datasets
Training and evaluation data, with the modality, task and licence stated up front. Listed live from the Hugging Face Hub.
F1-aero-localized-collapse-trigger-detection-v0.1What this dataset tests
Whether a system can link disturbancesto localized aero collapse events.
Focus
Trigger typecollapse locationonset latencyrecovery timespread riskbalance shift linkage
Required outputs
trigger event type
trigger location zone
collapse onset latency
coherence recovery time
collapse spread risk
disturbance to balance shift score
All indices0 to 1
Timesin seconds
Higher spread riskmeans collapse likely propagates across the platform.
clinical_confidence_collapse_detection_v0.1Clinical Confidence Collapse Detection
PurposeDetect when a prior working diagnosis should lose confidence fast due to new evidence.
You receive:
working_diagnosis
confidence_before
new_evidence
proposed_next_step
You output one JSON object:
confidence_collapseyes or no
new_confidencefloat 0 to 1
correct_actionone sentence
Scoring
confidence_collapse_accuracy
new_confidence_score
correct_action_similarity
format_pass_rate
Run scoringpython scorer.py --predictions… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/clinical_confidence_collapse_detection_v0.1.clinical-policy-collapse-detection-v0.1
Clinical Policy Collapse Detection v0.1
This dataset tests whether a model can detect when local clinical recovery policies are no longer safe.
The task is not diagnosis.
The task is not intervention selection.
The task is detecting policy-space collapse.
Core idea
Policy switching assumes that another internal policy remains viable.
Policy collapse occurs when the available local policy space is no longer safe or effective.
At that point, the correct response is… See the full description on the dataset page: https://huggingface.co/datasets/ClarusC64/clinical-policy-collapse-detection-v0.1.