This paper proposes a decomposition of human capital into three orthogonal components -- physical-manual (H^P), routine-cognitive (H^C), and augmentable-cognitive (H^A) -- and develops a production function in which AI capital interacts asymmetrically with these components: substituting for routine cognitive work while complementing augmentable cognitive work through an amplification function phi(D). I derive a corrected Mincerian wage equation and show that the standard specification is misspecified in AI-augmented economies. Using LLM-generated measures of occupational augmentability for 18,796 O*NET task statements mapped to 440 Colombian occupations, merged with household survey microdata (N = 105,517 workers), I estimate the augmented Mincer equation. The wage return to H^A increases with AI adoption in the formal sector (beta_2 = +0.051, p < 0.001), while informal workers cannot capture augmentation rents (beta_2 = -0.044). A triple interaction confirms formality as the binding mechanism (beta_{AHC x D x Formal} = +0.272, p < 0.001). The augmentation premium is strongest for experienced workers (ages 46-65) and in health and education sectors. These results provide the first developing-country evidence of cognitive factor decomposition in AI-augmented labor markets and demonstrate that the binding constraint on human-AI complementarity in the Global South is not technology access but labor market institutions.

Societies and organizations often fail to surface latent consensus because individuals fear social censure. A manager might suspect a silent majority would offer a criticism, support a change, report a risk, or endorse a policy -- if only it were safe. Likewise, individuals with beliefs they think are rare and controversial might stay quiet for fear of consequences at work or an online mob. In both cases pluralistic ignorance produces a public discourse misaligned with privately-held beliefs. Social assurance contracts unlock latent consensus, making the public discussion more accurately reflect the underlying distribution of actual beliefs. They are akin to an open letter that publishes only when a stated threshold number of private signatures is reached. If it is not reached, nothing is revealed and no one is exposed. Whereas a single hand raised in dissent might get cut off, a thousand can be raised safely together. I build a formal model and derive rules for choosing the threshold. The mechanism (i) induces participation from those willing to speak if assured of company, resolving the core coordination problem in pluralistic ignorance; (ii) makes the threshold a transparent policy lever -- sponsors can maximize success, maximize public-coalition revelation, or hit a desired success probability; and (iii) turns success into information: meeting the threshold publicly reveals hidden agreement and can widen the range of views that can be expressed in public. I consider robustness to mistrust, organized opposition, and network structure, and outline low-trust implementations like cryptographic escrow. Applications include employee voice, safety and compliance, whistleblowing, and civic expression.

Traditional econometric analyzes represent observations as vectors despite the inherent complexity of empirical data structures. When data are organized along dual classification dimensions, a matrix representation provides a more natural and interpretable framework. Building on recent advances in matrix autoregressive (MAR) modeling, this study introduces a novel error correction representation tailored for matrix-structured data. Through comparative analysis with existing methodologies, we demonstrate two critical advancements. First, the proposed model preserves the interpretative foundations of conventional cointegration analysis, with coefficients that explicitly capture dynamics rooted in adjustment toward steady-state positions. Second, in contrast to previous formulations, our error correction framework allows for an equivalent matrix autoregressive representation, preserving the fundamental structure of the data in both specifications. This ensures that the matrix representation reflects an intrinsic characteristic of the data.

This paper studies the economic role of persistent dispersion in allocations across agents. We develop a tractable model in which firms allocate resources under imperfect information and behavioral updating, generating sustained heterogeneity in beliefs and actions. While dispersion induces static misallocation, it also fosters decentralized experimentation, allowing the economy to explore a broader set of productive opportunities. We show that the economy converges to a stationary equilibrium with strictly positive dispersion and that, under plausible conditions, such disequilibrium can dominate the perfectly coordinated benchmark. The model provides a novel interpretation of observed dispersion in productivity and returns as reflecting both inefficiency and productive exploration. It also yields testable predictions linking dispersion to growth and innovation dynamics.

