mirror of
https://github.com/allaunthefox/Research-Stack.git
synced 2026-08-10 13:10:35 +00:00
679945c1a0
Cross-referenced against our prover orchestration layers: - Plan-Execute-Verify-Replan ↔ L0-L3 pipeline - Agents as specialists ↔ 11-agent swarm - Guardrails ↔ ProverWatchdog - Sandbox testing ↔ Virtual FPGA tests - Trajectory-aware eval ↔ BFS audit trail 5 gaps identified, 4 strengths confirmed
9 lines
919 B
Text
9 lines
919 B
Text
created: 20260507000000000
|
|
modified: 20260507000000000
|
|
tags: ResearchStack Search Graph Mining Semantic
|
|
title: Semantic Graph Mining
|
|
type: text/vnd.tiddlywiki
|
|
|
|
! Semantic Graph Mining
|
|
|
|
Semantic graph mining pipeline extracts concept graphs from the research corpus. Includes `5-Applications/scripts/build_graphml.py` (GraphML export), `build_manifold_graphml.py` (manifold-aware graphs), `compute_distance_matrix.py` (semantic distances), `cluster_supernodes.py` (community detection), and `build_unified_forest.py` (equation forest construction). The [[Graph-Evolving RAG]] system uses these graphs for retrieval-augmented generation. Mining outputs connect to [[HNSW Vector Search]] for ANN queries and [[Semantic Search]] (internal tool at `5-Applications/tools-scripts/search/`) for full-text retrieval. The [[Semantic Prime Refraction]] and [[Address-First Search Protocol]] provide specialized mining strategies.
|