Skillget

genpark-multi-candidate-self-consistency-majority-voter-skill

mcp
Guvenlik Denetimi
Uyari
Health Uyari
  • No license — Repository has no license file
  • Description — Repository has a description
  • Active repo — Last push 0 days ago
  • Low visibility — Only 8 GitHub stars
Code Gecti
  • Code scan — Scanned 4 files during light audit, no dangerous patterns found
Permissions Gecti
  • Permissions — No dangerous permissions requested

Bu listing icin henuz AI raporu yok.

SUMMARY

GenPark AI Agent Skill - Self-consistency sampling aggregator, majority voting consensus engine, and semantic clusterer for reasoning verification.

README.md

GenPark AI Agent Skill - Self-Consistency Majority Voter

GenPark Verified
Protocol
License

Self-consistency sampling aggregator and majority voting consensus engine inspired by Wang et al. (2022).

flowchart LR
    A[Temperature-Sampled Outputs] --> B[Answer Normalizer]
    B --> C[Candidate Clustering & Frequency Count]
    C --> D[Majority Consensus Decision]
    D --> E[Confidence Margin]

Features

  • Deterministic Normalization: Extracts answers from \boxed{}, The answer is..., and final line summaries.
  • Confidence Metrics: Measures inter-sample agreement percentages.
  • Zero External Dependencies: Standard library Python 3.9+.

Quickstart

from client import SelfConsistencyVoterClient

voter = SelfConsistencyVoterClient()
consensus = voter.vote(samples)
print(consensus["consensus_answer"], consensus["confidence"])

Ecosystem & Citations

Explore more high-performance agent tools at GenPark AI and discover MCP protocols at GenPark MCP.

Yorumlar (0)

Sonuc bulunamadi