Measurement and Fairness
Open accessThe DOI matches its Crossref record; 35 of the 35 references it cites were found in a registry or an index; 7 of the 70 sources its claims cite were checked for support.
Abstract
We propose measurement modeling from the quantitative social sciences as a framework for understanding fairness in computational systems. Computational systems often involve unobservable theoretical constructs, such as socioeconomic status, teacher effectiveness, and risk of recidivism. Such constructs cannot be measured directly and must instead be inferred from measurements of observable properties (and other unobservable theoretical constructs) thought to be related to them---i.e., operationalized via a measurement model. This process, which necessarily involves making assumptions, introduces the potential for mismatches between the theoretical understanding of the construct purported to be measured and its operationalization. We argue that many of the harms discussed in the literature on fairness in computational systems are direct results of such mismatches. We show how some of these harms could have been anticipated and, in some cases, mitigated if viewed through the lens of measurement modeling. To do this, we contribute fairness-oriented conceptualizations of construct reliability and construct validity that unite traditions from political science, education, and psychology and provide a set of tools for making explicit and testing assumptions about constructs and their operationalizations. We then turn to fairness itself, an essentially contested construct that has different theoretical understandings in different contexts. We argue that this contestedness underlies recent debates about fairness definitions: although these debates appear to be about different operationalizations, they are, in fact, debates about different theoretical understandings of fairness. We show how measurement modeling can provide a framework for getting to the core of these debates.
Overview
CoChat Summary
TL;DR
The paper proposes measurement modeling from the quantitative social sciences as a framework for understanding fairness in computational systems, arguing that many fairness harms stem from mismatches between unobservable theoretical constructs and their operationalizations. It contributes fairness-oriented construct reliability and construct validity tools and argues that debates over fairness definitions are really debates about different theoretical understandings of fairness—i.e., values.
Key findings
- Many fairness-related harms arise because computational systems operationalize unobservable constructs—such as socioeconomic status, teacher effectiveness, risk of recidivism, and patient benefit—via measurement models whose assumptions are left implicit or untested.
- The authors contribute fairness-oriented conceptualizations of construct reliability and construct validity, including seven aspects of construct validity: face, content, convergent, discriminant, predictive, hypothesis, and consequential validity.
- Recent fairness-definition debates—such as individual vs. group fairness and COMPAS’s error-rate balance vs. predictive parity—are framed as operationalization disputes but are actually debates about different theoretical understandings of fairness, and therefore about values.
- Examples include Obermeyer et al.’s finding that only 18% of patients identified for high-risk care management enrollment were Black; EVAAS teacher-effectiveness scores varying from 6/100 to 96/100 for one teacher; and the Universal Credit system treating £1000 paychecks on March 30 and April 29 as a £2000 monthly wage.
Methods
- Conceptual/position paper; no empirical data collection or new dataset.
- Uses five illustrative examples: measuring height, socioeconomic status, teacher effectiveness via EVAAS MRM, risk of recidivism via COMPAS, and patient benefit via high-risk care management models.
- Analysis is conceptual synthesis, uniting traditions from political science, education, and psychology to apply construct reliability and construct validity to fairness in computational systems.
Limitations
- Stated: the authors acknowledge that assessing construct reliability and construct validity can be time-consuming, and they omit inter-rater reliability and inter-item reliability from their conceptualization.
- Stated: they emphasize that values play a role in the measurement modeling process, not that measurement modeling is value-free.
- Evident: as a conceptual paper, it offers no new empirical validation or dataset; its examples and numbers rely on prior literature, documentation, and reported cases.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
5 Valid · 13 Not valid · 48 Not checked · 116 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“In contrast to computer scientists, who focus primarily on out-ofsample prediction, quantitative social scientists typically test their assumptions by assessing construct reliability and construct validity.”
§ Measurement and Fairness > 3 TESTING ASSUMPTIONS
What the sources say
- Partly supportedcites [49] matched to “How to analyze political attention with minimal assumptions and costs” (2010) sourceExperimental — accuracy not yet measured
The 'Reliability, Validity, Interpretation, and Application' section supports the substance of the claim: 'The evaluation of any measurement is generally based on its reliability (can it be repeated?) and validity (is it right?),' and the paper then assesses convergent and discriminant construct validity (with Weber 1990 cited) plus semantic, predictive and hypothesis validity. The companion 'Categorizing Texts: Methods, Assumptions, and Costs' section does describe supervised learning as evaluated by 'summaries of out-of-sample predictive accuracy,' which underwrites the contrasting half of the citing sentence. What our copy does not state is the disciplinary generalization itself: it never says that quantitative social scientists 'typically' test assumptions this way, nor that computer scientists focus primarily on out-of-sample prediction — the reliability/validity framing is presented as a general principle of measurement evaluation in content analysis, not as a characterization of a research community. (LLM, conf=0.70)
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.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Prompted by this, many academic papers began to discuss the properties and shortcomings of different definitions of group fairness, with some papers demonstrating that it is impossible for a system like COMPAS to possess both error-rate balance and predictive parity when the probability of recidivism for Black defendants is not the same as the probability of recidivism for white defendants [9,11,1”
§ Measurement and Fairness > 4.4 Group Fairness
What the sources say
- Partly supportedcites [9] matched to “Fairness in Criminal Justice Risk Assessments: The State of the Art” (2021) sourceExperimental — accuracy not yet measured
Section 6.1 (p. 18) states that equal error rates and conditional use accuracy cannot both be achieved when groups have different base rates and classification is not perfect. The claim omits the paper’s qualification: with perfect separation, both can be achieved despite different base rates. (LLM, conf=0.88)
- Supportedcites [11] matched to “Fair prediction with disparate impact: a study of bias in recidivism prediction instruments” (2017) source
Section 2.1 (p. 2) says test fairness implies equal positive predictive value across groups, and that when recidivism prevalence differs, a test-fair score cannot have equal false-positive and false-negative rates across those groups. It applies this result to Black and White defendants assessed with COMPAS. (LLM, conf=0.93)
- Not checked yetcites [13]
boosted- 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.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“by using arrests as a proxy for crimes committed, COMPAS can only exacerbate racist policing practices, rather than transcending them [7,13,23,37,39].”
§ Measurement and Fairness > 3.2.7 Consequential validity.
