The accuracy, fairness, and limits of predicting recidivism
Open accessThe DOI matches its Crossref record; 18 of the 18 references it cites were found in a registry or an index; none of the 9 sources its claims cite is checked for support yet.
Abstract
Should we trust computers to make life-altering decisions in the criminal justice system?
Overview
CoChat Summary
TL;DR
In a Broward County sample, nonexpert Amazon Mechanical Turk participants predicted recidivism about as accurately and with similar racial disparities as COMPAS, and COMPAS’s proprietary 137-feature score could be matched by simple linear classifiers using as few as two features. The authors conclude that algorithmic recidivism prediction, at least as represented by COMPAS, is no better than untrained human judgment and reaches a performance ceiling around 65% accuracy.
Key findings
- A crowd of nonexperts was statistically indistinguishable from COMPAS: crowd accuracy was 67.0% versus COMPAS’s 65.2% on the 1000-defendant subset (P = 0.85), and AUC-ROC was 0.71 ± 0.03 for participants versus 0.70 ± 0.04 for COMPAS.
- Both humans and COMPAS showed similar racial disparities in error rates: participants’ false-positive rate was 37.1% for black defendants versus 27.2% for white defendants (P = 0.027), while COMPAS’s was 40.4% versus 25.4% (P = 0.002); participants’ false-negative rate was 29.2% for black defendants versus 40.3% for white defendants (P = 0.034), while COMPAS’s was 30.9% versus 47.9% (P = 0.003).
- COMPAS’s accuracy was reproducible with simpler models: logistic regression with 7 features achieved 66.6% accuracy [64.4, 68.9], logistic regression with only 2 features—age and total number of previous convictions—achieved 66.8% [64.3, 69.2], and a nonlinear SVM achieved 65.2% [63.0, 67.2], all comparable to COMPAS’s 65.4% [64.3, 66.5].
- Including race in the human prediction task did not significantly change overall accuracy or fairness: crowd accuracy was 66.5% with race versus 67.0% without race (P = 0.66), while false-positive rates for black versus white defendants remained significantly different (40.0% vs. 26.2%, P = 0.001).
Methods
- Data came from 7214 pretrial defendants in Broward County, Florida, from 2013–2014, including demographics, criminal history, COMPAS recidivism risk scores, and 2-year rearrest records; human assessment used a fixed random subset of 1000 defendants.
- Human participants were recruited via Amazon’s Mechanical Turk: 462 in the no-race condition and 449 in the race condition, with catch trials removing inattentive respondents; each participant judged one of 20 subsets of 50 defendants, and crowd predictions used a majority-rules criterion.
- Algorithmic assessment trained logistic regression and nonlinear SVM classifiers on 7 features over 1000 random 80%/20% training/testing splits, and also tested all subsets of the 7 features, including a 2-feature logistic regression.
Limitations
- Stated in the paper: recidivism is operationalized as rearrest, not direct reoffending, and differences in arrest rates across race complicate direct comparison of false-positive and false-negative rates.
- Stated in the paper: participants were not instructed how to weight features; it remains unknown whether guidelines, dynamic risk factors, larger crowds, or criminal justice expertise would improve accuracy.
- Evident from the text: the human sample was drawn from Mechanical Turk and assumed to have little to no criminal justice expertise, there were not enough nonwhite participants to reliably measure differences across participant race, and COMPAS’s proprietary inner workings were not revealed, limiting independent verification.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures
Verification
Claims the paper makes
0 Valid · 1 Not valid · 8 Not checked · 47 Own results and interpretations
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This predictor yields similar results to COMPAS in terms of predictive fairness [Table 2, (A) and (D) columns].”
§ The accuracy, fairness, and limits of predicting recidivism > RESULTS > Algorithmic assessment
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The COMPAS accuracy for this subset of 1000 defendants was 65.2%.”
§ The accuracy, fairness, and limits of predicting recidivism > MATERIALS AND METHODS
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.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“With respect to fairness, participant accuracy is not significantly different for black defendants (66.2%) compared with white defendants (67.6%; P = 0.65, unpaired t test).”
