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 301–400 of 1,260
LimeOut: An Ensemble Approach to Improve Process Fairness
Bhargava, V., Couceiro, M., & Napoli, A. (2020) · Communications in computer and information science · doi:10.1007/978-3-030-65965-3_32 · Cited by 25
Gal, D., & Simonson, I. (2020) · Consumer Psychology Review · doi:10.1002/arcp.1068 · Cited by 33
Misinformation and Algorithmic Bias
Shin, D. (2024) · Springer eBooks · doi:10.1007/978-3-031-52569-8_2 · Cited by 26
An Algorithmic Assessment of Parole Decisions
Laqueur, H. S., & Copus, R. W. (2022) · Journal of Quantitative Criminology · doi:10.1007/s10940-022-09563-8 · Cited by 30
From Text to Trust: Empowering AI-assisted Decision Making with Adaptive LLM-powered Analysis
Li, Z., Zhu, H., Lu, Z., Xiao, Z., & Yin, M. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3713133 · Cited by 38
Advancing AI governance with a unified theoretical framework: a systematic review
Robles, P., & Mallinson, D. J. (2025) · Perspectives on Public Management and Governance · doi:10.1093/ppmgov/gvaf013 · Cited by 18
Enhancing Data Science Ethics Through Statistical Education and Practice
Utts, J. M. (2021) · International Statistical Review · doi:10.1111/insr.12446 · Cited by 28
On (assessing) the fairness of risk score models
Petersen, E., Ganz, M., Holm, S., & Feragen, A. (2023) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3593013.3594045 · Cited by 36
Winder, P. D., Hildebrand, C., & Hartmann, J. (2025) · PLoS ONE · doi:10.1371/journal.pone.0325459 · Cited by 36
Do I Look Like a Criminal? Examining how Race Presentation Impacts Human Judgement of Recidivism
Mallari, K., Inkpen, K., Johns, P., Tan, S., Ramesh, D., & Kamar, E. (2020) · Proceedings of the 2020 CHI Conference on Human Factors in Computing Systems · doi:10.1145/3313831.3376257 · Cited by 24
“For instance, Dressel and Farid, when comparing human and algorithmic accuracy for recidivism predictions, did not find race to be a factor influencing human judgement [13], while Green and Chen [17] found that users were more likely to predict higher recidivism risk for one racial group (i.”
BackgroundMethodInfluentialCohort bias in predictive risk assessments of future criminal justice system involvement
Montana, E., Nagin, D. S., Neil, R., & Sampson, R. J. (2023) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2301990120 · Cited by 24
Gender Bias in Text: Origin, Taxonomy, and Implications
Doughman, J., Khreich, W., Gharib, M. E., Wiss, M., & Berjawi, Z. (2021) · Workshop on Gender Bias in Natural Language Processing (GeBNLP) · doi:10.18653/v1/2021.gebnlp-1.5 · Cited by 40
Technologies for Trustworthy Machine Learning: A Survey in a Socio-Technical ContextPreprint
Toreini, E., Aitken, M., Coopamootoo, K., Elliott, K., González-Zelaya, V., Missier, P., Ng, M., & van Moorsel, A. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.08911 · Cited by 33
A step toward building a unified framework for managing AI bias
Rana, S. A., Azizul, Z. H., & Awan, A. A. (2023) · PeerJ Computer Science · doi:10.7717/peerj-cs.1630 · Cited by 23
Fogliato, R., Chouldechova, A., & Lipton, Z. (2021) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3479572 · Cited by 23
No Agent in the Machine: Being Trustworthy and Responsible about AI
Conradie, N. H., & Nagel, S. K. (2024) · Philosophy & Technology · doi:10.1007/s13347-024-00760-w · Cited by 29
Monroe‐White, T. (2021) · ACM SIGCPR Conference on Computer Personnel Research (SIGCPR) · doi:10.1145/3458026.3462161 · Cited by 24
