{
 "ground_truth_collected_2026-10-20": {
  "P1_wikipedia_markdown": {
   "extract_chars": 7826,
   "sentences_ge_40_chars": 50,
   "article_links_ns0_existing": 191,
   "images_listed": 4
  },
  "P2_python_json_docs": {
   "html_bytes": 114953,
   "doctest_lines_>>>": 42
  },
  "P3_quotes_toscrape_js": {
   "quotes_in_inline_script": 10,
   "rendered_quote_divs_in_static_html": 0
  },
  "P4_arxiv_2310.19923v4": {
   "abs_page_http": 200,
   "note": "export.arxiv.org API timed out (curl exit 28 after 30 s); abs page used instead"
  }
 },
 "comparison": "not possible: every r.jina.ai call returned HTTP 401"
}