Daily report — 2026-10-08
167 new papers screened · 10 analyzed · 0 reproduction runs · markdown
Reproductions
| status | paper | backend | claims matched |
|---|---|---|---|
| No reproduction runs today (opt-in). | |||
Top candidates
| score | paper | feasibility |
|---|---|---|
| 62.6 | Identifiability of a dissipative knowledge-dynamics model: exact recovery under designed excitation, degeneration on observational data Human learning is a dissipative dynamical process: mastery accumulates through practice, decays through forgetting, and propagates across interdependent concepts. We model it as a nonlinear dissipative system of ordinary differential equations whose parameters are mechanistically meaningful (a concept-transfer matrix encoding prerequisite coupling, per-concept forgetting rates, and a saturating pr Claimed: none extracted Evidence: + cheap/closed-form ("closed-form"); + toy/synthetic experiments ("synthetic"); + small/synthetic data ("synthetic"); + public benchmarks ("benchmarks"); + concrete method ("closed-form"); + formal statement ("We prove"); + claims simplicity ("simple"); no public code found | 8/10 heuristic |
| 61.6 | Finite-Rank Logistic Gaussian Processes with Exact Likelihood for Conditional Density Estimation Conditional density estimation describes how the entire distribution of a response changes with covariates, and in imaging studies also with location. Logistic Gaussian processes (LGP) give a flexible prior for such densities. Claimed: none extracted Evidence: + cheap/closed-form ("closed form"); + toy/synthetic experiments ("synthetic"); + small/synthetic data ("synthetic"); + concrete method ("closed form"); + formal statement ("bound"); no public code found; + keywords: sampling | 8/10 heuristic |
| 61.1 | A self-learning scientific agent for X-ray diffraction A central challenge for scientific agents is to turn analytical experience into reusable expertise grounded in physical evidence. Here we introduce Gan Jiang, a self-learning agent for powder X-ray diffraction built on a diffraction-analysis ecosystem we developed: XMatcher, XQueryer, XDecomposer and WPEM. Claimed: none extracted Evidence: + toy/synthetic experiments ("simulated"); + small/synthetic data ("simulated"); + claims simplicity ("simple"); - system/framework (many moving parts) ("agents is to turn analytical experience into reusable expertise grounded in physical evidence. Here we introduce Gan Jiang, a self-learning agent for powder X-ray diffraction built on a diffraction-analysis ecosystem we developed: XMatcher, XQueryer, XDecomposer and WPEM. Together, these engines span phase identification, multiphase decomposition and physics-constrained whole-pattern modelling. Gan Jiang converts analytical experience into executable skills by diagnosing failures, revising skill instructions and code, and validating revisions before reuse, without retraining the language model or changing the underlying physical models. Skills selected using development data and frozen before held-out evaluation achieve higher refinement scores than the original expert-designed skills across FullProf, GSAS-II and PyWPEM. The agent resolves strongly overlapping reflections, quantifies a five-phase ancient Egyptian cosmetic, tracks lattice evolution in an operating battery and compares atomic configurations in a disordered oxide catalyst. On DeltaXRDbench, it leads the evaluated methods in single- and multiphase identification across simulated and experimental data. Without supplied composition, single-phase top-1 accuracies reach 96.30\%, 81.78\% and 40.83\% on MP500, RRUFF and opXRD, respectively, compared with 58.00\%, 58.47\% and 26.45\% for the strongest comparator. These results demonstrate how an integrated scientific tool"); + code: https://github.com/DeltaGanjiang/XDecomposer; + 7 HF upvotes | 6/10 heuristic |
| 57.4 | Transition Path Sampling Using Koopman Operators and Exit-Time Optimal Control Sampling transitions between metastable states is a central problem in dynamical systems theory and molecular dynamics in particular. A key challenge is the existence of high free-energy barriers that separate the states, making transitions extremely rare. Claimed: none extracted Evidence: + cheap/closed-form ("closed form"); + toy/synthetic experiments ("simulation"); + concrete method ("we propose a new"); + formal statement ("We prove"); no public code found; + keywords: sampling, kernel | 7/10 heuristic |
| 56.8 | Q-Learning with Scalar Adjoint Matching Flow policies capture rich and diverse action distributions, and fine-tuning them with off-policy RL to improve beyond the demonstrations has drawn growing interest. However, fine-tuning a flow policy against a learned value function is not trivial, because the policy generates its action over many flow steps. Claimed: none extracted Evidence: - pretraining ("pretrained"); + cheap/closed-form ("closed-form"); + explicit algorithm/pseudocode ("Algorithm 1"); + concrete method ("closed-form"); + code: https://github.com/yonghdong/sqam; + 10 HF upvotes | 6/10 heuristic |