Haarsma, G., Davenport, S., White, D. C., Ormachea, P. A., Sheena, E., & Eagleman, D. M. (2020) · Frontiers in Psychology · doi:10.3389/fpsyg.2019.02926 · Cited by 23
Schwerzmann, K. (2021) · Philosophy & Technology · doi:10.1007/s13347-021-00491-2 · Cited by 34
Machine learning in bail decisions and judges’ trustworthiness
Morin-Martel, A. (2023) · AI & Society · doi:10.1007/s00146-023-01673-6 · Cited by 31
Questioning the assumptions behind fairness solutionsPreprint
Overdorf, R., Kulynych, B., Balsa, E., Troncoso, C., & Gürses, S. F. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.11293 · Cited by 23
Moratinos, G. L., & Parrilla, J. A. C. (2020) · Revista Chilena de Derecho y Tecnología · doi:10.5354/0719-2584.2020.56843 · Cited by 23
Inteligencia artificial y neuroderechos. Retos y perspectivas
Rodríguez, J. M. G. (2022) · Cuestiones Constitucionales Revista Mexicana de Derecho Constitucional · doi:10.22201/iij.24484881e.2022.46.17049 · Cited by 34
The Benchmarking Epistemology: Validity Theory for Evaluating Machine Learning Models
Freiesleben, T., & Zezulka, S. (2026) · Philosophy of Science · doi:10.1017/psa.2026.10280 · Cited by 27
ORES: Lowering Barriers with Participatory Machine Learning in WikipediaPreprint
Halfaker, A., & Geiger, R. S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.05189 · Cited by 22
The Dangers of Risk Prediction in the Criminal Justice System
Dressel, J., & Farid, H. (2021) · doi:10.21428/2c646de5.f5896f9f · Cited by 25
Self-citationWhy Organization Matters in “Algorithmic Discrimination”
Schwarting, R., & Ulbricht, L. (2022) · KZfSS Kölner Zeitschrift für Soziologie und Sozialpsychologie · doi:10.1007/s11577-022-00838-3 · Cited by 27
Poor Data Quality in Sub-Saharan Africa and Implications on Ethical AI Development
Vibbi, L. F. (2024) · SpringerBriefs in applied sciences and technology · doi:10.1007/978-3-031-52962-7_7 · Cited by 23
Keywords of the Datafied StatePreprint
Burrell, J., Singh, R., & Davison, P. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4734250 · Cited by 25
A Human-in-the-loop Framework to Construct Context-aware Mathematical Notions of Outcome Fairness
Yaghini, M., Krause, A., & Heidari, H. (2021) · Proceedings of the AAAI/ACM Conference on AI Ethics and Society · doi:10.1145/3461702.3462583 · Cited by 31
Monitoring Algorithmic Fairness
Henzinger, T. A., Karimi, M., Kueffner, K., & Mallik, K. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-37703-7_17 · Cited by 36
Valdivia, A., Hyde-Vaamonde, C., & Marcos, J. G. (2024) · AI & Society · doi:10.1007/s00146-024-02016-9 · Cited by 25
Just Algorithms: Using Science to Reduce Incarceration and Inform a Jurisprudence of Risk
Slobogin, C. (2021) · Cambridge University Press eBooks · doi:10.1017/9781108988025 · Cited by 29
Inteligencia artificial y proceso penal
Falconí, R. J. G., & Pazmiño, K. F. B. (2024) · Revista San Gregorio · doi:10.36097/rsan.v1i58.2808 · Cited by 25
MIMIC-IF: Interpretability and Fairness Evaluation of Deep Learning Models on MIMIC-IV Dataset
Meng, C., Trinh, L., Xu, N., & Liu, Y. (2021) · doi:10.21203/rs.3.rs-402058/v1 · Cited by 21
Algorithmic risk assessment in the hands of humans
Stevenson, M. T., & Doleac, J. L. (2024) · American Economic Journal: Economic Policy · doi:10.1257/pol.20220620 · Cited by 21
The Carceral State: An American Story
Khan, A. (2022) · Annual Review of Anthropology · doi:10.1146/annurev-anthro-041420-013930 · Cited by 21
