The paper introduces the InterModel Vigorish (IMV), a metric that quantifies differences in probabilistic fit as an expected betting advantage over a reference model. It presents three applications—SHAP-IMV for feature attribution, Multi-IMV for class discrimination, and Ablate-IMV for assessing architectural components—tested across diverse data types and multiple random seeds. The authors provide an open-source library (imvpy) and notebooks to replicate and extend their work.
arXiv:2605. 23595v2 Announce Type: replace-cross Abstract: The rapid advancement of machine learning has led to an unprecedented expansion of model ecosystems, making it increasingly difficult to assess the reliability of newly released models on unseen and unlabeled data.
The paper evaluates deep learning models for electrocardiogram‑based emotion recognition, focusing on generalization across datasets rather than dataset‑specific performance. It introduces two open‑source tools—ARRC for standardized benchmarking and ARDT for inter‑dataset training—to merge three public AER datasets (CUADS, ASCERTAIN, DREAMER) into a more variable benchmark. Using these tools, the authors compare three prominent deep learning architectures and two CNN baselines with hyperparameter tuning and 10‑fold cross‑validation, revealing trade‑offs between accuracy and model complexity and providing a reproducible benchmark for future research.
arXiv:2512. 22240v5 Announce Type: replace-cross Abstract: Machine learning models are primarily judged by predictive performance, especially in applied genomics, where explanations are read as biological findings.
TabICLv2 is a new state‑of‑the‑art tabular foundation model that outperforms existing methods on regression and classification tasks. It relies on a synthetic data generation engine for diverse pretraining, architectural innovations such as a scalable softmax attention, and optimized training protocols that replace AdamW with the Muon optimizer. On the TabArena and TALENT benchmarks, TabICLv2 surpasses the current best model, RealTabPFN‑2.5, without any tuning, while also being faster and capable of handling million‑scale datasets with limited GPU memory.
arXiv:2606. 02384v1 Announce Type: new Abstract: Progress in tabular machine learning has largely focused on increasingly sophisticated model architectures.
arXiv:2607. 01548v1 Announce Type: cross Abstract: Large language models are increasingly used as open-ended search operators in evolutionary optimization.
arXiv:2609.39673v1 Announce Type: new Abstract: Can a pretrained graph model replace training and tuning a separate predictor for each dataset? Answering this requires evaluating prediction quality a...
arXiv:2608. 11508v1 Announce Type: new Abstract: Machine learning pipelines commonly flatten relational data into single-table representations, discarding structural constraints.
arXiv:2605. 30188v2 Announce Type: replace-cross Abstract: Reliable probability estimates are critical in many machine learning applications, yet modern classifiers are often poorly calibrated.
arXiv:2606. 15314v1 Announce Type: cross Abstract: Industrial retrofit planning depends on structured operational data rather than free text: planners must estimate whether a newly registered prototype will require a retrofit, which retrofit package it will need, and how long the work will take.
arXiv:2509. 25289v4 Announce Type: replace-cross Abstract: Identifying an effective clustering algorithm for a given dataset remains a fundamental unsupervised learning issue.
arXiv:2606. 30410v1 Announce Type: cross Abstract: Foundation models for predictive machine learning on tabular data have recently gained significant traction in academia and industry.