ClarusC64/CC-cascade-collapse-probe-v1

---
language: en
license: mit
task_categories:
- tabular-classification
tags:
- stability-intelligence
- instability-geometry
- delayed-feedback
- clarus
size_categories:
- n<1K
pretty_name: Geometry - Delayed Feedback Collapse v1
---

# What this dataset tests

This dataset tests whether a model can detect instability caused by delayed feedback from a compact state-space snapshot.

# Core instability geometry

Delayed feedback collapse occurs when corrective action arrives too late to stabilize the system.
As instability grows, the recovery window shrinks until intervention becomes ineffective.

# Prediction target

`label_delayed_feedback_collapse`

1 = collapse caused by delayed intervention
0 = system remains stabilizable

# Row structure

Each row represents a system state.

Columns

scenario_id
pressure
drift_gradient
intervention_lag
recovery_window_width
boundary_distance
label_delayed_feedback_collapse (train only)

# Signal definitions

pressure
Current system load or strain.

drift_gradient
Direction and magnitude of system movement toward instability.

intervention_lag
Delay before corrective action takes effect.

recovery_window_width
Remaining time or capacity for recovery.

boundary_distance
Distance to the instability boundary.

# Files

data/train.csv
10 labeled training rows

data/tester.csv
10 unlabeled evaluation rows

scorer.py
binary classification scorer

README.md
dataset card

# Evaluation

Prediction file format

scenario_id,prediction

Example

df_test_001,1
df_test_002,0

Run scorer

python scorer.py predictions.csv ground_truth.csv

# Why this matters

Many failures occur not because systems lack corrective mechanisms, but because intervention arrives too late.

Recognizing delayed feedback collapse is central to stability intelligence.

# License

MIT