§ The accuracy, fairness, and limits of predicting recidivism > RESULTS > Human assessment
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“This crowd-based approach yields a prediction accuracy of 67.0%.”
§ The accuracy, fairness, and limits of predicting recidivism > RESULTS > Human assessment
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“The average COMPAS accuracy on 10,000 random subsets of size 1000 each was 65.4% with a 95% confidence interval of (62.6, 68.1).”
§ The accuracy, fairness, and limits of predicting recidivism > MATERIALS AND METHODS
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.
20 more claims
Create a free account to see all 56 claims and to verify the 6 references still open.
- It may state two separate claims as one. 28
- Probably not a substantial claim. 6
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
“In fact, quite a lot of effort has been made by scientists to understand how COMPAS depends on important variables like race and age, without a lot of success (59, 60).”
From Interpretable algorithmic forensics (2023) · cites this paper as [59]
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
“For instance, this work has demonstrated that simple interpretable models (with two and respectively three features) can perform as well as the widely used criminal justice COMPAS algorithm, which instead draws on 137 features.”
From Accountable Artificial Intelligence: Holding Algorithms to Account (2021) · cites this paper as Dressel and Farid 2018
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
“Another example is [399], where the authors propose a fair-by-design approach in order to develop ML models that jointly have less bias and include as explanations human comprehensible rules.”
From Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AI (2020) · cites this paper as [400]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Dressel and Farid (2018) achieved this result by using a linear predictor-logistic regressor that made use of only two variables (age and total number of previous convictions of the subject).”
From Ethical principles in machine learning and artificial intelligence: cases from the field and possible ways forward (2020) · cites this paper as Dressel and Farid (2018)
The cited source says what the claim attributes to it.
In the citing paper
“Recent research for predicting social outcomes has shown that even with complex models and large datasets, there are strong limits to predictive performance.49,83”
From Leakage and the reproducibility crisis in machine-learning-based science (2023) · cites this paper as [83]
2 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
Cortes, C., & Vapnik, V. (1995) · Machine Learning · doi:10.1007/bf00994018 · Cited by 59,421
The Regression Analysis of Binary Sequences
Cox, D. R. (1958) · Journal of the Royal Statistical Society Series B: Statistical Methodology · doi:10.1111/j.2517-6161.1958.tb00292.x · Cited by 2,813
Predicting relapse: A meta-analysis of sexual offender recidivism studies.
Hanson, R. K., & Bussière, M. T. (1998) · Journal of Consulting and Clinical Psychology · doi:10.1037/0022-006x.66.2.348 · Cited by 2,375
A META‐ANALYSIS OF THE PREDICTORS OF ADULT OFFENDER RECIDIVISM: WHAT WORKS!*
GENDREAU, P., LITTLE, T., & GOGGIN, C. (1996) · Criminology · doi:10.1111/j.1745-9125.1996.tb01220.x · Cited by 1,244
Hanson, R. K., & Morton-Bourgon, K. E. (2009) · Psychological Assessment · doi:10.1037/a0014421 · Cited by 1,050
Inherent Trade-Offs in the Fair Determination of Risk Scores
Kleinberg, J., Mullainathan, S., & Raghavan, M. (2016) · arXiv · doi:10.48550/arxiv.1609.05807 · Cited by 941
Where Should We Intervene?: Dynamic Predictors of Sexual Offense Recidivism
HANSON, R. K., & HARRIS, A. J. R. (2000) · Criminal Justice and Behavior · doi:10.1177/0093854800027001002 · Cited by 793
Predictive Policing: The Role of Crime Forecasting in Law Enforcement Operations
Perry, W., McInnis, B., Price, C., Smith, S., & Hollywood, J. (2013) · doi:10.7249/rr233 · Cited by 693
The efficacy of violence prediction: a meta-analytic comparison of nine risk assessment tools.
Yang, M., Wong, S. C. P., & Coid, J. (2010) · Psychological Bulletin · doi:10.1037/a0020473 · Cited by 525
The Robust Beauty of Majority Rules in Group Decisions.
