Fisher, R. A. (1925). Statistical methods for research workers. Oliver & Boyd.
  28. Fisher, R. A. (1935). The design of experiments. Oliver & Boyd.
  29. Floridi, L. (2011). Semantic information and the correctness theory of truth. Erkenntnis, 74(2), 147–175. · DOI
  30. Friedman, J. H. (2001). Greedy function approximation: A gradient boosting machine. Annals of Statistics, 29(5), 1189–1232. · DOI · Paper page
  31. Frye, C., Feige, I., & Rowat, C. (2020). Asymmetric Shapley values: Incorporating causal knowledge into model-agnostic explainability. Advances in Neural Information Processing Systems, pp. 1229–1239.
  32. Fukumizu, K., Gretton, A., Sun, X., & Schölkopf, B. (2008). Kernel measures of conditional dependence. Advances in Neural Information Processing Systems, pp. 489–496.
  33. Galhotra, S., Pradhan, R., & Salimi, B. (2021). Explaining black-box algorithms using probabilistic contrastive counterfactuals. In: Proceedings of the international conference on management of data (pp. 577–590). · DOI
  34. Gelman, A., & Carlin, J. (2014). Beyond power calculations: Assessing type S (sign) and type M (magnitude) errors. Perspectives on Psychological Science, 9(6), 641–651. · DOI · Paper page
  35. Gimenez, J. R., & Zou, J. (2019). Discovering conditionally salient features with statistical guarantees. In: Proceedings of the 36th international conference on machine learning (pp. 2290–2298).
  36. Goldman, A. (1979). What is justified belief? In G. S. Pappas (Ed.), Justification and Knowledge (pp. 1–25). Reidel.
  37. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep Learning. MIT Press.
  38. Greenland, S. (2019). Valid p-values behave exactly as they should: Some misleading criticisms of p-values and their sesolution with s-values. American Statistician, 73(sup1), 106–114. · DOI
  39. Gregorutti, B., Michel, B., & Saint-Pierre, P. (2015). Grouped variable importance with random forests and application to multiple functional data analysis. Computational Statistics & Data Analysis, 90, 15–35. · DOI
  40. Grice, P. (1989). Studies in the way of words. Harvard University Press.
  41. Guedj, B. (2019). A Primer on PAC-Bayesian Learning. arXiv preprint, 1901.05353. · arXiv
  42. Heaton, J. B., Polson, N. G., & Witte, J. H. (2017). Deep learning for finance: Deep portfolios. Applied Stochastic Models in Business and Industry, 33(1), 3–12. · DOI
  43. Heinze-Deml, C., Peters, J., & Meinshausen, N. (2018). Invariant causal prediction for nonlinear models. Journal of Causal Inference, 6(2), 20170016. · DOI
  44. Hempel, C. (1965). Aspects of scientific explanation and other essays in the philosophy of science. Free Press.
  45. Hintikka, J. (1999). Inquiry as inquiry: A logic of scientific discovery. Springer. · DOI
  46. Hodges, W., & Väänänen, J. (2019). Logic and Games. In E. N. Zalta (Ed.), The stanford encyclopedia of philosophy (Fall 2019). Metaphysics Research Lab, Stanford University.
  47. Hooker, G., & Mentch, L. (2019). Please stop permuting features: An explanation and alternatives. arXiv preprint, 1905.03151. · arXiv
  48. Hume, D. (1739). A treatise of human nature (L. A. Selby-Bigge & P. H. Nidditch, Eds.). Oxford: Clarendon Press. · DOI
  49. Hume, D. (1748). An enquiry concerning human understanding. Oxford: Oxford University Press.
  50. Janzing, D., Minorics, L., & Bloebaum, P. (2020). Feature relevance quantification in explainable AI: A causal problem. In: Proceedings of the 23rd international conference on artificial intelligence and statistics (pp. 2907–2916).
