{"slug": "can-an-ai-agent-rediscover-a-blaschke-curve-invariant", "title": "Can an AI Agent Rediscover a Blaschke-Curve Invariant?", "summary": "An AI agent rediscovered a degree-four Blaschke-curve invariant from numerical data, fitting a homogeneous cubic whose frozen coefficients predicted 480 lines from 80 unseen parameter values with a recorded RMS scale-free residual of 8.88×10^-17, according to arXiv paper 2609.38369v1. The single-instance case study reports that a separate one-configuration run found insufficient evidence for invariance, and a post-review deterministic degree-search baseline also recovered the cubic, so the experiment does not establish an advantage over polynomial fitting. The authors present the work as a protocol for separating conjecture, numerical validation, and proof, with explicit limitations concerning agent metadata, prior knowledge, and reproducibility.", "body_md": "arXiv:2609.38369v1 Announce Type: new \nAbstract: We study generalized Blaschke curves as a controlled environment for AI-assisted mathematical rediscovery. For one fixed degree-four Blaschke product, an agent receives numerical coordinates of the six pair-lines determined by each of 80 boundary configurations. The target theorem is withheld from the task instructions. The saved research log reports rejected geometric hypotheses and a homogeneous cubic fitted to polygon sides. Its frozen coefficients predict 480 lines from 80 unseen parameter values, with a recorded RMS scale-free residual of $8.88\\times10^{-17}$. Discovery-set diagonals provide an out-of-fit consistency check, not a fully held-out test. A separate one-configuration run reports insufficient evidence for invariance. A post-review deterministic degree-search baseline also recovers the cubic, so the experiment does not establish an advantage over polynomial fitting. We present this single-instance case study as a protocol for separating conjecture, numerical validation, and proof, with explicit limitations concerning agent metadata, prior knowledge, and reproducibility.", "url": "https://wpnews.pro/news/can-an-ai-agent-rediscover-a-blaschke-curve-invariant", "canonical_source": "https://arxiv.org/abs/2609.38369", "published_at": "2026-10-01 04:00:00+00:00", "updated_at": "2026-10-01 04:17:34.187385+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-research", "machine-learning"], "entities": ["arXiv", "Blaschke curves", "Blaschke product"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/can-an-ai-agent-rediscover-a-blaschke-curve-invariant", "markdown": "https://wpnews.pro/news/can-an-ai-agent-rediscover-a-blaschke-curve-invariant.md", "text": "https://wpnews.pro/news/can-an-ai-agent-rediscover-a-blaschke-curve-invariant.txt", "jsonld": "https://wpnews.pro/news/can-an-ai-agent-rediscover-a-blaschke-curve-invariant.jsonld"}}