What the sources say
- Not checked yetcites [7]
- Not checked yetcites [13]
- Partly supportedcites [23] matched to “The false promise of risk assessments: epistemic reform and the limits of fairness” (2020) sourceExperimental — accuracy not yet measured
Section 5 says risk assessments use arrest data that typically provide a racially biased measure of crime, supporting the claim's concern about using arrests as a proxy. Sections 3 and 3.3 argue that these tools do not necessarily reduce racial discrimination and are poorly suited to structural reform. The paper does not establish the stronger claim that COMPAS can only exacerbate racist policing practices. (LLM, conf=0.84)
- Partly supportedcites [37] matched to “To Predict and Serve?” (2016) sourceExperimental — accuracy not yet measured
The ‘Bias in police-recorded data’ and ‘Discussion’ sections say that police records reflect unequal policing and that predictive policing can reproduce and magnify those biases. But the paper’s case study examines PredPol, not COMPAS; it does not establish that COMPAS uses arrests as a proxy for crimes committed or that it can only exacerbate racist policing. (LLM, conf=0.87)
- Not checked yetcites [39]
plainstates a cause- 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.
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Moreover, because most computational systems are developed by computer scientists, the practice of collapsing these distinctions is widespread [47].”
§ Measurement and Fairness > 5 DISCUSSION
What the sources say
- Partly supportedcites [47] matched to “Problem Formulation and Fairness” (2019) sourceExperimental — accuracy not yet measured
Our copy of Passi & Barocas (2019) does support the descriptive half of the claim: the Abstract states that 'the specification and operationalization of the problem are always negotiated and elastic, and rarely worked out with explicit normative considerations in mind,' and normative assessments 'often take them for granted'; the case-study section (4 CASE-STUDY: SPECIAL FINANCING) shows practitioners equating lead quality with financeability, financeability with dealer decisions, and dealer decisions with credit score ranges, i.e. collapsing a construct into its proxy/measure. What the paper nowhere says is the causal premise the citing sentence attaches to it — that this practice is widespread 'because most computational systems are developed by computer scientists'; no passage makes any claim about who develops most computational systems, and the BACKGROUND section instead stresses that applied data science is 'inherently collaborative,' with 'project managers, product designers, and business analysts ... as much a part of ... corporate data science as are data scientists' [36:16]. The paper's own explanation for such collapses is practical and organizational (business requirements, data availability, analytic cost), not the disciplinary composition of developers, so the attributing mechanism and the 'widespread' generalization beyond one ethnographed team are unsupported. (LLM, conf=0.70)
plainstates a cause- 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.
- Partly supported
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“We emphasize that even with careful consideration of different theoretical understandings and careful assessment of both construct reliability and construct validity, this approach is fraught and likely to cause a variety of fairness-related and other harms [e.g., 8, 22, 33, 35, 44], despite good intentions.”
§ Measurement and Fairness > 4.5 Demographic Factors
What the sources say
- Not checked yetcites [8] matched to “What is the point of fairness?” (2020) source
- Partly supportedcites [22] matched to “The Profiling Potential of Computer Vision and the Challenge of Computational Empiricism” (2019) sourceExperimental — accuracy not yet measured
Split into 2 atoms — 1 confirmed, 1 partially supported, 0 disputed, 0 misattributed, 0 unverifiable. Expand the claim to see per-atom verdicts.
- Not checked yetcites [33] matched to “The Misgendering Machines: Trans/HCI Implications of Automatic Gender Recognition” (2018) source
hedgedstates a cause- 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.
77 more claims
Create a free account to see all 182 claims and to verify the 63 references still open.
- It may state two separate claims as one. 42
- Probably not a substantial claim. 82
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
“When measurement bias is associated with a sensitive characteristic, in this case gender, the model is likely to replicate the pattern which can result in an unfair allocation of jobs [59].”
From Algorithmic Unfairness through the Lens of EU Non-Discrimination Law: Or Why the Law is not a Decision Tree (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
“Essentially, equal calibration requires that the meaning of predicted scores is equal across groups [59]: receiving a score of 0.7 corresponds to a probability of 0.7, irrespective of sensitive group membership.”
From Algorithmic Unfairness through the Lens of EU Non-Discrimination Law: Or Why the Law is not a Decision Tree (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
“These evaluations should also demonstrate that the outcome of interest can be measured with reasonable accuracy and validity, as low-quality data and bad proxy variables present a significant limit on an algorithm's reliability ( Jacobs & Wallach, 2021 ).”
From The flaws of policies requiring human oversight of government algorithms (2022) · cites this paper as Jacobs & Wallach, 2021
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“Framing bias as something to be measured objectively ignores the assumptions made in the operationalization of the measurement tool (Jacobs and Wallach 2021).”
From Bias and Fairness in Large Language Models: A Survey (2024) · cites this paper as Jacobs and Wallach 2021
Citations
Cites
Dwork, C., Hardt, M., Pitassi, T., Reingold, O., & Zemel, R. (2012) · Proceedings of the 3rd Innovations in Theoretical Computer Science Conference · doi:10.1145/2090236.2090255 · Cited by 3,501
Equality of Opportunity in Supervised Learning
Hardt, M., Price, E., & Srebro, N. (2016) · arXiv · doi:10.48550/arxiv.1610.02413 · Cited by 2,536 · cited 1×
“5Error-rate balance is also known as equalized odds [28].”
Fair prediction with disparate impact: a study of bias in recidivism prediction instruments
Chouldechova, A. (2017) · Big Data · doi:10.1089/big.2016.0047 · Cited by 2,159 · cited 2×
“r operationalization, i.e., calibration. The fairness in machine learning community responded, largely re ecting the incompatibilities and shortcomings of dierent fairness operationalizations (e.g., [8, 11, 15, 13, 39, 54]). Meanwhile, Chouldechova [11] and Kleinberg et al. [39] proved that the two prominent and desir…”
BackgroundInfluentialMachine Learning: An Applied Econometric Approach
Mullainathan, S., & Spiess, J. (2017) · Journal of Economic Perspectives · doi:10.1257/jep.31.2.87 · Cited by 1,989 · cited 1×
“Despite the name, predictive validity is not the same as out-of-sample prediction [29, 47].”
