{
 "name": "softverse-validated-use",
 "title": "Validated use: per-package counts from replication code",
 "licenses": [
  {
   "name": "CC0-1.0",
   "path": "https://creativecommons.org/publicdomain/zero/1.0/"
  }
 ],
 "created": "2026-08-16T01:10:06.790411+00:00",
 "resources": [
  {
   "name": "usage_by_package",
   "path": "usage_by_package.csv",
   "format": "csv",
   "schema": {
    "fields": [
     {
      "name": "package",
      "type": "string"
     },
     {
      "name": "language",
      "type": "string"
     },
     {
      "name": "ecosystem",
      "type": "string"
     },
     {
      "name": "n_deposits",
      "type": "string"
     },
     {
      "name": "n_files",
      "type": "string"
     },
     {
      "name": "n_mentions",
      "type": "string"
     },
     {
      "name": "first_year",
      "type": "string"
     },
     {
      "name": "last_year",
      "type": "string"
     },
     {
      "name": "n_deposits_dataverse_legacy",
      "type": "string"
     },
     {
      "name": "n_deposits_zenodo",
      "type": "string"
     },
     {
      "name": "n_deposits_at_risk",
      "type": "string"
     },
     {
      "name": "share_of_deposits",
      "type": "string"
     },
     {
      "name": "n_at_risk_dataverse_legacy",
      "type": "string"
     },
     {
      "name": "n_at_risk_zenodo",
      "type": "string"
     }
    ]
   }
  },
  {
   "name": "usage_by_package_year",
   "path": "usage_by_package_year.csv",
   "format": "csv",
   "schema": {
    "fields": [
     {
      "name": "package",
      "type": "string"
     },
     {
      "name": "language",
      "type": "string"
     },
     {
      "name": "year",
      "type": "string"
     },
     {
      "name": "n_deposits",
      "type": "string"
     }
    ]
   }
  },
  {
   "name": "usage_by_collection",
   "path": "usage_by_collection.csv",
   "format": "csv",
   "schema": {
    "fields": [
     {
      "name": "source",
      "type": "string"
     },
     {
      "name": "collection_id",
      "type": "string"
     },
     {
      "name": "language",
      "type": "string"
     },
     {
      "name": "package",
      "type": "string"
     },
     {
      "name": "n_deposits",
      "type": "string"
     }
    ]
   }
  },
  {
   "name": "usage_by_function",
   "path": "usage_by_function.csv",
   "format": "csv",
   "schema": {
    "fields": [
     {
      "name": "source",
      "type": "string"
     },
     {
      "name": "language",
      "type": "string"
     },
     {
      "name": "package",
      "type": "string"
     },
     {
      "name": "function",
      "type": "string"
     },
     {
      "name": "n_calls",
      "type": "string"
     },
     {
      "name": "n_deposits",
      "type": "string"
     }
    ]
   }
  },
  {
   "name": "unknown_names",
   "path": "unknown_names.csv",
   "format": "csv",
   "schema": {
    "fields": [
     {
      "name": "name",
      "type": "string"
     },
     {
      "name": "language",
      "type": "string"
     },
     {
      "name": "n_mentions",
      "type": "string"
     }
    ]
   }
  },
  {
   "name": "language_presence",
   "path": "language_presence.csv",
   "format": "csv",
   "schema": {
    "fields": [
     {
      "name": "source",
      "type": "string"
     },
     {
      "name": "language",
      "type": "string"
     },
     {
      "name": "n_deposits",
      "type": "string"
     }
    ]
   }
  },
  {
   "name": "usage_by_package",
   "path": "usage_by_package.parquet",
   "format": "parquet",
   "schema": {
    "fields": [
     {
      "name": "package",
      "type": "string"
     },
     {
      "name": "language",
      "type": "string"
     },
     {
      "name": "ecosystem",
      "type": "string"
     },
     {
      "name": "n_deposits",
      "type": "integer"
     },
     {
      "name": "n_files",
      "type": "integer"
     },
     {
      "name": "n_mentions",
      "type": "integer"
     },
     {
      "name": "first_year",