Hastie, R., & Kameda, T. (2005) · Psychological Review · doi:10.1037/0033-295x.112.2.494 · Cited by 462
Cited by
Items 101–200 of 1,260
Prognostic models will be victims of their own success, unless…
Lenert, M. C., Matheny, M. E., & Walsh, C. G. (2019) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocz145 · Cited by 92
Menard, P., & Bott, G. J. (2024) · Information Systems Journal · doi:10.1111/isj.12544 · Cited by 121
Swiss-Judgment-Prediction: A Multilingual Legal Judgment Prediction Benchmark
Niklaus, J., Chalkidis, I., & Stuermer, M. (2021) · Natural Legal Language Processing Workshop (NLLP) · doi:10.18653/v1/2021.nllp-1.3 · Cited by 165
Contini, F. (2020) · Law Technology and Humans · doi:10.5204/lthj.v2i1.1478 · Cited by 96
Widder, D. G., Zhen, D., Dabbish, L., & Herbsleb, J. (2023) · 2023 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3593013.3594012 · Cited by 94
Travaini, G. V., Pacchioni, F., Bellumore, S., Bosia, M., & Micco, F. D. (2022) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph191710594 · Cited by 124
Kuo, T.-S., Shen, H., Geum, J., Jones, N., Hong, J. I., Zhu, H., & Holstein, K. (2023) · Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3580882 · Cited by 82
Human Perceptions on Moral Responsibility of AI: A Case Study in AI-Assisted Bail Decision-Making
Lima, G., Grgić-Hlača, N., & Cha, M. (2021) · Proceedings of the 2021 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3411764.3445260 · Cited by 70
Human-centred artificial intelligence: a contextual morality perspective
van Berkel, N., Tag, B., Goncalves, J., & Hosio, S. (2022) · Behaviour & Information Technology · doi:10.1080/0144929x.2020.1818828 · Cited by 83
Digital footprints: an emerging dimension of digital inequality
Micheli, M., Lutz, C., & Büchi, M. (2018) · Journal of Information Communication and Ethics in Society · doi:10.1108/jices-02-2018-0014 · Cited by 108
Jabłonowska, A., Kuziemski, M., Nowak, A. M., Micklitz, H., Pałka, P., & Sartor, G. (2018) · SSRN Electronic Journal · doi:10.2139/ssrn.3228051 · Cited by 112
AI-generated faces influence gender stereotypes and racial homogenization
AlDahoul, N., Rahwan, T., & Zaki, Y. (2025) · Scientific Reports · doi:10.1038/s41598-025-99623-3 · Cited by 107
POTs: protective optimization technologies
Kulynych, B., Overdorf, R., Troncoso, C., & Gürses, S. (2020) · Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency · doi:10.1145/3351095.3372853 · Cited by 57
Banerjee, S., Alsop, P. H., Jones, L. A., & Cardinal, R. N. (2022) · Patterns · doi:10.1016/j.patter.2022.100506 · Cited by 95
The Impact of Artificial Intelligence on the Right to a Fair Trial: Towards a Robot Judge?
Ulenaers, J. (2020) · Asian Journal of Law and Economics · doi:10.1515/ajle-2020-0008 · Cited by 114
Mesejo, P., Martos, R., Ibáñez, O. C., Novo, J., & Ortega, M. (2020) · Applied Sciences · doi:10.3390/app10144703 · Cited by 92
Waldman, A. E., & Martin, K. E. (2022) · Big Data & Society · doi:10.1177/20539517221100449 · Cited by 95
ORES: Lowering Barriers with Participatory Machine Learning in Wikipedia
Halfaker, A., & Geiger, R. S. (2020) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3415219 · Cited by 82
“Academic debates followed over what it meant for such a system to be “fair” or “biased” [2, 9, 17, 24, 110] As Mulligan et al.”
BackgroundA Framework for Understanding Sources of Harm throughout the Machine Learning Life Cycle
Suresh, H., & Guttag, J. (2021) · Equity and Access in Algorithms, Mechanisms, and Optimization · doi:10.1145/3465416.3483305 · Cited by 82
“, “rearrest” to measure “recidivism” [15]) were also differentially measured proxies.”