| 56.3 | On KL-Regularized Policy Optimization Asynchronous reinforcement learning (RL) for large language model (LLM) agents trains one policy on trajectories generated by another: rollouts come from stale checkpoints, and the inference engine's probabilities differ from the trainer's even at identical parameters. Standard remedies either clip importance ratios, which biases the update, or, as in GRPO, sample a group of responses per prompt, Claimed: none extracted Evidence: - LLM-based ("large language model"); + cheap/closed-form ("closed-form"); + concrete method ("closed-form"); + formal statement ("bound"); - system/framework (many moving parts) ("agents trains one policy on trajectories generated by another: rollouts come from stale checkpoints, and the inference engine's probabilities differ from the trainer's even at identical parameters. Standard remedies either clip importance ratios, which biases the update, or, as in GRPO, sample a group of responses per prompt, which is costly when episodes are long. We propose KL-Regularized Policy Optimization (KLPO), a framework that anchors the KL regularizer at the sampler. The regularized improvement step then has a closed-form Gibbs solution, and KLPO fits its log-ratio optimality condition by least squares on the sampler's own trajectories, so the sampler probability enters through a log-ratio and no importance weights are needed. Profiling out the regression intercept replaces the intractable log-partition function with the signal's sampler mean plus a sampler-to-trainer KL divergence. For token-level policy mirror descent targets, we show that the resulting gradient can be computed from terminal returns without a critic, via sampler-centered scores or a single trajectory residual, even under stochastic tool"); + code: https://github.com/yifanzhang-pro/KLPO; + keywords: monte carlo; + 18 HF upvotes | 5/10 heuristic |
| 55.8 | Dataset Pruning from First Principles: A Label-Free Linear Programming Approach Dataset pruning reduces a large training set to a representative subset while preserving model performance. Existing geometry-based methods typically assume that nearby points in embedding space share similar properties. Claimed: none extracted Evidence: + cheap/closed-form ("closed-form"); + small/synthetic data ("CIFAR-10"); + public benchmarks ("benchmarks"); + concrete method ("closed-form"); + formal statement ("convergence"); - system/framework (many moving parts) ("framework"); no public code found; + keywords: sampling | 7/10 heuristic |
| 53.7 | RobotWorld: Benchmarking Multimodal Agents for Robot Use Across Diverse Tasks and Embodiments General-purpose agents increasingly write code, use tools, and complete complex digital tasks, raising the question of how far these capabilities carry into the physical world. To investigate this, we introduce RobotWorld, a challenging simulation testbed for robot use: turning instructions and observations into physical task execution through robot interfaces. Claimed: none extracted Evidence: + toy/synthetic experiments ("simulation"); + formal statement ("bound"); - system/framework (many moving parts) ("agents increasingly write code, use tools"); + code: https://github.com/robotworldai/robotworld; + 25 HF upvotes | 5/10 heuristic |
| 51.1 | Conformal Prediction for Spatially Dependent Data via Sequential Whitening Split conformal prediction uses prediction errors on held-out (calibration) data to determine how wide the prediction intervals should be. It guarantees distribution-free finite-sample coverage when these errors and the error at the target site are exchangeable. Claimed: none extracted Evidence: + toy/synthetic experiments ("simulated"); + small/synthetic data ("simulated"); + formal statement ("bound"); no public code found; + keywords: sampling | 6/10 heuristic |
| 51.1 | DSReg: Provably Recovering Individual World Latents without Reconstruction Methods that recover individual latent variables of the world, from nonlinear ICA to dictionary learning and causal representation learning, anchor the latents to observations through reconstruction, auxiliary supervision, or distributional asymmetries such as non-Gaussianity. Methods without these anchors, including joint-embedding predictive architectures (JEPAs), identify the latent state only Claimed: none extracted Evidence: + toy/synthetic experiments ("synthetic"); + small/synthetic data ("synthetic"); + formal statement ("we prove"); no public code found; + keywords: regularization | 6/10 heuristic |