experimental-design

Tag

Cards List
#experimental-design

Synergizing Physically Constrained MCMC and Chemical-Informed Gaussian Processes for Reaction Network Discovery

arXiv cs.LG · 2026-06-24 Cached

This paper presents PC-MCMC-CIGP, a gray-box workflow that combines spike-and-slab topology sampling with physical constraints and a Chemical-Informed Gaussian Process for reaction network discovery. The method demonstrates improved yield on styrene epoxidation and distinguishes elementary pathways from deceptive fits on a hydrogen-bromine benchmark.

0 favorites 0 likes
#experimental-design

Small Experiments, Cheaper Decisions: A Case Study in Staged Promotion for Micro-Pretraining

arXiv cs.CL · 2026-06-11 Cached

This paper studies a staged promotion protocol for micro-pretraining, using escalating budgets from minutes to hours to filter configurations. It finds that early screens are useful but unstable, and that a staged approach can retain a long-horizon reference while identifying alternatives that fail continuation thresholds.

0 favorites 0 likes
#experimental-design

When Should an AI Scientist Stop? Verifiable Experiment Steering and Refusal for Autonomous Discovery

arXiv cs.LG · 2026-06-09 Cached

This paper introduces Cartograph, a verification layer for AI scientists that couples subspace experiment steering, ambiguity resolution, and library inadequacy detection. The framework outperforms baselines in autonomous discovery testbeds and retrospectively flags inconclusive claims in the A-Lab materials system.

0 favorites 0 likes
#experimental-design

Staged Factorial Screening for Budget-Constrained Micro-Pretraining

arXiv cs.LG · 2026-06-05 Cached

This paper proposes a staged factorial screening workflow for budget-constrained micro-pretraining, demonstrating that short designed experiments can identify stable hyperparameter penalty directions and support a screen-then-refine strategy.

0 favorites 0 likes
#experimental-design

@rwayne: ScienceClaw — AI assistant framework integrating 285 research skills. ScienceClaw is a framework that modularizes the entire research workflow into 285 Skills. PubMed, Semantic Scholar, ArXiv all connected at once, all can be used by L…

X AI KOLs Timeline · 2026-05-15

ScienceClaw is an AI assistant framework integrating 285 research skills, modularizing the entire research workflow into Skills. It supports connecting to databases such as PubMed, Semantic Scholar, and ArXiv, providing functions like literature search, paper deep reading, citation analysis, experimental design assistance, and writing assistance. It is suitable for advanced users who want deep customization.

0 favorites 0 likes
#experimental-design

Evaluating LLMs as Human Surrogates in Controlled Experiments

arXiv cs.CL · 2026-04-20 Cached

This paper evaluates whether off-the-shelf LLMs can reliably simulate human responses in controlled behavioral experiments by comparing LLM-generated data with human survey responses on accuracy perception. The findings show that while LLMs capture directional effects and aggregate belief-updating patterns, they do not consistently match human-scale effect magnitudes, clarifying when synthetic LLM data can serve as behavioral proxies.

0 favorites 0 likes
← Back to home

Submit Feedback