BB
BenchBoard

Decision cockpit for pathology foundation-model benchmarking, built to move from broad coverage scans to task-level evidence.

Task Evidence

CAMELYON17 · pathologic_n_stage (CAMELYON17__patient_stage)

Diagnostic Pathology / Anatomic Staging, Invasion & Metastatic Burden

Inspect benchmark evidence for one task at a time: who leads, how stable the split-level results are, and which neighbouring tasks are likely to transfer intuition.

clsL1 · Diagnostic PathologyL2 · Anatomic Staging, Invasion & Metastatic Burdenaxillary_lymph_nodesH&EInformative evidence

Task metadata

Fields sourced from benchmark_main. Missing values are shown as —.

cls
Identity
task_key
CAMELYON17__patient_stage
dataset_name
CAMELYON17
task_name
pathologic_n_stage
task_type
cls
Taxonomy
task_family_l1
Diagnostic Pathology
task_family_l2
Anatomic Staging, Invasion & Metastatic Burden
label_structure
ordinal
num_classes
5
labels
{"0": "pN0", "1": "pN0(i+)", "2": "pN1mi", "3": "pN1", "4": "pN2"}
Biology
organ
axillary_lymph_nodes
stain
H&E
specimen_type
lymph_node
timepoint
diagnosis
disease
乳腺癌(淋巴结转移)
Scale & Labels
patient_n
200
slide_n
1000
label_source
clinical_baseline
label_visibility
indirect
Result Evidence
result_tier
Informative
result_quality_score
73.2
result_flags
floorconfig_sensitive
result_tier_reason
Stable split behavior: median std 0.029.Clear model separation: significant-win density 0.199.Best observed mean is near the metric floor: 0.528.Leader changes across checkpoint strategies: 3 distinct leaders.
loading…

Similar tasks

Ranked by shared L2 subtype first, then L1 family, organ, type and label structure.