Public Package API

LabelConfig	Complete label definition for one benchmarking run.
AnnotationMode	Supported annotation semantics for array-based benchmarking.
BenchmarkScope	Metric scopes available in Stage 1 array benchmarking.
BEND_LABEL_CONFIG	Complete label definition for one benchmarking run.
EvalMetrics	Available evaluation metric groups.
LocusMatchingMode	Controls how GT and prediction transcripts are paired within a locus.
benchmark_from_arrays	Benchmark paired GT/prediction label-array lists (the array entry point).
StreamingBenchmark	Incrementally aggregate per-sequence benchmarks without materialising them.
benchmark_from_gff	Run the full benchmark pipeline from GFF/GTF files.
compare_multiple_predictions	Generate all summary plots and return them as a dict.
load_dataset	Fetch (or reuse cached) dataset and return resolved file paths.
list_datasets	Names of all datasets in the registry, in declaration order.
get_dataset_info	Return the DatasetSpec for name without downloading.
LoadedDataset	Resolved on-disk paths for a benchmark dataset.
log_benchmark_scalars	Log scalar benchmark metrics to an active W&B run.
log_benchmark_all_scalars	Log every numeric scalar in the benchmark result to an active W&B run.
log_benchmark_media	Log all diagnostic plots to W&B as stepwise media history.
log_benchmark_media_videos	Log the active run's buffered media histories as W&B videos and drop them.
clear_benchmark_media_video_buffer	Drop all buffered media frames (every run) without logging them.
init_wandb_with_presets	Initialise a W&B run with pre-configured metric groupings.