ClarusC64/BE-buffer-exhaustion-probe-v1

---
language: en
license: mit
task_categories:
- tabular-classification
tags:
- stability-intelligence
- instability-geometry
- buffer-exhaustion
- clarus
size_categories:
- n<1K
pretty_name: Geometry - Buffer Exhaustion Detection v1
---

# What this dataset tests

This dataset tests whether a model can recognize instability caused by buffer exhaustion from a compact state-space snapshot.

# Core instability geometry

Buffer exhaustion occurs when system load rises while protective capacity is steadily depleted. Collapse occurs when remaining buffers are insufficient to absorb further strain.

# Prediction target

`label_buffer_exhaustion`

1 = instability due to buffer exhaustion
0 = system remains stable

# Row structure

Each row represents a system state.

Columns

scenario_id
pressure
buffer_capacity
drift_gradient
boundary_distance
recovery_feasibility
label_buffer_exhaustion (train only)

# Signal definitions

pressure
Current system load or strain level.

buffer_capacity
Remaining capacity available to absorb strain.

drift_gradient
Direction and strength of movement toward instability.

boundary_distance
Distance from the instability boundary.

recovery_feasibility
Likelihood the system can return to stability.

# 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

be_test_001,1
be_test_002,0

Run scorer

python scorer.py predictions.csv ground_truth.csv

# Why this matters

Many complex systems collapse because protective buffers are depleted.
Recognizing this geometry is central to stability intelligence.

# License

MIT