This paper examines the optimal contracts in a two-dimensional screening model where one dimension(group identity) is verifiable by agents but not falsifiable. A principal offers contracts to agents who differ in cost types and group membership. Motivated by the United States Federal policy, Work Opportunity Tax Credit, the principal receives tax benefits for hiring agents from protected groups. Under the assumption that the protected agents tend to have higher cost types, the optimal contract induces full separation across both dimensions: agents reveal the cost type and the group identity through contract choice. Furthermore, the principal is willing to hire the trait agents with a higher cost threshold than the non-trait agents, and this threshold increases with the tax credit. Conversely, when the protected agents tend to have lower cost types, the optimal design without tax credits pools groups while separating by cost type. These results demonstrate that both affirmative action and non-discrimination can be optimal depending on the cost distribution ordering across groups.

Generative AI helps users solve problems more efficiently, but without leaving a public trace. Fewer discussions and solutions reach public platforms, and the archives that future problem-solvers depend on can shrink. We build a dynamic model of public good provision where agents contribute by solving problems that other agents posted on a public platform, and the accumulated solutions form a depreciating public archive. AI reduces archive creation through two margins that require different instruments. The flow margin: the posted volume of knowledge-enhancing queries declines as AI resolves more problems privately before they reach the platform. The resolution margin: the probability that posted queries are resolved declines as AI raises contributors' outside options, thinning the contributor pool and creating congestion on the platform. The two margins interact through a self-undermining feedback that can generate low-archive traps. The decomposition yields a diagnostic prediction: in the congested regime, a joint decline in posted volume and conditional resolution requires that supply-side pool thinning is quantitatively present, whereas volume decline with stable or rising resolution indicates that private diversion alone is the dominant force. Encouraging public sharing of AI-assisted solutions offsets the decline associated with private diversion but cannot repair participation-driven deterioration in conditional resolution, which requires maintaining contributor engagement directly.

Carbon farming is the collection of agricultural best practices specifically designed to maximize the capture and long-term storage of atmospheric carbon dioxide in soils and plant biomass, while simultaneously reducing greenhouse gas emissions from cultivation practices. Carbon farming can be viewed as a promising pathway to simultaneously address climate change mitigation, soil degradation, and farmer welfare. For example, if the entire agricultural cropland in India practices carbon farming, this will spectacularly offset about 50% of emissions from the country's annual transport-sector emissions. However, practical deployment of carbon farming is constrained by scientific challenges, inherent complexity, and fragmented understanding across disciplines. This inter-disciplinary, expository survey offers the first unified treatment of carbon farming for practitioners, policymakers, and researchers. The survey integrates insights from agronomy, soil science, climate science, measurement, reporting, and verification (MRV), economics, carbon markets, and policy design. We begin by establishing the conceptual foundations of soil organic carbon dynamics and agricultural carbon sequestration, and compare carbon farming with the paradigms of sustainable, regenerative, and organic agriculture. We then present a comprehensive landscape analysis of carbon-farming best practices, including both generic and crop-specific interventions, and systematically examine their co-benefits and trade-offs. The paper offers a rigorous review of MRV frameworks, emerging digital MRV technologies, and the carbon-credit project life cycle, followed by a structured analysis of voluntary and compliance carbon markets...

Many common estimators in machine learning and causal inference are linear smoothers, where the prediction is a weighted average of the training outcomes. Some estimators, such as ordinary least squares and kernel ridge regression, allow for arbitrarily negative weights, which improve feature imbalance but often at the cost of increased dependence on parametric modeling assumptions and higher variance. By contrast, estimators like importance weighting and random forests (sometimes implicitly) restrict weights to be non-negative, reducing dependence on parametric modeling and variance at the cost of worse imbalance. In this paper, we propose a unified framework that directly penalizes the level of extrapolation, replacing the current practice of a hard non-negativity constraint with a soft constraint and corresponding hyperparameter. We derive a worst-case extrapolation error bound and introduce a novel "bias-bias-variance" tradeoff, encompassing biases due to feature imbalance, model misspecification, and estimator variance; this tradeoff is especially pronounced in high dimensions, particularly when positivity is poor. We then develop an optimization procedure that regularizes this bound while minimizing imbalance and outline how to use this approach as a sensitivity analysis for dependence on parametric modeling assumptions. We demonstrate the effectiveness of our approach through synthetic experiments and a real-world application, involving the generalization of randomized controlled trial estimates to a target population of interest.

