Loading...
Loading...
Social network graphs, knowledge graphs, citation networks, molecular graphs for GNN, web link graphs
426 datasets
A PDF document containing information about the 2026/2027 admission application form for Osun State College of Nursing in Osogbo, Nigeria. The document is published on figshare by iuiykili iuiui under a CC-BY-4.0 license and was last updated on May 11, 2026. The file size is 47.5 KB.
Ablation experimental results for the MNDGNN model on multiplex networks using a 5-fold cross-validation test. The dataset is a 5.5 KB Excel file containing the results of an ablation study, authored by Pingting Li and last updated in May 2026. It is shared under a CC-BY-4.0 license on the figshare platform.
A dataset comparing the predictive performance of the MNDGNN model against other baseline models on multiplex networks. The dataset is 5.5 KB in size and was authored by Pingting Li. It was last updated on May 14, 2026.
Zekun Zhou published a performance comparison of different knowledge graph embedding models on the CMKG dataset on figshare in May 2026. The dataset is a 5.5 KB Excel file containing evaluation results. It is shared under a CC-BY-4.0 license.
An anonymized topology-spatial graph dataset for HVAC systems in BIM-based operation and maintenance. It contains public local graph fragments extracted from real BIM HVAC models, preserving component categories, MEP system labels, local spatial attributes, and explicit connection edges. The dataset was created by pinhaohuang7 and was last updated on 2026-05-26.
A 187.3 MB dataset supporting a transferable framework for predicting potential energy surfaces in hierarchically structured chemical systems. Siqi Chen developed the FB-GNN-MBE model, which integrates fragment-based graph neural networks with many-body expansion theory, and the data was last updated in April 2026. It includes benchmarks for water, phenol, and mixture systems, demonstrating chemical accuracy for two-body and three-body energy predictions.
Contemplative Agent is a JSON-LD knowledge graph encoding the concept layer of an autonomous CLI agent built in Python. The dataset, authored by Shimo4228, was last updated on Hugging Face in May 2026. It represents the agent's architectural principles, including structural capability limitation, minimal dependency, cyclic knowledge maintenance, and memory dynamics with decay.
A code release for modeling street vitality using street-view imagery, scene graphs, and graph neural networks. The package is 809.0 MB in size and was last updated on 2026-05-10. It is released under an MIT license by an author named Li.
A heterogeneous graph of 14,053 HuggingFace model, dataset, paper, and codebase nodes. It contains 51,337 observed evaluation edges linking models to datasets with performance metrics, intended for benchmarking link prediction and attribute regression tasks. The dataset was created by user lwaekfjlk and was last updated on 2026-05-16.
17244 peptide samples underpin the statistical t-test results comparing a complete PepLM-GNN model against four ablation variants (A, B, C, D). The table reports p-values for accuracy (ACC) from five-fold cross-validation, indicating the significance of each removed module. Authored by Ke Yan, this data supports analysis of model component contributions in peptide-protein interaction prediction.
A JSON-LD federation index linking the five sibling research lines of the shimo4228 research program. The graph connects three agent-design lines and two cross-cutting lines with their ecosystem repositories. The dataset is a mirror of a graph.jsonld file from a GitHub repository, authored by Shimo4228 and last updated on 2026-05-18.
A JSON-LD knowledge graph encodes the concept layer of the Attention, Not Self research line. The dataset maps concepts between five Buddhist traditions (Theravāda, Sarvāstivāda, Yogācāra, Chan/Zen, Pure Land) and contemporary computational phenomenology frameworks. It was authored by Shimo4228 and last updated on Hugging Face in May 2026.
Edward Appau Nketiah published parameter value estimates for a space-time self-exciting point process model applied to crime data. The 5.5 KB dataset contains results from a study analyzing burglary patterns in Chicago, Illinois, United States. It was last updated in April 2026.
Parameter estimates support the application of space-time self-exciting point process models to crime data. The 5.5 KB Excel file contains results from a study analyzing burglary patterns in Chicago, Illinois. Edward Appau Nketiah authored the work, which was last updated in April 2026.
Parameter estimates model the strong clustering phenomenon in Chicago burglary data using a space-time self-exciting point process. The 5.5 KB Excel file contains results from a study applying a multi-dimensional Gaussian-type exponent approximation method. Edward Appau Nketiah authored this research, which was last updated in April 2026.
Parameter estimates for a space-time self-exciting point process model applied to crime data. The dataset contains results from a study analyzing burglary patterns in Chicago, Illinois, United States, authored by Edward Appau Nketiah and published in April 2026. The 5.5 KB size indicates a small, focused set of model outputs rather than raw event data.
Machine-readable entity data for Dr. Saeid Ghezelbaash and his aesthetic clinic in Kermanshah, Iran, published in 2026. The dataset includes service taxonomy, local business information, reputation context, and AI positioning guidance. It was created by author 'doctor-ghezelbaash' and last updated on May 13, 2026.
SALT-KG is a benchmark dataset for semantics-aware learning on enterprise tables, presented at the EurIPS'25 Table Representation Workshop. The dataset is hosted by SAP and was last updated in May 2026. It includes metadata for an Operational Business Knowledge Graph.
2,475 scientist log books from 2,367 surveys by UK research vessels, dating back to 1904, were retrieved and archived by CEFAS. The catalogue provides a continuous record of vessel activity, except for periods during the World Wars. All data are now catalogued and stored in secure modern archiving facilities under the custodianship of the CEFAS Library.
FWA Synthetic Graph v1 is a synthetic knowledge graph modeling federal grant and loan program entities with planted fraud typologies. It contains 925 planted fraud clusters and models operations including applicants, applications, payments, vendors, and agencies. The dataset was created by kvirtue and last updated on Hugging Face in May 2026.