BackgroundWang, A., Kapoor, S., Barocas, S., & Narayanan, A. (2024) · ACM Journal on Responsible Computing · doi:10.1145/3636509 · Cited by 57
A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cycle
Suresh, H., & Guttag, J. V. (2019) · arXiv · doi:10.48550/arxiv.1901.10002 · Cited by 82
The explanation game: a formal framework for interpretable machine learning
Watson, D. S., & Floridi, L. (2021) · Synthese · doi:10.1007/s11229-020-02629-9 · Cited by 71
Criminal courts’ artificial intelligence: the way it reinforces bias and discrimination
Malek, A. (2022) · AI and Ethics · doi:10.1007/s43681-022-00137-9 · Cited by 130
Projection to Fairness in Statistical LearningPreprint
Gouic, T. L., Loubes, J., & Rigollet, P. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.11720 · Cited by 81
Predictive Validity of Pretrial Risk Assessments: A Systematic Review of the Literature
Desmarais, S. L., Zottola, S. A., Duhart Clarke, S. E., & Lowder, E. M. (2021) · Criminal Justice and Behavior · doi:10.1177/0093854820932959 · Cited by 79
“…ProPublica’s analysis of the Correctional Offender Management Profiling for Alternative Sanctions (COMPAS) in Broward County, Florida (Angwin et al., 2016) and a subsequent study that concluded COMPAS assessments performed no better than lay persons at predicting recidivism (Dressel & Farid, 2018).”
BackgroundAutomation and Augmentation: Artificial Intelligence, Robots, and Work
Lei, Y.-W., & Kim, R. (2024) · Annual Review of Sociology · doi:10.1146/annurev-soc-090523-050708 · Cited by 95
Code is law: how COMPAS affects the way the judiciary handles the risk of recidivism
Engel, C., Linhardt, L., & Schubert, M. (2024) · Artificial Intelligence and Law · doi:10.1007/s10506-024-09389-8 · Cited by 79
Dashing hopes? The predictive accuracy of domestic abuse risk assessment by police
Turner, E., Medina, J., & Brown, G. (2019) · The British Journal of Criminology · doi:10.1093/bjc/azy074 · Cited by 78
Chalkidis, I., Fergadiotis, M., Tsarapatsanis, D., Aletras, N., Androutsopoulos, I., & Malakasiotis, P. (2021) · Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/2021.naacl-main.22 · Cited by 78
A Deep Learning Architecture for Psychometric Natural Language Processing
Ahmad, F., Abbasi, A., Li, J., Dobolyi, D. G., Netemeyer, R. G., Clifford, G. D., & Chen, H. (2020) · ACM Transactions on Information Systems · doi:10.1145/3365211 · Cited by 90
König, G., Molnar, C., Bischl, B., & Grosse‐Wentrup, M. (2021) · Proceedings - International Conference on Pattern Recognition/Proceedings/International Conference on Pattern Recognition · doi:10.1109/icpr48806.2021.9413090 · Cited by 82
Effects of Explanations in AI-Assisted Decision Making: Principles and Comparisons
Wang, X., & Yin, M. (2022) · ACM Transactions on Interactive Intelligent Systems · doi:10.1145/3519266 · Cited by 74
Crowdsourcing Perceptions of Fair Predictors for Machine Learning: A Recidivism Case Study
van Berkel, N., Goncalves, J., Hettiachchi, D., Wijenayake, S., Kelly, R. M., & Kostakos, V. (2019) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3359130 · Cited by 60
Kim, J., & Park, N. (2020) · Applied Sciences · doi:10.3390/app10144718 · Cited by 76
A cognitive approach to human–AI complementarity in dynamic decision-making
González, C., & Heidari, H. (2025) · Nature Reviews Psychology · doi:10.1038/s44159-025-00499-x · Cited by 92
Lee, M. H. J., Montgomery, J., & Lai, C. K. (2024) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3630106.3658975 · Cited by 104