Competitive balance, which refers to the level of control teams have over a sports competition, is a crucial indicator for tournament organisers. According to previous studies, competitive balance has significantly declined in the UEFA Champions League group stage over the recent decades. Our paper introduces alternative indices to investigate this issue. Two ex ante measures are based on Elo ratings, and four dynamic concentration indicators compare the final group ranking to reasonable benchmarks. Using these indices, we find no evidence of any long-run trend in the competitive balance of the UEFA Champions League group stage between the 2003/04 and 2023/24 seasons.

We consider treatment-effect estimation with a two-periods panel, where units are untreated at period one, and receive strictly positive doses at period two. First, we consider designs with some quasi-untreated units, with a period-two dose local to zero. We show that under a parallel-trends assumption, a weighted average of slopes of units' potential outcomes is identified by a difference-in-difference estimand using quasi-untreated units as the control group. We leverage results from the regression-discontinuity-design literature to propose a nonparametric estimator. Then, we propose estimators for designs without quasi-untreated units. Finally, we propose a test of the homogeneous-effect assumption underlying two-way-fixed-effects regressions.

The Council of the European Union (EU) is one of the main decision-making bodies of the EU. A number of decisions require a qualified majority, the support of 55% of the member states (currently 15) that represent at least 65% of the total population. We investigate how the power distribution based on the Shapley--Shubik index and the proportion of winning coalitions change if these criteria are modified within reasonable bounds. The power of the two countries, with approximately 4% of the total population each, is found to be almost flat. The decisiveness index decreases if the population criterion is above 68\% or the states criterion is at least 17. Some quota combinations contradict the principles of double majority. The proportion of winning coalitions can be increased from 13.2% to 20.8% (30.1%) such that the maximal relative change in the Shapley--Shubik indices remains below 3.5% (5.5%). Our results are indispensable for evaluating any proposal to reform the qualified majority voting system.

We present a model of a forecaster who must predict the future value of a variable that depends on an exogenous state and on the intervention of a policy-maker. We investigate the incentives of the forecaster to acquire costly private information to use in his forecasting exercise. We show that the policy-making environment plays a crucial role in determining the incentives of the forecaster to acquire information. Key parameters are the expected strength of policy intervention, the precision of the policy-maker's private information, and the precision of public information. We identify conditions, which are plausible in applications, under which the forecaster optimally acquires little or no private information, and instead bases his forecast exclusively on information publicly known at the time the forecast is made. Furthermore we show that, also under plausible conditions, stronger policy intervention and more precise policy-maker's information crowd-out forecaster's information acquisition.

Randomized controlled trials (RCTs) provide the most credible estimates of advertising incrementality but are difficult to scale. We propose Predicted Incrementality by Experimentation (PIE), which reframes ad measurement as a campaign-level prediction problem. PIE uses a sample of RCTs to learn a mapping from campaign features to causal effects, then applies it to campaigns not run as RCTs. Because the RCTs identify the causal effects, PIE can incorporate post-determined features -- campaign-level aggregates such as test-group outcomes, exposure rates, and last-click conversions, computed after campaign completion. These metrics reflect the consumer behaviors that generate treatment effects, so they carry predictive information about incrementality even though they would be invalid controls in a causal model. Using 2,226 Meta ad experiments, PIE achieves an out-of-sample $R^2 = 0.88$ for incremental conversions per dollar, compared to $R^2 = 0.19$ for industry-standard 7-day last-click attribution. In a decision-making framework, PIE disagrees with RCT-based decisions in only 8-12% of campaigns, compared to 12-20% for last-click attribution. We conclude that PIE can help scale causal measurement from a limited number of RCTs to a large set of non-experimental campaigns.

