Interpretable machine learning is essential in high-stakes domains where decision-making requires accountability, transparency, and trust. While rule-based models offer global and exact interpretability, learning rule sets that simultaneously achieve high predictive performance and low, human-understandable complexity remains challenging. To address this, we introduce TT-Sparse, a flexible neural building block that leverages differentiable truth tables as nodes to learn sparse, effective connections. A key contribution of our approach is a new soft TopK operator with straight-through estimation for learning […]

Ver mais

arXiv:2602.07593v1 Announce Type: cross Abstract: Modern benchmarks such as HELM MMLU account for multiple metrics like accuracy, robustness and efficiency. When trying to turn these metrics into a single ranking, natural aggregation procedures can become incoherent or unstable to changes in the model set. We formalize this aggregation as a social choice problem where each metric induces a preference ranking over models on each dataset, and a benchmark operator aggregates these votes across metrics. While prior work has […]

Ver mais

arXiv:2602.04774v1 Announce Type: cross Abstract: Setting the learning rate for a deep learning model is a critical part of successful training, yet choosing this hyperparameter is often done empirically with trial and error. In this work, we explore a solvable model of optimal learning rate schedules for a powerlaw random feature model trained with stochastic gradient descent (SGD). We consider the optimal schedule $eta_T^star(t)$ where $t$ is the current iterate and $T$ is the total training horizon. This […]

Ver mais

arXiv:2510.19672v3 Announce Type: replace-cross Abstract: Policy learning algorithms are widely used in areas such as personalized medicine and advertising to develop individualized treatment regimes. However, most methods force a decision even when predictions are uncertain, which is risky in high-stakes settings. We study policy learning with abstention, where a policy may defer to a safe default or an expert. When a policy abstains, it receives a small additive reward on top of the value of a random guess. […]

Ver mais

In the world of security and DevOps, AI agents are being pushed from demos into production quickly. They triage security alerts, coordinate incident response, provision infrastructure, and decide which remediation playbooks to run. When it all works, everyone is happy. It’s a force multiplier. But when an AI agent fails … who do you blame? It can be hard to tell who made the call, why it happened, or what evidence exists to explain it. This is even […]

Ver mais

Back in my student years, I had a book by a rather famous Dane about a rather famous programming language. And although I harbored genuine warm feelings for C++, I couldn’t get through even half of that book—the reading was that dreary. Well, it didn’t stop me from continuing to believe in the destiny fate had in store for me and C++. So, in the summer of 2011, I went to interview for a C++ developer. This is […]

Ver mais

arXiv:2603.23633v1 Announce Type: new Abstract: Large language models can generate runnable software artifacts, but their security remains difficult to evaluate end to end. This study examines that problem through a Detect–Repair–Verify (DRV) workflow, in which vulnerabilities are detected, repaired, and then rechecked with security and functional tests. It addresses four gaps in current evidence: the lack of test-grounded benchmarks for LLM-generated artifacts, limited evidence on pipeline-level effectiveness, unclear reliability of detection reports as repair guidance, and uncertain repair […]

Ver mais

Most enterprise data still sits inside PDFs, scans, and slide decks. Large language models and agents cannot use that data until it becomes structured JSON. Open-source document extraction has become the standard way to do that conversion on your own hardware. Two different problems hide under the phrase ‘PDF to JSON.’ The first is schema-driven extraction: you define fields, and a model fills them with values. The second is document parsing: a model reconstructs the page into structured […]

Ver mais