Skip to main content
Powered by ShareScore

Find research datasets worth reusing

Search datasets from major research repositories and use ShareScore to quickly assess how well each record supports discovery, access, and reuse.

14

datasets available to search

ShareScore release 0.7.1

Reset

Dataset results

14 results for “Explainable AI”

Learn how ShareScore rates datasets ↗
zenodo44/100

Explainable AI for unveiling deep learning pollen classification model - Pollen dataset

<p>Dataset consists automatic particle detector Rapid-E measurements&nbsp;of&nbsp;pollen grains from 12 classes: Acer, Alnus, Alopecurus, Carex, Cupressus, Dactylis, Juglans,&nbsp;Morus,&nbsp;Platanus,&nbsp;Populus, Salix and Ulmus. Data are available i json format.</p> <p>Dataset also contains preprocessed data packed into csv files &nbsp;of 3 modalities: spectrum, lifetime, scattering and&nbsp;additional features from scattering and lifetime data are also available. These are ready to be used with machine learning models. Labels 0, 1, 2, ... 11&nbsp;correspond&nbsp;to alphabetical order of examined pollen classes Acer, Alnus, Alopecurus ...&nbsp;Ulmus.</p> <p>&nbsp;</p>

opencc-by-4.0Sep 2022View details →
zenodo44/100

Replication Package for the Paper Titled "Emerging Results in Using Explainable AI to Improve Software Vulnerability Prediction"

<p>This is a replication package for the paper titled "Emerging Results in Using Explainable AI to Improve Software Vulnerability Prediction".</p>

opencc-by-4.0Oct 2024View details →
zenodo44/100

Convergent approaches to AI Explainability for HEP muonic particles pattern recognition Dataset

<p>Dataset associated to the publication &quot;Convergent approaches to AI Explainability for HEP muonic particles pattern recognition&quot;,&nbsp;Leandro Maglianella, Lorenzo Nicoletti, Stefano Giagu*, Christian Napoli,&nbsp;and Simone Scardapane, submitted to&nbsp;Computing and Software for Big Science.</p> <p>*corresponding author:&nbsp;stefano.giagu [AT]&nbsp;uniroma1.it</p> <p>Description:</p> <p>provided as a compressed zip file. Contains 7 numpy .npy files:</p> <ul> <li>train_images_with_noise.npy: numpy array containing 850003 &quot;images&quot; of muonic tracks with detector noise (shape&nbsp;(850003, 9, 384)). Each image contains 1 muonic track.</li> <li>train_images_without_noise.npy: numpy array containing 850003 &quot;images&quot; of muonic tracks w/o detector noise (shape&nbsp;(850003, 9, 384)).&nbsp;Each image contains 1 muonic track.</li> <li>train_labels.npy: labels associated to each image (shape&nbsp;(850003, 5)), corresponding to&nbsp;&nbsp;(pT, eta, phi, 0, nhits) of the muonic track, with pT: transverse momentum, eta: pseudo-rapidity,&nbsp;&nbsp;phi: azimuthal angle, and&nbsp;nhits:&nbsp;the number of pixels turned on by the muon</li> <li>test_images_with_noise.npy: same as above for a&nbsp;94445 images test set</li> <li>test_images_without_noise.npy:&nbsp;same as above for a&nbsp;94445 images test set</li> <li>test_labels.npy:&nbsp;same as above for a&nbsp;94445 images test set</li> <li>images_only_noise.npy:&nbsp;numpy array containing 944448 &quot;images&quot; w/o muons, containing&nbsp;detector noise only (shape&nbsp;(944448, 9, 384))</li> </ul>

opencc-by-4.0Dec 2022View details →
zenodo36/100

Explainable AI for Retinoblastoma Diagnosis: Interpreting Deep Learning Models with LIME and SHAP

<p>Retinoblastoma is a rare and aggressive form of childhood eye cancer that requires prompt diagnosis and treatment to prevent vision loss and even death. Deep learning models have shown promising results in detecting retinoblastoma from fundus images, but their decision-making process is often considered a &quot;black box&quot; that lacks transparency and interpretability. In this project, we explore the use of LIME and SHAP, two popular explainable AI techniques, to generate local and global explanations for a deep learning model based on InceptionV3 architecture trained on retinoblastoma and non-retinoblastoma fundus images. We collected and labeled a dataset of 400 retinoblastoma and 400 non-retinoblastoma images, split it into training, validation, and test sets, and trained the model using transfer learning from the pre-trained InceptionV3 model. We then applied LIME and SHAP to generate explanations for the model&#39;s predictions on the validation and test sets. Our results demonstrate that LIME and SHAP can effectively identify the regions and features in the input images that contribute the most to the model&#39;s predictions, providing valuable insights into the decision-making process of the deep learning model. In addition, the use of InceptionV3 architecture with spatial attention mechanism achieved high accuracy of 97\% on the test set, indicating the potential of combining deep learning and explainable AI for improving retinoblastoma diagnosis and treatment.</p>

opencc-by-4.0May 2023View details →
dryad36/100

PestReKNet-X: Integrating Explainable AI to enhance pest disease detection and combat crop senescence