This article demonstrates how a large number of efficiency measures known in the literature in production economics can be interpreted through the notion of utility function, based on the concept of Stone-Geary utility. Several relationships between these utility functions and distance functions, a commonly used tool in production theory, are established. To achieve these objectives, a generalized mean distance function is introduced, inspired by the Atkinson inequality index, itself derived from the notion of the Aczel mean. It measures the maximum sum of netput expansions required to reach an efficient point. Several duality theorems are established, linking the new distance functions to the profit function. For all feasible production vectors, the results include as special cases most of the dual correspondences previously established in the literature. Finally, a large class of measures is identified for which these duality results can be obtained without requiring convexity. A numerical example is provided.

This paper extends the Acemoglu-Restrepo task exposure framework to address the labor market effects of agentic artificial intelligence systems: autonomous AI agents capable of completing entire occupational workflows rather than discrete tasks. Unlike prior automation technologies that substitute for individual subtasks, agentic AI systems execute end-to-end workflows involving multi-step reasoning, tool invocation, and autonomous decision-making, substantially expanding occupational displacement risk beyond what existing task-level analyses capture. We introduce the Agentic Task Exposure (ATE) score, a composite measure computed algorithmically from O*NET task data using calibrated adoption parameters--not a regression estimate--incorporating AI capability scores, workflow coverage factors, and logistic adoption velocity. Applying the ATE framework across five major US technology regions (Seattle-Tacoma, San Francisco Bay Area, Austin, New York, and Boston) over a 2025-2030 horizon, we find that 93.2% of the 236 analyzed occupations across six information-intensive SOC groups (financial, legal, healthcare, healthcare support, sales, and administrative/clerical) cross the moderate-risk threshold (ATE >= 0.35) in Tier 1 regions by 2030, with credit analysts, judges, and sustainability specialists reaching ATE scores of 0.43-0.47. We simultaneously identify seventeen emerging occupational categories benefiting from reinstatement effects, concentrated in human-AI collaboration, AI governance, and domain-specific AI operations roles. Our findings carry implications for workforce transition policy, regional economic planning, and the temporal dynamics of labor market adjustment

This paper studies how uncertainty about problem difficulty shapes problem-solving strategies. I develop a dynamic model where an agent solves a problem by brainstorming approaches of unknown quality and allocating a fixed effort budget among them. Success arrives from spending effort pursuing good approaches, at a rate determined by the unknown problem difficulty. The agent balances costly exploration (expanding the set of approaches) with exploitation (pursuing existing approaches). Failures could signal either a bad idea or a hard problem, and this uncertainty generates novel dynamics: optimal search alternates between trying new approaches and revisiting previously abandoned ones. I then examine a principal-agent environment, where moral hazard arises on the intensive margin: how the agent explores. Dynamic commitment leads contracts to frontload incentives, which can be counteracted by the presence of learning. The framework reflects scientific discovery, product development, and other creative work, providing insights into innovation and organizational design.

We provide a complete description of the set of all solutions to a vector autoregressive law of motion. Every solution is shown to be the sum of three components, each corresponding to a directed flow of time. One component flows forward from the arbitrarily distant past; one flows backward from the arbitrarily distant future; and one flows outward from time zero. The three components are obtained by applying three complementary spectral projections to the solution, these corresponding to a separation of the eigenvalues of the autoregressive coefficient matrix according to whether they are inside, outside or on the unit circle. We establish a one-to-one correspondence between the set of all solutions and a finite-dimensional space of initial conditions.