d^{poly(ℓ/ε)} algorithms for exponential families under polynomial-approximable unknown truncation, including first results for arbitrary Gaussians; poly(d/ε) for halfspaces/rectangles.
Imbens and Donald B
8 Pith papers cite this work. Polarity classification is still indexing.
8
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
verdicts
UNVERDICTED 8roles
background 1polarities
background 1representative citing papers
CausaLab introduces a scalable benchmark for LLM agents on interactive causal discovery using random SCMs, revealing high task accuracy but low structural recovery in experiments with models like GPT-5.2.
DR-ME is the first semiparametrically efficient finite-location kernel test for interpretable distributional treatment effects, using orthogonal doubly robust features derived from observational data.
Biomass burning aerosols produce -2.5 W m^{-2} regional shortwave cooling over the South-East Atlantic, decomposed equally into ARI, ARI adjustments, and ACI after causal removal of confounding biases.
Wage subsidies boosted apprentice commencements by 70% but did not raise retention or completions, with evidence of sharp practice converting existing workers in non-trade roles.
The Latency-Elastic Trust Window is a telemetry-driven UX governor that maps network latency conditions to adaptive feedback modes to preserve trust and engagement during real-time payments in WebRTC streaming.
Framework using potential outcomes and within-treatment regression models to estimate plot-level SOC sequestration potentials from covariates and approximate optimal policies, demonstrated on California rangeland data where targeting low-baseline-SOC plots improves outcomes over uniform policies.
Hierarchical clustering of geos by marketing spend correlation after normalization reduces multicollinearity and enables separate causal identification of ad channel effects in a Bayesian marketing mix model.
citing papers explorer
-
Efficient Statistics With Unknown Truncation, Polynomial Time Algorithms, Beyond Gaussians
d^{poly(ℓ/ε)} algorithms for exponential families under polynomial-approximable unknown truncation, including first results for arbitrary Gaussians; poly(d/ε) for halfspaces/rectangles.
-
CausaLab: A Scalable Environment for Interactive Causal Discovery Toward AI Scientists
CausaLab introduces a scalable benchmark for LLM agents on interactive causal discovery using random SCMs, revealing high task accuracy but low structural recovery in experiments with models like GPT-5.2.
-
Semiparametric Efficient Test for Interpretable Distributional Treatment Effects
DR-ME is the first semiparametrically efficient finite-location kernel test for interpretable distributional treatment effects, using orthogonal doubly robust features derived from observational data.
-
Dissipating the correlation smokescreen: Causal decomposition of the radiative effects of biomass burning aerosols over the South-East Atlantic
Biomass burning aerosols produce -2.5 W m^{-2} regional shortwave cooling over the South-East Atlantic, decomposed equally into ARI, ARI adjustments, and ACI after causal removal of confounding biases.
-
A rapid evaluation of Australia's COVID-era apprentice wage subsidy programs
Wage subsidies boosted apprentice commencements by 70% but did not raise retention or completions, with evidence of sharp practice converting existing workers in non-trade roles.
-
Discovering the Latency-Elastic Trust Window: A Patentable UX Governor for Real-Time Payment Confirmation in WebRTC Streaming
The Latency-Elastic Trust Window is a telemetry-driven UX governor that maps network latency conditions to adaptive feedback modes to preserve trust and engagement during real-time payments in WebRTC streaming.
-
Estimating soil carbon sequestration potential and approximating optimal management policies
Framework using potential outcomes and within-treatment regression models to estimate plot-level SOC sequestration potentials from covariates and approximate optimal policies, demonstrated on California rangeland data where targeting low-baseline-SOC plots improves outcomes over uniform policies.
-
Hierarchical Clustering As a Novel Solution to the Notorious Multicollinearity Problem in Observational Causal Inference
Hierarchical clustering of geos by marketing spend correlation after normalization reduces multicollinearity and enables separate causal identification of ad channel effects in a Bayesian marketing mix model.