  51. Jaynes, E. T. (2003). Probability theory: The logic of science (G. L. Bretthorst, Ed.). Cambridge: Cambridge University Press. · DOI · Paper page
  52. Jung, C., Kearns, M., Neel, S., Roth, A., Stapleton, L., & Wu, Z. S. (2019). Eliciting and enforcing subjective individual fairness. arXiv preprint, 1905.10660. · arXiv
  53. Kaptchuk, T. J. (2001). The double-blind, randomized, placebo-controlled trial: Gold standard or golden calf? Journal of Clinical Epidemiology, 54(6), 541–549. · DOI · Paper page
  54. Karimi, A.-H., Barthe, G., Schölkopf, B., & Valera, I. (2020). A survey of algorithmic recourse: Definitions, formulations, solutions, and prospects. arXiv preprint, 2010.04050. · arXiv
  55. Keiff, L. (2011). Dialogical logic. In E. N. Zalta (Ed.), The Stanford Encyclopedia of Philosophy (Summer 201). Metaphysics Research Lab, Stanford University.
  56. Kitcher, P. (1989). Explanatory unification and the causal structure of the world. In P. Kitcher & W. Salmon (Eds.), Scientific explanation (pp. 410–505). University of Minnesota Press.
  57. Mothilal, R. K., Mahajan, D., Tan, C., & Sharma, A. (2021). Towards unifying feature attribution and counterfactual explanations: Different means to the same end. In Proceedings of the 2021 AAAI/ACM conference on AI, ethics, and society (pp. 652–663). · DOI
  58. Krishnan, M. (2020). Against interpretability: A critical examination of the interpretability problem in machine learning. Philosophy & Technology, 33(3), 487–502. · DOI
  59. Kuhn, T. S. (1970). The structure of scientific revolutions. University of Chicago Press.
  60. Kyburg, H. (1992). The scope of Bayesian reasoning. PSA: Proceedings of the Biennial Meeting of the Philosophy of Science Association, 2, 139–152.
  61. Lakkaraju, H., Kamar, E., Caruana, R., & Leskovec, J. (2019). Faithful and customizable explanations of black box models. In: Proceedings of the 2019 AAAI/ACM conference on AI, ethics, and society, pp. 131–138. · DOI
  62. Lakkaraju, H., & Bastani, O. (2020). “How do I fool you?”: Manipulating user trust via misleading black box explanations. In:Proceedings of the AAAI/ACM conference on ai, ethics, and society, pp. 79–85. · DOI · Paper page
  63. Lehmann, E. L., & Romano, J. P. (2005). Testing Statistical Hypotheses (3rd ed.). Springer.
  64. Lei, J., G’Sell, M., Rinaldo, A., Tibshirani, R. J., & Wasserman, L. (2018). Distribution-free predictive inference for regression. Journal of American Statistical Association, 113(523), 1094–1111. · DOI · Paper page
  65. Lewis, D. (1973). Counterfactuals. Blackwell.
  66. Lin, W., Wu, Z., Lin, L., Wen, A., & Li, J. (2017). An ensemble random forest algorithm for insurance big data analysis. IEEE Access, 5, 16568–16575. · DOI
  67. Lundberg, S. M., & Lee, S.-I. (2017). A unified approach to interpreting model predictions. Advances in Neural Information Processing Systems, pp. 4765–4774.
  68. Mayo, D. G. (1996). Error and the growth of experimental knowledge. University of Chicago Press. · DOI · Paper page
  69. Mayo, D. G., & Spanos, A. (2004). Methodology in practice: Statistical misspecification testing. Philosophy in Science, 71(5), 1007–1025. · DOI
  70. Mayo, D. G., & Spanos, A. (2006). Severe testing as a basic concept in a Neyman–Pearson philosophy of induction. The British Journal for the Philosophy of Science, 57(2), 323–357. · DOI
  71. Mentch, L., & Hooker, G. (2016). Quantifying uncertainty in random forests via confidence intervals and hypothesis tests. Journal of Machine Learning Research, 17(1), 841–881.
  72. Mittelstadt, B., Russel, C., & Wachter, S. (2019). Explaining explanations in AI. In: Proceedings of the conference on fairness, accountability, and transparency. · DOI · Paper page
  73. Molnar, C. (2019). Interpretable machine learning: A guide for making black box models interpretable. Münich: Christoph Molnar.
