The daily ledger

True Positive Weekly #183

The most important artificial intelligence and machine learning news and articles

Does Agentic RAG Actually Retrieve Better Evidence? I Tested It on 298 Questions

I let an AI agent search again whenever it chose. It found some papers plain search had missed, lost some plain search had found, and gained too little to trust. The post Does Agentic RAG Actually Retrieve Better…

Raman Spectra Preprocessing and Non-Negative Least Squares Modelling in Python: Monitoring Zeolite Crystallization

A short, reproducible tutorial on spectral unmixing using real in situ interzeolite conversion data The post Raman Spectra Preprocessing and Non-Negative Least Squares Modelling in Python: Monitoring Zeolite…

Same Answer, Different Reason: What a Reasoning Model Says When It Follows a Planted Hint

I put wrong answers in front of 200 exam questions and read what a small model’s reasoning said when it fell for them. The post Same Answer, Different Reason: What a Reasoning Model Says When It Follows a Planted Hint…

Could On-Policy Self-Distillation Revolutionize Post-Training?

Teaching foundation models new skills without breaking them is hard. A new reinforcement learning-based approach might have the power to change that. The post Could On-Policy Self-Distillation Revolutionize…

😺 New Claude Duet works while your phone's off

Claude Duet Can Prepare Your Work. How Much Will You Need to Check?

Claude Duet checks connected applications and prepares business tasks for approval. Its value depends on whether the time saved gathering information exceeds the effort users spend verifying its recommendations.

Minimax-Optimal Predictive Flow Matching under Distribution Drift

arXiv:2610.28898v1 Announce Type: new Abstract: Flow matching learns a generative velocity field by regression, but under distribution drift a field must be deployed before the current data arrive. We study this…

FracEvent: Event-Camera Simulation via Fractional-Relaxation Pixel Dynamics

arXiv:2606.26636v4 Announce Type: replace-cross Abstract: Event cameras asynchronously report brightness changes with microsecond-level temporal resolution, but real event data remain difficult to collect at scale…

Inverse RL Helps Align AI by Imitating Humans

arXiv:2607.24900v2 Announce Type: replace Abstract: Language model alignment aims to make model behavior reflect desirable properties such as helpfulness, safety, and instruction following. Existing methods draw…

Characterizing Oblivious Common-Reward Multi-Player Bandits: Universal Stationarity, Coordination Traps, and Certified Global Rates

arXiv:2610.29673v1 Announce Type: new Abstract: This paper presents a theoretical analysis of the oblivious common-reward multi-player multi-armed bandit (OC-MPMAB), a minimal multi-player bandit model in which multiple…

Predictor-Guided Latent Space Codon Optimization for Maximizing Protein Expression

arXiv:2610.03098v2 Announce Type: replace-cross Abstract: Codon optimization, the process of selecting synonymous codons to improve mRNA translation efficiency and protein expression, is central to therapeutic protein…

GPU-Accelerated Construction of the Gabriel Graph: Parallelization Strategies and Applications to Large-Margin Classification and Graph-Based Clustering

arXiv:2610.28759v1 Announce Type: cross Abstract: The Gabriel graph is a proximity graph widely used in computational geometry and geometric machine learning, underlying large-margin classifiers and, as we show in this…

Asymmetric Likelihood-Free Hypothesis Testing

arXiv:2610.29798v1 Announce Type: new Abstract: In likelihood-free hypothesis testing (LFHT), given samples from two unknown distributions $P,Q$ on $[n]$ with $\mathrm{d_{TV}}(P,Q)\geq\varepsilon$, and from a third…

ChemBART: Pre-training a Reaction Language Model for Comprehensive Synthesis Planning

arXiv:2601.02915v2 Announce Type: replace Abstract: Recent advances in large language models (LLMs) have demonstrated transformative potential across diverse fields. However, in computer-aided synthesis planning (CASP),…

Unintended Side Effects of Value Training in LLMs

arXiv:2610.29922v1 Announce Type: cross Abstract: As LLMs are increasingly deployed in value-sensitive contexts, aligning them with human values has emerged as a post-training objective in NLP, aimed at instilling…

Generalization Bounds via Vector-Valued $L_p$ Correlation $V_\alpha$

arXiv:2610.29425v1 Announce Type: new Abstract: Understanding generalization of randomized learning algorithms remains a central challenge. Mutual-information and total-variation bounds provide complementary ways to…

Let It Be Simple: One-Step Action Generation for Vision-Language-Action Models

arXiv:2606.05737v3 Announce Type: replace-cross Abstract: One-step generation from standard diffusion or Flow-Matching training is rarely effective for text-to-image or video generation without distillation or…

Real PMIDs, Wrong Papers: Harness Design for Biomedical Claim-Verification Agents

arXiv:2610.29812v1 Announce Type: cross Abstract: Literature-searching language agents are becoming a standard component of scientific assistants for the life sciences, yet there is little controlled evidence on which…

Structure-Aware Message Passing on Petri Nets through Directed Walks and Incidence Diffusion

arXiv:2610.29725v1 Announce Type: new Abstract: A common application of the process mining discipline is to connect observed event data with Petri nets, which are bipartite, directed graphical process models with rich…