Open the record for dataset details and reuse information.

publicOct 2025View details →
zenodo32/100

Exploring the Black Box: Analyzing Explainable AI Challenges and Best Practices Through Stack Exchange Discussions

Open the record for dataset details and reuse information.

opencc-by-4.0Apr 2024View details →
zenodo32/100

Automated rationale generation: a technique for explainable AI and its effects on human perceptions (Dataset)

<p>Explainable AI Dataset for paper published in the proceedings of IUI 2019 titled, &quot;<strong>Automated rationale generation: a technique for explainable AI and its effects on human perceptions</strong>&quot;. Consists of data collected from human participants via Mechanical Turk.<br> <strong>Abstract</strong>:<br> <em>Automated rationale generation</em> is an approach for real-time explanation generation whereby a computational model learns to translate an autonomous agent&#39;s internal state and action data representations into natural language. Training on human explanation data can enable agents to learn to generate human-like explanations for their behavior. In this paper, using the context of an agent that plays <em>Frogger</em>, we describe (a) how to collect a corpus of explanations, (b) how to train a neural rationale generator to produce different styles of rationales, and (c) how people perceive these rationales. We conducted two user studies. The first study establishes the plausibility of each type of generated rationale and situates their user perceptions along the dimensions of <em>confidence, humanlike-ness, adequate justification, and understandability.</em> The second study further explores user preferences between the generated rationales with regard to <em>confidence</em> in the autonomous agent, communicating <em>failure and unexpected behavior.</em> Overall, we find alignment between the intended differences in features of the generated rationales and the perceived differences by users. Moreover, context permitting, participants preferred detailed rationales to form a stable mental model of the agent&#39;s behavior.</p>

opencc-by-4.0Mar 2019View details →
zenodo32/100

Supplementary data: "Revealing drivers and risks for power grid frequency stability with explainable AI"

<p>This repository contains processed data and result files for the paper <a href="https://arxiv.org/abs/2106.04341">Revealing drivers and risks for power grid frequency stability with explainable AI</a>.&nbsp; The code for producing the processed data and the results is <a href="https://github.com/johkruse/XAI-for-grid-frequency-stability">available at github</a>.</p> <p><strong>Data</strong></p> <p>For each area, the data folder contains the feature and target data used to train the ML model.</p> <ul> <li><em>raw_input_data.h5</em><strong> </strong>:<strong> </strong>The aggregated external features without additional engineered features.</li> <li><em>input_forecast.h5 </em>and<em> input_actual.h5: </em>The day-ahead available (forecast) and ex-post available (actual) data of external features including the engineered features.</li> <li><em>outputs.h5 </em>:&nbsp; The grid frequency stability indicators.</li> <li><em>version_2021-07-01</em>: Folder containing the training and test sets used for the results.</li> <li><em>documentation_of_data_download</em><strong>: </strong>Plots and information files concerning the ENTSO-E raw data and its aggregation.</li> </ul> <p><strong>Data sources</strong></p> <p>The data for input features (<em>raw_input_data.h5, input_forecast.h5 </em>and<em> input_actual.h5</em>) is derived from ENTSO-E Transparency Platform data [1]. The target data (<em>outputs.h5</em>) is based on power grid frequency recordings from the German Transmission System Operator TransnetBW [2].</p> <p><strong>Results</strong></p> <p>For each area and each target, the result folder comprises the results of hyper-parameter optimization, model prediction and interpretation via SHAP. The results refer to the full model and the restricted model (containing only day-ahead features).</p> <ul> <li><em>cv_results_gtb_full.csv</em> and <em>cv_results_gtb_day_ahead.csv</em> : Performance results for each combination in the hyper-parameter grid search.</li> <li><em>cv_best_params_gtb_full.csv</em> and <em>cv_best_params_gtb_day_ahead.csv</em> : Hyper-parameters used in the final (optimized) model.</li> <li><em>shap_values_gtb_full.npy</em> and <em>shap_interaction_values_gtb_full.npy </em>: First-order SHAP values and second-order SHAP interaction values for the full model.</li> <li><em>y_pred.h5</em> : Predictions of daily profile predictor, full model and day-ahead model.</li> </ul> <p><strong>Disclaimer</strong></p> <p>The data might be subject to copyright or related rights. Please consult the primary data owner.</p>

opennotspecifiedJul 2021View details →
zenodo32/100

Supplementary data: "Secondary control activation analysed and predicted with explainable AI"

