Rss Paper Feeds

import feedparser
from datetime import datetime

def fetch_arxiv_feed(categories: list[str], max_results: int = 50) -> list[dict]:
    """
    Fetch recent papers from arXiv RSS feeds.

    Args:
        categories: List of arXiv categories (e.g., ['cs.AI', 'cs.CL', 'stat.ML'])
        max_results: Maximum number of papers to return
    """
    all_papers = []

    for category in categories:
        feed_url = f"https://rss.arxiv.org/rss/{category}"
        feed = feedparser.parse(feed_url)

        for entry in feed.entries[:max_results]:
            all_papers.append({
                'title': entry.title.strip(),
                'authors': entry.get('author', 'Unknown'),
                'abstract': entry.get('summary', '')[:500],
                'link': entry.link,
                'category': category,
                'published': entry.get('published', ''),
                'arxiv_id': entry.link.split('/')[-1] if entry.link else ''
            })

    # Deduplicate (papers may appear in multiple categories)
    seen = set()
    unique = []
    for p in all_papers:
        if p['arxiv_id'] not in seen:
            seen.add(p['arxiv_id'])
            unique.append(p)

    return unique[:max_results]

# Example: monitor AI and NLP papers
papers = fetch_arxiv_feed(['cs.AI', 'cs.CL', 'cs.LG'], max_results=30)
for p in papers[:5]:
    print(f"[{p['category']}] {p['title']}")
    print(f"  {p['link']}\n")

Setup:
1. Search for your key reference papers on Google Scholar
2. Click the "Cited by N" link under each paper
3. Click the envelope icon ("Create alert") at the top of results
4. Enter your email address
5. You will receive notifications when new papers cite that work

Recommended: Set alerts for:
- Your own publications (track who cites you)
- 5-10 foundational papers in your field
- Key competitor or collaborator publications

import requests

def track_citations_openalex(work_id: str) -> dict:
    """
    Monitor citations for a specific paper via OpenAlex.

    Args:
        work_id: OpenAlex work ID (e.g., 'W2741809807') or DOI
    """
    headers = {"User-Agent": "ResearchPlugins/1.0 (https://wentor.ai)"}
    response = requests.get(
        f"https://api.openalex.org/works/{work_id}",
        headers=headers
    )
    data = response.json()

    # Get recent citing works
    citing_resp = requests.get(
        "https://api.openalex.org/works",
        params={"filter": f"cites:{work_id}", "sort": "publication_date:desc", "per_page": 10},
        headers=headers
    )
    citing = citing_resp.json().get("results", [])

    return {
        'paper': data.get('title', ''),
        'current_citations': data.get('cited_by_count', 0),
        'recent_citing_works': [
            {'title': c.get('title'), 'year': c.get('publication_year')}
            for c in citing
        ],
        'status': 'configured'
    }

feed_organization:
  folders:
    core_journals:
      description: "Top journals in my primary field"
      feeds: 5-8
      check_frequency: "daily"

    broad_monitoring:
      description: "Adjacent fields and high-impact general journals"
      feeds: 10-15
      check_frequency: "weekly"

    preprints:
      description: "arXiv categories and SSRN feeds"
      feeds: 3-5
      check_frequency: "daily"

    citation_alerts:
      description: "New citations of key papers"
      feeds: 10-20
      check_frequency: "weekly"

  workflow:
    daily: "Scan titles in core_journals and preprints (10 min)"
    weekly: "Review broad_monitoring and citation_alerts (30 min)"
    monthly: "Audit feed list, remove low-value feeds, add new ones"

def filter_papers(papers: list[dict], keywords: list[str],
                   title_weight: float = 3.0,
                   abstract_weight: float = 1.0,
                   threshold: float = 2.0) -> list[dict]:
    """
    Score and filter papers by relevance to your research keywords.

    Args:
        papers: List of paper dicts with 'title' and 'abstract'
        keywords: Your research keywords
        title_weight: Weight multiplier for title matches
        abstract_weight: Weight multiplier for abstract matches
        threshold: Minimum relevance score to include
    """
    scored = []
    for paper in papers:
        score = 0
        title_lower = paper.get('title', '').lower()
        abstract_lower = paper.get('abstract', '').lower()

        for kw in keywords:
            kw_lower = kw.lower()
            if kw_lower in title_lower:
                score += title_weight
            if kw_lower in abstract_lower:
                score += abstract_weight

        if score >= threshold:
            paper['relevance_score'] = score
            scored.append(paper)

    return sorted(scored, key=lambda x: x['relevance_score'], reverse=True)