{
  "aliases": [],
  "authors": [
    "Sarah E. Chasins",
    "Maria Mueller",
    "Rastislav Bodik"
  ],
  "details": {
    "publication": {
      "authors": [
        "Sarah E. Chasins",
        "Maria Mueller",
        "Rastislav Bodik"
      ],
      "date_basis": "Supplied year precision: 2018. Rousillon entry: UIST 2018",
      "date_parts": [
        2018
      ],
      "doi": "10.1145/3242587.3242661",
      "event_dates": null,
      "evidence_urls": [
        "https://schasins.com/papers/",
        "https://schasins.com/assets/papers/rousillon.pdf"
      ],
      "identity_basis": "No same-work record located in the full active catalog. Similarity screening was not used as automatic identity approval. The raw archive and exclusions are additionally checked during normalization.",
      "issue": null,
      "notes": "This is browser interaction learned from demonstrations, rather than a generic server-side crawling library. Final proceedings page range and volume are not established. Manuscript pages 1-13 are not substituted for publisher pagination. Exact publication month/day is not inferred from conference dates.",
      "pages": null,
      "pdf_url": "https://schasins.com/assets/papers/rousillon.pdf",
      "publisher": null,
      "series": null,
      "title": "Rousillon: Scraping Distributed Hierarchical Web Data",
      "type": "conference-paper",
      "url": "https://doi.org/10.1145/3242587.3242661",
      "venue": "Proceedings of the 31st Annual ACM Symposium on User Interface Software and Technology",
      "volume": null
    }
  },
  "environments": [
    "web"
  ],
  "evidence": [
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T09:57:38Z",
      "role": "primary",
      "sha256": "6b7e584bb3862e0de51ca164d0f311c2a853e97bd63d56658ce62f0b49d86557",
      "supports": [
        "details.publication.date_basis",
        "details.publication.date_parts",
        "details.publication.notes",
        "details.publication.type",
        "details.publication.venue"
      ],
      "url": "https://schasins.com/papers/"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T09:55:12Z",
      "role": "primary",
      "sha256": "764dd1f5fe1db398188f403b4b1f6e3658e3238e4d8aac9ceed360dcad87e818",
      "supports": [
        "details.publication.authors",
        "details.publication.doi",
        "details.publication.identity_basis",
        "details.publication.notes",
        "details.publication.pdf_url",
        "details.publication.title",
        "details.publication.url"
      ],
      "url": "https://schasins.com/assets/papers/rousillon.pdf"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T09:55:12Z",
      "role": "primary",
      "sha256": "764dd1f5fe1db398188f403b4b1f6e3658e3238e4d8aac9ceed360dcad87e818",
      "supports": [
        "details.publication.authors",
        "details.publication.doi",
        "details.publication.identity_basis",
        "details.publication.notes",
        "details.publication.pdf_url",
        "details.publication.title",
        "details.publication.url",
        "environments",
        "name",
        "scope",
        "summary",
        "topics"
      ],
      "url": "https://schasins.com/assets/papers/rousillon.pdf"
    },
    {
      "method": "editorial_primary_review",
      "retrieved_at": "2026-10-17T09:57:38Z",
      "role": "primary",
      "sha256": "6b7e584bb3862e0de51ca164d0f311c2a853e97bd63d56658ce62f0b49d86557",
      "supports": [
        "details.publication.date_basis",
        "details.publication.date_parts",
        "details.publication.notes",
        "details.publication.type",
        "details.publication.venue",
        "kind"
      ],
      "url": "https://schasins.com/papers/"
    }
  ],
  "id": "url:97c0b1896525632434e2",
  "identifiers": {
    "doi": "10.1145/3242587.3242661"
  },
  "kind": "paper",
  "last_verified_at": "2026-10-17T09:55:12Z",
  "licenses": {
    "code": null,
    "data": null,
    "document": null,
    "weights": null
  },
  "links": [
    {
      "rel": "primary",
      "url": "https://doi.org/10.1145/3242587.3242661"
    },
    {
      "rel": "publication_pdf",
      "url": "https://schasins.com/assets/papers/rousillon.pdf"
    }
  ],
  "name": "Rousillon: Scraping Distributed Hierarchical Web Data",
  "notes": "The annotation was reviewed against retained primary publication sources. Experiments have not been independently reproduced. This is browser interaction learned from demonstrations, rather than a generic server-side crawling library.",
  "published_at": null,
  "relations": [],
  "review_status": "curated",
  "scope": "core",
  "summary": "Introduces Rousillon, which generalizes a demonstration of collecting one hierarchical data row into a browser-automation program that traverses related pages. The paper develops relation-selection and generalization methods and evaluates users building such scripts.",
  "topics": [
    "web-navigation",
    "recording",
    "automation"
  ],
  "updated_at": null,
  "url": "https://doi.org/10.1145/3242587.3242661"
}
