This work shows that an OLS action readout fitted on a fixed neural representation admits an exact case-based decomposition, and identifies a sufficient regime for CBDT similarity semantics; outside it, the coefficients should generally be treated as signed Gram-geometric influence.
Abstract
Neural networks increasingly guide decisions in high-stakes domains such as medical diagnosis, credit approval, and energy bidding. Audit in these settings requires case-level evidence: which training cases support an action and what outcomes they carried. Case-based decision theory (CBDT) formalizes this reasoning by aggregating outcome support from remembered cases. We show that an OLS action readout fitted on a fixed neural representation admits an exact case-based decomposition. Each action score is a weighted sum of training-case returns, with coefficients determined by empirical Gram geometry. We identify a sufficient regime for CBDT similarity semantics; outside it, the coefficients should generally be treated as signed Gram-geometric influence. The decomposition yields audit signals that trace scores to training cases, measure action coherence, and identify weak support. Across synthetic CBDT, PJM, Adult Income, and Default Credit tasks, the method recovers case-level preference structure and achieves the highest mean Top-30 consistency among compared attribution baselines, while remaining competitive on support reconstruction. The audit requires only fitting an OLS top-layer probe, without retraining the representation or accessing the original optimization trajectory; probe fidelity is measured by score reconstruction.
This work shows that pooled refitting recomputes the inverse-Gram geometry used to weight source evidence, which can reverse shared preferences, and derive exact and approximate preservation conditions, and develops a three-stage audit that traces strict pairwise reversals through decision changes to task-defined utility loss.
The methodological bridge connecting causal reasoning with modern supervised learning is reviewed and why correlation-driven models give biased answers to questions about actions is explained.
R. M.· Eduschool International Jour...· 0 citations
: Environmental, Social, and Governance (ESG) evaluation is traditionally treated as a predictive task, where machine learning models estimate scores from financial and contextual features. Such approaches remain fundamentally limited: they provide predictions without structured reasoning, fail to resolve conflicting signals, and cannot support counterfactual decision analysis. This paper proposes a Machine Reasoning (MR) framework that transforms ESG evaluation into a structured decision-making process. The system decomposes ESG evidence into three independent streams: environmental efficiency, financial comparative position, and causal profit-margin effects estimated via DoWhy, and integrates them through five conditional reasoning regimes that resolve conflicts rather than average them. The architecture possesses three properties absent from standard ML pipelines, explanations are produced by the same conditional logic that generates predictions, not inferred post-hoc; hard weight discontinuities at regime boundaries prevent financial strength from compensating for environmental failure; and counterfactual interventions re-run the full reasoning pipeline, capturing non-linear regime shifts that surrogate-model approaches cannot represent. Validated on 11,000 firm-year observations without lagged ESG inputs, the fusion model achieves R²=0.641, a +0.44 R² gain over financial-only baselines with structured decision traces and intervention analysis as additional outputs.
Nizam Tanzina, Kyupil Yeon· International Conference on...· 0 citations
Machine learning systems deployed for credit, hiring, and resource distribution are increasingly subject to regulatory oversight from policies such as the EU AI Act and GDPR. Current fairness governance practices rely on observational fairness metrics, post-hoc explainability, and immutable audit logs, but provide limited support for causal attribution and efficient evidentiary verification. We introduce Causal Evidentiary Governance (CEG), a framework in which regulated institutions commit to a versioned directed acyclic graph (DAG) that partitions causal pathways into allowable and disallowed groups. The Causal Harm Rate measures prediction variation attributable to disallowed causal pathways. Each decision is accompanied by a signed Decision-Evidence Packet (DEP), cryptographically binding the prediction to a digest of the published DAG and path-specific attributions. DEP digests can be appended to a Merkle tree to enable logarithmic-cost inclusion proofs. We validate CEG through a two-layer empirical methodology using demographic summaries from four years of PMA credit supervisory data to construct 10,000 synthetic credit applicants across four strategic DAG counterfactuals. Causal Harm Rate isolates injected causal effects more clearly than demographic parity or equalized odds. Cross-model validation and ablation studies assess robustness. Evaluation on the German Credit dataset shows that harm associated with specific causal pathways can be substantially understated by associational fairness metrics. Finally, a proof-of-concept implementation demonstrates operationally plausible throughput and highlights relevant performance tradeoffs.
FinRiskAtlas is introduced, a Chinese-language benchmark that evaluates financial LLMs along two complementary dimensions: operation execution under fixed evidence states and evidence-state control under evolving review conditions, and shows that broad financial capability scores do not fully capture where models are reliable in professional workflows.
Suyang Zhong, Jingzhe Zhu, Qi Xu et al.· 0 citations
Predictive machine learning (ML) models are increasingly used to aid human decision-makers across various high-risk domains such as healthcare and criminal justice. There is a growing recognition of the need to evaluate the causal impact of deploying these systems on downstream outcomes, such as patient survival or crime recidivism. Randomized control trials (RCTs) can provide high-quality evidence on the impact of a deployed model, but they run into a challenge: it is often infeasible to run repeated trials when models are updated or retrained to improve predictive performance. In this work, we present a partial-identification approach to using prior RCT data to construct bounds on the causal effect of a new model. The core innovation in our approach is to leverage assumptions relating fine-grained predictive accuracy to downstream outcomes. We do so via two monotonicity assumptions: first, on individual-level `counterfactual correctness'(all else being equal, a correct prediction leads to non-inferior outcomes); and second, on the relation between subgroup predictive performance and outcomes, interpretable as an assumption regarding trust in model outputs. We demonstrate our method with a simulation study, illustrating how incorporating this information can lead to more informative bounds compared to prior work.
Jonathan Zhang, Erik Skalnes, Jacob M. Chen et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
