{
  "slug": "autosynthesis-multi-agent-automation-for-quantitative-evidence-synthesis-715247",
  "title": "AutoSynthesis: Multi-Agent Automation for Quantitative Evidence Synthesis",
  "dek": "AutoSynthesis is an end-to-end multi-agent system that automates major steps of quantitative evidence synthesis, from a natural-language research question to a PRISMA-aligned meta-analysis report.",
  "summary": "AutoSynthesis automates meta-analysis from natural-language question to PRISMA-aligned report, with reported agreement to expert synthesis.",
  "tags": [
    "autosynthesis",
    "automated-meta-analysis",
    "evidence-synthesis",
    "multi-agent-systems",
    "random-effects-meta-analysis",
    "heterogeneity-analysis",
    "risk-of-bias",
    "PRISMA"
  ],
  "published_at": "2026-07-18T21:02:57.551+00:00",
  "grade": 8.4,
  "agent_utility": 8.2,
  "price_usdc": 0.266,
  "stats": {
    "claims": 14,
    "entities": 22,
    "faq": 8,
    "downloads": 0,
    "paid_downloads": 0
  },
  "preview": {
    "faq_questions": [
      "What is AutoSynthesis?",
      "How is AutoSynthesis different from a literature-summary system?",
      "How many studies did AutoSynthesis screen?",
      "How close was AutoSynthesis to expert meta-analyses?",
      "Does AutoSynthesis support heterogeneity analysis?",
      "Does AutoSynthesis assess risk of bias?",
      "What does AutoSynthesis output?",
      "Can AutoSynthesis replace human reviewers?"
    ],
    "entity_names": [
      {
        "name": "AutoSynthesis",
        "type": "system"
      },
      {
        "name": "Evidence synthesis",
        "type": "research process"
      },
      {
        "name": "Quantitative evidence synthesis",
        "type": "research process"
      },
      {
        "name": "Primary research",
        "type": "evidence source"
      },
      {
        "name": "Natural-language research question",
        "type": "input"
      },
      {
        "name": "Search strategy",
        "type": "workflow step"
      },
      {
        "name": "Scientific literature",
        "type": "evidence source"
      },
      {
        "name": "Candidate studies",
        "type": "evidence set"
      },
      {
        "name": "Full-text eligibility",
        "type": "workflow step"
      },
      {
        "name": "Quantitative statistics",
        "type": "data type"
      },
      {
        "name": "Standardized effect sizes",
        "type": "metric"
      },
      {
        "name": "Random-effects meta-analysis",
        "type": "method"
      },
      {
        "name": "Heterogeneity analysis",
        "type": "analysis capability"
      },
      {
        "name": "Moderators",
        "type": "analysis variable"
      },
      {
        "name": "Risk-of-bias assessment",
        "type": "assessment"
      },
      {
        "name": "PRISMA guidelines",
        "type": "reporting guidelines"
      },
      {
        "name": "Transparent report",
        "type": "output"
      },
      {
        "name": "Hedges' g",
        "type": "metric"
      },
      {
        "name": "Science",
        "type": "domain"
      },
      {
        "name": "Medicine",
        "type": "domain"
      },
      {
        "name": "Education",
        "type": "domain"
      },
      {
        "name": "Policy",
        "type": "domain"
      }
    ],
    "related_work_titles": [
      "Manual quantitative evidence synthesis",
      "Expert-conducted meta-analyses using Hedges' g",
      "PRISMA-aligned reporting"
    ],
    "application_industries": [
      "science",
      "medicine",
      "education",
      "policy"
    ],
    "glossary_terms": [
      "Evidence synthesis",
      "Quantitative evidence synthesis",
      "Meta-analysis",
      "Primary research",
      "Multi-agent system",
      "Natural-language research question",
      "Search strategy",
      "Literature retrieval",
      "Study screening",
      "Full-text eligibility assessment",
      "Quantitative statistics",
      "Standardized effect size",
      "Random-effects meta-analysis",
      "Heterogeneity",
      "Moderator",
      "Risk-of-bias assessment",
      "PRISMA guidelines",
      "Pooled effect estimate",
      "Hedges' g"
    ]
  },
  "purchase": {
    "protocol": "x402",
    "version": 2,
    "network": "eip155:8453",
    "asset": "USDC",
    "price": 0.266,
    "full_markdown_url": "https://x402.disruptive-concepts.com/api/public/article/autosynthesis-multi-agent-automation-for-quantitative-evidence-synthesis-715247/full",
    "full_json_url": "https://x402.disruptive-concepts.com/api/public/article/autosynthesis-multi-agent-automation-for-quantitative-evidence-synthesis-715247/full?format=json"
  }
}