Awad, E., Levine, S., Anderson, M., Anderson, S. L., Conitzer, V., Crockett, M. J., Everett, J. A. C., Evgeniou, T., Gopnik, A., Jamison, J. C., et al. (2022) · Trends in Cognitive Sciences · doi:10.1016/j.tics.2022.02.009 · Cited by 50
Social impacts of algorithmic decision-making: A research agenda for the social sciences
Gerdon, F., Bach, R. L., Kern, C. A., & Kreuter, F. (2022) · Big Data & Society · doi:10.1177/20539517221089305 · Cited by 88
Racism, responsibility and autonomy in HCI: Testing perceptions of an AI agent
Hong, J.-W., & Williams, D. (2019) · Computers in Human Behavior · doi:10.1016/j.chb.2019.06.012 · Cited by 69
Procedural fairness in algorithmic decision-making: the role of public engagement
Decker, M. C., Wegner, L., & Leicht-Scholten, C. (2024) · Ethics and Information Technology · doi:10.1007/s10676-024-09811-4 · Cited by 78
Interpretable algorithmic forensics
Garrett, B. L., & Rudin, C. (2023) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2301842120 · Cited by 68
“In fact, quite a lot of effort has been made by scientists to understand how COMPAS depends on important variables like race and age, without a lot of success (59, 60).”
BackgroundRacist Algorithms or Systemic Problems? Risk Assessments and Racial Disparities
Vincent, G. M., & Viljoen, J. L. (2020) · Criminal Justice and Behavior · doi:10.1177/0093854820954501 · Cited by 68
Spiegelhalter, D. (2020) · Harvard Data Science Review · doi:10.1162/99608f92.cb91a35a · Cited by 64
Responsibility Gaps and Black Box Healthcare AI: Shared Responsibilization as a Solution
Lang, B. H., Nyholm, S. R., & Blumenthal‐Barby, J. (2023) · Digital Society · doi:10.1007/s44206-023-00073-z · Cited by 71
Fragile algorithms and fallible decision-makers: Lessons from the justice system
Ludwig, J., & Mullainathan, S. (2021) · Journal of Economic Perspectives · doi:10.1257/jep.35.4.71 · Cited by 66
The Myth in the Methodology: Towards a Recontextualization of Fairness in Machine Learning
Green, B., & Hu, L. J. (2018) · International Conference on Machine Learning · Cited by 133
Flaxman, S., Chirico, M., Pereira, P., & Loeffler, C. (2019) · The Annals of Applied Statistics · doi:10.1214/19-aoas1284 · Cited by 59
Fold-stratified cross-validation for unbiased and privacy-preserving federated learning
Bey, R., Goussault, R., Grolleau, F., Benchoufi, M., & Porcher, R. (2020) · Journal of the American Medical Informatics Association · doi:10.1093/jamia/ocaa096 · Cited by 70
Malgieri, G., & Pasquale, F. (2023) · Computer law & security review · doi:10.1016/j.clsr.2023.105899 · Cited by 87
“Part Man, Part Machine, All Cop”: Automation in Policing
Adensamer, A., & Klausner, L. D. (2021) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2021.655486 · Cited by 64
Evaluating causes of algorithmic bias in juvenile criminal recidivism
Miron, M., Tolan, S., Gómez, E., & Castillo, C. (2020) · Artificial Intelligence and Law · doi:10.1007/s10506-020-09268-y · Cited by 77
Bouchetara, M., Zerouti, M., & Zouambi, A. R. (2024) · EDPACS · doi:10.1080/07366981.2024.2377351 · Cited by 94
Bridging the gap: Towards an expanded toolkit for AI-driven decision-making in the public sector
Fischer-Abaigar, U., Kern, C. A., Barda, N., & Kreuter, F. (2024) · Government Information Quarterly · doi:10.1016/j.giq.2024.101976 · Cited by 80
Fair Classification with Group-Dependent Label Noise
Wang, J., Liu, Y., & Levy, C. (2021) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3442188.3445915 · Cited by 118
Assessing trustworthy AI: Technical and legal perspectives of fairness in AI
Kattnig, M., Angerschmid, A., Reichel, T., & Kern, R. (2024) · Computer law & security review · doi:10.1016/j.clsr.2024.106053 · Cited by 77