<p>This repository contains processed data and result files for the paper&nbsp;&nbsp;<a href="https://arxiv.org/abs/2109.04802">Secondary control activation analysed and predicted with explainable AI</a> . &nbsp; The code for producing the processed data and the results is <a href="https://github.com/johkruse/XAI-for-aFRR-activation">available at github</a>.</p> <p><strong>Data</strong></p> <p>The data folder contains the feature and target data used to train the ML model. The data for Germany comprises the following folders and files:</p> <ul> <li><em>raw_input_data.h5</em><strong> </strong>:<strong> </strong>The aggregated external features without additional engineered features.</li> <li><em>inputs_&lt;model_type&gt;.h5 </em><em>:</em> The input features for the different model types used in the paper including the engineered features. Depending on the model type, the input files also contain the IGCC features.</li> <li><em>outputs.h5 </em>:&nbsp; The activated aFRR volumes in Germany.</li> <li><em>version_2021-08-20</em>: Folder containing the training and test sets used for the results.</li> <li><em>documentation_of_data_download</em>: Information files concerning the ENTSO-E raw data and its aggregation.</li> </ul> <p>In addition to the German time series, the data folder contains the raw input data for the remaining IGCC states. Note that the results contain more model types as actually discussed in the paper.</p> <p><strong>Data sources</strong></p> <p>The data for input features (<em>raw_input_data.h5</em> and <em>input_&lt;model_type&gt;.h5</em>) is derived from ENTSO-E Transparency Platform data [1]. The target data (<em>outputs.h5</em>) is based on publicly available data from the German Transmission System Operators (TSOs) [2].</p> <p><strong>Results</strong></p> <p>The result folder comprises the results of hyper-parameter optimization, model prediction and interpretation via SHAP. The model type, the loss function to train the model and the data set for prediction/interpretation were varied.</p> <ul> <li><em>cv_results_&lt;model_type&gt;_&lt;loss_function&gt;.csv</em> : Performance results for each combination in the hyper-parameter grid search.</li> <li><em>cv_best_params_&lt;model_type&gt;_&lt;loss_function&gt;.csv</em> : Hyper-parameters used in the final (optimized) model.</li> <li><em>shap_values_&lt;data_set&gt;_&lt;model_type&gt;_&lt;loss_function&gt;.npy</em> : First-order SHAP values calculated on different data sets: The train set, the randomized test set and the continuous test set.</li> <li><em>y_pred_&lt;data_set&gt;.h5</em> : Predictions of daily profile predictor and Machine Learning models.</li> </ul> <p><strong>Disclaimer</strong></p> <p>The data might be subject to copyright or related rights. Please consult the primary data owner.</p>

opennotspecifiedSep 2021View details →
zenodo32/100

Understanding Explainability during System Design for Safety Critical AI Systems

<p>Our research aims to explore the perspective of internal stakeholders on explainability</p>

opencc-by-4.0Jun 2023View details →
ClinicalTrials.gov28/100

Using Explainable AI Risk Predictions to Nudge Influenza Vaccine Uptake

ClinicalTrials.gov study NCT05009251. IPD Sharing: YES. Countries: 1. Publications: 0.

controlledIPD-YESFeb 2026View details →
zenodo24/100

Replication Package for the paper titled "On Using Explainable AI to Improve Deep Learning Models with Emerging Results in Vulnerability Prediction"

<p>This is a replication Package for the paper titled &quot;On Using Explainable AI to Improve Deep Learning Models with Emerging Results in Vulnerability Prediction&quot;.</p> <p>The directory contains Python scripts to run the vulnerability prediction models as well as the scripts to run the explainability tool.</p> <p>The directory also contains the datasets used in the paper.</p>

restrictedcc-by-4.0Sep 2023View details →
ClinicalTrials.gov24/100

Safe and Explainable AI

ClinicalTrials.gov study NCT06694181. IPD Sharing: NO. Countries: 0. Publications: 0.

closedIPD-NOFeb 2026View details →
zenodo20/100

Supplementary data: "Revealing interactions between HVDC cross-area flows and frequency stability with explainable AI"