  74. Moulin, B., Irandoust, H., Bélanger, M., & Desbordes, G. (2002). Explanation and argumentation capabilities: Towards the creation of more persuasive agents. Artificial Intelligence Review, 17(3), 169–222. · DOI
  75. Nembrini, S., König, I. R., & Wright, M. N. (2018). The revival of the Gini importance? Bioinformatics, 34(21), 3711–3718. · DOI
  76. Neyman, J., & Pearson, E. S. (1933). On the problem of the most efficient tests of statistical hypotheses. Philosophical Transactions of the Royal Society A, 231(694–706), 289–337.
  77. Nicodemus, K. K., Malley, J. D., Strobl, C., & Ziegler, A. (2010). The behaviour of random forest permutation-based variable importance measures under predictor correlation. BMC Bioinformatics, 11(1), 110. · DOI
  78. Páez, A. (2019). The pragmatic turn in explainable artificial intelligence (XAI). Minds and Machines, 29(3), 441–459. · DOI
  79. Pearl, J. (2000). Causality: Models, reasoning, and inference. Cambridge University Press.
  80. Pearl, J. (2018). Challenging the hegemony of randomized controlled trials: A commentary on Deaton and Cartwright. Social Science and Medicine, 210, 60–62. · DOI
  81. Pearl, J., & Bareinboim, E. (2014). External validity: From do-calculus to transportability across populations. Statistical Science, 29(4), 579–595. · DOI
  82. Peters, J., Janzing, D., & Schölkopf, B. (2017). The elements of causal inference: Foundations and learning algorithms. The MIT Press.
  83. Popper, K. (1959). The logic of scientific discovery. Routledge.
  84. Poyiadzi, R., Sokol, K., Santos-Rodriguez, R., De Bie, T., & Flach, P. (2020). FACE: Feasible and actionable counterfactual explanations. In: Proceedings of the AAAI/ACM conference on AI, ethics, and society (pp. 344–350). · DOI · Paper page
  85. Pruthi, D., Gupta, M., Dhingra, B., Neubig, G., & Lipton, Z. C. (2020). Learning to deceive with attention-based explanations. In: Proceedings of the 58th annual meeting of the association for computational linguistics (pp. 4782–4793). · DOI · Paper page
  86. Quine, WvanO. (1960). Word and Object. The MIT Press.
  87. Quine, WvanO. (1980). Methods of logic (4th ed.). Harvard University Press.
  88. Reichenbach, H. (1956). The direction of time. University of California Press. · DOI
  89. Ribeiro, M. T., Singh, S., & Guestrin, C. (2016). “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 (pp. 1135–1144). · DOI · Paper page
  90. Rinaldo, A., Wasserman, L., & G’Sell, M. (2019). Bootstrapping and sample splitting for high-dimensional, assumption-lean inference. The Annals of Statistics, 47(6), 3438–3469. · DOI
  91. Romeijn, J.-W. (2017). Philosophy of statistics. In E. N. Zalta (Ed.), The stanford encyclopedia of philosophy (Spring 201). Metaphysics Research Lab, Stanford University.
  92. Rubin, D. B. (1974). Estimating causal effects of treatments in randomized and nonrandomized studies. Journal of Educational Psychology, 66(5), 688–701. · DOI · Paper page
  93. Salmon, W. (1971). Statistical explanation. In W. Salmon (Ed.), Statistical explanation and statistical relevance (pp. 29–87). University of Pittsburgh Press. · DOI
  94. Salmon, W. (1984). Scientific explanation and the causal structure of the world. Princeton University Press.
  95. Schapire, R. E., & Freund, Y. (2012). Boosting: Foundations and algorithms. MIT Press. · DOI
  96. Schölkopf, B., & Smola, A. (2017). Learning with kernels: Support vector machines, regularization, optimization, and beyond (2nd ed.). The MIT Press.
  97. Schwab, P., & Karlen, W. (2019). CXPlain: Causal explanations for model interpretation under uncertainty. Advances in Neural Information Processing Systems 32 (pp. 10220–10230).