Algorithms and values in justice and security
Hayes, P., van de Poel, I., & Steen, M. (2020) · AI & Society · doi:10.1007/s00146-019-00932-9 · Cited by 71
Algorithmic Risk Assessment in the Hands of Humans
Stevenson, M., & Doleac, J. L. (2019) · doi:10.2139/ssrn.3489440 · Cited by 60
The Effectiveness of Big Data-Driven Predictive Policing: Systematic Review
Lee, Y., Bradford, B., & Pósch, K. (2024) · Justice Evaluation Journal · doi:10.1080/24751979.2024.2371781 · Cited by 73
Imai, K., Jiang, Z., Greiner, D. J., Halen, R., & Shin, S. (2023) · Journal of the Royal Statistical Society Series A (Statistics in Society) · doi:10.1093/jrsssa/qnad010 · Cited by 83
FairLex: A Multilingual Benchmark for Evaluating Fairness in Legal Text Processing
Chalkidis, I., Pasini, T., Zhang, S., Tomada, L., Schwemer, S. F., & Søgaard, A. (2022) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2022.acl-long.301 · Cited by 92
Counterfactual Explanations Can Be ManipulatedPreprint
Slack, D., Hilgard, S., Lakkaraju, H., & Singh, S. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2106.02666 · Cited by 181
Introducing students to machine learning with decision trees using CODAP and Jupyter Notebooks
Biehler, R., & Fleischer, Y. (2021) · Teaching Statistics · doi:10.1111/test.12279 · Cited by 58
Investigating Human + Machine Complementarity for Recidivism Predictions
Tan, S., Adebayo, J., Inkpen, K. M., & Kamar, E. S. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1808.09123 · Cited by 25
Investigating Gender and Racial Biases in DALL-E Mini Images
Cheong, M., Abedin, E., Ferreira, M., Reimann, R., Chalson, S., Robinson, P., Byrne, J., Ruppanner, L., Alfano, M., & Klein, C. (2024) · ACM Journal on Responsible Computing · doi:10.1145/3649883 · Cited by 57
“…was found to be gender-biased [24, 45]; Google algorithms for search engines, photo tagging and ad placement were found to be racially biased [5, 9, 40, 74]; and systems that purportedly determine criminal risk of recidivism and crime patterns arguably reproduce racist biases [6, 30, 68].”
BackgroundDigital prediction technologies in the justice system: The implications of a ‘race-neutral’ agenda
Ugwudike, P. (2020) · Theoretical Criminology · doi:10.1177/1362480619896006 · Cited by 83
Explaining Machine Learning Decisions
Zerilli, J. (2022) · Philosophy of Science · doi:10.1017/psa.2021.13 · Cited by 50
Psychological AI: Designing Algorithms Informed by Human Psychology
Gigerenzer, G. (2023) · Perspectives on Psychological Science · doi:10.1177/17456916231180597 · Cited by 69
Bezuidenhout, L. M., & Ratti, E. (2020) · AI & Society · doi:10.1007/s00146-020-01112-w · Cited by 68
Anahideh, H., Asudeh, A., & Thirumuruganathan, S. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.116981 · Cited by 82
Afrose, S., Song, W., Nemeroff, C. B., Lu, C., & Yao, D. D. (2022) · Communications Medicine · doi:10.1038/s43856-022-00165-w · Cited by 64
Probing into the Fairness of Large Language Models: A Case Study of ChatGPT
Li, Y., Zhang, L., & Zhang, Y. (2024) · Conference on Information Sciences and Systems · doi:10.1109/ciss59072.2024.10480206 · Cited by 66
Anti-Black Structural Racism Goes Online: A Conceptual Model for Racial Health Disparities Research
Volpe, V. V., Hoggard, L. S., Willis, H. A., & Tynes, B. M. (2021) · Ethnicity & Disease · doi:10.18865/ed.31.s1.311 · Cited by 59
Tree Space Prototypes: Another Look at Making Tree Ensembles Interpretable
Tan, S., Soloviev, M., Hooker, G., & Wells, M. T. (2020) · Proceedings of the 2020 ACM-IMS on Foundations of Data Science Conference · doi:10.1145/3412815.3416893 · Cited by 49
