INDEX
Every paper Pith has read and judged, in one searchable index.
-
cs.LG arXiv submitted 2026-07-08Two-layer nets need large Lip constant to fit noisy labels
Yitzchak Shmalo · “A law of robustness for two-layer neural networks with arbitrary weights”
2607.07778 -
math.ST arXiv submitted 2026-07-08Sampling turns size gaps into rates for growing models
Eitan Levin +1 · “Any-Dimensional Learning by Sampling”
2607.07680 -
physics.optics arXiv submitted 2026-07-08AI turns brightfield microscopes into virtual Raman spectrometers
Srilakshmi Premachandran +2 · “Pic2Spec: Generative Modeling Reconstructs Single Cell Raman Fingerprints from Brightfield Images”
2607.07651 -
stat.AP arXiv submitted 2026-07-08Continuous spatial model beats zone-based flood insurance pricing
Mulah Moriah +4 · “Bayesian spatial modelling framework for assessing residential flood risk in property insurance”
2607.07609 -
stat.ME arXiv submitted 2026-07-08One U-statistic test covers variances
M. Romero-Madro\~nal +2 · “Testing the equality of estimable parameters”
2607.07588 -
stat.ME arXiv submitted 2026-07-08One test to compare any parameter across any number of populations
M. Romero-Madro\~nal +2 · “Testing the equality of estimable parameters”
2607.07588 -
stat.ML arXiv submitted 2026-07-08One convex density fills missing values and samples them
Andrea Basteri +2 · “Distributionally Faithful Imputation via Positive Semi-Definite Kernel Density Estimation”
2607.07767 -
stat.ME arXiv submitted 2026-07-08Modified pesticide safety test lets harmful substances slip through
Dimitry Wintermantel +3 · “Equivalence testing in pesticide risk assessment -- Evaluation and practical guidance for design, analysis and interpretation”
2607.07543 -
quant-ph arXiv submitted 2026-07-08Quantum toolkit cuts sample complexity for power-sum functionals from α² to α
Qisheng Wang · “Towards Minimax Estimation of High-Order Functionals by Quantum Arguments”
2607.07540 -
cs.LG arXiv submitted 2026-07-08Failure regions can swell exponentially during training
Adam M. Oberman · “Avoiding unsafe sets when training with Langevin Dynamics”
2607.07538 -
cs.LG arXiv submitted 2026-07-08Failure regions stay rare after a burn-in of order d
Adam M. Oberman · “Avoiding unsafe sets when training with Langevin Dynamics”
2607.07538 -
stat.ML arXiv submitted 2026-07-08This paper proposes a unified framework for detecting AI-generated content—fake text
Xifeng Zhang +3 · “A Unified Detection Framework for AI-Related Content and Artifacts”
2607.07527 -
cs.LG arXiv submitted 2026-07-08No gradients needed: metric reshapes space to bridge modes
Ricardo Baptista +1 · “Gradient-free Riemannian Langevin Sampler”
2607.07519 -
math.ST arXiv submitted 2026-07-08Plug-in SPMLE estimates survive non-uniqueness and nonresponse
Eitan Greenshtein +1 · “Empirical Bayes Estimation of the Mean of a Function of the Latent Variable with Applications to the Treatment of Nonresponse”
2607.07516 -
cs.LG arXiv submitted 2026-07-08Why self-supervised learning needs so few labels: an O(1/n) rate
Adam M. Oberman · “Fast Rates for Semi-Supervised Learning via Data-Augmentation Graph Regularization”
2607.07513 -
cs.LG arXiv submitted 2026-07-08Augmentation graphs give labels a fast 1/n error rate
Adam M. Oberman · “Fast Rates for Semi-Supervised Learning via Data-Augmentation Graph Regularization”
2607.07513 -
stat.ME arXiv submitted 2026-07-08Imputing unreported outcomes to debias meta-analyses
Cora Burgwinkel +2 · “Adjusting for Outcome Reporting Bias in Meta-analysis: A Multiple Imputation Approach”
2607.07509 -