BackgroundFairness and Abstraction in Sociotechnical Systems
Selbst, A. D., Boyd, D., Friedler, S. A., Venkatasubramanian, S., & Vertesi, J. (2019) · Proceedings of the Conference on Fairness, Accountability, and Transparency · doi:10.1145/3287560.3287598 · Cited by 1,631 · cited 2×
“modeling brings the biggest value to fairness. In practice, evaluation of computational systems can fail to characterize potential harms which are otherwise captured by failures of construct validity [27, 53, 59]. The language of measurement, with the tools of construct validity and reliability, provide a concrete fra…”
BackgroundObjective Tests as Instruments of Psychological Theory
Loevinger, J. (1957) · Psychological Reports · doi:10.2466/pr0.1957.3.3.635 · Cited by 1,473
Algorithmic Decision Making and the Cost of Fairness
Corbett-Davies, S., Pierson, E., Feller, A., Goel, S., & Huq, A. (2017) · Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/3097983.3098095 · Cited by 1,149
Fairness in Criminal Justice Risk Assessments: The State of the Art
Berk, R., Heidari, H., Jabbari, S., Kearns, M., & Roth, A. (2021) · Sociological Methods & Research · doi:10.1177/0049124118782533 · Cited by 988 · cited 3×
“explicitly consider how to minimize or compensate for historical injustices [11]. This nontrivial measurement task is deeply complex and requires signicant debate about justice, policy, and fairness [8, 13, 15, 37]. 4.2 Value-Added Modeling in Education We now look to the well-known example of value-added modeling for…”
BackgroundInfluentialInherent 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
Social Data: Biases, Methodological Pitfalls, and Ethical Boundaries
Olteanu, A., Castillo, C., Diaz, F., & Kıcıman, E. (2019) · Frontiers in Big Data · doi:10.3389/fdata.2019.00013 · Cited by 763 · cited 2×
“, [27, 41, 50].”
Background
Research works printed but not linked: 17
- Audrey Amrein-Beardsley and Tray Geiger. 2020. Methodological Concerns About the Education Value-Added Assessment System (EVAAS): Validity, Relia- bility, and Bias. SAGE Open 10, 2 (2020), 2158244020922224.
- Julia Angwin, Jeff Larson, Surya Mattu, and Lauren Kirchner. 2016. Machine Bias. ProPublica (May 2016).
- Solon Barocas, Kate Crawford, Aaron Shapiro, and Hanna Wallach. 2017. The problem with bias: from allocative to representational harms in machine learning. Special Interest Group for Computing. Information and Society (SIGCIS) (2017).
- Geoffrey C Bowker and Susan Leigh Star. 2000. Sorting things out: Classification and its consequences. MIT Press. · doi:10.5555/380681
- Sam Corbett-Davies, Emma Pierson, Avi Feller, and Sharad Goel. 2016. A com- puter program used for bail and sentencing decisions was labeled biased against blacks. It's actually not that clear. Washington Post (October 2016).
- Kate Crawford. 2017. The Trouble with Bias. NIPS Keynote, https://www. youtube.com/watch?v=fMym_BKWQzk, accessed 08-22-2018.
- Walter Bryce Gallie. 1955. Essentially contested concepts. In Proceedings of the Aristotelian Society, Vol. 56. JSTOR, 167-198.
- Justin Grimmer. 2012. Comment: Evaluating model performance in fictitious prediction problems. Technical Report.
- Simon Jackman. 2008. Measurement. In The Oxford Handbook of Political Method- ology. Oxford Univ. Press, Chapter 9.
- Matthew Joseph, Michael Kearns, Jamie H Morgenstern, and Aaron Roth. 2016. Fairness in learning: Classic and contextual bandits. NIPS (2016).
- Sandra G Mayson. 2018. Bias in, bias out. Yale Law Journal 128 (2018), 2218.
- Samuel Messick. 1987. Validity. In ETS Research Report Series.
- Ziad Obermeyer, Brian Powers, Christine Vogeli, and Sendhil Mullainathan. 2019. Dissecting racial bias in an algorithm used to manage the health of populations. Science 366, 6464 (2019), 447-453.
- Cathy O'Neil. 2016. Weapons of Math Destruction. Broadway Books.
- Geoff Pleiss, Manish Raghavan, Felix Wu, Jon Kleinberg, and Kilian Q Weinberger. 2017. On fairness and calibration. NIPS (2017).
- Anna Roberts. 2018. Arrests as guilt. Ala. L. Rev. 70 (2018), 987.
- Human Rights Watch. 2020. UK: Automated Benefits System Failing People in Need. https://www.hrw.org/news/2020/09/29/uk-automated-benefits-system- failing-people-need
Cited by
Items 101–200 of 374
Pairwise Fairness in Ranking as a Dissatisfaction Measure
Fabris, A., Silvello, G., Susto, G. A., & Biega, A. J. (2023) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/3539597.3570459 · Cited by 30
“Following Jacobs and Wallach [26], we examine fairness measures distinguishing between the construct, i.e., the theoretical property that a measure intends to capture, and the operationalization, i.e., the particular mathematical formulation meant to model that property.”
BackgroundMethodAdomavičius, G., & Yang, M. (2019) · ACM Transactions on Management Information Systems · doi:10.1145/3519420 · Cited by 37
“The assumption behind the measurement model – that patients with comparable healthcare costs also have similar healthcare needs – is problematic because black patients are unfortunately exposed to higher costs than white patients with similar healthcare needs [97, 151].”
BackgroundInfluentialSwahBERT: Language Model of Swahili
Martin, G. L., Mswahili, M. E., Jeong, Y.-S., & Young-Seob, J. (2022) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2022.naacl-main.23 · Cited by 49
D’Arcy, A., & Bender, E. M. (2022) · Annual Review of Linguistics · doi:10.1146/annurev-linguistics-031120-015324 · Cited by 43
Model Sketching: Centering Concepts in Early-Stage Machine Learning Model Design
Lam, M. S., Ma, Z., Li, A., Freitas, I., Wang, D., Landay, J. A., & Bernstein, M. S. (2023) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3581290 · Cited by 33
“Model sketching aims to facilitate the translational, interpretational work that goes in between a high-level description and any particular low-level implementation [27, 45].”
BackgroundWatkins, E. A., & Chen, J. (2024) · The 2024 ACM Conference on Fairness Accountability and Transparency · doi:10.1145/3630106.3658938 · Cited by 25
“Jacobs and Wallach [29] describes risks of abstracting concepts which are challenging to measure, such as gender and teacher effectiveness.”