Fairness Under Unawareness: Assessing Disparity When Protected Class Is UnobservedPreprint
Chen, J., Kallus, N., Mao, X., Svacha, G., & Udell, M. R. (2018) · arXiv (Cornell University) · doi:10.48550/arxiv.1811.11154 · Cited by 21
Capiola, A., Lyons, J. B., Harris, K. N., Hamdan, I. A., Kailas, S., & Sycara, K. P. (2023) · Computers in Human Behavior · doi:10.1016/j.chb.2023.107966 · Cited by 22
Freedom and Constraint in Digital Environments: Implications for the Self
Talaifar, S., & Lowery, B. S. (2022) · Perspectives on Psychological Science · doi:10.1177/17456916221098036 · Cited by 24
Toward a Race-Conscious Entrepreneurship Education
Monroe‐White, T., & McGee, E. O. (2023) · Entrepreneurship Education and Pedagogy · doi:10.1177/25151274231164927 · Cited by 22
Mitigating allocative tradeoffs and harms in an environmental justice data tool
Huynh, B. Q., Chin, E. T., Koenecke, A., Ouyang, D., Ho, D. E., Kiang, M. V., & Rehkopf, D. H. (2024) · Nature Machine Intelligence · doi:10.1038/s42256-024-00793-y · Cited by 25
Fazel, S., Sariaslan, A., & Fanshawe, T. R. (2022) · European Journal on Criminal Policy and Research · doi:10.1007/s10610-022-09520-y · Cited by 25
Chalkidis, I., Fergadiotis, M., Tsarapatsanis, D., Αλέτρας, Ν., Androutsopoulos, I., & Malakasiotis, P. (2021) · White Rose Research Online (University of Leeds, The University of Sheffield, University of York) · doi:10.48550/arxiv.2103.13084 · Cited by 34
Lavelle-Hill, R. E., Smith, G., Deininger, H., & Murayama, K. (2025) · Psychological Methods · doi:10.1037/met0000772 · Cited by 24
Fairness improvement for black-box classifiers with Gaussian process
Nguyen, D., Gupta, S., Rana, S., Shilton, A., & Venkatesh, S. (2021) · Information Sciences · doi:10.1016/j.ins.2021.06.095 · Cited by 27
Clinical Promise of Brain-Phenotype Modeling: A Review
Greene, A. S., & Constable, R. T. (2023) · JAMA Psychiatry · doi:10.1001/jamapsychiatry.2023.1419 · Cited by 20
Fairness-Aware Range Queries for Selecting Unbiased Data
Shetiya, S., Swift, I. P., Asudeh, A., & Das, G. (2022) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde53745.2022.00111 · Cited by 33
Investigating Oversampling Techniques for Fair Machine Learning Models
Rančić, S., Radovanović, S., & Delibašić, B. (2021) · Lecture notes in business information processing · doi:10.1007/978-3-030-73976-8_9 · Cited by 31
Rawls’s Original Position and Algorithmic Fairness
Franke, U. (2021) · Philosophy & Technology · doi:10.1007/s13347-021-00488-x · Cited by 29
New Digital Work: Digital Sovereignty at the Workplace
Shajek, A., & Hartmann, E. (2023) · Springer eBooks · doi:10.1007/978-3-031-26490-0 · Cited by 27
Travel Demand Forecasting: A Fair AI Approach
Zhang, X., Ke, Q., & Zhao, X. (2024) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2024.3395061 · Cited by 25
Predicting and explaining behavioral data with structured feature space decomposition
Fennell, P. G., Zuo, Z., & Lerman, K. (2019) · EPJ Data Science · doi:10.1140/epjds/s13688-019-0201-0 · Cited by 20
Accountability and AI: Redundancy, Overlaps and Blind-Spots
Elliott, M. T. J., & MacCárthaigh, M. (2025) · Public Performance & Management Review · doi:10.1080/15309576.2025.2493889 · Cited by 22
Censorship of Online Encyclopedias: Implications for NLP Models
Yang, E., & Roberts, M. E. (2021) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3442188.3445916 · Cited by 28
Fair governance with humans and machines.
