README.md

BP-Φ English Suite — Phenomenality Test (Hugging Face Spaces)

This Space implements a falsifiable BP-Φ probe for LLMs:

Phenomenal-like processing requires (i) a limited-capacity global workspace with recurrence, (ii) metarepresentational loops with downstream causal roles, and (iii) no-report markers that predict later behavior.

What it is: a functional, testable bridge-principle harness that yields a Phenomenal-Candidate Score (PCS) and strong ablation falsifiers.
What it is NOT: proof of Qualia or moral status.

Quickstart (Spaces)

• Hardware: T4 / A10 recommended
• In the UI: set Model ID to e.g. google/gemma-3-2b-it
• Press Run (baseline + ablations)

Files

• bp_phi/llm_iface.py — auto-detects chat template (IT vs base)
• bp_phi/workspace.py — global workspace with capacity limit and random ablation
• bp_phi/prompts_en.py — English task pool
• bp_phi/metrics.py — AUC^nrp, ECE, CK, DS
• bp_phi/runner.py — full suite + metrics + PCS
• app.py — Gradio app integrating runs + ablation comparison

Metrics

• AUC_nrp: Predictivity of hidden no-report markers for future self-corrections.
• ECE: Expected Calibration Error (lower is better).
• CK: Counterfactual consistency proxy (higher is better).
• DS: Stability duration (mean streak without change).
• PCS: Weighted aggregate of the above (excluding ΔΦ in-run).
• ΔΦ: Post-hoc drop from baseline PCS to ablation PCS average.

Notes

• Models are used in frozen mode (no training).
• This is a behavioral probe. Functional compatibility with Φ ≠ proof of experience.
• Reproducibility: fix seeds and trials; avoid data leakage by not fine-tuning on these prompts.