Fixed result universe
The fixed core matches the Standard Overall leaderboard: 12 configurations across 7 backbones, each with complete 198 / 198 coverage.
Aggregate analysis
Capability Map
Explore a fixed full-coverage core through separate Evaluation Paradigm and Model Origin taxonomies, with backbone- and dataset-equal aggregation.
Fixed Overall capability core
The analysis uses the same complete method universe as the Standard Overall leaderboard: 12 configurations across 7 backbones, each evaluated on all 198 datasets.
Configuration scores are averaged within each backbone first. Backbones and datasets then receive equal weight, preventing classifier-rich backbones from receiving extra influence.
198
datasets
12
configurations
7
backbones
198 / 198
result coverage
Comparison taxonomy
Choose one independent analysis lens
Groups are mutually exclusive within each taxonomy. Evaluation Paradigm and Model Origin are calculated and ranked separately.
Property coverage
Choose a benchmark attribute
Every property has reviewed metadata for all 198 datasets; coverage remains visible for audit transparency.
Capability heatmap
Evaluation Paradigm × modality
198 of 198 datasets contribute to this property view. N is the dataset count in each condition.
| Taxonomy group | Univariate1 channel | Multivariate2 or more channels |
|---|---|---|
| Native time-series ICL1 backbone · 1 configuration | 81.2% N=128 | 73.8% N=70 |
| Frozen representation + classifier4 backbones · 9 configurations | 74.0% N=128 | 68.6% N=70 |
| Tabular ICL adaptation2 backbones · 2 configurations | 77.9% N=128 | 69.7% N=70 |
Aggregate evidence
Condition-level detail
Every row is a fixed-core aggregate; no dataset-level record is exposed or downloadable.
Hierarchical Accuracy
For each dataset, configuration accuracies are averaged within their shared backbone. Backbone scores are then averaged with equal backbone weight within each taxonomy group. The resulting group scores are averaged with equal dataset weight within the selected condition.
Best / Tied Best / Other
Best / Tied Best / Other counts whether a group is uniquely highest / tied for highest / below the highest within the active taxonomy on each dataset.
| Condition | Taxonomy group | Accuracy | Avg. Group Rank | Best / Tied / Other | Datasets | Backbones | Configurations |
|---|---|---|---|---|---|---|---|
| Univariate | Native time-series ICL | 81.2% | 1.50 | 69 / 2 / 57 | 128 | 1 | 1 |
| Univariate | Frozen representation + classifier | 74.0% | 2.66 | 5 / 0 / 123 | 128 | 4 | 9 |
| Univariate | Tabular ICL adaptation | 77.9% | 1.84 | 52 / 2 / 74 | 128 | 2 | 2 |
| Multivariate | Native time-series ICL | 73.8% | 1.49 | 42 / 1 / 27 | 70 | 1 | 1 |
| Multivariate | Frozen representation + classifier | 68.6% | 2.46 | 4 / 0 / 66 | 70 | 4 | 9 |
| Multivariate | Tabular ICL adaptation | 69.7% | 2.06 | 23 / 1 / 46 | 70 | 2 | 2 |
Reading guide
Methodology and privacy boundaries
Rank definition
Average Rank ranks the mutually exclusive groups within the active taxonomy on each dataset, using average ranks for exact ties.
Separate taxonomies
Evaluation Paradigm and Model Origin are separate taxonomies. Groups are mutually exclusive within each taxonomy and are never ranked across taxonomies.
Public data boundary
Only aggregate condition-level statistics are published. Dataset identities, source mappings, backbone names, and configuration names are excluded.