Sainyam Galhotra
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Research Interests
Sainyam Galhotra has a total of 58 co-authors. Here are the top co-authors by number of shared publications:
- Brit Youngmann
Technion, Haifa, Israel
4 shared publications - Barna Saha
UC Berkeley
3 shared publications - Stavros Sintos
Department of Computer Science, University of Illinois Chicago, Chicago, IL, USA
3 shared publications - Amir Gilad
Hebrew University, Jerusalem, Israel
2 shared publications - Anna Mazhar
Cornell University, Ithaca, USA
2 shared publications Arya Mazumdar
College of Information and Computer Sciences University of Massachusetts Amherst 01003 Amherst MA
2 shared publications
Latest Publications
- 1 January 2027
- Published by Springer Nature
Data Discovery in Data Lakes
- Open Access
- 12 October 2026
- Published by Association for Computing Machinery (ACM) in ACM Journal on Responsible Computing
- Vol. 3 (4) , 1-26
FAIR-SHEPHERD: Fairness beyond Statistical Parity toward Structural Alignment
All fairness algorithms unavoidably rely on normative assumptions about fair treatment, yet these assumptions often remain implicit. We argue that these assumptions should be formalized as explicit, auditable policies and introduce FAIR-SHEPHERD , a structural policy-based framework for transparent fairness in real-world settings with noisy labels and shifting distributions. FAIR-SHEPHERD uses gradients as attribution signals, encoded in a Structural Fairness Specification (SFS) that defines vertical coherence and orthogonality to vulnerable proxies. We introduce SFS metrics: Vertical Coherence Score (VCS) to measure directional coherence across adjacent normative slices, and Horizontal Leakage Score (HLS), augmented by a signed directional variant, to detect gradient alignment with policy-declared vulnerable or proxy directions. To enforce these policies, we develop S-agnostic tools that optimize policy-aligned gradient objectives using lattice-defined proxies. We demonstrate that outcome-based auditing is brittle to measurement error: under 10% label noise on Adult, Worst-Group AUC for ERM drops by 0.159. In contrast, our gradient-based structural metrics provide a label-agnostic audit of the decision logic, remaining stable even when evaluation labels are corrupted. Specialized fairness baselines including ARL, JTT, and GoG retain substantial structural leakage on COMPAS, with HLS values from about 0.47 to 0.71. Some also reduce EOD relative to ERM, which shows that outcome and structural criteria can diverge. Using our S-agnostic Gradient Penalty tools, we reduce policy-specified structural leakage by roughly 85% on COMPAS (0.478 → 0.073) and over 94% on Adult (0.138 → 0.008) while retaining competitive AUC and Worst-Group AUC. We have released our source code to facilitate further research here.
- 12 October 2026
- Published by Association for Computing Machinery (ACM) in ACM Journal on Responsible Computing
- Vol. 3 (4) , 1-26
Open AccessFAIR-SHEPHERD: Fairness beyond Statistical Parity toward Structural Alignment
All fairness algorithms unavoidably rely on normative assumptions about fair treatment, yet these assumptions often remain implicit. We argue that these assumptions should be formalized as explicit, auditable policies and introduce FAIR-SHEPHERD , a structural policy-based framework for transparent fairness in real-world settings with noisy labels and shifting distributions. FAIR-SHEPHERD uses gradients as attribution signals, encoded in a Structural Fairness Specification (SFS) that defines vertical coherence and orthogonality to vulnerable proxies. We introduce SFS metrics: Vertical Coherence Score (VCS) to measure directional coherence across adjacent normative slices, and Horizontal Leakage Score (HLS), augmented by a signed directional variant, to detect gradient alignment with policy-declared vulnerable or proxy directions. To enforce these policies, we develop S-agnostic tools that optimize policy-aligned gradient objectives using lattice-defined proxies. We demonstrate that outcome-based auditing is brittle to measurement error: under 10% label noise on Adult, Worst-Group AUC for ERM drops by 0.159. In contrast, our gradient-based structural metrics provide a label-agnostic audit of the decision logic, remaining stable even when evaluation labels are corrupted. Specialized fairness baselines including ARL, JTT, and GoG retain substantial structural leakage on COMPAS, with HLS values from about 0.47 to 0.71. Some also reduce EOD relative to ERM, which shows that outcome and structural criteria can diverge. Using our S-agnostic Gradient Penalty tools, we reduce policy-specified structural leakage by roughly 85% on COMPAS (0.478 → 0.073) and over 94% on Adult (0.138 → 0.008) while retaining competitive AUC and Worst-Group AUC. We have released our source code to facilitate further research here.
