Your personalresearch library

Phillip J. Haubrock, Antonín Kouba, Ismael Soto, Neil Angelo S. Abreo, Lorenzo Vilizzi, Dagmara Błońska, Ali Serhan Tarkan, Vanessa De Santis, Ronaldo Sousa, António Barbosa Nogueira, Senne Heeren, Joana Garrido Nogueira, Carlos Cano-Barbacil, Bruno Cremella, Diederik Strubbe, Janine Pereira da Silva, Riccardo Poloni, Pablo Deschepper, Eli S. J. Thoré, Benjamin Misteli, Jingrui Sun, Martina Panisi, David Dudgeon, Valentini Stamatiadou, Shams M. Galib, Chelly Maes, Nompumelelo C. Baso, Wouter Beukema, Barbora Števove, Eva Záhorská, Irmak Kurtul, Davinder Kaur, Augusto Frederico Huber, Dariusz Halabowski, Janeide de Assis Guilherme Padilha, Paride Balzani, Cüneyt Kaya, Esra Bayçelebi, Michele Mugnai, Danish A. Ahmed, Gülşah Saç, Sadi Aksu, Burak Malik Kaya, Mulkibar Ciftcioglu, Xiaoming Jiang, Marta Rodríguez-Rey, Irene Martín-Forés, Suzana Gonçalves Leles, Lucian Pârvulescu, Jan Pergl, Federica Rossetto, Hui Wei, Natalia I. Kirichenko, Elizabeta Briski, Luca Gallitelli, J. Robert Britton, Teun Everts

Nature Human Behaviour·2026

No abstract available

No ratings yet

View paper →

Why It Is (Probably) Not Your Fault if Your Studies Do Not Work Out

Ethan Meimoun, Daniël Lakens

Perspectives on Psychological Science·2026

Early career researchers, because of their role in data collection and analysis, are often first to experience the emotional impact of null or nonreplicable results. In this article, we lift the veil on null results by presenting their causes (i.e., low prior probability of the hypothesis, theoretical ambiguity) and consequences and offer early career researchers—especially researchers at less wealthy institutions—tools to deal with null results.

No ratings yet

View paper →

Page 1 of 630Next

How Proper Scoring Rules Shape LLM Forecasting

Turtel, Benjamin, Wilczewski, Paul, Skotheim, Kris, Satopää, Ville A., Tetlock, Philip E.

arXiv·2026

This paper evaluates how reward function choice shapes the performance and behavior of LLM forecasters. We compare five proper scoring rules as training objectives for binary forecasts of resolved real-world events. Although the rules share the same theoretical incentive for truthful probability reporting, the resulting models differ in calibration, probability use, and estimated profiles of bias, information, and noise, with smaller differences in aggregate accuracy and discrimination. The Brier-trained model has the lowest observed Brier score and highest AUC-ROC, while the log-trained model has the highest observed log score and lowest calibration error. Models with similar aggregate performance also reach that performance through different combinations of bias, information, and noise. Proper scoring rules therefore need not behave interchangeably as training objectives. Reward choice may shape not only how well an LLM forecasts, but how its forecasting errors are structured. Each condition uses a single seed, so some differences may reflect training stochasticity.

No ratings yet

View paper →

Classification testing: A new framework for drawing qualitative conclusions from quantitative estimates

Andrew C. Eggers, Zikai Li

arXiv·2026

Social scientists rely on hypothesis testing to support their research conclusions, but the standard tests are designed for testing one hypothesis rather than adjudicating between rival possibilities. We develop a new framework, "classification testing", as an alternative. Instead of selecting one hypothesis to test, a researcher conducting a classification test decides what qualitative distinctions ("classes") are most substantively relevant; the test either assigns the estimand to a class with error control similar to that of a conventional hypothesis test, or declares the result inconclusive. We argue that classification testing is superior to current practice not just when the objective is to adjudicate between rival possibilities but also when there is one research hypothesis to be tested, because classification testing exposes that hypothesis to refutation. We illustrate the framework by applying it to a well-known media experiment and offer an R package to aid in implementation.

No ratings yet

View paper →

The Value of a Prompt: An LLM-Relative Kolmogorov-Complexity Approach

Rafael Pass

arXiv·2026

In a world where valuable artifacts are increasingly created, completed, or processed by LLMs, the central economic question is not only what the LLM can produce, but what \emph{value} remains in the inputs (i.e., the prompts) we provide to it. Given a prompt, hint, critique, problem statement, or partial solution that helps an LLM produce an artifact $z$---a proof, program, design, or scientific hypothesis---how should we measure the value of that input? Intuitively, an input is valuable when it makes the target artifact easier for the model to generate: either by increasing its sampling probability, or by reducing the thinking time needed to find it. We propose a computational Levin--Kolmogorov complexity approach to this problem, by appropriately replacing the universal Turing machine in the classical definitions by the LLM itself. Concretely, we introduce an LLM-relative notion of \emph{probabilistic Levin--Kolmogorov complexity} $pKt$---treating the model's thinking as the random tape of the program, and charging logarithmically for it in Levin's manner---and define prompt value as algorithmic mutual information with respect to $pKt$. This captures the intuition above: a prompt having $b$ bits of value for an artifact $z$ makes $z$ $2^b$ times ``easier to obtain'', by multiplying the success probability by $2^b$, by dividing the required computation by $2^b$, or by any corresponding tradeoff between probability and computation. In contrast to the classical notion of algorithmic mutual information, ours is efficiently estimable. We additionally show that, under a natural reproduction experiment, a prompt value of $b$ bits means that reproducing $z$ without the prompt has median token cost $2^b$ times that of reproducing it with the prompt.

No ratings yet

View paper →

Your personalresearch library

All Papers

Thời báo chí sôi nổi khai mở nền văn chương Việt Nam hiện đại

What I Learned About Asset Pricing

How contemporary academic structures constrain scientific creativity and hold back early-career researchers

Why It Is (Probably) Not Your Fault if Your Studies Do Not Work Out

Double robust, flexible adjustment methods for causal inference: An overview and an evaluation

How Proper Scoring Rules Shape LLM Forecasting

What Filipino Filmmakers Really Think of Piracy

Classification testing: A new framework for drawing qualitative conclusions from quantitative estimates

The Films That Found Me

Minutes of the Federal Open Market Committee July 28–29, 2026

The Abandoned Order: Learning to Live in a Post-American World

The Value of a Prompt: An LLM-Relative Kolmogorov-Complexity Approach