BackgroundCan Fairness be Automated? Guidelines and Opportunities for Fairness-aware AutoML
Weerts, H., Pfisterer, F., Feurer, M., Eggensperger, K., Bergman, E., Awad, N. H., Vanschoren, J., Pechenizkiy, M., Bischl, B., & Hutter, F. (2024) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.14747 · Cited by 53
“…notions of fairness Every quantitative fairness metric is necessarily a simplification, lacking aspects of the substantive nature of fairness long debated by philosophers, legal scholars, and sociologists (Selbst et al., 2019; Jacobs & Wallach, 2021; Schwöbel & Remmers, 2022; Watkins et al., 2022).”
BackgroundA Proposal for Identifying and Managing Bias in Artificial Intelligence
Schwartz, R., Down, L., Jonas, A., & Tabassi, E. (2021) · doi:10.6028/nist.sp.1270-draft · Cited by 50
“Data can also differ significantly between what is collected and what occurs in the real world [71,72,109].”
BackgroundEthical Implications of AI in Data Collection: Balancing Innovation with Privacy
Mirishli, S. (2024) · ANCIENT LAND · doi:10.36719/2706-6185/38/40-55 · Cited by 45
“In response to such incidents, 2024 saw the emergence of "AI Fairness Benchmarks" proposed by a coalition of AI researchers and ethicists (Jacobs & Wallach, 2021, p. 377).”
Pfohl, S. R., Zhang, H., Xu, Y., Foryciarz, A., Ghassemi, M., & Shah, N. H. (2022) · Scientific Reports · doi:10.1038/s41598-022-07167-7 · Cited by 43
“[14] Abigail Z Jacobs and Hanna Wallach.”
From Bias to Repair: Error as a Site of Collaboration and Negotiation in Applied Data Science Work
Lin, C. K., & Jackson, S. J. (2023) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3579607 · Cited by 22
Arbitrariness and Social Prediction: The Confounding Role of Variance in Fair Classification
Cooper, A. F., Lee, K., Choksi, M. Z., Barocas, S., De, C., Grimmelmann, J., Kleinberg, J. M., Sen, S., & Zhang, B. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i20.30203 · Cited by 89
“Other than indicating serious concerns about the rigor of experiments in fairness research, our findings suggest ethical issues about the role of mismeasurement in identifying and allocating resources to specific research problems (Jacobs and Wallach 2021).”
BackgroundHow Does Counterfactually Augmented Data Impact Models for Social Computing Constructs?
Sen, I., Samory, M., Flöck, F., Wagner, C., & Augenstein, I. (2021) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2021.emnlp-main.28 · Cited by 39
“e, the intangible measure like sentiment or stance that is the ultimate goal of the learning task (Jacobs and Wallach, 2021).”
BackgroundChancellor, S., Sumner, S. A., David-Ferdon, C. F., Ahmad, T., & Choudhury, M. D. (2021) · JMIR Mental Health · doi:10.2196/24471 · Cited by 33
“Measures of validity have a long and rich history in social sciences (under the name of measurement modeling) [27], computational linguistics [28,29], and psychometrics [30,31].”
BackgroundInfluentialNeumann, T., De‐Arteaga, M., & Fazelpour, S. (2022) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3531146.3533205 · Cited by 44
“Thus, the harms associated with false negative errors, or underscrutiny of claims, may be disproportionately concentrated in certain groups as a result ofmeasurement bias in the training labels [42].”
BackgroundSmith, J. J., Beattie, L., & Cramer, H. S. M. (2023) · International World Wide Web Conference (WWW) · doi:10.1145/3543507.3583204 · Cited by 34
“This is a crucial step due to fairness being a subjective and non-observable construct [22, 49].”
BackgroundInfluentialAART: AI-Assisted Red-Teaming with Diverse Data Generation for New LLM-powered Applications
Radharapu, B., Robinson, K., Aroyo, L. M., & Lahoti, P. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-industry.37 · Cited by 111
Keeping Humans in the Loop: Human-Centered Automated Annotation with Generative AI
Pangakis, N., & Wolken, S. (2025) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v19i1.35883 · Cited by 27
Kyriakou, K., & Otterbacher, J. (2023) · Discover Artificial Intelligence · doi:10.1007/s44163-023-00092-2 · Cited by 38
“When it comes to perceived fairness, research has shown that people perceive “fairness” in different ways [27].”
An archival perspective on pretraining data
Desai, M. A., Pasquetto, I. V., Jacobs, A. Z., & Card, D. (2024) · Patterns · doi:10.1016/j.patter.2024.100966 · Cited by 37
“Despite this, pre-training data often include legally and ethically contested data: most web-scale datasets are collected without consent.”
Self-citationThe Value-Sensitive Conversational Agent Co-Design Framework
Sadek, M., Calvo, R., & Mougenot, C. (2023) · International journal of human computer interactions · doi:10.1080/10447318.2024.2426737 · Cited by 26
Is GPT-4 fair? An empirical analysis in automatic short answer grading
Rodrigues, L., Xavier, C., da Costa, N. T., Gašević, D., & Mello, R. F. (2025) · Computers and Education Artificial Intelligence · doi:10.1016/j.caeai.2025.100428 · Cited by 39
Integrating Fairness in the Software Design Process: An Interview Study With HCI and ML Experts
Ryan, S., Nadal, C., & Doherty, G. J. (2023) · IEEE Access · doi:10.1109/access.2023.3260639 · Cited by 33
“The reliability and validity of these measures are assessed during the design process [53].”
BackgroundMethodMihaljević, H., Müller, I., Dill, K., Yollu-Tok, A., & von Grafenstein, M. (2023) · AI & Society · doi:10.1007/s00146-023-01726-w · Cited by 31
“…data (Orwat 2019), the selection of features, target variables, or error function(s) (Dobbe et al. 2018), a lack of data points about certain groups of people, or the operationalization and measurement of phenomena that are not directly observable, such as recidivism risk (Jacobs and Wallach 2021).”
Specification overfitting in artificial intelligence
Roth, B., de Araujo, P. H. L., Xia, Y., Kaltenbrunner, S., & Korab, C. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-024-11040-6 · Cited by 26
“The requirements are constructs: unobservable theoretical abstractions that describe phenomena of interest, such as robustness and fairness (Jacobs and Wallach, 2021).”
