MIRTO: a registration-gated, multiverse-tested evaluation protocol for unsupervised anomaly segmentation in brain MRI

Local Support Learning

We explore catastrophic forgetting in the context of large pre-trained models. By considering forgetting as a geometric problem in the input space of each weight matrix, we uncover a natural retention…

2026-10-01 ·arxiv.org

Sources: Anthropic could start formal marketing for its IPO as soon as the week of November 9, putting it in line to begin trading before Thanksgiving (Bailey Lipschultz/Bloomberg)

Anthropic PBC is seeking to go public as soon as the middle of November, according to people familiar with the matter …

2026-10-01 ·bloomberg.com

Argo-Bench: Evaluating Data Agents on Enterprise-Scale Workflows

Real-world enterprise data science and analytics workflows require reasoning across dozens of tables, performing statistical analyses, and acting on the results.

2026-10-01 ·arxiv.org

Finetuning with Sampling: SFT Learns Better Than You Think

Introducing new capabilities to frontier models has long been the goal of posttraining, which predominantly employs supervised finetuning (SFT) and reinforcement learning (RL) to this end.

2026-10-01 ·arxiv.org

From Knowledge Access to Source Learning: Developing Source-Specific Competence

Large language model (LLM) agents increasingly rely on persistent external sources to solve sequences of knowledge-intensive tasks.

2026-10-01 ·arxiv.org

Opus 5.5 loves to tell you ‘this matters’ (and other AI writing tells)

Opus 5.5’s biggest tell is the word “dependable,” which pops up 23 times more often than in human samples.

• "Dependable" appears 23 times more often in Claude Opus 5.5's writing than in humans
• "This matters" occurs 116 times more frequently in Opus 5.5 than in human writing
• Astra model emphasizes "another dimension" and uses "may provide" or "can provide" hedging

2026-10-01 ·techcrunch.com