ETH Zürich Research Collection2027 · Image data
Functional benchmarking across ten chondrogenic cell sources reveals cartilage regeneration ranging from fibrocartilaginous to near-native tissueZivaHub2027 · dataset · restricted
Information Filter-based Diffusion Transformer for medical image super-resolutionMedical image super-resolution (SR) aims to recover fine anatomical details from low-resolution (LR) scans, yet obtaining high-resolution images is often challenging due to clinical limitations, such as acquisition time and radiation exposure. To address the limitation of conventional diffusion models with uniform noise perturbation in preserving sparse but clinically important structures, we prop
ZivaHub2027 · dataset · restricted
Retrieval-Augmented Decoding for Improving Truthfulness in Open-Ended GenerationEnsuring truthfulness in large language models (LLMs) remains a critical challenge for reliable text generation. While supervised fine-tuning and reinforcement learning with human feedback have shown promise, they require a substantial amount of annotated data and computational resources, limiting scalability. In contrast, decoding-time interventions offer lightweight alternatives without model re
ETH Zürich Research Collection2026 · Table · CSV
Code for publication GREAT: Grassmannian REcursive Algorithm for Tracking & Online System IdentificationETH Zürich Research Collection2026 · Crystal structure
Supplemental Material: Treatment of human oocytes with extracellular vesicles from follicular fluid during rescue in vitro maturation enhances maturation rates and modulates oocyte proteome and ultrastructureNCL Data2026 · dataset
Code, split files, out-of-fold predictions and latency measurements for "Coil leakage, training variance and FLOP proxies in the evaluation of real-time steel surface defect detectors"<p dir="ltr">Supplementary material for the article "Coil leakage, training variance and FLOP proxies in the evaluation of real-time steel surface defect detectors" (submitted to the Journal of Real-Time Image Processing).</p><p dir="ltr">The study re-evaluates real-time steel surface defect detectors on NEU-DET and GC10-DET with five-fold cross-validation, coil-disjoint folds for GC10-DET, repeat
NCL Data2026 · Astronomical catalogue
<p>MAE (mean and scan-level standard deviation) and Pearson correlation in the secondary retrospective set for the AI-CE and OCT-CET models.</p><p>MAE (mean and scan-level standard deviation) and Pearson correlation in the secondary retrospective set for the AI-CE and OCT-CET models.</p>
NCL Data2026 · Astronomical catalogue
<p>Result metrics (MAE and Pearson r value) across all, and across the individual normal and three LSCD severity classes (Stage 1, Stage 2, and Stage 3) for the AI-CE, MSU-Net, and OCT-CET models tested on the original dataset.</p><p>Result metrics (MAE and Pearson r value) across all, and across the individual normal and three LSCD severity classes (Stage 1, Stage 2, and Stage 3) for the AI-CE, MSU-Net, and OCT-CET models tested on the original dataset.</p>
NCL Data2026 · dataset
<p>Eukaryotic chromosome classification metrics across five class-composition settings.</p><p>Eukaryotic chromosome classification metrics across five class-composition settings.</p>
NCL Data2026 · Astronomical catalogue
<p>Stability of EffAtt-LungNet over five random seeds and test-set bootstrap (1,000 resamples). Values are mean standard deviation; brackets give 95% CI.</p><p>Stability of EffAtt-LungNet over five random seeds and test-set bootstrap (1,000 resamples). Values are mean standard deviation; brackets give 95% CI.</p>
NCL Data2026 · dataset
De-identified Survey and Contextual Inquiry Data for Video-Based Software Learning Practices, Device Ecologies, and Usability Barriers<p dir="ltr">This Figshare item contains de-identified data and derived analysis materials supporting the manuscript “Understanding Practices, Device Ecologies, and Challenges in Video-Based Software Learning: An Empirical Study and Design Opportunities.”</p><p dir="ltr">The item includes three Excel workbooks:</p><ol><li><code>study1_survey_device_setup_paired_data.xlsx</code> contains de-identif
NCL Data2026 · dataset
<p>Key literature on polyurethane biomaterials, hemocompatibility assessment, and artificial intelligence-driven image analysis.</p><p>Key literature on polyurethane biomaterials, hemocompatibility assessment, and artificial intelligence-driven image analysis.</p>
NCL Data2026 · dataset
robustness_check from Evolutionary dynamics of a four-stakeholder ecosystem for misinformation governance on short-video platformsrobustness_check.m
NCL Data2026 · dataset