- Open Access
- 5 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1207-1211
Towards Reliable Testing of Machine Unlearning
Machine learning components are now central to AI-infused software systems, from recommendations and code assistants to clinical decision support. As regulations and governance frameworks increasingly require deleting sensitive data from deployed models, machine unlearning is emerging as a practical alternative to full retraining. However, unlearning introduces a software quality-assurance challenge: under realistic deployment constraints and imperfect oracles, how can we test that a model no longer relies on targeted information? This paper frames unlearning testing as a first-class software engineering problem. We argue that practical unlearning tests must provide (i) thorough coverage over proxy and mediated influence pathways, (ii) debuggable diagnostics that localize where leakage persists, (iii) cost-effective regression-style execution under query budgets, and (iv) black-box applicability for API-deployed models. We outline a causal, pathway-centric perspective, causal fuzzing, that generates budgeted interventions to estimate residual direct and indirect effects and produce actionable "leakage reports". Proof-of-concept results illustrate that standard attribution checks can miss residual influence due to proxy pathways, cancellation effects, and subgroup masking, motivating causal testing as a promising direction for unlearning testing.
- 5 July 2026
- Published by Association for Computing Machinery (ACM)
- p. 1207-1211
Open AccessTowards Reliable Testing of Machine Unlearning
Machine learning components are now central to AI-infused software systems, from recommendations and code assistants to clinical decision support. As regulations and governance frameworks increasingly require deleting sensitive data from deployed models, machine unlearning is emerging as a practical alternative to full retraining. However, unlearning introduces a software quality-assurance challenge: under realistic deployment constraints and imperfect oracles, how can we test that a model no longer relies on targeted information? This paper frames unlearning testing as a first-class software engineering problem. We argue that practical unlearning tests must provide (i) thorough coverage over proxy and mediated influence pathways, (ii) debuggable diagnostics that localize where leakage persists, (iii) cost-effective regression-style execution under query budgets, and (iv) black-box applicability for API-deployed models. We outline a causal, pathway-centric perspective, causal fuzzing, that generates budgeted interventions to estimate residual direct and indirect effects and produce actionable "leakage reports". Proof-of-concept results illustrate that standard attribution checks can miss residual influence due to proxy pathways, cancellation effects, and subgroup masking, motivating causal testing as a promising direction for unlearning testing.
- Open Access
- 26 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 1367-1371
Goal-Oriented Reliability and Self-Improvement for Multi-Agent Systems
- 26 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 1367-1371
Open AccessGoal-Oriented Reliability and Self-Improvement for Multi-Agent Systems
- Open Access
- 26 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 483-496
Trace-Level Analysis of Information Contamination in Multi-Agent Systems
- 26 May 2026
- Published by Association for Computing Machinery (ACM)
- p. 483-496
Open AccessTrace-Level Analysis of Information Contamination in Multi-Agent Systems
- Open Access
- 18 May 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 4 (3) , 1-27
Interpretable Attribute Discretization
Data discretization, the conversion of numeric attributes into categorical bins, underpins many data-driven tasks, from visualization and causal analysis to symbolic learning. Interpretable partitions make results easier to communicate and act upon. Yet, a fundamental tension underlies this discretization process: partitions that are interpretable to humans often differ from those that maximize utility performance (e.g., causal analysis). Despite the abundance of discretization techniques, reconciling this utility-semantics trade-off remains an open challenge. In this work, we formally define the interpretable attribute discretization problem and introduce a reinforcement-learning-based framework that jointly optimizes utility and semantic fidelity. Our approach learns a partition selection policy that can navigate a vast space of candidates and accurately estimate the optimal partitions by strategically sampling only 200 candidates out of millions. We measure success by the average Hausdorff distance between the estimated and true Pareto frontier of the utility–semantics trade-off. On seven datasets across four tasks (visualization, modeling, imputation, causal analysis) and multiple semantic measures, our method achieves the lowest overall error, typically 2–4 × smaller than strong alternatives, yielding a more accurate Pareto frontier that reveals the complete utility–semantics trade-off.