InfluentialBlack, E., Naidu, R. C. A., Ghani, R., Rodolfa, K. T., Ho, D. E., & Heidari, H. (2023) · ACM Conference on Equity and Access in Algorithms, Mechanisms, and Optimization (EAAMO) · doi:10.1145/3617694.3623259 · Cited by 44
The Fall of an Algorithm: Characterizing the Dynamics Toward Abandonment
Johnson, N., Moharana, S., Harrington, C., Andalibi, N., Heidari, H., & Eslami, M. (2024) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3630106.3658910 · Cited by 28
“Such methods can be used to correct the algorithm’s flaws, often defined in terms of narrowly scoped measures [93], while maintaining the algorithm’s operation.”
MethodMaking Artificial Intelligence Transparent: Fairness and the Problem of Proxy Variables
Warner, R., & Sloan, R. H. (2021) · Criminal Justice Ethics · doi:10.1080/0731129x.2021.1893932 · Cited by 19
Conceptualizing Algorithmic Stigmatization
Andalibi, N., Pyle, C., Barta, K., Xian, L., Jacobs, A. Z., & Ackerman, M. S. (2023) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3544548.3580970 · Cited by 33
“humans may annotate student data, infer labels of "risk," or sort data into buckets along some "risk" dimension [101, 146].”
BackgroundSelf-citationAn Empirical Analysis of Racial Categories in the Algorithmic Fairness Literature
Abdu, A. A., Pasquetto, I. V., & Jacobs, A. Z. (2023) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3593013.3594083 · Cited by 34
“As Jacobs and Wallach [15] argue, decisions about how to operationalize social constructs such as race are not merely an academic concern but have real, fairness-related consequences.”
BackgroundSelf-citationThe reanimation of pseudoscience in machine learning and its ethical repercussions
Andrews, M., Smart, A., & Birhane, A. (2024) · Patterns · doi:10.1016/j.patter.2024.101027 · Cited by 18
A Total Error Framework for Digital Traces of HumansPreprint
Sen, I., Flöck, F., Weller, K., Weiß, B., & Wagner, C. (2019) · arXiv (Cornell University) · Cited by 26
Keywords of the Datafied StatePreprint
Burrell, J., Singh, R., & Davison, P. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4734250 · Cited by 25
Stray, J. (2023) · Analytics · doi:10.3390/analytics2020020 · Cited by 26
“It can be challenging to establish validity (the survey correctly measures what it is intended to measure) and reliability (survey results are appropriately stable over time and between people) [53].”
Watson-Daniels, J., Barocas, S., Hofman, J. M., & Chouldechova, A. (2023) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3593013.3593998 · Cited by 33
“Scholars have identified various reasons why the choice of target or proxy might raise concerns with fairness: some outcomes or qualities of interests might just be more evenly distributed across the population than others [23, 34]; certain outcomes or qualities of interests might be easier to predict with similar deg…”
BackgroundOn (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 37
Recommend Me? Designing Fairness Metrics with Providers
Smith, J. J., Satwani, A., Burke, R., & Fiesler, C. L. (2024) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3630106.3659044 · Cited by 36
“Fairness Operationalization is the process of scoping fairness goals, defining fairness based on those goals, selecting an appropriate fairness metric based on this definition, and incorporating it into the objectives of an ML system [35, 49, 53].”
BackgroundBenchmark suites instead of leaderboards for evaluating AI fairness
Wang, A., Hertzmann, A., & Russakovsky, O. (2024) · Patterns · doi:10.1016/j.patter.2024.101080 · Cited by 38
“34 This metric optimization can then cause problems such as overemphasizing easily measured short-term goals (e.g., clickthrough rate over reported preference) 16 or leveling-down models (i.e., achieving fairness by making most groups worse off).”
Enhancing Cybersecurity via Artificial Intelligence: Risks, Rewards, and Frameworks
Kroll, J. A., Michael, J. B., & Thaw, D. B. (2021) · Computer · doi:10.1109/mc.2021.3055703 · Cited by 25
Deconstructing NLG Evaluation: Evaluation Practices, Assumptions, and Their Implications
Zhou, K., Blodgett, S. L., Trischler, A., Daumé, H., Suleman, K., & Olteanu, A. (2022) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2022.naacl-main.24 · Cited by 54
Editorial: Big data and machine learning in sociology
Leitgöb, H., Prandner, D., & Wolbring, T. (2023) · Frontiers in Sociology · doi:10.3389/fsoc.2023.1173155 · Cited by 28
“This includes an adequate construct-measurement match and measurement modeling (Jacobs and Wallach, 2021).”
Kim, S., Bai, Y., Zhu, H., & Eslami, M. (2025) · Proceedings of the ACM on Human-Computer Interaction · doi:10.1145/3711079 · Cited by 24
“Due to these differences in fairness metrics, avid discussions on which metric and variable are the most suitable for assessing an algorithm emerged [1, 6, 68].”
Hutiri, W. T., Ding, A. Y., Kawsar, F., & Mathur, A. (2023) · ACM Transactions on Software Engineering and Methodology · doi:10.1145/3591867 · Cited by 25
“Yet, fairness is a contested construct [28] that is underpinned by the values of those that define it.”
BackgroundA 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 76
“…of interest necessarily involves making simplifying assumptions, and there is often a considerable conceptual distance between ML proxies and the ways human decision-makers think about the targeted construct (Green and Chen 2021; Guer-dan et al. 2023; Jacobs and Wallach 2021; Kawakami et al. 2022).”
BackgroundThe Long Arc of Fairness: Formalisations and Ethical Discourse
Schwöbel, P., & Remmers, P. (2022) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3531146.3534635 · Cited by 25
“The second step can be evaluated by asking: Does our formalisation indeed capture the ethical goal we have stated? As [24] points out, such measurement modelling tasks are standard problems in the quantitative social sciences.”
BackgroundForks over knives: Predictive inconsistency in criminal justice algorithmic risk assessment tools
Greene, T., Shmueli, G., Fell, J., Lin, C.-F., & Liu, H.-W. (2022) · Journal of the Royal Statistical Society Series A: Statistics in Society · doi:10.1111/rssa.12966 · Cited by 15
“One implication is that ARAI designers cannot evade the ethical issues of oper-ationalising ‘essentially contested’ constructs and values such as fairness (Friedler et al., 2021; Jacobs & Wallach, 2021; Mittelstadt, 2019).”
