Claims Browser

The SWIFTe-LDE4 ensemble achieved the best calibration after temperature scaling but still exhibited residual miscalibration with an expected calibration error of 0.217

"SWIFTe-LDE4 achieved the lowest calibration errors among the four configurations after temperature scaling (expected calibration error, 0.217; Brier score, 0.222), although the absolute expected calibration error indicates residual miscalibration"

The efficiency-calibration patterns observed are robust across different pretrained initializations but do not demonstrate external clinical generalizability

"Similar efficiency-calibration patterns were observed using the public VoCo checkpoint, supporting robustness across pretrained initializations rather than external clinical generalizability"

Active diffusion-based methods can discover correct parameter regions even when initial training bounds exclude true parameters by iteratively detecting and correcting model misspecification through posterior uncertainty

"By iteratively detecting and correcting model misspecification through posterior uncertainty, the method discovers and learns the correct region of parameter space, even when initial training bounds exclude the true parameters."

The proposed diffusion-based inverse solver is effective for quantum chromodynamics analysis of nucleon structure, specifically parameterizing quantum correlation functions to event observables

"We demonstrate the effectiveness of our inverse solver for a toy inverse problem with infinite solutions, and for the parameterization of the quantum correlation functions to event observables in a Quantum Chromodynamics analysis of nucleon structure."

Reliable medical conversational AI requires authentic expert-patient interaction data, but such datasets are scarce for low-resource languages like Bengali

"Reliable medical conversational AI requires authentic expert--patient interaction data, yet such datasets remain scarce, especially for low-resource languages such as Bengali."

DocTalkBN preserves spontaneity, contextual richness, and spoken characteristics of authentic medical interactions unlike prior resources from forums, written content, or synthetic data

"Unlike prior resources derived from medical forums, written health content, or synthetic data, our dataset preserves the spontaneity, contextual richness, and spoken characteristics of authentic medical interactions in a low-resource setting."

DocTalkBN is a practically useful resource, particularly for clinically grounded reasoning tasks

"Our results show that DocTalkBN is a practically useful resource, particularly for clinically grounded reasoning tasks."

The DocTalkBN dataset will facilitate future research on reliable medical NLP and safer, more culturally grounded healthcare systems for low-resource languages

"We release this resource to facilitate future research on reliable medical NLP and safer, more culturally grounded healthcare systems for low-resource languages."

Monolingual language models trained on non-parallel data learn alignable representations without joint training

"monolingual models trained on non-parallel data learn alignable representations without joint training"

Monolingual models develop alignable representational geometry that strengthens with increased data scale, model scale, or linguistic proximity

"these models develop alignable representational geometry across layers, with alignment strengthening as data scale, model scale, or linguistic proximity increases"

A single Procrustes rotation fitted on parallel sentences can map hidden states between independently trained monolingual models

"a single Procrustes rotation fit on parallel sentences maps hidden states between models"

Rotated cross-lingual representations transfer functional content, as demonstrated by patching rotated English residuals into German models flipping predictions to the donor's answer

"the same rotation transfers functional content; patching a rotated English residual into a German model on a factual cloze flips the prediction to the donor's capital in most cases"

Cross-lingual alignment emerges from the structure of language itself rather than requiring joint training

"cross-lingual alignment can emerge from the structure of language and the information it carries rather than from joint training"

This finding enables practical applications including model stitching, merging, and modular multilingual systems built from monolingual components

"this points to practical future directions including model stitching, merging, and modular multilingual systems built from monolingual components"

AI models can form aesthetic categorization of human-produced media without explicit labels or cross-modal supervision

"What remains under-explored is how AI models form their own aesthetic categorization of human-produced media without explicit labels or cross-modal supervision."

A self-supervised framework can project four modalities into a shared 256-dimensional embedding space and discover aesthetic structure through iterative clustering

"We present a self-supervised framework that projects four modalities (text, audio, image and video) into a shared 256-dimensional embedding space and applies iterative clustering to discover aesthetic structure."

There is divergence between AI-generated cluster assignments and human affective register labels

"We discuss the divergence between AI-generated cluster assignments and human affective register labels on a weakly supervised multimodal dataset."

This approach has applications in understanding AI cross-modal similarity, organizing media collections for RAG, and automated data labeling

"This work has applications in understanding how AI structures cross-modal similarity, organizing heterogeneous media collections for Retrieval-Augmented Generation (RAG), and automated data labeling."