stat.ML arXiv submitted 2026-07-08Sparse recovery rates for nonlinear inverse problems proven optimal
Abhishake Rastogi +3 · “Statistical inverse learning and $\ell^1$-regularization”
2607.07468 -
stat.ME arXiv submitted 2026-07-08Bayesian model learns hidden states in circular-linear data
Federico P. Cortese +1 · “Infinite hidden Markov models for cylindrical data”
2607.07464 -
cs.LG arXiv submitted 2026-07-08Learning full Chain-of-Thought traces costs no extra samples
Zhiyuan Li · “The Optimal Sample Complexity of Learning Autoregressive Chain-of-Thought”
2607.07423 -
stat.ME arXiv submitted 2026-07-08Synergy can hide behind redundancy in complex systems
Yuri Antonacci +5 · “From Statistical to Structural Synergy: A Predictability Framework to Quantify the Effects due to High-Order Mechanisms”
2607.07286 -
stat.ME arXiv submitted 2026-07-08Forecasting subnational mortality: modeling the gap from national data wins
Han Lin Shang +1 · “Visualizing and forecasting subnational life-table death counts: Gap forecasting methods”
2607.07284 -
stat.AP arXiv submitted 2026-07-08MLP beats linear models by 13% for same-hour PM2.5 in Beijing
Yusheng Wang +1 · “Nowcasting PM2.5 in Beijing Using Synchronous Covariates and Lagged Features: Model Comparison and Variable Selection Stability”
2607.07279 -
math.ST arXiv submitted 2026-07-08Optimal rate found for minimizing derivatives from noisy queries
Arya Akhavan +2 · “Gradient-free stochastic optimization of derivatives under strong convexity”
2607.07249 -
stat.ME arXiv submitted 2026-07-08Simple kNN beats MICE for missing clinical data at high rates
Pakpoom Wongyikul +6 · “Comparing Imputation Methods for Clinical Prediction Model Development under Complex Missingness Scenarios: A Simulation Study Using Real-World Cardiac Data”
2607.07247 -
math.ST arXiv submitted 2026-07-08One randomization step unifies three families of FDR tests
Mingzhou Deng +1 · “The Randomized BH Procedure: A Generalized Framework Encompassing Conformal and Competition Tests”
2607.07245 -
stat.ML arXiv submitted 2026-07-08Train on small graphs, generate big ones: diffusion on graphons scales up
Sergio Rozada +4 · “DiPhon: Diffusion on Graphons for Scalable Graph Generation”
2607.07232 -
stat.ME arXiv submitted 2026-07-08The paper shows that the standard Moran statistic used in spatial analysis is badly…
Levi John Wolf +1 · “Robust Indicators of Spatial Association”
2607.07215 -
stat.ME arXiv submitted 2026-07-08Theil-Sen Moran beats OLS for outlier-proof map analysis
Levi John Wolf +1 · “Robust Indicators of Spatial Association”
2607.07215 -
stat.CO arXiv submitted 2026-07-08Entrance distribution governs trans-model MCMC mixing efficiency
Xiyun Jiao +2 · “Mixing efficiency of trans-model Markov chain Monte Carlo algorithms with applications in Bayesian phylogenetics”
2607.07188 -
math.ST arXiv submitted 2026-07-08Copula density from stochastic inversion factors as base times weight
Alexander J. McNeil +1 · “Stochastic Inversion of Multivariate Uniform-Distribution-Preserving Transformations”
2607.07174 -
stat.ME arXiv submitted 2026-07-08Gain rule on variational bound recovers true factor count
Jinsong Chen +1 · “Recovering Latent Structures after Variational Bayesian Variable Selection: Fit Assessment and Factor-Number Selection in Partially Exploratory Factor Analysis”
2607.07159 -
cs.CL arXiv submitted 2026-07-08Text embeddings predict test-item difficulty at R²=0.53
Shi-Ting Chen +1 · “From Text to Parameters: Predicting Item Parameters from Embedding Regularization with Reliability and Design Ceilings”
2607.07141 -
cs.LG arXiv submitted 2026-07-08A Lipschitz constant that calibrates networks by construction