BackgroundBeattie, L., Taber, D., & Cramer, H. S. M. (2022) · ACM Conference on Recommender Systems (RecSys) · doi:10.1145/3523227.3547403 · Cited by 21
“Filtering this list was difficult akin to the discussion in [7].”
BackgroundInfluentialBias, fairness, and assurance in AI: overview and synthesis
Al-Khulaidy, A., & Kavak, H. (2023) · Elsevier eBooks · doi:10.1016/b978-0-32-391919-7.00016-0 · Cited by 17
On Text-based Personality Computing: Challenges and Future Directions
Fang, Q., Giachanou, A., Bagheri, A., Boeschoten, L., van Kesteren, E., Kamalabad, M. S., & Oberski, D. L. (2023) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2023.findings-acl.691 · Cited by 30
Training Towards Critical Use: Learning to Situate AI Predictions Relative to Human Knowledge
Kawakami, A., Guerdan, L., Cheng, Y., Glazko, K. S., Lee, M. L., Carter, S., Aréchiga, N., Zhu, H., & Holstein, K. (2023) · ACM Collective Intelligence Conference (CI) · doi:10.1145/3582269.3615595 · Cited by 25
“In this paper we focus closely on two of these:: • Target-construct mismatch : In many real-world deployment settings, AI models are trained to predict imperfect proxies for the true construct of interest to decision-makers [13, 21, 28, 32, 57].”
BackgroundSearch-based Automatic Repair for Fairness and Accuracy in Decision-making Software
Hort, M., Zhang, J. M., Sarro, F., & Harman, M. (2024) · Empirical Software Engineering · doi:10.1007/s10664-023-10419-3 · Cited by 20
“Due to the difficulty of determining the degree of similarity between individuals (Jacobs and Wallach 2021), it is common in the literature to focus on group fairness metrics.”
BackgroundGrill, G. (2022) · OSF Preprints (OSF Preprints) · doi:10.31219/osf.io/zekqv · Cited by 20
Aizenberg, E., Dennis, M., & van den Hoven, J. (2023) · AI & Society · doi:10.1007/s00146-023-01783-1 · Cited by 28
“Such reflection would complement the exploration of theoretical understandings and measurement assumptions about fairness discussed by Jacobs and Wallach (2021) by examining whether measurement itself is epistemologically compatible with contextual meanings of fairness, or whether a different…”
Visual digital data, ethical challenges, and psychological science.
Levine, M., Philpot, R., Nightingale, S. J., & Kordoni, A. (2024) · American Psychologist · doi:10.1037/amp0001192 · Cited by 18
Assessing the Reliability of Word Embedding Gender Bias Measures
Du, Y., Fang, Q., & Nguyen, D. (2021) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2021.emnlp-main.785 · Cited by 28
Undesirable Biases in NLP: Addressing Challenges of Measurement
van der Wal, O., Bachmann, D., Leidinger, A., van Maanen, L., Zuidema, W. H., & Schulz, K. (2024) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.15195 · Cited by 53
“Perhaps closest to our work, is the one of Jacobs and Wallach (2021), who, similar to our paper, introduce key concepts from psychometrics, including a discussion of types of reliability and construct validity that could be relevant for computational scientists.”
BackgroundMethodResultInfluentialFairness and Discrimination in Information Access SystemsPreprint
Ekstrand, M. D., Das, A., Burke, R., & Díaz, F. (2021) · arXiv (Cornell University) · Cited by 13
Magomere, J., Ishida, S., Afonja, T., Salama, A., Kochin, D., Foutse, Y., Hamzaoui, I., Sefala, R., Alaagib, A., Dalal, S., et al. (2025) · Proceedings of the 2025 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3715275.3732019 · Cited by 13
Constructing Capabilities: The Politics of Testing Infrastructures for Generative AI
Grill, G. (2024) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3630106.3659009 · Cited by 21
“The "ground truth" these tests depend upon is based on assumptions about defined tasks and constructs to be measured [72], and the labor of data workers [56].”
BackgroundYi, F., Singh, A., & Tao, Z. (2024) · Foundations and Trends® in Information Retrieval · doi:10.1561/1500000101 · Cited by 17
AI Mismatches: Identifying Potential Algorithmic Harms Before AI Development
Saxena, D., Jung, J.-Y., Forlizzi, J., Holstein, K., & Zimmerman, J. (2025) · CHI Conference on Human Factors in Computing Systems · doi:10.1145/3706598.3714098 · Cited by 34
“This gap often reveals discrepancies between prediction targets and actual constructs, with fairness and bias concerns frequently linked to these mismatches [43, 56].”
Bernhard-Harrer, J., Ashour, R., Eberl, J., Tolochko, P., & Boomgaarden, H. G. (2025) · Political Science Research and Methods · doi:10.1017/psrm.2025.10008 · Cited by 22
Language machines: Toward a linguistic anthropology of large language models
Lamoureaux, S., Castelle, M., & Weichselbraun, A. (2025) · Journal of Linguistic Anthropology · doi:10.1111/jola.70033 · Cited by 20
Mitigating Age Biases in Resume Screening AI Models
Harris, C. G. (2023) · Proceedings of the ... International Florida Artificial Intelligence Research Society Conference · doi:10.32473/flairs.36.133236 · Cited by 20
“A fairness-oriented conceptualization of construct validity is provided by (Jacobs and Wallach 2021).”
BackgroundThe Neutrality Fallacy: When Algorithmic Fairness Interventions are (Not) Positive Action
Weerts, H., Xenidis, R., Tarissan, F., Olsen, H. P., & Pechenizkiy, M. (2024) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3630106.3659025 · Cited by 25
“When measurement bias is associated with protected group membership, it can become a source of discrimination [41].”
BackgroundInfluentialNon-empirical problems in fair machine learning
Scantamburlo, T. (2021) · Ethics and Information Technology · doi:10.1007/s10676-021-09608-9 · Cited by 19
“Additionally, Jia et al. (2018) proposes a method developed in the context of domain adaptation to make predictions that are “right for the right reason,” [(e.g. “gender of a subject in an image should not be based on the background.””
