{
 "claim": "UltraData-Code-L2 is sold as \"algorithmically relevant code\". By the project's own role classifier, shipped in the `category` column of the data itself, 26.6% of its 266,878,376 rows are ALGO. The plurality label is TOOL at 41.7%. Two thresholds the card never states are visible in the released scores: no file in any of the eleven languages has a `quality_score` below 3.0 — the lowest surviving score ranges from 3.00000 to 3.00019, and `algo_rel_score` has a per-language floor of 0.50 to 0.85 — except Python, whose floor is 0.00.",
 "method": "Hugging Face datasets-server /statistics, one call per split. The `category` frequency table and the score min/max are computed by the server over the rows it reads: the whole split for R (843,971 rows, partial=false), a 1.3–60% leading-shard sample elsewhere. ALGO share is that sample's share; rows is the exact count from /size.",
 "source": "https://datasets-server.huggingface.co/statistics?dataset=openbmb%2FUltraData-Code&config=UltraData-Code-L2&split=r",
 "captured": "2026-09-18",
 "note": "R is the one split measured end to end: 162,047 ALGO files out of 843,971 rows, exactly 19.2%. Python is the outlier on every column — its relevance floor is zero, 11.2% of sampled rows score below 0.1, and it is both the largest split and the one carrying the card's headline Python results table.",
 "columns": [
  {
   "key": "lang",
   "label": "language"
  },
  {
   "key": "rows",
   "label": "rows",
   "align": "right"
  },
  {
   "key": "algo_floor",
   "label": "algo_rel floor",
   "align": "right"
  },
  {
   "key": "q_floor",
   "label": "quality floor",
   "align": "right"
  },
  {
   "key": "algo_share",
   "label": "ALGO share",
   "align": "right"
  },
  {
   "key": "top",
   "label": "plurality label"
  },
  {
   "key": "top_share",
   "label": "its share",
   "align": "right"
  }
 ],
 "rows": [
  {
   "lang": "C++",
   "rows": 23290266,
   "algo_floor": "0.85",
   "q_floor": "3.00000",
   "algo_share": "86.7%",
   "top": "ALGO",
   "top_share": "86.7%"
  },
  {
   "lang": "C#",
   "rows": 25779706,
   "algo_floor": "0.60",
   "q_floor": "3.00001",
   "algo_share": "11.2%",
   "top": "TOOL",
   "top_share": "76.9%"
  },
  {
   "lang": "Go",
   "rows": 3778910,
   "algo_floor": "0.50",
   "q_floor": "3.00000",
   "algo_share": "44.1%",
   "top": "TOOL",
   "top_share": "46.9%"
  },
  {
   "lang": "Java",
   "rows": 43480052,
   "algo_floor": "0.70",
   "q_floor": "3.00012",
   "algo_share": "47.1%",
   "top": "ALGO",
   "top_share": "47.1%"
  },
  {
   "lang": "JavaScript",
   "rows": 57088927,
   "algo_floor": "0.75",
   "q_floor": "3.00019",
   "algo_share": "7.9%",
   "top": "TOOL",
   "top_share": "44.9%"
  },
  {
   "lang": "PHP",
   "rows": 27474889,
   "algo_floor": "0.85",
   "q_floor": "3.00002",
   "algo_share": "4.0%",
   "top": "TOOL",
   "top_share": "47.8%"
  },
  {
   "lang": "Python",
   "rows": 72844227,
   "algo_floor": "0.00",
   "q_floor": "3.00001",
   "algo_share": "25.1%",
   "top": "TOOL",
   "top_share": "31.0%"
  },
  {
   "lang": "R",
   "rows": 843971,
   "algo_floor": "0.50",
   "q_floor": "3.00000",
   "algo_share": "19.2%",
   "top": "TOOL",
   "top_share": "45.4%"
  },
  {
   "lang": "Ruby",
   "rows": 6480797,
   "algo_floor": "0.75",
   "q_floor": "3.00002",
   "algo_share": "10.2%",
   "top": "CONFIG",
   "top_share": "43.1%"
  },
  {
   "lang": "Rust",
   "rows": 2746449,
   "algo_floor": "0.50",
   "q_floor": "3.00001",
   "algo_share": "30.8%",
   "top": "TOOL",
   "top_share": "47.9%"
  },
  {
   "lang": "Shell",
   "rows": 3070182,
   "algo_floor": "0.85",
   "q_floor": "3.00000",
   "algo_share": "8.1%",
   "top": "TOOL",
   "top_share": "86.3%"
  }
 ]
}