Supercell 62: Model Predictions, Graph Statistics, and Evaluation Metrics

Yixiang Huang published this 320.7 KB XLSX file on figshare in May 2026. It contains detailed outputs for downstream evaluations of a supercell-based model, including a confusion matrix, ground-truth and predicted labels, cell-to-supercell assignments, and graph adjacency matrices.

Use Cases

• Calculate model performance metrics based on the provided confusion matrix.
• Analyze graph structure and node centrality for Supercell 62 based on the adjacency matrix and degree centrality.
• Evaluate label pruning strategies based on the provided per-cell ground-truth and predicted labels.
• Study cell aggregation patterns based on the cell-to-supercell assignments and supercell counts.

Strengths

• File size is precisely 320.7 KB, indicating a manageable download.
• License is clearly defined as CC-BY-4.0, permitting broad reuse.
• Data includes multiple evaluation components (confusion matrix, labels, assignments, graph stats) in a single file.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Description metadata is limited; actual data quality requires manual inspection after download.

Provenance

Source

figshare

Collection Method

Likely generated as output from a machine learning model evaluation pipeline.

Time Range

null

Freshness

Last updated 2026-05-06 17:42:49; freshness should be verified.

Geography

null