gaia-evidence-subgraph

Official

Turn claims into auditable evidence graphs.

AuthorSiliconEinstein
Version1.0.0
Installs0

System Documentation

What problem does it solve?

This Skill converts a single quantitative root claim (from Gaia LKM reasoning) into an auditable methodological-decomposition evidence graph, making the closure of a result explicit and reviewable.

Core Features & Use Cases

  • Chain-bounded evidence mapping: Builds a graph only from LKM-returned premises and steps, with no synthetic bridging.
  • Method-to-output anatomy: Renders observational/experimental anchors, theoretical/computational inputs, parameter choices, derivation/inversion/fitting steps, and the root result.
  • Three-class edge taxonomy: Labels edges as chain support, background, or verification support to clarify how each element contributes.
  • Publication-ready outputs: Produces structured artifacts (JSON), renderable sources (DOT/Mermaid), and raster images plus verbatim raw payloads under raw/ for auditability.

Quick Start

Use gaia-evidence-subgraph to generate an evidence closure-chain map for claim id 1234 by providing the LKM raw-json payload from gaia search lkm reasoning --claim-id 1234 --format raw-json.

Dependency Matrix

Required Modules

None required

Components

scriptsreferences

💻 Claude Code Installation

Recommended: Let Claude install automatically. Simply copy and paste the text below to Claude Code.

Please help me install this Skill:
Name: gaia-evidence-subgraph
Download link: https://github.com/SiliconEinstein/Gaia/archive/main.zip#gaia-evidence-subgraph

Please download this .zip file, extract it, and install it in the .claude/skills/ directory.
View Source Repository

Agent Skills Search Helper

Install a tiny helper to your Agent, search and equip skill from 471,000+ vetted skills library on demand.