{
  "aliases": [],
  "authors": [],
  "details": {
    "benchmark_protocol": {
      "actions": [
        "search queries",
        "click actions",
        "product option selection"
      ],
      "counts": [
        {
          "basis": "reported",
          "evidence_url": "https://raw.githubusercontent.com/princeton-nlp/WebShop/HEAD/README.md",
          "population": "crowd-sourced instruction collection",
          "qualifier": "exact",
          "unit": "instructions",
          "value": 12087
        },
        {
          "basis": "reported",
          "evidence_url": "https://raw.githubusercontent.com/princeton-nlp/WebShop/HEAD/README.md",
          "population": "full product inventory",
          "qualifier": "approximately",
          "unit": "products",
          "value": 1180000
        }
      ],
      "evaluation": "",
      "evidence_urls": [
        "https://raw.githubusercontent.com/princeton-nlp/WebShop/HEAD/README.md"
      ],
      "focus": [
        "instruction-conditioned product selection",
        "web navigation"
      ],
      "notes": "This is a simulated shop. The default preview loads 1,000 products, while the full inventory is much larger; report the loaded subset and observation mode. Instructions and products are different populations. Detailed reward semantics are not normalized in this profile.",
      "observations": [
        "HTML pages",
        "simplified text views"
      ],
      "setting": "interactive"
    }
  },
  "environments": [
    "web"
  ],
  "evidence": [
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-16T06:35:57Z",
      "role": "primary",
      "sha256": "79b7a90a1413a52deb53142b5bbd81ecf40f61743bd4601c2835e91375898ec0",
      "supports": [
        "name",
        "kind",
        "summary",
        "environments",
        "topics",
        "scope",
        "relations",
        "details"
      ],
      "url": "https://raw.githubusercontent.com/princeton-nlp/WebShop/HEAD/README.md"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-16T06:35:57Z",
      "role": "primary",
      "sha256": "79b7a90a1413a52deb53142b5bbd81ecf40f61743bd4601c2835e91375898ec0",
      "supports": [
        "details.benchmark_protocol"
      ],
      "url": "https://raw.githubusercontent.com/princeton-nlp/WebShop/HEAD/README.md"
    },
    {
      "method": "license_header",
      "retrieved_at": "2026-10-16T06:41:58Z",
      "role": "primary",
      "sha256": "8872dbf8660b00890b5e07ce1ea1f7a44fa7ae4e1857da56caba172b51dab3cb",
      "supports": [
        "licenses.code"
      ],
      "url": "https://raw.githubusercontent.com/princeton-nlp/WebShop/HEAD/LICENSE.md"
    }
  ],
  "id": "github:princeton-nlp/webshop",
  "identifiers": {},
  "kind": "benchmark",
  "last_verified_at": "2026-10-16T06:35:57Z",
  "licenses": {
    "code": {
      "basis": "repository LICENSE header; not a weights/data license",
      "declared": "MIT",
      "retrieved_at": "2026-10-16T06:41:58Z",
      "url": "https://raw.githubusercontent.com/princeton-nlp/WebShop/HEAD/LICENSE.md"
    },
    "data": null,
    "document": null,
    "weights": null
  },
  "links": [
    {
      "rel": "primary",
      "url": "https://github.com/princeton-nlp/WebShop"
    }
  ],
  "name": "WebShop",
  "notes": "",
  "published_at": null,
  "relations": [
    {
      "evidence_url": "https://raw.githubusercontent.com/princeton-nlp/WebShop/HEAD/README.md",
      "target_id": "arxiv:2207.01206",
      "type": "documented_by"
    }
  ],
  "review_status": "curated",
  "scope": "core",
  "summary": "Simulated shopping environment for instruction-following web agents.",
  "topics": [
    "evaluation",
    "web-navigation"
  ],
  "updated_at": null,
  "url": "https://github.com/princeton-nlp/WebShop"
}