arXiv:2608.26375v1 Announce Type: new Abstract: Standard machine-learning training minimizes a loss function over a dataset, but does not guarantee that the resulting model will satisfy predefined rules or constraints on its outputs. In many real-world applications, ranging from autonomous systems…
arXiv:2608.14776v2 Announce Type: replace Abstract: Collegiate running in the United States generates thousands of race results annually in cross country and track and field, yet no large-scale dataset has been publicly available for research. Existing websites such as Athletic.net, MileSplit,…
arXiv:2608.26423v1 Announce Type: new Abstract: This paper proposes a framework for constructing a classifier as a safeguard layer, and for developing a complementary diagnostic that identifies which of the classifier’s confident decisions can be trusted. This framework, the Latent Diagnostic…
arXiv:2608.26462v1 Announce Type: new Abstract: Finetuning has become the gold standard for refining existing behaviors and inducing new ones in language models, yet it often remains unclear exactly which behaviors emerge during this process. As models grow ever more capable,…
arXiv:2608.26324v1 Announce Type: new Abstract: Best-of-N (BoN) sampling is the simplest and most widely deployed inference-time alignment strategy, but it suffers from two distinct problems: reward hacking, in which the selected response exploits errors in the proxy reward model, and…
arXiv:2509.07274v4 Announce Type: replace-cross Abstract: Migration has been a core topic in German political debate, from postwar expellee displacement to labor migration and recent refugee movements. Large-scale analysis of such political discourse has traditionally required extensive manual annotation, limiting coverage.…
arXiv:2608.26332v1 Announce Type: new Abstract: Managed LLM services are now part of real production systems, but model selection and service planning still rely heavily on capability benchmarks that reveal little about operational behavior after deployment. We present Operational Embedding (OpEmbed),…
arXiv:2608.26469v1 Announce Type: new Abstract: In many reinforcement learning (RL) domains, environments are connected by prerequisite relations, such as difficulty-increasing edits or parameter increments, which induce a directed acyclic curriculum graph (DAG). Although this structure is often exploited only implicitly,…
arXiv:2608.26309v1 Announce Type: new Abstract: Modern machine learning models rely on large amounts of labeled data. However, manual annotation of large-scale datasets is expensive and time-consuming. Label spreading is a semi-supervised learning technique that addresses this challenge by propagating information…
arXiv:2605.23955v4 Announce Type: replace-cross Abstract: Deploying machine learning in regulated financial environments — credit risk, fraud detection, and anti-money laundering — exposes critical vulnerabilities in algorithmic reproducibility. While early financial ML addressed statistical challenges such as backtest overfitting, deep neural…
