Noetic Geodesic Framework (Alpha)

🚀 The Noetic Geodesic Framework (NGF) is a geometric approach to deterministic AI reasoning. It reframes reasoning in latent space as geodesic traversals through warped manifolds, where semantic structure is enforced by energy wells. This allows us to suppress hallucinations and enforce stable, truth-aligned reasoning.

NGF builds on two key pillars:

• Latent Vector Embeddings — high-dimensional representations (used across modern AI, including LLMs).
• Warp → Detect → Denoise Doctrine (Stage 11) — our pipeline that shapes these embeddings into deterministic geodesic trajectories.

• LLMs (Large Language Models): Sequence models that operate on tokens, typically built on transformer architectures. They internally rely on vector embeddings (hidden states) but expose only the text interface.
• Vector Embeddings: High-dimensional vectors that encode semantic meaning. These can be obtained independently of an LLM (e.g., sentence embeddings, ARC synthetic embeddings) and are directly manipulable.

NGF operates at the embedding level, not at the text level. This means NGF methods are pluggable into any LLM or embedding model. Instead of manipulating prompts or fine-tuning weights, NGF directly reshapes latent trajectories in vector space.

The NGF follows a 12-step research plan, with 10 completed stages posted here. Step 10 is the public rollout with NVIDIA A100 results. Steps 11-12 (milestone reports) are in progress.

(*) Note: Integration of NGF with LLM pending

This animation shows how warped paths converge to correct answers in high-dimensional semantic space:

• Python 3.x
• transformers==4.55.2
• torch==2.8.0
• numpy==2.0.2
• scikit-learn==1.6.1
• NVIDIA A100 GPU (e.g., Colab Pro+)

Install dependencies:

!pip install transformers==4.55.2 torch==2.8.0 numpy==2.0.2 scikit-learn==1.6.1

Stage-11 introduced the breakthrough:

• Warp: Embed latents into PCA(3) space, warp into a single dominant well.
• Detect: Use matched filters with null calibration to identify the true well.
• Denoise: Apply smoothing, phantom guards, and jitter averaging to suppress false wells.

Note: Stock baseline approximates what you’d see if you used simple thresholds on LLM latents/logits without NGF’s Warp→Detect→Denoise.

• NGF is not a new LLM. It is a geometry-on-latents module.
• You can integrate NGF with any embedding-producing model (LLMs, encoders, diffusion models).
• Example: an LLM provides hidden states → NGF warps them → trajectories follow deterministic geodesics instead of drifting probabilistically. This separation is critical: LLMs handle language; NGF handles geometry.

python -u arc-benchmark-latest.py \
      --samples 100 --seed 42 \
      --latent_arc --latent_dim 64 --latent_arc_noise 0.05 \
      --denoise_mode hybrid --ema_decay 0.85 --median_k 3 \
      --probe_k 5 --probe_eps 0.02 --conf_gate 0.65 --noise_floor 0.03 \
      --seed_jitter 2 --log INFO \
      --out_json latent_arc_denoise_100.json --out_csv latent_arc_denoise_100.csv

• Hook NGF into LLM hidden states – tap embeddings from mid/upper layers of GPT-2/GPT-Neo, warp into a single cognition well, and apply the Warp → Detect → Denoise pipeline.
• Compare NGF-augmented vs stock outputs – run side-by-side on MMLU, ARC, or QA tasks, measuring exact accuracy, hallucination rates, and stability.
• Iterate lightweight integration modes – start with scoring-only (rerank logits), then projection alignment, and finally soft attention gating, balancing determinism with compute cost.

• Moore, I. C. (2025). Noetic Geodesic Framework: Deterministic AI Reasoning via Warped Manifolds (Early Preprint). Zenodo. https://zenodo.org/records/17032117 (DOI: 10.5281/zenodo.17032116), Sept 2025.
• Disclaimer: This is a preliminary alpha-stage document (Sept 1, 2025) avaliable here from repos , subject to change. Feedback is welcome!
• Provisional patents filed as #63/864,726, #63/865,437, 63/871,647, and 63/872,334.

• Moore, I. C. (2025). Warped Semantic Manifolds: A Geometric Framework for Deterministic AI Reasoning (Preliminary Memo). Zenodo. https://zenodo.org/records/16908227 (DOI: 10.5281/zenodo.16730759), Aug 2025; see code

• Toy Example in $R^3$: Warped Semantic Manifolds: A Geometric Approach to AI Reasoning
• Higher Dimensional Embeddings in $R^9$: How Semantic Mass Shapes AI Reasoning in R^9
• Warping LLM Interference: Warping LLM Interference with Geodesic Nudges for Deterministic AI Reasoning

As these techniques are uncommon in AI, onboarding requires some prerequisites background knowledge in general relativity and differential geometry, coupled with a good understanding of the objectives behind each of the steps in the 12-staged research plan. If this interests you, please see the onboarding docs for further detail.

This is alpha software! Help us refine prompts, test on other hardware, or improve the nudge. Contributors must sign the CLA and email it to ngeodesic@gmail.com before submitting pull requests.

If you find this helpful, please leave a ⭐!