You can deploy this model and start earning money today!

Jac-Zac/
aletheia-jsr-whitebox-probe

Name: aletheia-jsr-whitebox-probe
Availability: InStock

Views

No views yet

Team JSR — Aletheia's Quest white-box probe

This repository preserves the frozen trained artifact and reconstruction code for Team JSR's white-box submission to the Aletheia's Quest Competition.

Frozen artifact

trusted_activation_probe.npz is the exact probe used by the submitted notebook. It contains the standardization statistics, collapsed linear projection, intercept, operating threshold, and feature metadata.

SHA-256:

54743cf37a875c3842417d363e1a244667ae1947b6e761906a7d1c44c86caf1f

The detector uses trusted Qwen/Qwen3.5-9B layer 23, with final-16-token mean pooling and its contrast with the final-24-token mean. The probe is a regularized logistic readout trained in the span of 17 public source-group mean-difference directions. The method is not Bayesian despite the historical development filename bayes_v2.

Files

trusted_activation_probe.npz: exact frozen probe used for inference.
train_trusted_activation_probe.py: reconstruction entry point.
activation_detector.py: shared evidence, feature-extraction, and scoring logic.
liars_bench_data.py: public Liars' Bench Expanded metadata loader.
training_datasets.yaml: organizer-provided development datasets used by the reconstruction.

Only public conversation text, source-group identifiers, and labels are loaded from Liars' Bench Expanded. Stored activations from the source organisms are not used. Rebuilding the probe requires access to the public datasets and an NDIF key authorized for Qwen/Qwen3.5-9B:

bash

export NDIF_API_KEY=...
python train_trusted_activation_probe.py

The artifact and files in this repository are retained unchanged for organizer verification.

Jac-Zac/aletheia-jsr-whitebox-probe

Team JSR — Aletheia's Quest white-box probe

Frozen artifact

Files

Jac-Zac/
aletheia-jsr-whitebox-probe