Data and code for "Equivalent Modulo the Ledger: Document-Grounded Accounting Identities for Verifying Financial Programs"<p dir="ltr">This item contains the code and derived data for the paper "Equivalent Modulo the Ledger: Document-Grounded Accounting Identities for Verifying Financial Programs" (submitted to Knowledge-Based Systems).</p><p dir="ltr">Contents:</p><p dir="ltr">(1) code/ – the identity miner, the three-outcome equivalence checker, labelling, verifier training and evaluation scripts;</p><p dir="ltr">(
NCL Data2026 · dataset
<p>Balanced accuracy of the best machine learning models. The model architecture and statistical feature test are listed.</p><p>Balanced accuracy of the best machine learning models. The model architecture and statistical feature test are listed.</p>
NCL Data2026 · dataset
Project Analysis Dataset.<p dir="ltr">These thesis focused on usability evaluation of mobile banking applications using the SNECAS model, focusing on how users interact with and experience mobile banking applications. The study examines factors that influence ease of use, navigation, accessibility, and overall effectiveness of mobile banking applications</p>
NCL Data2026 · Astronomical catalogue
<p>Offline label-preserving augmentation used to expand each lung class from 5,000 to 8,500 images. Operations were applied to the released 768768 LC25000 images before the train/validation/test split.</p><p>Offline label-preserving augmentation used to expand each lung class from 5,000 to 8,500 images. Operations were applied to the released 768768 LC25000 images before the train/validation/test split.</p>
NCL Data2026 · dataset
LASSBio-classFLOW: A Semiautomated KNIME Workflow for Classification Model Benchmarking and Virtual ScreeningMachine learning-based quantitative structure–activity relationship (ML-QSAR) modeling requires consistent data preparation, validation, and model comparison. We present LASSBio-classFLOW, an open, modular, and semiautomated KNIME workflow for classification-based ligand screening. It integrates basic molecular structure preparation, configurable class assignment, descriptors and fingerprints calc
NCL Data2026 · dataset
<p>Raw model performance results across feature selection methods and population groups.</p><p>This table contains the complete set of unfiltered machine-learning model outputs, including balanced accuracy (BA), average precision (AP), false positive rate (FPR), and false negative rate (FNR). Results are reported across multiple feature selection techniques, model types, random seeds, and population strata.</p> <p>(CSV)</p>
NCL Data2026 · dataset
In-Ride Alcohol-Impairment Detection in E-Scooterists with False-Alarm Control<p dir="ltr">Code and data to reproduce the results from "In-Ride Alcohol-Impairment Detection in E-Scooterists with False-Alarm Control"</p>
NCL Data2026 · dataset
Environmental Monitoring of Broiler Chickens During Summer and Winter<p dir="ltr">The workbook records environmental sensor measurements together with flock age and the lighting schedule. It is suitable for comparing environmental conditions between summer and winter and for examining how conditions vary by flock age and time of day.<br></p><p dir="ltr">The dataset describes the environmental conditions experienced by broiler chickens during two seasons. Each recor
NCL Data2026 · dataset
<p>External validation performance across bacterial dominance boundaries.</p><p>This table reports balanced accuracy (BA) from validation analyses comparing pairwise bacterial dominance boundaries (e.g., non-Lactobacillus taxa versus Lactobacillus species and combined Lactobacillus groups). Results are presented for the total sample and stratified population groups, providing an external assessment of model generalizability across taxonomic contrasts and demographic strata
NCL Data2026 · dataset
<p>Sample-level CamFi metrics on the CAMI II marine dataset.</p><p>Sample-level CamFi metrics on the CAMI II marine dataset.</p>
NCL Data2026 · dataset
Table 1_Applications of artificial intelligence in traditional Chinese medicine tongue diagnosis: a bibliometric review of research trends and hotspots, 2015–2026.docxObjectives<p>This study aimed to characterize the development landscape of artificial intelligence (AI)-assisted tongue diagnosis in Traditional Chinese Medicine (TCM) by comparing publication trends, collaboration patterns, research hotspots, and emerging topics between CNKI-indexed and WoSCC-indexed literature.</p>Methods<p>Literature published between January 2015 and August 2026 was retrieved
NCL Data2026 · dataset
Table 1_Development and internal validation of machine learning models for identifying suicidal behavior in inpatients with mood disorders.docxBackground<p>Suicidal behavior (SB) is a major concern in mood disorders. Models developed from retrospective records are vulnerable to ambiguous targets, data leakage, and inappropriate handling of class imbalance. We developed and internally validated a model to identify the risk of suicidal behavior in patients with mood disorders upon admission.</p>Methods<p>The dataset included 1, 099 inpatie