Hermstrüwer, Y., & Langenbach, P. (2023) · Psychology, Public Policy, and Law · doi:10.1037/law0000381 · Cited by 19
AI as Social Actor: A Lacanian Investigation into Social Technology
Heimann, M., & Hübener, A.-F. (2023) · Journal of Digital Social Research · doi:10.33621/jdsr.v5i1.159 · Cited by 23
How to Evaluate Explainability? - A Case for Three Criteria
Speith, T. (2022) · IEEE International Requirements Engineering Conference Workshops (REW) · doi:10.1109/rew56159.2022.00024 · Cited by 21
Values and inductive risk in machine learning modelling: the case of binary classification models
Karaca, K. (2021) · European Journal for Philosophy of Science · doi:10.1007/s13194-021-00405-1 · Cited by 29
Wang, Y., Wang, L., Zhou, Z., Novoa-Laurentiev, J., Lakin, J. R., Zhou, L., & Hong, P. (2024) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2024.104677 · Cited by 23
The perfect technological storm: artificial intelligence and moral complacency
Kaas, M. H. L. (2024) · Ethics and Information Technology · doi:10.1007/s10676-024-09788-0 · Cited by 21
Long-Term Impacts of Fair Machine Learning
Zhang, X., Khalili, M. M., & Liu, M. (2019) · Ergonomics in Design The Quarterly of Human Factors Applications · doi:10.1177/1064804619884160 · Cited by 30
Designing an AI compatible open government data ecosystem for public governance
Tan, E. (2023) · Information Polity · doi:10.3233/ip-220020 · Cited by 18
Minding the AI: Ethical Challenges and Practice for AI Mental Health Care Tools
Martinez‐Martin, N. (2021) · Advances in neuroethics · doi:10.1007/978-3-030-74188-4_8 · Cited by 31
He, J., & Zhang, Z. (2025) · Laws · doi:10.3390/laws14040054 · Cited by 26
Exacerbating Algorithmic Bias through Fairness Attacks
Mehrabi, N., Naveed, M., Morstatter, F., & Galstyan, A. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i10.17080 · Cited by 57
Algorithms and the individual in criminal law
Jorgensen, R. (2022) · Canadian Journal of Philosophy · doi:10.1017/can.2021.28 · Cited by 18
Gupte, S., & Paparrizos, J. (2025) · Proceedings of the ACM on Management of Data · doi:10.1145/3725420 · Cited by 20
A Novel Approach for Fair Principal Component Analysis Based on Eigendecomposition
Pelegrina, G. D., & Duarte, L. T. (2023) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2023.3298291 · Cited by 21
Singular race models: addressing bias and accuracy in predicting prisoner recidivism
Jain, B., Huber, M., Fegaras, L., & Elmasri, R. A. (2019) · International Conference on PErvasive Technologies Related to Assistive Environments (PETRA) · doi:10.1145/3316782.3322787 · Cited by 22
From Explanation to Recommendation: Ethical Standards for Algorithmic Recourse
Sullivan, E., & Verreault-Julien, P. (2022) · Proceedings of the AAAI/ACM Conference on AI Ethics and Society · doi:10.1145/3514094.3534185 · Cited by 23
Emergent Virtual Analytics: Artificial Intelligence and Human-Computer Interactions
Ninness, C., & Ninness, S. K. (2020) · Behavior and Social Issues · doi:10.1007/s42822-020-00031-1 · Cited by 21
Zehlike, M., Loosley, A., Jonsson, H., Wiedemann, E., & Hacker, P. (2025) · Artificial Intelligence · doi:10.1016/j.artint.2024.104280 · Cited by 27
Interpreting Deep Neural Networks Through Variable ImportancePreprint
Ish-Horowicz, J., Udwin, D., Flaxman, S. R., Filippi, S., & Crawford, L. A. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1901.09839 · Cited by 24
On prediction-modelers and decision-makers: why fairness requires more than a fair prediction model
Scantamburlo, T., Baumann, J., & Heitz, C. (2024) · AI & Society · doi:10.1007/s00146-024-01886-3 · Cited by 28
A comparative user study of human predictions in algorithm-supported recidivism risk assessment
Portela, M., Castillo, C., Tolan, S., Karimi-Haghighi, M., & Pueyo, A. A. (2024) · Artificial Intelligence and Law · doi:10.1007/s10506-024-09393-y · Cited by 23
Liu, J., & Li, D. M. (2024) · Asian Journal of Criminology · doi:10.1007/s11417-024-09429-x · Cited by 21
An Algorithmic Equity Toolkit for Technology Audits by Community Advocates and ActivistsPreprint
Katell, M. A., Young, M., Herman, B., Dailey, D., Tam, A., Guetler, V., Binz, C., Raz, D., & Krafft, P. M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1912.02943 · Cited by 18