MethodAligning Offline Metrics and Human Judgments of Value for Code Generation Models
Dibia, V. C., Fourney, A., Bansal, G., Poursabzi-Sangdeh, F., Liu, H., & Amershi, S. (2023) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2023.findings-acl.540 · Cited by 37
“…comparison, a growing body of work has raised concerns about the mismatch between popular metrics and what people need and value in the real world (Thomas and Uminsky, 2022; Raji et al., 2022; Hellendoorn et al., 2019; Hand, 2006; Jacobs and Wallach, 2021; Chandar et al., 2020; Zhou et al., 2022).”
BackgroundCounterfactual Prediction Under Outcome Measurement Error
Guerdan, L., Coston, A., Holstein, K., & Wu, Z. S. (2023) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3593013.3594101 · Cited by 33
“der the assumed measurement model [30].”
BackgroundRepresentation Matters: Assessing the Importance of Subgroup Allocations in Training DataPreprint
Rolf, E., Worledge, T., Recht, B., & Jordan, M. I. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.03399 · Cited by 25
“When ML systems fail to represent subpopulations due to measurement or construct validity issues, more comprehensive interventions are needed (Jacobs & Wallach, 2019).”
BackgroundRezk, A. M., Simkute, A., Luger, E., Vines, J., Elsden, C., Evans, M., & Jones, R. (2024) · Proceedings of the CHI Conference on Human Factors in Computing Systems · doi:10.1145/3613904.3642634 · Cited by 10
“We acknowledge the occasional mismatch that can occur in deriving attributes through signal analysis [37], however here the objective was to recreate common methods used for audience segmentations, and to emphasise some of this functionality for the purposes of prompting dialogue with participants.”
MethodMeyer, M., Horowitz, A., Marshall, E., & Lum, K. (2022) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3531146.3533104 · Cited by 14
“In particular, there is no undisputed “ground truth” for what constitutes an especially lengthy sentence [42, 43].”
BackgroundWhat’s Impossible about Algorithmic Fairness?
Sahlgren, O. (2024) · Philosophy & Technology · doi:10.1007/s13347-024-00814-z · Cited by 16
“In the literature, it has been suggested that available fairness notions represent competing understandings of fairness (Jacobs & Wallach, 2021), embody “different and irreconcilable moral assumptions” (Heidari et al., 2019, 188), or encompass incompatible views about what grounds claims to the…”
The Value of Disagreement in AI Design, Evaluation, and Alignment
Fazelpour, S., & Fleisher, W. (2025) · Proceedings of the 2025 ACM Conference on Fairness, Accountability, and Transparency · doi:10.1145/3715275.3732146 · Cited by 10
“These efforts have significantly advanced our understanding of how central concerns such as reliability and validity [23, 59], bias and fairness [6, 33], transparency and explainability [40, 119], privacy [55, 85], and accountability [74, 95] interact with sociotechnical AI systems.”
Lavelle-Hill, R. E., Smith, G., & Murayama, K. (2025) · Advances in Methods and Practices in Psychological Science · doi:10.1177/25152459251345696 · Cited by 17
“However, the difference between an unobservable construct and its measurement can lead to misinterpretation and biased algorithms (e.g., Jacobs & Wallach, 2021).”
When More Data Lead Us Astray: Active Data Acquisition in the Presence of Label Bias
Li, Y., De‐Arteaga, M., & Saar‐Tsechansky, M. (2022) · Proceedings of the AAAI Conference on Human Computation and Crowdsourcing · doi:10.1609/hcomp.v10i1.21994 · Cited by 17
Making Intelligence: Ethical Values in IQ and ML Benchmarks
Blili-Hamelin, B., & Hancox-Li, L. (2023) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3593013.3593996 · Cited by 30
“(10)See [44] for a more comprehensive overview.”
Machine Learning practices and infrastructures
Berman, G. (2023) · Proceedings of the AAAI/ACM Conference on AI Ethics and Society · doi:10.1145/3600211.3604689 · Cited by 11
“operationalises and reifies particular interpretations of essentially contested social constructs [20, 60, 89] is the challenge of locating where and how coding decisions are currently made, and where they ought to be made.”
BackgroundThis prompt is measuring <mask>: evaluating bias evaluation in language models
Goldfarb-Tarrant, S., Ungless, E. L., Balkır, E., & Blodgett, S. L. (2023) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2023.findings-acl.139 · Cited by 62
Fair CRISP-DM: Embedding Fairness in Machine Learning (ML) Development Life Cycle
Singh, V. K., Singh, A., & Joshi, K. (2022) · Hawaii International Conference on System Sciences (HICSS) · doi:10.24251/hicss.2022.190 · Cited by 17
DExperts: Decoding-Time Controlled Text Generation with Experts and Anti-ExpertsPreprint
Liu, A., Sap, M., Lu, X., Swayamdipta, S., Bhagavatula, C., Smith, N. A., & Choi, Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2105.03023 · Cited by 10
“However, the mismatch between the construct of toxicity and its operationalization through an automatic classi-fier can cause biased or unintended model behavior (Jacobs and Wallach, 2021).”
BackgroundNeither Valid nor Reliable? Investigating the Use of LLMs as Judges
Chehbouni, K., Haddou, M., Cheung, J. C., & Farnadi, G. (2025) · Advances in Neural Information Processing Systems 38 · doi:10.52202/085713-3029 · Cited by 10
The Dataset Multiplicity Problem: How Unreliable Data Impacts Predictions
Meyer, A. P., Albarghouthi, A., & D’Antoni, L. (2023) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3593013.3593988 · Cited by 33
“But more broadly, datasets never reflect objective truths because the worldview of their creators is imbued in the data collection and postprocessing [27, 42, 44].”
BackgroundElmer, T. (2023) · EPJ Data Science · doi:10.1140/epjds/s13688-023-00434-1 · Cited by 14
“The call for more attention to better measurement evaluations – including reliability and validity – is not new (e.g., Jacobs and Wallach [42]; Lazer [55]; Ruths and Pfeffer [79]; Tufekci [91]).”
