Geometric-brain-mcp
API, MCP, and Python interface for spectral diagnostics, comparisons, and audit workflows.
API-accessible diagnostics, research-grade instrumentation, and advanced drift monitoring for teams that need measurable signals about model behavior.
Geometric Assurance is a spectral diagnostics and model integrity suite for transformer systems. Geometric-brain-mcp is the front door, Unitarity-lab is the research engine, and VAR is the advanced monitoring layer.
Geometric Assurance is a spectral diagnostics and model integrity suite for transformer systems.
One front door, one research engine, one advanced monitoring layer.
API, MCP, and Python interface for spectral diagnostics, comparisons, and audit workflows.
Research and audit engine for deep instrumentation, hidden-state analysis, and reproducible experiments.
Enterprise beta monitoring layer for drift, anomaly, and integrity workflows.
Hidden-state and eigenvalue analysis are primary evidence-bearing modes. Text proxy mode remains available only as an indirect demo path.
Direct instrumentation of latent activations for model comparison, drift monitoring, and reproducible audits.
Spectral structure measurements to support anomaly detection and integrity monitoring workflows.
Text proxy mode is a lightweight demo and screening path. It does not inspect true hidden states and should not be treated as equivalent to hidden-state or eigenvalue analysis.
A practical engagement path designed for trust and fast first outcomes.
Share the target components and examples for initial scoping.
Execute spectral diagnostics and model comparison passes.
Get a structured summary of measured signals, caveats, and next actions.
Extend into research-grade instrumentation or pilot monitoring based on goals.
Sample audit report coming next.
Educational research-station workflow for spectral structure measurement and model comparison.
Measures spectral structure, not output correctness; does not detect hallucination or judge content quality.
Three paths from any HuggingFace model to a spectral audit. The notebook is the fastest start.
AutoModelForCausalLM.from_pretrained("your/model-id"), attaches activation hooks, and computes hidden-state eigenvalues automatically.
External proxy returns r-ratio and regime from spectral analysis. For production work, use hidden-state and eigenvalue analysis in the research engine.
Key reference parameters for spectral rigidity measurement.
r ≈ 0.5996
The GUE (Gaussian Unitary Ensemble) r-statistic measures the average ratio of consecutive eigenvalue gaps in the model's hidden-state weight matrices. The Wigner surmise predicts r ≈ 0.5996 (empirically ~0.602); Poisson-distributed spacings give r ≈ 0.3863. This measures spectral structure only — it does not indicate output quality or coherence.
Text proxy mode is a screening shortcut only. For production-grade results, connect directly to the research engine or the API layer.
Full hidden-state and eigenvalue instrumentation. Attach activation hooks, run reproducible audit notebooks, export audit trails. This is where r-statistics and spectral metrics are derived from real hidden states rather than text proxies.
REST API, MCP server, and Python SDK for spectral diagnostics and model comparison workflows. Integrate into CI pipelines, compare model checkpoints, or run batch audits across a model family without custom instrumentation.
Two core strategies for audit and monitoring integration.
API and Python interface for lightweight spectral diagnostics, model comparisons, and audit initialization. Integrate with your pipeline for ongoing screening.
Advanced drift, anomaly, and integrity monitoring layer. Pilot-ready for teams wanting operational drift detection and tamper-evident controls.