Skip to content

Repository files navigation

Consciousness Benchmark / Mind Lab

DOI License Python 3.9+

English | 中文

This repository contains the code and release materials for:

Measurement Validation Reveals Five Dissociable Operational Constructs Underlying Self-Model and Agency in Artificial Neural Architectures

The project studies how internal proxy measures can be checked against independent behavioral probes in small, controlled artificial systems. The claims are about measurement validity for operational constructs. They are not claims about subjective experience, sentience, or consciousness in deployed AI systems.

Paper And Materials

Scope

The current release includes five reference constructs:

  • action_agency
  • boundary_self
  • identity_temporal_self
  • action_ownership
  • distributed_body_schema_self

The architectures in this repository are small custom simulations used as controlled measurement testbeds. They are not production-scale language models or general-purpose AI systems.

Repository Layout

  • consciousness_benchmark/: benchmark abstractions, validators, reference constructs, and CLI.
  • mind_lab/: controlled simulation systems used by the paper.
  • scripts/: statistics, figure generation, diagnostics, and online benchmark runners.
  • examples/: minimal examples for reference and online benchmark runs.
  • docs/paper/statistics/final_20260521/: frozen primary statistics.
  • docs/paper/statistics/reference_20260521/: compact raw tables used by the reference benchmark.
  • docs/paper/statistics/transformer_20260522/: minimal attention follow-up diagnostics.
  • docs/paper/statistics/supplementary_20260522/: supplementary robustness checks.
  • docs/paper/figures/: paper and supplementary figures.

Large raw run directories are excluded from the public release. The compact statistics tables and figure manifests are kept for traceability.

Installation

python -m pip install -e .

Optional online Mind Lab runs use the optional dependency group:

python -m pip install -e ".[mind-lab]"

Reproduce The Reference Report

The paper reports frozen statistics. You do not need to rerun the long experiments to reproduce the main table.

python -m consciousness_benchmark reference --bootstrap 10000 --seed 20260521

This writes:

Regenerate Figures And Submission Files

python scripts/generate_paper_figures_v2.py
python scripts/generate_transformer_figure6.py
python scripts/generate_supplementary_figures.py
python scripts/build_submission_package.py

Run A Small Online Smoke Test

python -m consciousness_benchmark online --condition-sets thalamus --seeds 1 --warmup 32 --quick --bootstrap 500

Frozen Result Locations

Primary paper statistics:

Reference benchmark inputs:

Supplementary robustness checks:

Citation

@misc{measurement_validation_constructs_2026,
  title = {Measurement Validation Reveals Five Dissociable Operational Constructs Underlying Self-Model and Agency in Artificial Neural Architectures},
  author = {Feng, Fuwang},
  year = {2026},
  publisher = {Zenodo},
  doi = {10.5281/zenodo.20372255},
  url = {https://doi.org/10.5281/zenodo.20372255}
}

License

Code is licensed under the Apache License 2.0. See LICENSE.

The preprint files on Zenodo are distributed under CC BY 4.0.

About

Benchmark and paper package for validating operational self-model and agency constructs in controlled artificial neural architectures.

Topics

Resources

Stars

3 stars

Watchers

1 watching

Forks

Releases

Packages

Contributors

Languages