Trust in Public Policy Algorithms
Kennedy, R. P., Waggoner, P. D., & Ward, M. M. (2022) · The Journal of Politics · doi:10.1086/716283 · Cited by 46
Justice by Algorithm: The Limits of AI in Criminal Sentencing
Taylor, I. (2023) · Criminal Justice Ethics · doi:10.1080/0731129x.2023.2275967 · Cited by 66
Albalawi, Y., Buckley, J., & Nikolov, N. S. (2021) · Journal Of Big Data · doi:10.1186/s40537-021-00488-w · Cited by 54
Srivastava, M., Heidari, H., & Krause, A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1902.04783 · Cited by 56
Diversity in sociotechnical machine learning systems
Fazelpour, S., & De-Arteaga, M. (2022) · Big Data & Society · doi:10.1177/20539517221082027 · Cited by 38
The Accuracy, Equity, and Jurisprudence of Criminal Risk Assessment
Goel, S., Shroff, R., Skeem, J. L., & Slobogin, C. (2018) · Edward Elgar Publishing eBooks · doi:10.4337/9781788972826.00007 · Cited by 59
Auditing fairness under unawareness through counterfactual reasoning
Cornacchia, G., Anelli, V. W., Biancofiore, G. M., Narducci, F., Pomo, C., Ragone, A., & Sciascio, E. D. (2022) · Information Processing & Management · doi:10.1016/j.ipm.2022.103224 · Cited by 67
Fairness in Machine Learning: Against False Positive Rate Equality as a Measure of Fairness
Long, R. (2021) · Journal of Moral Philosophy · doi:10.1163/17455243-20213439 · Cited by 63
Chen, L., Hsieh, J. J. P.-A., & Rai, A. (2022) · Information Systems Research · doi:10.1287/isre.2021.1097 · Cited by 61
Yu, B., Yuan, Y., Terveen, L., Wu, Z. S., Forlizzi, J., & Zhu, H. (2020) · Proceedings of the 2020 ACM Designing Interactive Systems Conference · doi:10.1145/3357236.3395528 · Cited by 44
The use-the-best heuristic facilitates deception detection
Verschuère, B., Lin, C.-C., Huismann, S., Kleinberg, B., Willemse, M., Mei, E. C. J., van Goor, T., Loewy, L. H. S., Appiah, O. K., & Meijer, E. H. (2023) · Nature Human Behaviour · doi:10.1038/s41562-023-01556-2 · Cited by 59
AI and Holistic Review: Informing Human Reading in College Admissions
Alvero, A. J., Arthurs, N., antonio, A. L., Domingue, B. W., Gebre-Medhin, B., Giebel, S., & Stevens, M. L. (2020) · Proceedings of the AAAI/ACM Conference on AI, Ethics, and Society · doi:10.1145/3375627.3375871 · Cited by 35
Inherent Limitations of AI Fairness
Buyl, M., & Bie, T. D. (2024) · Communications of the ACM · doi:10.1145/3624700 · Cited by 73
The effects of mixing machine learning and human judgment
Vaccaro, M., & Waldo, J. (2019) · Communications of the ACM · doi:10.1145/3359338 · Cited by 49
Getting a CLUE: A Method for Explaining Uncertainty Estimates
Antorán, J., Bhatt, U., Adel, T., Weller, A., & Hernández-Lobato, J. M. (2021) · Apollo - University of Cambridge Repository · doi:10.17863/cam.69929 · Cited by 49
Fairness in Learning-Based Sequential Decision Algorithms: A Survey
Zhang, X., & Liu, M. (2021) · Studies in systems, decision and control · doi:10.1007/978-3-030-60990-0_18 · Cited by 76
The implicit fairness criterion of unconstrained learningPreprint
Liu, L. T., Simchowitz, M., & Hardt, M. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1808.10013 · Cited by 103
Ma, S., Chen, Q., Wang, X., Zheng, C., Peng, Z., Yin, M., & Ma, X. (2025) · Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713423 · Cited by 48
“With remarkable technological advancements, AI has been increasingly used to support people in making decisions in various domains, including criminal justice [32, 35], admissions [25, 140], financial investment [53], and medical diagnosis [21, 79], among others.”
