{"total":11,"items":[{"citing_arxiv_id":"2606.20427","ref_index":194,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Private Rate-Double-Robust Inference","primary_cat":"math.ST","submitted_at":"2026-06-18T16:08:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":8.0,"formal_verification":"none","one_line_summary":"Local privacy mechanisms preserve rate-double-robustness, enabling unbiased and semiparametrically efficient inference on target parameters indexed linearly by infinite-dimensional and nonlinearly by low-dimensional components from noisy private data.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.20003","ref_index":124,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Estimating treatment duration effects via clone-censor-weight: a breast cancer case study","primary_cat":"stat.ME","submitted_at":"2026-05-19T15:34:49+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":5.0,"formal_verification":"none","one_line_summary":"The clone-censor-weight approach is formalized and tested via simulations before application to a breast cancer cohort comparing 2 versus 5 years of adjuvant tamoxifen, yielding estimates with substantial uncertainty.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.18724","ref_index":12,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Sensitivity analysis for causal mediation: bridge score, sharp sensitivity bounds, and calibration","primary_cat":"stat.ME","submitted_at":"2026-05-18T17:50:57+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"Introduces bridge score for covariate balancing in mediator stage and derives sharp pointwise variance bounds on unidentified mediator-outcome confounding with residual budget calibration and Bayesian inference.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"mean heterogeneity to use the full residual variance budget, whilek a = 0 recovers the sequential ignorability anchor on theη a side. The residual selection parameterγ a(m, b) is a likelihood ratio between the conditional and reduced laws of the latent confounder within an arm and bridge score stratum, and is not identifiable either. Introduce a user-specified grid valueg a ≥1 and assume γa(m, b)≤g a, a∈ {0,1}.(12) Values such asg a ∈ {1.25,1.5,2,3}parallel the multiplicative selection ratio scale in sensitivity analysis (Ding and Vanderweele, 2016; VanderWeele et al., 2014).g a is the largest plausible tilt in the latent confounder density induced by conditioning onM=m after conditioning on the bridge score. The choiceg a = 1 enforcesγ a(m, b)≡1 and recovers"},{"citing_arxiv_id":"2605.13550","ref_index":72,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Causal Discovery via Statistical Power (CDSP)","primary_cat":"stat.ME","submitted_at":"2026-05-13T13:56:31+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"CDSP uses an effect-size asymmetry assumption and statistical power to estimate causal directions from bivariate data with uncertainty, reducing false discoveries by 18% on 100 benchmark pairs.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.09733","ref_index":77,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Small and Complex I: The Three Component Structure of $z \\sim 0$ Massive Compact Quiescent Galaxies","primary_cat":"astro-ph.GA","submitted_at":"2026-05-10T20:06:05+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"75% of massive compact quiescent galaxies at z~0 require three-component photometric models (bulge + disk + envelope), versus only 7% of mass-matched control quiescent galaxies.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.09168","ref_index":12,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"CIVeX: Causal Intervention Verification for Language Agents","primary_cat":"cs.AI","submitted_at":"2026-05-09T21:06:15+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"CIVeX maps agent tool calls to structural causal queries, checks identifiability, and issues auditable verdicts to prevent false executions while preserving utility on confounded benchmarks.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2605.08034","ref_index":30,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Semiparametric Efficient Test for Interpretable Distributional Treatment Effects","primary_cat":"stat.ML","submitted_at":"2026-05-08T17:23:34+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"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.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"Average treatment effects are often too coarse for causal questions involving risk, heterogeneity, or structured outcomes. A treatment may leave the mean outcome nearly unchanged while altering dispersion, tails, multimodality, or the probability of rare but consequential events. This is the motivation behind distribu- tional treatment-effect analysis, including nonparametric policy effects [30] and inference on interventional distributions [3]. The issue is even sharper when outcomes are images, sequences, graphs, embeddings, or high-dimensional measurements [8]: reducing such outcomes to a small number of hand-chosen scalar summaries can obscure the effect of interest. We therefore study tests of interventional outcome distributions, rather than tests that only address average effects."},{"citing_arxiv_id":"2605.05706","ref_index":5,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Resolving the bias-precision paradox with stochastic causal representation learning for personalized medicine","primary_cat":"cs.AI","submitted_at":"2026-05-07T05:51:21+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"Stochastic causal representation learning with sMMD resolves the bias-precision paradox, improving accuracy under distribution shift by up to 11.5% and clinician accuracy by 14.7% on large ICU cohorts.","context_count":1,"top_context_role":"background","top_context_polarity":"background","context_text":"variable-level attribution scores, temporal contribution patterns, and counterfactual treatment trajectories (right-bottom). An LLM-generated explanation provides a structured clinical rationale with treatment preference distribution (left-bottom). Data sources: MIMIC-III (N=25,186, United States) and AmsterdamUMCdb (N=2,597, the Netherlands). 4 than random allocation [5, 6]. To address this, state-of-the-art frameworks enforce distributional alignment between treated and untreated populations in the learned representation space (Figure 1a) [7-10]. This deconfounding process introduces an under-examined trade-off: the patient features that drive treatment assignment, and thus differ most between groups, are often the most clinically informative."},{"citing_arxiv_id":"2604.21721","ref_index":8,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"A Riesz Representer Perspective on Targeted Learning","primary_cat":"stat.ME","submitted_at":"2026-04-23T14:24:30+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":6.0,"formal_verification":"none","one_line_summary":"A recursive Riesz representer-based targeted minimum loss estimation procedure unifies asymptotically efficient estimation of causal estimands such as time-varying treatment effects and mediation effects.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null},{"citing_arxiv_id":"2604.21658","ref_index":1,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Estimator-Aligned Prospective Sample Size Determination for Designs Using Inverse Probability of Treatment Weighting","primary_cat":"stat.ME","submitted_at":"2026-04-23T13:20:58+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":7.0,"formal_verification":"none","one_line_summary":"A GEE-based stacked M-estimation framework merges propensity score and marginal structural models to directly compute the large-sample variance of the IPTW estimator from pilot data for prospective sample size planning, with bootstrap stabilization.","context_count":1,"top_context_role":"method","top_context_polarity":"use_method","context_text":"International Council for Harmonisation. E9(R1) statistical principles for clinical trials: Addendum: Es- timands and sensitivity analysis in clinical trials, 2021. URL https://www.fda.gov/media/148473/ download. Guidance for Industry. Paul R Rosenbaum and Donald B Rubin. The central role of the propensity score in observational studies for causal effects.Biometrika, 70(1):41-55, 1983. doi: 10.1093/biomet/70.1.41. Peter C Austin and Elizabeth A Stuart. Moving towards best practice when using inverse probability of treatment weighting (IPTW) using the propensity score to estimate causal treatment effects in observational studies.Statistics in Medicine, 34(28):3661-3679, 2015. doi: 10.1002/sim.6607. Shein-Chung Chow, Jun Shao, Hansheng Wang, and Yuliya Lokhnygina."},{"citing_arxiv_id":"2506.05967","ref_index":10,"ref_count":1,"confidence":0.88,"is_internal_anchor":false,"paper_title":"Preference Learning for AI Alignment: a Causal Perspective","primary_cat":"cs.AI","submitted_at":"2025-06-06T10:45:42+00:00","verdict":"UNVERDICTED","verdict_confidence":"LOW","novelty_score":4.0,"formal_verification":"none","one_line_summary":"Advocates applying causal inference to preference learning for LLM alignment to diagnose generalization failures and guide better data practices.","context_count":0,"top_context_role":null,"top_context_polarity":null,"context_text":null}],"limit":50,"offset":0}