- 18 May 2026
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 4 (3) , 1-27
Open AccessInterpretable Attribute Discretization
Data discretization, the conversion of numeric attributes into categorical bins, underpins many data-driven tasks, from visualization and causal analysis to symbolic learning. Interpretable partitions make results easier to communicate and act upon. Yet, a fundamental tension underlies this discretization process: partitions that are interpretable to humans often differ from those that maximize utility performance (e.g., causal analysis). Despite the abundance of discretization techniques, reconciling this utility-semantics trade-off remains an open challenge. In this work, we formally define the interpretable attribute discretization problem and introduce a reinforcement-learning-based framework that jointly optimizes utility and semantic fidelity. Our approach learns a partition selection policy that can navigate a vast space of candidates and accurately estimate the optimal partitions by strategically sampling only 200 candidates out of millions. We measure success by the average Hausdorff distance between the estimated and true Pareto frontier of the utility–semantics trade-off. On seven datasets across four tasks (visualization, modeling, imputation, causal analysis) and multiple semantic measures, our method achieves the lowest overall error, typically 2–4 × smaller than strong alternatives, yielding a more accurate Pareto frontier that reveals the complete utility–semantics trade-off.
- Open Access
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1
VERIRAG: Healthcare Claim Verification via Statistical Audit in Retrieval-Augmented Generation
- 12 October 2025
- Published by Association for Computing Machinery (ACM)
- p. 1
Open AccessVERIRAG: Healthcare Claim Verification via Statistical Audit in Retrieval-Augmented Generation
- Open Access
- 22 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 143-146
SeerCuts: Explainable Attribute Discretization
- 22 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 143-146
Open AccessSeerCuts: Explainable Attribute Discretization
- Open Access
- 22 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 775-787
Privacy and Security in Distributed Data Markets
- 22 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 775-787
Open AccessPrivacy and Security in Distributed Data Markets
- Open Access
- 17 June 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 3 (3) , 1-28
Fair and Actionable Causal Prescription Ruleset
Prescriptions, or actionable recommendations, are commonly generated across various fields to influence key outcomes such as improving public health, enhancing economic policies, or increasing business efficiency. While traditional association-based methods may identify correlations, they often fail to reveal the underlying causal factors needed for informed decision-making. On the other hand, in decision making for tasks with significant societal or economic impact, it is crucial to provide recommendations that are interpretable and justifiable, and equitable in terms of the outcome for both the protected and non-protected groups. Motivated by these two goals, this paper introduces a fairness-aware framework leveraging causal reasoning for generating a set of interpretable and actionable prescription rules (ruleset) toward betterment of an outcome while preventing exacerbating inequalities for protected groups. By considering group and individual fairness metrics from the literature, we ensure that both protected and non-protected groups benefit from these recommendations, providing a balanced and equitable approach to decision-making. We employ efficient optimizations to explore the vast and complex search space considering both fairness and coverage of the prescription ruleset. Empirical evaluation and case study on real-world datasets demonstrates the utility of our framework for different use cases.
- 17 June 2025
- Published by Association for Computing Machinery (ACM) in Proceedings of the ACM on Management of Data
- Vol. 3 (3) , 1-28
Open AccessFair and Actionable Causal Prescription Ruleset
Prescriptions, or actionable recommendations, are commonly generated across various fields to influence key outcomes such as improving public health, enhancing economic policies, or increasing business efficiency. While traditional association-based methods may identify correlations, they often fail to reveal the underlying causal factors needed for informed decision-making. On the other hand, in decision making for tasks with significant societal or economic impact, it is crucial to provide recommendations that are interpretable and justifiable, and equitable in terms of the outcome for both the protected and non-protected groups. Motivated by these two goals, this paper introduces a fairness-aware framework leveraging causal reasoning for generating a set of interpretable and actionable prescription rules (ruleset) toward betterment of an outcome while preventing exacerbating inequalities for protected groups. By considering group and individual fairness metrics from the literature, we ensure that both protected and non-protected groups benefit from these recommendations, providing a balanced and equitable approach to decision-making. We employ efficient optimizations to explore the vast and complex search space considering both fairness and coverage of the prescription ruleset. Empirical evaluation and case study on real-world datasets demonstrates the utility of our framework for different use cases.