  98. Scriven, M. (1962). Explanations, predictions, and laws. In H. Feigl & G. Maxwell (Eds.), Scientific explanation, space, and time (pp. 170–230). University of Minnesota Press.
  99. Selbst, A., & Powles, J. (2017). Meaningful information and the right to explanation. International Data Privacy Law, 7(4), 233–242. · DOI · Paper page
  100. Shah, R., & Peters, J. (2020). The hardness of conditional independence testing and the generalised covariance measure. Annals of Statistics, 48(3), 1514–1538. · DOI
  101. Shmueli, G. (2010). To explain or to predict? Statistical Science, 25(3), 289–310. · DOI
  102. Shpitser, I., & Pearl, J. (2008). Complete identification methods for the causal hierarchy. Journal of Machine Learning Research, 9, 1941–1979.
  103. Slack, D., Hilgard, S., Jia, E., Singh, S., & Lakkaraju, H. (2020). Fooling LIME and SHAP: Adversarial attacks on post-hoc explanation methods. In: Proceedings of the AAAI/ACM conference on ai, ethics, and society, pp. 180–186. · DOI · Paper page
  104. Slack, D., Hilgard, A., Singh, S., & Lakkaraju, H. (2021). Reliable post-hoc explanations: Modeling uncertainty in explainability. Advances in Neural Information Processing Systems, 34.
  105. Sokol, K., & Flach, P. (2020a). LIMEtree: Interactively customisable explanations based on local surrogate multi-output regression trees. arXiv preprint, 2005.01427. · arXiv
  106. Sokol, K., & Flach, P. (2020b). One explanation does not fit all. Künstliche Intelligenz, 34(2), 235–250. · DOI · Paper page
  107. Spirtes, P., Glymour, C. N., & Scheines, R. (2000). Causation, prediction, and search (2nd ed.). The MIT Press.
  108. Stokes, J. M., Yang, K., Swanson, K., Jin, W., Cubillos-Ruiz, A., Donghia, N. M., & Collins, J. J. (2020). A deep learning approach to antibiotic discovery. Cell, 180(4), 688-702.e13. · DOI · Paper page
  109. Strawson, P. F. (1964). Intention and convention in speech acts. Philosophical Review, 73(4), 439–460. · DOI
  110. Strobl, C., Boulesteix, A.-L., Kneib, T., Augustin, T., & Zeileis, A. (2008). Conditional variable importance for random forests. BMC Bioinformatics, 9(1), 307. · DOI
  111. Sullivan, E. (2020). Understanding from machine learning models. The British Journal for the Philosophy of Science
  112. Talbott, W. (2016). Bayesian epistemology. In E. N. Zalta (Ed.), The stanford encyclopedia of philosophy (Winter 201). Metaphysics Research Lab, Stanford University.
  113. Topol, E. J. (2019). High-performance medicine: The convergence of human and artificial intelligence. Nature Medicine, 25(1), 44–56. · DOI · Paper page
  114. Ustun, B., Spangher, A., & Liu, Y. (2019). Actionable recourse in linear classification. In: Proceedings of the conference on fairness, accountability, and transparency (pp. 10–19). · DOI · Paper page
  115. van der Laan, M. J., & Rose, S. (Eds.). (2011). Targeted learning: Causal inference for observational and experimental data. Springer.
  116. van Fraassen, B. C. (1980). The scientific image. Oxford University Press. · DOI · Paper page
  117. Vapnik, V., & Chervonenkis, A. (1971). On the uniform convergence of relative frequencies to their probabilities. Theory Probab. Appl., 16(2), 264–280. · DOI · Paper page
  118. Vilone, G., & Longo, L. (2020). Explainable artificial intelligence: A systematic review. arXiv preprint, 2006.00093. · arXiv
  119. Vinyals, O., Babuschkin, I., Czarnecki, W. M., Mathieu, M., Dudzik, A., Chung, J., & Silver, D. (2019). Grandmaster level in StarCraft II using multi-agent reinforcement learning. Nature, 575(7782), 350–354. · DOI · Paper page
  120. Walton, D. (2004). A new dialectical theory of explanation. Philosophical Explorations, 7(1), 71–89. · DOI
  121. Walton, D. (2006). Examination dialogue: An argumentation framework for critically questioning an expert opinion. Journal of Pragmatics, 38(5), 745–777. · DOI
  122. Walton, D. (2011). A dialogue system specification for explanation. Synthese, 182(3), 349–374. · DOI
  123. Watson, D., Gultchin, L., Taly, A., & Floridi, L. (2021). Local explanations via necessity and sufficiency: Unifying theory and practice. In:Proceedings of the 37th conference on uncertainty in artificial intelligence.