Horesh, Y., Haas, N., Mishraky, E., Resheff, Y. S., & Lador, S. M. (2020) · Communications in computer and information science · doi:10.1007/978-3-030-43823-4_47 · Cited by 20
IB-GAN: A Unified Approach for Multivariate Time Series Classification under Class Imbalance
Deng, G., Han, C., Dreossi, T., Lee, C. C., & Matteson, D. S. (2022) · Society for Industrial and Applied Mathematics eBooks · doi:10.1137/1.9781611977172.25 · Cited by 25
Rashomon Effect and Consistency in Explainable Artificial Intelligence (XAI)
Leventi-Peetz, A.-M., & Weber, K. (2022) · Lecture notes in networks and systems · doi:10.1007/978-3-031-18461-1_52 · Cited by 18
Generating and leveraging explanations of AI/ML models in materials and manufacturing research
Braham, E. J., Ruddock, J. M., & Hardin, J. O. (2025) · Patterns · doi:10.1016/j.patter.2025.101340 · Cited by 22
Target specification bias, counterfactual prediction, and algorithmic fairness in healthcare
Tal, E. (2023) · Proceedings of the AAAI/ACM Conference on AI Ethics and Society · doi:10.1145/3600211.3604678 · Cited by 26
A Multi-Objective Framework for Balancing Fairness and Accuracy in Debiasing Machine Learning Models
Nagpal, R., Khan, A., Borkar, M., & Gupta, A. D. (2024) · Machine Learning and Knowledge Extraction · doi:10.3390/make6030105 · Cited by 21
Algorithmic Fairness Verification with Graphical Models
Ghosh, B., Basu, D., & Meel, K. S. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i9.21187 · Cited by 28
Algorithmic Regimes: Methods, Interactions, and Politics
Jarke, J., Prietl, B., Egbert, S., Boeva, Y., Heuer, H., & Arnold, M. (2024) · Amsterdam University Press eBooks · doi:10.1515/9789048556908 · Cited by 23
Machine learning and behavioral economics for personalized choice architecturePreprint
Hrnjić, E., & Tomczak, N. (2019) · RePEc: Research Papers in Economics · doi:10.48550/arxiv.1907.02100 · Cited by 25
Engel, C., & Grgić-Hlača, N. (2021) · Journal of Legal Analysis · doi:10.1093/jla/laab001 · Cited by 16
The AI Generalization Gap: One Size Does Not Fit All
Huisman, M., & Hannink, G. (2023) · Radiology Artificial Intelligence · doi:10.1148/ryai.230246 · Cited by 18
Köbis, N., Starke, C., & Rahwan, I. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2102.11567 · Cited by 16
First- and Second-Level Bias in Automated Decision-making
Franke, U. (2022) · Philosophy & Technology · doi:10.1007/s13347-022-00500-y · Cited by 21
Belaid, M. K., Bornemann, R., Rabus, M., Krestel, R., & Hüllermeier, E. (2023) · Communications in computer and information science · doi:10.1007/978-3-031-44067-0_5 · Cited by 19
Foresight-Based Leadership. Decision-Making in a Growing AI Environment
Reez, N. (2020) · Advanced sciences and technologies for security applications · doi:10.1007/978-3-030-42523-4_22 · Cited by 16
Approximation Algorithms for Socially Fair ClusteringPreprint
Makarychev, Y., & Vakilian, A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.02512 · Cited by 71
Application of fairness to healthcare, organizational justice, and finance: A survey
Birzhandi, P., & Cho, Y.-S. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.119465 · Cited by 22
A Bio-Inspired Framework for Machine Bias Interpretation
Robertson, J., Stinson, C., & Hu, T. (2022) · Proceedings of the AAAI/ACM Conference on AI Ethics and Society · doi:10.1145/3514094.3534126 · Cited by 26
International AI Safety Report
Bengio, Y., Mindermann, S., Privitera, D., Besiroglu, T., Bommasani, R., Casper, S., Choi, Y., Fox, P., Garfinkel, B., Goldfarb, D., et al. (2025) · arXiv · doi:10.48550/arxiv.2501.17805 · Cited by 16
Identification, Categorisation and Forecasting of Court Decisions
Medvedeva, M. (2022) · University of Groningen research database (University of Groningen / Centre for Information Technology) · doi:10.33612/diss.236807643 · Cited by 16
A comparative study on the impact of model compression techniques on fairness in language models
Ramesh, K., Chavan, A., Pandit, S., & Sitaram, S. (2023) · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2023.acl-long.878 · Cited by 15
König, P. D., & Krafft, T. D. (2021) · Current Issues in Criminal Justice · doi:10.1080/10345329.2020.1849932 · Cited by 16
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.
