HSDE — Hybrid Symbolic Discovery Engine

Neural-symbolic reasoning prototypes: a recursive CA + attention + symbolic hybrid, and an Enhanced Symbolic Discovery Engine targeting AIME / SAT / GSM8K.

Sat Jun 01 2024 00:00:00 GMT+0000 (Coordinated Universal Time)

Exploratory architectures for reasoning systems that sit between pure neural methods and pure symbolic methods — built around the hypothesis that the right intermediate representation for LLM reasoning is a rule-mined causal graph extracted from attention, not free-form chain-of-thought.

Module 1 — ASI (Recursive CA + Attention + Symbolic)

Phased architecture:

  1. 2D cellular automaton as a controllable dynamical substrate.
  2. Transformer trained on the CA trajectories with attention hooks exposed.
  3. Attention tensors → binary causal matrix → temporal causal graph → FP-growth rule mining over that graph.

The bet: attention isn’t the explanation, but the causal graph built from attention is a substrate you can do symbolic discovery on.

Module 2 — ESDE (Enhanced Symbolic Discovery Engine)

Targets AIME / SAT / GSM8K via a neural-symbolic hybrid: Phi-3 / Mistral via Ollama → SketchNegotiator → RuleEngine backed by SymPy / Z3 → Contrastive Evolver → CodeBERT embeddings + FAISS MemoryGraph + FP-growth → FeedbackLoop.

Status

Prototypes, not products. Architectural boundaries are clean and the core ideas survive contact with real data, but benchmark results, ablations, and end-to-end reliability aren’t there yet. The strongest publishable slice is ASI Phases 1–3B with controlled experiments against a transformer-only baseline — fits ICLR ME-FoMo, NeurIPS SRI, or NeSy workshop.