Loading...
Loading...
Social network graphs, knowledge graphs, citation networks, molecular graphs for GNN, web link graphs
322 datasets
Wikitolica Knowledge Graph provides structured access to over 3000 nodes of information on Catholicism from the Spanish-language Wikitolica Catholic Encyclopedia. The dataset is a linked knowledge graph hosted externally in JSON-LD format, designed for semantic querying and exploration of theological concepts and church history. It serves as a machine-readable representation of encyclopedia articles and their relationships.
Supplementary material 5 for a research paper on predicting 31P Nuclear Magnetic Resonance signals using a light-weight Graph Neural Network. The dataset is a 1.6 MB CSV file published on figshare by Dimitri Domnjuk under a CC-BY-4.0 license and last updated on 2026-04-27. Its specific content and row count are not detailed in the provided metadata.
Ablation experiment results compare the performance of five PepLM-GNN model variants, including the complete model and four ablated versions. The dataset contains mean and standard deviation for ACC and AUC metrics calculated from five-fold cross-validation. It was created by Ke Yan and published on figshare in March 2026.
17244 benchmark samples underpin the p-values from statistical t-tests comparing the PepLM-GNN model to other baseline methods. The data reports whether PepLM-GNN's accuracy is statistically significantly higher, based on mean ACC values from five-fold cross-validation. Author Ke Yan published this table on figshare under a CC BY 4.0 license.
Supplementary material 6 for a research paper on predicting 31P Nuclear Magnetic Resonance signals using a light-weight Graph Neural Network. The 161.1 MB file, published on figshare by Dimitri Domnjuk under a CC-BY-4.0 license, was last updated on 2026-04-27. The specific content and structure of the data require verification after download.
Supplementary material 8 from a research article on predicting 31P Nuclear Magnetic Resonance signals using a light-weight Graph Neural Network. The dataset is published on figshare under a CC-BY-4.0 license by author Dimitri Domnjuk and was last updated on 2026-04-27. The specific content and structure of this supplementary file are not detailed in the available metadata.
Supplementary material 3 for a research paper on a light-weight Graph Neural Network for predicting 31P Nuclear Magnetic Resonance signals. The dataset is published on figshare by author Dimitri Domnjuk under a CC-BY-4.0 license and was last updated on 2026-04-27. The file is 1.6 MB in size and is provided in an IPYNB (Jupyter Notebook) format.
A 3.6 MB supplementary file published on figshare by Dimitri Domnjuk on 2026-04-27. The file is an IPYNB notebook likely containing code, data, or analysis supporting a research paper on predicting 31P Nuclear Magnetic Resonance signals using a light-weight Graph Neural Network. The specific data content and structure require verification after download.
Supplementary material 1 for a research paper on a light-weight Graph Neural Network. The 57.4 MB file, published on figshare by Dimitri Domnjuk, contains a model file for predicting 31P Nuclear Magnetic Resonance signals. It was last updated on 2026-04-27.
Supplementary material 2 for a research paper on predicting 31P Nuclear Magnetic Resonance signals using a light-weight Graph Neural Network. The dataset, published on figshare by Dimitri Domnjuk under a CC-BY-4.0 license, is a 258.4 KB IPYNB file. Its last update was recorded on 2026-04-27.
Version 1.2 science-quality wind speed data from the CYGNSS satellite constellation, produced by NOAA/NESDIS. The dataset provides daily netCDF-4 files containing time-tagged and geolocated average wind speeds in 25x25 kilometer grid cells, with a latency of approximately 6 days from the last measurement. It includes updates for high wind speed performance, revised quality flags, and a wind speed retrieval error variable.
Posts scraped from Moltbook's public API, which requires no authentication. The dataset likely contains discussions from an AI agent social network, featuring fields such as title, content, author, and engagement metrics. It was uploaded by caginb and last updated on May 7, 2026.
A 5.5 KB Excel file comparing a proposed hybrid method against Singular Value Decomposition (SVD) and Graph Neural Network (GNN) benchmarks. The dataset was authored by T. Keerthika and last updated on April 13, 2026. It is licensed under CC-BY-4.0 and hosted on figshare.
Real robot disassembly episodes include per-frame constraint graphs, SAM2 segmentation masks, 256D feature embeddings, and full 3D depth information. The dataset was created by Chang Liu of Texas A&M University for a CoRL 2026 project on GNN world models for constraint-aware video generation. It was last updated on Hugging Face on April 11, 2026.
A small dataset contains CODMAC Level 6 products linked to the Rosetta Orbiter's ALICE UV Spectrometer. It collects supplementary documentation and data of interest to users of the Rosetta Alice data products from the comet phase around comet 67P/Churyumov-Gerasimenko, which took place between 2014-01-21 and 2016-09-30. The dataset was provided by the National Aeronautics and Space Administration and last updated in March 2026.
1.7 GB of pre-trained ALIGNN models for predicting properties from the JARVIS-DFT materials database. The models were created by Kamal Choudhary and updated in March 2026. This resource is shared under a CC BY 4.0 license.
22 pediatric patient records form the basis for evaluating agreement between HP-GNN model explanations and clinical judgment. The dataset, created by Masoud Amiri, was last updated in April 2026 and is shared under a CC-BY-4.0 license. It contains metrics assessing the alignment of a hypergraph neural network's reasoning with expert clinical assessments.
PepLM-GNN's statistical superiority is evaluated through t-test p-values against other peptide prediction methods. The data aggregates results from four independent test sets, using mean ACC values from five-fold cross-validation. A p-value below 0.05 indicates PepLM-GNN's significant performance advantage.
The Vessel Electronic Reporting System (VERS) database facilitates the collection of research data aboard federally permitted commercial fishing vessels. Data are collected via Fisheries Logbook Data Recording Software (FLDRS) to address research needs and satisfy federal Vessel Trip Reporting (VTR) requirements. The dataset is maintained by the National Oceanic and Atmospheric Administration (NOAA) and was last updated on March 14, 2026.
The Department of the Interior packaged processed datasets used to develop a resistance surface for coastal marten connectivity modeling. The collection includes data layers for roads, forested and non-forested land cover, rivers, waterbodies, bays, estuaries, and serpentine soils. Data are packaged in a geodatabase and ArcGIS Pro Map Package format, last updated on March 4, 2026.