      "type": "integer"
     },
     {
      "name": "last_year",
      "type": "integer"
     },
     {
      "name": "n_deposits_dataverse_legacy",
      "type": "integer"
     },
     {
      "name": "n_deposits_zenodo",
      "type": "integer"
     },
     {
      "name": "n_deposits_at_risk",
      "type": "integer"
     },
     {
      "name": "share_of_deposits",
      "type": "number"
     },
     {
      "name": "n_at_risk_dataverse_legacy",
      "type": "integer"
     },
     {
      "name": "n_at_risk_zenodo",
      "type": "integer"
     }
    ]
   }
  },
  {
   "name": "usage_by_package_year",
   "path": "usage_by_package_year.parquet",
   "format": "parquet",
   "schema": {
    "fields": [
     {
      "name": "package",
      "type": "string"
     },
     {
      "name": "language",
      "type": "string"
     },
     {
      "name": "year",
      "type": "integer"
     },
     {
      "name": "n_deposits",
      "type": "integer"
     }
    ]
   }
  },
  {
   "name": "usage_by_collection",
   "path": "usage_by_collection.parquet",
   "format": "parquet",
   "schema": {
    "fields": [
     {
      "name": "source",
      "type": "string"
     },
     {
      "name": "collection_id",
      "type": "string"
     },
     {
      "name": "language",
      "type": "string"
     },
     {
      "name": "package",
      "type": "string"
     },
     {
      "name": "n_deposits",
      "type": "integer"
     }
    ]
   }
  },
  {
   "name": "usage_by_function",
   "path": "usage_by_function.parquet",
   "format": "parquet",
   "schema": {
    "fields": [
     {
      "name": "source",
      "type": "string"
     },
     {
      "name": "language",
      "type": "string"
     },
     {
      "name": "package",
      "type": "string"
     },
     {
      "name": "function",
      "type": "string"
     },
     {
      "name": "n_calls",
      "type": "integer"
     },
     {
      "name": "n_deposits",
      "type": "integer"
     }
    ]
   }
  },
  {
   "name": "unknown_names",
   "path": "unknown_names.parquet",
   "format": "parquet",
   "schema": {
    "fields": [
     {
      "name": "name",
      "type": "string"
     },
     {
      "name": "language",
      "type": "string"
     },
     {
      "name": "n_mentions",
      "type": "integer"
     }
    ]
   }
  },
  {
   "name": "language_presence",
   "path": "language_presence.parquet",
   "format": "parquet",
   "schema": {
    "fields": [
     {
      "name": "source",
      "type": "string"
     },
     {
      "name": "language",
      "type": "string"
     },
     {
      "name": "n_deposits",
      "type": "integer"
     }
    ]
   }
  },
  {
   "name": "mentions",
   "path": "mentions.parquet",
   "format": "parquet",
   "schema": {
    "fields": [
     {
      "name": "mention_uid",
      "type": "string"
     },
     {
      "name": "file_uid",
      "type": "string"
     },
     {
      "name": "dataset_doi",
      "type": "string"
     },
     {
      "name": "source",
      "type": "string"
     },
     {
      "name": "collection_id",
      "type": "string"
     },
     {
      "name": "deposit_year",
      "type": "integer"
     },
     {
      "name": "language",
      "type": "string"
     },
     {
      "name": "construct",
      "type": "string"
     },
     {
      "name": "raw_name",
      "type": "string"
     },
     {
      "name": "called_function",
      "type": "string"
     },
     {
      "name": "normalized_name",
      "type": "string"
     },
     {
      "name": "resolved_package",
      "type": "string"
     },
     {
      "name": "ecosystem",
      "type": "string"
     },
     {
      "name": "resolution",
      "type": "string"
     },
     {
      "name": "line",
      "type": "integer"
     },
     {
      "name": "col",
      "type": "integer"
     },
     {
      "name": "byte_start",
      "type": "integer"
     },
     {
      "name": "byte_end",
      "type": "integer"
     },
     {