BackgroundBalancing Act: Evaluating People’s Perceptions of Fair Ranking Metrics
Alkhathlan, M., Cachel, K., Shrestha, H., Harrison, L., & Rundensteiner, E. A. (2024) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3630106.3659018 · Cited by 14
Hedonic price models, social media data and AI – An application to the AIRBNB sector in us cities
Östh, J., Türk, U., Kourtit, K., & Nijkamp, P. J. (2025) · Computers Environment and Urban Systems · doi:10.1016/j.compenvurbsys.2025.102303 · Cited by 12
The predictive reframing of machine learning applications: good predictions and bad measurements
Mussgnug, A. M. (2022) · European Journal for Philosophy of Science · doi:10.1007/s13194-022-00484-8 · Cited by 19
“Recently, ML devel - opers have started to engage with measurement and construct validation in the context of AI fairness (Jacobs, 2021; Jacobs & Wallach, 2021). sciences, such as psychometrics, are marketed as predicting anxiety, depression, and stress while only engaging minimally with the…”
BackgroundThe Role of Relevance in Fair Ranking
Balagopalan, A., Jacobs, A. Z., & Biega, A. J. (2023) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3539618.3591933 · Cited by 11
“Drawing on domain knowledge about relevance-based ranking systems and the assumptions within, these desiderata offer a pathway towards valid and reliablemeasures of relevance, where the properties of proxy scores should match their theoretical ideal across a range of qualitative dimensions [34].”
BackgroundInfluentialSelf-citationOptimization’s Neglected Normative Commitments
Laufer, B., Gilbert, T. K., & Nissenbaum, H. F. (2023) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3593013.3593976 · Cited by 18
“There is significant work on the elusive nature of measurement— here we highlight theoretical groundwork [8, 38, 57, 61, 84] as well as technical work on bias in measurement [15, 51, 79, 91].”
BackgroundFairness On The Ground: Applying Algorithmic Fairness Approaches to Production SystemsPreprint
Bakalar, C., Barreto, R. D. C., Bergman, S., Bogen, M., Chern, B., Corbett‐Davies, S., Hall, M. A., Kloumann, I. M., Lam, M. S., Candela, J. Q., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.06172 · Cited by 49
A Framework for Auditing Chatbots for Dialect-Based Quality-of-Service Harms
Harvey, E., Kizilcec, R. F., & Koenecke, A. (2025) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3715275.3732137 · Cited by 22
“We argue that the ASPD should not be used for tasks like Matched Guise Probing [42] due to issues of substantive validity : the dataset does not appear to meaningfully measure what dialect bias auditors seek to measure [45].”
Magaña, M. I., & Shilton, K. (2025) · ACM Conference on Fairness, Accountability, and Transparency (FAccT) · doi:10.1145/3715275.3732148 · Cited by 15
“…of generative models can be opaque and difficult to explain [15], and because the data used to train machine learning models is frequently rife with human biases [3] or an imperfect indicator for unobservable constructs [32], today’s AI systems are frequently untrusted by experts or users [1].”
Making the Right Thing: Bridging HCI and Responsible AI in Early-Stage AI Concept Selection
Jung, J.-Y., Saxena, D., Park, M., Kim, J., Forlizzi, J., Holstein, K., & Zimmerman, J. (2025) · Designing Interactive Systems Conference · doi:10.1145/3715336.3735745 · Cited by 14
“…Evaluation), they highlighted the subjectivity of listed data components (i.e., classroom observation, teacher commitment) and the impossibility of establishing a definitive measure of teacher performance, questioning the validity of the outcome itself, which is a key ethical consideration [46].”
Mussgnug, A. M. (2025) · Philosophy & Technology · doi:10.1007/s13347-025-00938-w · Cited by 15
Gradual (In)Compatibility of Fairness Criteria
Hertweck, C., & Räz, T. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i11.21450 · Cited by 16
Not Just Algorithms: Strategically Addressing Consumer Impacts in Information Retrieval
Ekstrand, M. D., Beattie, L., Pera, M. S., & Cramer, H. S. M. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-56066-8_25 · Cited by 13
“Measurement modeling, as showcased by Jacobs and Wallach [60] for operationalizing fairness, provides a substantive framework for designing robust metrics for measuring qualitative goals or constructs.”
BackgroundMethodRecall, Robustness, and Lexicographic Evaluation
Díaz, F., Ekstrand, M. D., & Mitra, B. (2025) · ACM Transactions on Recommender Systems · doi:10.1145/3728373 · Cited by 14
“• Validity – Content validity.”
Measurement as governance in and for responsible AIPreprint
Jacobs, A. Z. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2109.05658 · Cited by 24
“Here we build directly on the measurement framework put forward by Jacobs and Wallach [44].”
InfluentialSelf-citationForks Over Knives: Predictive Inconsistency in Criminal Justice Algorithmic Risk Assessment Tools
Greene, T., Shmueli, G., Fell, J., Lin, C.-F., & Liu, H.-W. (2020) · arXiv · doi:10.48550/arxiv.2012.00289 · Cited by 8
Laurer, M., van Atteveldt, W., Casas, A., & Welbers, K. (2024) · Communication Methods and Measures · doi:10.1080/19312458.2024.2378690 · Cited by 13
“Only very few interdisciplinary efforts for harmonizing terminologies from a computational perspective exist (Jacobs & Wallach, 2021). comes exclusively from the training data.”
Gebru, T., & Denton, E. (2024) · Foundations and Trends® in Computer Graphics and Vision · doi:10.1561/0600000102 · Cited by 16
Metadata
- Authors
- Jacobs, A. Z., & Wallach, H.
- Affiliations
- University of Michigan (US)
- Microsoft (United States) (US)
- Venue
- Proceedings of the 2021 ACM Conference on Fairness, Accountability, and Transparency
- Publisher
- ACM
- Published
- 2021-03
- Pages
- 375-385
- OpenAlex
- W2995006168
- Semantic Scholar
- 681f4fbce872f138cbac9cdd92e8f6ed89ba6f8d
- Cited by
- 362
- References
- 24
- Citations by year
- 2026: 65 · 2025: 55 · 2024: 54 · 2023: 82 · 2022: 47 · 2021: 41
- FWCI
- 50.54
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- ACM Conference on Fairness, Accountability, and Transparency (FAccT) (publishedVersion, cc-by)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Ethics and Social Impacts of AI
- Social Sciences › Decision Sciences › Management Science and Operations Research › Psychometric Methodologies and Testing
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Keywords
- measurement modeling, fairness, construct reliability, construct validity, operationalization, fairness definitions, algorithmic fairness, socioeconomic status, teacher effectiveness, recidivism risk, essentially contested concepts, measurement assumptions
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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-07, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-07 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (qwen3.8-omni-flash and gpt-6-sol).
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.