<p>This repository contains processed data and result files for the paper <a href="https://arxiv.org/abs/2204.10727">Revealing interactions between HVDC cross-area flows and frequency stability with explainable AI</a>.&nbsp;The code for producing the processed data and the results is&nbsp;<a href="https://github.com/sebastianptz/XAI-for-HVDC">available at github</a>.</p> <p><strong>Data</strong></p> <p>The data folder contains the feature and target data used to train the ML model:</p> <ul> <li>stability_input: A Folder containing training and test sets for the stability model for each area.</li> <li>flow_input: A Folder containing training and test sets for the flow model for each&nbsp;link.</li> <li><em>raw_input_data.h5</em><strong>&nbsp;</strong>:<strong>&nbsp;</strong>The aggregated external features without additional engineered features.</li> <li><em>input_forecast.h5&nbsp;</em>and<em>&nbsp;input_actual.h5:&nbsp;</em>The day-ahead available (forecast) and ex-post available (actual) data of external features including the engineered features.</li> <li><em>indicators.h5&nbsp;</em>:&nbsp; The grid frequency stability indicators.</li> <li><em>documentation_of_data_download</em>: Information files concerning the ENTSO-E raw data and its aggregation.</li> <li>HVDClinks: A Folder containing preprocessed time series for scheduled and unscheduled HVDC flows</li> </ul> <p><strong>Data sources</strong></p> <p>Most of the&nbsp;data is derived from ENTSO-E Transparency Platform data [1]. The grid stability indicators&nbsp;(indicators<em>.h5</em>) are&nbsp;based on publicly available data from the German Transmission System Operators (TSOs) [2].</p> <p><strong>Results</strong></p> <p>The stability_results and the flow_results folder contain&nbsp;the results of hyperparameter optimization, model prediction and interpretation via SHAP for the respective models.</p> <ul> <li><em>cv_results_gtb_full.csv</em>&nbsp;: Performance results for each combination in the hyperparameter optimization.</li> <li><em>cv_best_params_gtb_full.csv</em>&nbsp;: Hyperparameters used in the final (optimized) model.</li> <li><em>shap_values_gtb_full.npy</em>&nbsp;: First-order SHAP values calculated on different data sets: The train set, the randomized test set and the continuous test set.</li> <li><em>y_pred.h5/y_pred_links.h5</em>&nbsp;: Predictions of daily profile predictor and Machine Learning models.</li> </ul> <p><strong>Disclaimer</strong></p> <p>The data might be subject to copyright or related rights. Please consult the primary data owner.</p> <p>&nbsp;</p> <p>&nbsp;</p> <div>&nbsp;</div>

opennotspecifiedJun 2022View details →

ScienceDex guides

Understand access before you commit

These curated guides explain access requirements, typical timelines, costs, and reuse considerations for widely used research datasets.

Compare curated datasets

Allen Brain Atlas

Allen Brain Atlas is an Allen Institute collection of brain map atlases, datasets, APIs, and analysis tools covering mouse, human, and non-human primate brain resources.

allen-brain-atlas
neuroscienceopenDocumentation, web resources, and API references are available online.
Last verified 2026-04-30Open record

Annotated Behaviour and Observability Dataset (ABODe)

ABODe is a University of Edinburgh DataShare dataset for behavior classification in group-housed mice using home-cage video, identities, bounding boxes, ground-plate positions, and annotator labels.

abode-home-cage
behavioral-neuroscienceopenThe DataShare record exposes download links for annotations, documentation, license text, and the zipped per-snippet data directory.
Last verified 2026-04-30Open record

DANDI Archive for NWB datasets

DANDI is a BRAIN Initiative archive for publishing and sharing neurophysiology data, including electrophysiology, optophysiology, and behavioral data packaged as NWB and related standards.

dandi-nwb
electrophysiologyopenPublished Dandiset metadata and archive endpoints are available through the production DANDI API.
Last verified 2026-04-30Open record

International Brain Laboratory public data

The International Brain Laboratory public data releases expose standardized mouse decision-making experiments, including Neuropixels recordings, widefield calcium imaging, behavior, and session metadata accessed through the ONE API.

ibl
behavioral-neuroscienceopenPublic sessions can be searched and loaded from the IBL public data server through ONE.
Last verified 2026-04-29Open record

OpenNeuro

OpenNeuro is a free, open platform for sharing neuroimaging datasets, with public search, dataset pages, and download paths for web, S3, DataLad, and the OpenNeuro CLI.

openneuro
neuroscienceopenPublished datasets are available on demand over the internet.
Last verified 2026-04-29Open record