      "name": "snippet",
      "type": "string"
     },
     {
      "name": "cell_index",
      "type": "number"
     },
     {
      "name": "chunk_label",
      "type": "string"
     },
     {
      "name": "is_conditional",
      "type": "boolean"
     },
     {
      "name": "is_dynamic",
      "type": "boolean"
     },
     {
      "name": "is_reachable",
      "type": "string"
     },
     {
      "name": "extractor_version",
      "type": "string"
     },
     {
      "name": "grammar_version",
      "type": "string"
     },
     {
      "name": "registry_lock_id",
      "type": "string"
     }
    ]
   }
  },
  {
   "name": "files",
   "path": "files.parquet",
   "format": "parquet",
   "schema": {
    "fields": [
     {
      "name": "file_uid",
      "type": "string"
     },
     {
      "name": "dataset_version_uid",
      "type": "string"
     },
     {
      "name": "dataset_doi",
      "type": "string"
     },
     {
      "name": "source",
      "type": "string"
     },
     {
      "name": "collection_id",
      "type": "string"
     },
     {
      "name": "dataverse_file_id",
      "type": "number"
     },
     {
      "name": "container_file_uid",
      "type": "string"
     },
     {
      "name": "path_in_container",
      "type": "string"
     },
     {
      "name": "directory_label",
      "type": "string"
     },
     {
      "name": "relative_path",
      "type": "string"
     },
     {
      "name": "filename",
      "type": "string"
     },
     {
      "name": "extension",
      "type": "string"
     },
     {
      "name": "language",
      "type": "string"
     },
     {
      "name": "size_bytes",
      "type": "number"
     },
     {
      "name": "md5_api",
      "type": "string"
     },
     {
      "name": "sha256_local",
      "type": "string"
     },
     {
      "name": "md5_verified",
      "type": "string"
     },
     {
      "name": "restricted",
      "type": "string"
     },
     {
      "name": "encoding",
      "type": "string"
     },
     {
      "name": "encoding_confidence",
      "type": "number"
     },
     {
      "name": "is_vendored",
      "type": "boolean"
     },
     {
      "name": "vendor_rule",
      "type": "string"
     },
     {
      "name": "duplicate_of",
      "type": "string"
     },
     {
      "name": "file_role",
      "type": "string"
     },
     {
      "name": "is_reachable",
      "type": "string"
     },
     {
      "name": "parse_status",
      "type": "string"
     },
     {
      "name": "parse_error_nodes",
      "type": "number"
     },
     {
      "name": "n_mentions",
      "type": "integer"
     },
     {
      "name": "in_analysis_set",
      "type": "boolean"
     },
     {
      "name": "download_ts",
      "type": "string"
     },
     {
      "name": "local_path",
      "type": "string"
     }
    ]
   }
  },
  {
   "name": "declared_dependencies",
   "path": "declared_dependencies.parquet",
   "format": "parquet",
   "schema": {
    "fields": [
     {
      "name": "dataset_doi",
      "type": "string"
     },
     {
      "name": "source_file_uid",
      "type": "string"
     },
     {
      "name": "manifest_kind",
      "type": "string"
     },
     {
      "name": "package",
      "type": "string"
     },
     {
      "name": "version_constraint",
      "type": "string"
     },
     {
      "name": "ecosystem",
      "type": "string"
     },
     {
      "name": "dependency_role",
      "type": "string"
     }
    ]
   }
  },
  {
   "name": "environment_signals",
   "path": "environment_signals.parquet",
   "format": "parquet",
   "schema": {
    "fields": [
     {
      "name": "dataset_doi",
      "type": "string"
     },
     {
      "name": "source_file_uid",
      "type": "string"
     },
     {
      "name": "manifest_kind",
      "type": "string"
     },
     {
      "name": "signal",
      "type": "string"
     },
     {
      "name": "value",
      "type": "string"
     }
    ]
   }
  }
 ]
}