Arthur Chiron (IRIT +8 · “LiST: Lipschitz Scaling Training for Robust and Calibrated Neural Networks”
2607.07745 -
stat.AP arXiv submitted 2026-07-08Rare exposures break standard confounding adjustment
M. Ehsan Karim +1 · “Which Regularized Propensity-Score and Doubly Robust Methods Are Best Calibrated When Exposures or Outcomes Are Rare? A Plasmode Study of Proxy-Based Confounding Adjustment”
2607.07065 -
cs.LG arXiv submitted 2026-07-08Directed graph PEs without eigenvectors
Jiaqing Xie +1 · “Eigenbasis-Independent Learnable Spectral Positional Encodings for Directed Graphs via Hermitian Block Krylov Subspaces”
2607.07032 -
cs.LG arXiv submitted 2026-07-08Directed graph positions without eigenvectors: Krylov suffices
Jiaqing Xie +1 · “Eigenbasis-Independent Learnable Spectral Positional Encodings for Directed Graphs via Hermitian Block Krylov Subspaces”
2607.07032 -
math.PR arXiv submitted 2026-07-08Small perturbations can't kill exponential region growth in deep nets
Recep \"Ozkan +1 · “Local large deviations for linear-region growth in random piecewise-linear networks”
2607.07014 -
stat.ML arXiv submitted 2026-07-08Tensorized filtering cuts fHMM cost from O(M²) to O(M·ΣMₖ)
Roxana Barrios +1 · “Tensorized algorithms and scalable filtering methods for hidden Markov and factorial hidden Markov models”
2607.07008 -
math.ST arXiv submitted 2026-07-08Extropy of consecutive-k systems derived
Aman Pandey +1 · “A Study on Cumulative Residual Extropy of Linear Consecutive k-out-of-n:G Systems”
2607.06992 -
stat.AP arXiv submitted 2026-07-08Crypto catastrophe bonds get arbitrage-free pricing and on-chain settlement
Yue Wang +3 · “Multi-Trigger Crypto CAT Bonds with On-Chain Settlement: Valuation and Optimal Design”
2607.06981 -
stat.ME arXiv submitted 2026-07-08Detect signals without knowing the background
Aritra Banerjee +1 · “Compensator-based inference for signal detection under unknown background: the binned data case”
2607.06939 -
stat.ME arXiv submitted 2026-07-08Shared signal split from domain noise in transfer LDA
Yonghan Zhang +3 · “Transfer Learning for Linear Discriminant Analysis with a Shared Classification Signal”
2607.06936 -
math.OC arXiv submitted 2026-07-08Bellman operators unify reinforcement learning's algorithmic zoo
Denis Belomestny +7 · “Mathematical methods of reinforcement learning”
2607.06935 -
stat.AP arXiv submitted 2026-07-08Three-model framework reveals Rust Belt heart deaths diverge by race
Christopher Blaszczak-Boxe +5 · “A Hierarchical Multilevel Inference Framework for Structural Cardiovascular Risk Modeling: County-Scale Analysis of Cardiovascular Mortality in Ohio and Pennsylvania (1999-2020)”
2607.06916 -
stat.ME arXiv submitted 2026-07-08Causal effects without measuring confounders: the power of outcome supports
Shane Sparkes · “Causal Inference for Case Studies in Behavioral Health”
2607.06912 -
stat.AP arXiv submitted 2026-07-08Six-dimensional embeddings from a shallow net match or beat larger models for test item
James Sharpnack +1 · “Learning Item Embeddings and Hyperparameters for IRT Calibration via Monte Carlo EM”
2607.06905 -
stat.ML arXiv submitted 2026-07-08Random resampling reaches true stationarity
Felipe Areces +2 · “Finding a stationary point of a stochastic convex problem”
2607.06883 -
stat.ML arXiv submitted 2026-07-08True stationarity from stochastic samples
Felipe Areces +2 · “Finding a stationary point of a stochastic convex problem”
2607.06883 -
cs.LG arXiv submitted 2026-07-08Cheap AI Predictions Cut Costly Experiments by Up to 61%
Tianyi Ma +3 · “Best-Arm Identification with Generative Proxy”
2607.06879