  124. Watson, D. S., & Floridi, L. (2020). The explanation game: a formal framework for interpretable machine learning. Synthese, 198(10), 9211–9242. · DOI
  125. Watson, D., Krutzinna, J., Bruce, I. N., Griffiths, C. E. M., McInnes, I. B., Barnes, M. R., & Floridi, L. (2019). Clinical applications of machine learning algorithms: Beyond the black box. BMJ, 364, 446–448.
  126. Wexler, J., Pushkarna, M., Bolukbasi, T., Wattenberg, M., Viégas, F., & Wilson, J. (2020). The what-if tool: Interactive probing of machine learning models. IEEE Transactions on Visualization and Computer Graphics, 26(1), 56–65.
  127. Wittgenstein, L. (1953). Philosophical investigations (R. Rhees & G. E. M. Anscombe, Eds.; G. E. M. Anscombe, Trans.). Oxford: Blackwell.
  128. Woodward, J. (2019). Scientific explanation. In E. N. Zalta (Ed.), The stanford encyclopedia of philosophy (Winter 201). Metaphysics Research Lab, Stanford University.
  129. Woodward, J. (2003). Making things happen: A theory of causal explanation. Oxford University Press.
  130. Worrall, J. (2007). Why there’s no cause to randomize. The British Journal for the Philosophy of Science, 58(3), 451–488. · DOI
  131. Zerilli, J., Knott, A., Maclaurin, J., & Gavaghan, C. (2019). Transparency in algorithmic and human decision-making: Is there a double standard? Philos. Technol., 32(4), 661–683. · DOI · Paper page
  132. Zhang, K., Peters, J., Janzing, D., & Schölkopf, B. (2011). Kernel-based conditional independence test and application in causal discovery. In: Proceedings of the 27th conference on uncertainty in artificial intelligence, pp. 804–813.
  133. Zhao, Q., & Hastie, T. (2019). Causal interpretations of black-box models. Journal of Business & Economic Statistics, 272–281. · DOI
  134. Ziliak, S. T., & McCloskey, D. N. (2008). The cult of statistical significance: How the standard error costs us jobs, justice, and lives. University of Michigan Press.

Cited by

Sorted by citations

Metadata

Authors
Watson, D. S.
Affiliations
University College London (GB)
Corresponding author
Watson, David S.
ORCID
Watson, David S.
Venue
Synthese
Publisher
Springer Science and Business Media LLC
Published
2022-03-01
Volume
200
Issue
2
ISSN
  • 0039-7857 (ISSN-L)
  • 1573-0964
DOI
10.1007/s11229-022-03485-5
OpenAlex
W4220803452
Cited by
87
References
27
Citations by year
2026: 11 · 2025: 25 · 2024: 30 · 2023: 14 · 2022: 7
FWCI
5.09
Type
journal article
Language
en
Open access
Licence
Locations
  • Synthese (publishedVersion, cc-by)
  • SSRN Electronic Journal (acceptedVersion)
  • UCL Discovery (University College London) (submittedVersion, cc-by)
  • Oxford University Research Archive (ORA) (University of Oxford) (submittedVersion, cc-by)
Funders
Office of Naval Research (N62909-19-1-2096)
Topics
  • Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
  • Social Sciences › Arts and Humanities › History and Philosophy of Science › Philosophy of Biology and Scientific Explanation
  • Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
Keywords
model interpretability, algorithmic explainability, conceptual difficulties, error rate, severe testing, epistemology of explanation, philosophy of science, counterfactual explanations, local linearization

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