Studying human-to-computer bias transference
Johansen, J., Pedersen, T., & Johansen, C. (2021) · AI & Society · doi:10.1007/s00146-021-01328-4 · Cited by 54
Retooling Politics: How Digital Media Are Shaping Democracy
Jungherr, A. M., Rivero, G., & Gayo-Avello, D. (2020) · Cited by 48
Beyond Open vs. Closed: Balancing Individual Privacy and Public Accountability in Data Sharing
Young, M., Rodriguez, L., Keller, E., Sun, F., Sa, B., Whittington, J., & Howe, B. (2019) · Proceedings of the Conference on Fairness, Accountability, and Transparency · doi:10.1145/3287560.3287577 · Cited by 41
Artificial intelligence and democratic legitimacy. The problem of publicity in public authority
Beckman, L., Rosenberg, J. H., & Jebari, K. (2022) · AI & Society · doi:10.1007/s00146-022-01493-0 · Cited by 58
Farayola, M. M., Tal, I., Connolly, R., Saber, T., & Bendechache, M. (2023) · Information · doi:10.3390/info14080426 · Cited by 63
Artificial Intelligence Threatens Critical Thinking in Education Systems
Özer, M., Tanberkan, H., & Perc, M. (2025) · Journal of Higher Education and Science · doi:10.5961/higheredusci.1747885 · Cited by 47
A Taxonomy of Human and ML Strengths in Decision-Making to Investigate Human-ML Complementarity
Rastogi, C., Leqi, L., Holstein, K., & Heidari, H. (2023) · Proceedings of the AAAI Conference on Human Computation and Crowdsourcing · doi:10.1609/hcomp.v11i1.27554 · Cited by 72
Omission and commission errors underlying AI failures
Chanda, S. S., & Banerjee, D. N. (2024) · AI & SOCIETY · doi:10.1007/s00146-022-01585-x · Cited by 45
A social cognition perspective on autonomous technology
Frischknecht, R. (2021) · Computers in Human Behavior · doi:10.1016/j.chb.2021.106815 · Cited by 47
Metadata
- Authors
- Dressel, J., & Farid, H.
- Affiliations
- Dartmouth College (US)
- Corresponding author
- Farid, Hany
- Venue
- Science Advances
- Published
- 2018-01-05
- Volume
- 4
- Issue
- 1
- Pages
- eaao5580-eaao5580
- ISSN
- 2375-2548 (ISSN-L)
- PMC
- PMC5777393
- OpenAlex
- W2785011159
- Cited by
- 1,071
- References
- 17
- Citations by year
- 2026: 138 · 2025: 124 · 2024: 149 · 2023: 153 · 2022: 126 · 2021: 127 · 2020: 148 · 2019: 76 · 2018: 29
- FWCI
- 188.76
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- cc-by-nc
- Locations
- Science Advances (publishedVersion, cc-by-nc)
- Europe PMC (PubMed Central) (publishedVersion, cc-by-nc)
- PubMed Central (publishedVersion, cc-by-nc)
- PubMed (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Social Sciences › Sociology and Political Science › Criminal Justice and Corrections Analysis
- Social Sciences › Law › Artificial Intelligence in Law
- Keywords
- recidivism prediction, COMPAS, risk assessment software, algorithmic fairness, algorithmic accuracy, criminal justice, parole decisions, sentencing, linear predictor, algorithmic bias
- MeSH terms
- Recidivism, Algorithms, Humans, ROC Curve, Area Under Curve
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 2026-11-09, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-11-09 (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.
