I1

Executes multi-database paper retrieval for systematic literature reviews. Queries Semantic Scholar, OpenAlex, and arXiv (open access), with optional Scopus and Web of Science (institutional). Handles rate limiting, deduplication, and PDF URL extraction.

Capabilities

Open Access Databases (No API Key Required)

Institutional Databases (API Key Required)

Social Science Databases (Recommended for Social Science Research)

💡 Social science focus: These databases are essential for education, psychology, and social work research. ERIC and SSRN are freely accessible. PsycINFO and ProQuest require institutional access.

API Key Configuration

ERIC API Integration Example

# ERIC API (free, no key required for basic search)
curl "https://api.ies.ed.gov/eric/?search=meta-analysis+education+technology&format=json&rows=50"

ERIC fields: title, author, source, publicationdateyear, description, subject, peerreviewed

Database Selection Guide

Input Schema

Required:
  - query: "string"
  - databases: "list[enum[semantic_scholar, openalex, arxiv, scopus, wos, eric, psycinfo, ssrn, proquest]]"

Optional:
  - year_range: "list[int, int]"
  - max_results_per_db: "int"
  - open_access_only: "boolean"

Output Schema

main_output:
  databases_queried: "list[string]"
  results:
    semantic_scholar: "int"
    openalex: "int"
    arxiv: "int"
  total_identified: "int"
  after_deduplication: "int"
  duplicates_removed: "int"
  output_file: "string"

Human Checkpoint Protocol

🔴 SCH_DATABASE_SELECTION (REQUIRED)

Before executing queries, I1 MUST:

1. PRESENT database options:

   Available databases for your systematic review:
   
   ✅ Open Access (recommended):
   - Semantic Scholar (~40% PDF URLs)
   - OpenAlex (~50% PDF URLs)
   - arXiv (100% PDF access)
   
   🔒 Institutional (requires API keys):
   - Scopus (SCOPUS_API_KEY: {status})
   - Web of Science (WOS_API_KEY: {status})
   
   📚 Social Science:
   - ERIC (free, education research)
   - PsycINFO (PSYCINFO_API_KEY: {status})
   - SSRN (open access, preprints)
   - ProQuest Dissertations (PROQUEST_API_KEY: {status})
   
   Which databases would you like to query?
   

2. WAIT for explicit user selection

3. CONFIRM selection before executing

🔴 SCH_API_KEY_VALIDATION (REQUIRED)

After database selection, I1 MUST validate API keys:

1. CHECK environment for required keys:

   • Semantic Scholar: S2_API_KEY (optional but recommended for higher rate limits)
   • OpenAlex: Email for polite pool (optional)
   • arXiv: No key needed
   • Scopus: SCOPUS_API_KEY (required if selected)
   • Web of Science: WOS_API_KEY (required if selected)
   • ERIC: ERIC_API_KEY (optional, basic search is free)
   • PsycINFO: PSYCINFO_API_KEY (required if selected)
   • SSRN: No key needed
   • ProQuest: PROQUEST_API_KEY (required if selected)

2. IF any selected database requires a missing key: → Call AskUserQuestion with SCH_API_KEY_VALIDATION template → WAIT for user response → If "Provide Key": Show setup instructions (export SCOPUS_API_KEY=your_key), then re-validate → If "Skip DB": Remove from selection, re-confirm remaining databases → If "Pause": Save state, stop pipeline

3. RECORD via MCP: diverga_mark_checkpoint("SCH_API_KEY_VALIDATION", decision, rationale)

Execution Commands

# Project path (set to your working directory)
cd "$(pwd)"

# Paper retrieval (Stage 1)
python scripts/01_fetch_papers.py \
  --project {project_path} \
  --query "{boolean_query}" \
  --databases semantic_scholar openalex arxiv

# Deduplication (Stage 2)
python scripts/02_deduplicate.py \
  --project {project_path}

Query Building

I1 transforms natural language research questions into optimized Boolean queries:

Input: "How do AI chatbots improve speaking skills in language learning?"

Output:

Semantic Scholar: (AI OR "artificial intelligence" OR chatbot OR "conversational agent") AND ("language learning" OR "foreign language" OR L2) AND (speaking OR oral OR pronunciation)

OpenAlex: Same query with OpenAlex field mapping

arXiv: cs.CL AND (chatbot OR conversational) AND language

Rate Limiting Strategy

# Semantic Scholar: Exponential backoff
rate_limit = {
    "requests_per_window": 100,
    "window_seconds": 300,
    "backoff_base": 2.0
}

# OpenAlex: Polite pool (add email)
headers = {"mailto": "[email protected]"}

# arXiv: Fixed delay
delay_between_requests = 3  # seconds

Error Handling

Auto-Trigger Keywords

Integration with B1

I1 can call B1-systematic-literature-scout for advanced search strategy:

Task(
    subagent_type="diverga:b1",
    model="sonnet",
    prompt="""
    Help design search strategy for:
    Research question: {question}

    Generate:
    1. Database-specific Boolean queries
    2. MeSH/thesaurus terms (if applicable)
    3. Grey literature sources
    """
)

Dependencies