iiRecord
Agentic AI Atlas · DS-1000 full set
test-set:ds1000-fulla5c.ai
II.
TestSet JSON

test-set:ds1000-full

Structured · live

DS-1000 full set json

Inspect the normalized record payload exactly as the atlas UI reads it.

File · benchmarks/test-sets/source-backed-benchmark-test-sets.yamlCluster · benchmarks
Record JSON
{
  "id": "test-set:ds1000-full",
  "_kind": "TestSet",
  "_file": "benchmarks/test-sets/source-backed-benchmark-test-sets.yaml",
  "_cluster": "benchmarks",
  "attributes": {
    "displayName": "DS-1000 full set",
    "benchmarkId": "benchmark:ds1000",
    "caseCount": 1000,
    "releasedAt": "2022-11-21",
    "composition": "DS-1000's full data-science code-generation suite spanning seven\nPython data-science libraries with realistic perturbations and\nfunctional correctness checks.\n",
    "homepageUrl": "https://ds1000-code-gen.github.io/",
    "description": "Canonical DS-1000 artifact for data-science code-generation evaluation.\n"
  },
  "outgoingEdges": [
    {
      "from": "test-set:ds1000-full",
      "to": "benchmark:ds1000",
      "kind": "belongs_to_benchmark"
    }
  ],
  "incomingEdges": []
}