Joshua Lin

Zhongyi Zhang, Guixia Li, Ziqiang Wang et al.

Despite high global prevalence of hepatic steatosis, no automated diagnostics demonstrated generalizability in detecting steatosis on multiple international datasets. Traditionally, hepatic steatosis detection relies on clinicians selecting the region of interest (ROI) on computed tomography (CT) to measure liver attenuation. ROI selection demands time and expertise, and therefore is not routinely performed in populations. To automate the process, we validated an existing artificial intelligence (AI) system for 3D liver segmentation and used it to purpose a novel method: AI-ROI, which could automatically select the ROI for attenuation measurements. AI segmentation and AI-ROI method were evaluated on 1,014 non-contrast enhanced chest CT images from eight international datasets: LIDC-IDRI, NSCLC-Lung1, RIDER, VESSEL12, RICORD-1A, RICORD-1B, COVID-19-Italy, and COVID-19-China. AI segmentation achieved a mean dice coefficient of 0.957. Attenuations measured by AI-ROI showed no significant differences (p = 0.545) and a reduction of 71% time compared to expert measurements. The area under the curve (AUC) of the steatosis classification of AI-ROI is 0.921 (95% CI: 0.883 - 0.959). If performed as a routine screening method, our AI protocol could potentially allow early non-invasive, non-pharmacological preventative interventions for hepatic steatosis. 1,014 expert-annotated liver segmentations of patients with hepatic steatosis annotations can be downloaded here: https://drive.google.com/drive/folders/1-g_zJeAaZXYXGqL1OeF6pUjr6KB0igJX.

Rohit Agarwal, Joshua Lin, Mark Braverman et al.

We study AI alignment through the lens of law-and-economics models of deterrence and enforcement. In these models, misconduct is not treated as an external failure, but as a strategic response to incentives: an actor weighs the gain from violation against the probability of detection and the severity of punishment. We argue that the same logic arises naturally in agentic AI pipelines. A solver may benefit from producing a persuasive but incorrect answer, hiding uncertainty, or exploiting spurious shortcuts, while an auditor or verifier must decide whether costly monitoring is worthwhile. Alignment is therefore a fixed-point problem: stronger penalties may deter solver misbehavior, but they can also reduce the auditor's incentive to inspect, since auditing then mainly incurs cost on a population that appears increasingly aligned. This perspective also changes what should count as a post-training signal. Standard feedback often attaches reward to the final answer alone, but a solver-auditor pipeline exposes the full correction event: whether the solver erred, whether the auditor inspected, whether the error was caught, and whether oversight incentives remained active. We formalize this interaction in a two-agent model in which a principal chooses rewards over joint correction outcomes, inducing both solver behavior and auditor monitoring. Reward design is therefore a bilevel optimization problem: rewards are judged not by their immediate semantic meaning, but by the behavioral equilibrium they induce. We propose a bandit-based outer-loop procedure for searching over reward profiles using noisy interaction feedback. Experiments on an LLM coding pipeline show that adaptive reward profiles can maintain useful oversight pressure and improve principal-aligned outcomes relative to static hand-designed rewards, including a substantial reduction in hallucinated incorrect attempts.