{
  "profile": "tabular-data-package",
  "name": "aitrace",
  "title": "AI Trace: documented corporate AI practices",
  "description": "Documented AI practices of companies, with the cited evidence for each. Field definitions, enum values, and the citation forms are published at https://www.aitrace.org/methodology/codebook.",
  "homepage": "https://www.aitrace.org",
  "licenses": [
    {
      "name": "CC-BY-SA-4.0",
      "title": "Creative Commons Attribution-ShareAlike 4.0 International",
      "path": "https://creativecommons.org/licenses/by-sa/4.0/"
    }
  ],
  "contributors": [
    {
      "title": "Trace Foundation",
      "role": "author",
      "path": "https://www.aitrace.org"
    }
  ],
  "resources": [
    {
      "name": "companies",
      "title": "Companies",
      "description": "One row per company profile. The id is the stable identifier; the slug is the current URL path and can change when a company is renamed.",
      "path": "companies.csv",
      "profile": "tabular-data-resource",
      "format": "csv",
      "mediatype": "text/csv",
      "encoding": "utf-8",
      "schema": {
        "fields": [
          {
            "name": "id",
            "title": "Company id",
            "type": "string",
            "description": "Stable unique identifier for the company. Cite by id: https://www.aitrace.org/r/company/{id} resolves to the current page even after a rename.",
            "format": "uuid",
            "constraints": {
              "required": true
            }
          },
          {
            "name": "name",
            "title": "Name",
            "type": "string",
            "description": "Company display name.",
            "constraints": {
              "required": true
            }
          },
          {
            "name": "slug",
            "title": "Slug",
            "type": "string",
            "description": "URL-safe company identifier, the path segment of the company page. Unique at any one time; may change when a company is renamed, so it is not a stable citation key.",
            "constraints": {
              "required": true
            }
          },
          {
            "name": "website",
            "title": "Website",
            "type": "string",
            "description": "Primary company website URL.",
            "format": "uri"
          },
          {
            "name": "description",
            "title": "Description",
            "type": "string",
            "description": "Short description of the company shown on its profile."
          },
          {
            "name": "industry_tags",
            "title": "Industry tags",
            "type": "array",
            "description": "Array of industry tags assigned to the company."
          },
          {
            "name": "aliases",
            "title": "Aliases",
            "type": "array",
            "description": "Other names the company is known by; used to match searches and reports to the profile."
          },
          {
            "name": "ai_status",
            "title": "AI status",
            "type": "string",
            "description": "Overall company AI status: confirmed_use, suspected_use, no_known_use, or under_review. Set by a moderator on the company record.",
            "constraints": {
              "required": true,
              "enum": [
                "confirmed_use",
                "suspected_use",
                "no_known_use",
                "under_review"
              ]
            }
          },
          {
            "name": "parent_company_id",
            "title": "Parent company id",
            "type": "string",
            "description": "Id of the parent company when this company is a subsidiary. Null for top-level companies.",
            "format": "uuid"
          },
          {
            "name": "last_verified_at",
            "title": "Last verified",
            "type": "datetime",
            "description": "Updated whenever a moderator publishes or edits a practice or a cited source under this company. It records the most recent moderator action on the company's record; it does not mean every claim was re-checked on that date. Null when no moderator action has been recorded."
          },
          {
            "name": "created_at",
            "title": "Created",
            "type": "datetime",
            "description": "Timestamp the company record was created.",
            "constraints": {
              "required": true
            }
          },
          {
            "name": "updated_at",
            "title": "Updated",
            "type": "datetime",
            "description": "Timestamp the company record was most recently updated.",
            "constraints": {
              "required": true
            }
          }
        ],
        "primaryKey": "id",
        "foreignKeys": [
          {
            "fields": [
              "parent_company_id"
            ],
            "reference": {
              "resource": "companies",
              "fields": [
                "id"
              ]
            }
          }
        ],
        "missingValues": [
          ""
        ]
      }
    },
    {
      "name": "practices",
      "title": "Practices",
      "description": "One row per documented AI practice. Every structured field supports an explicit \"unknown\" or \"unclear\" value, and every descriptive field may be left null, when sources do not support a specific value. We do not guess.",
      "path": "practices.csv",
      "profile": "tabular-data-resource",
      "format": "csv",
      "mediatype": "text/csv",
      "encoding": "utf-8",
      "schema": {
        "fields": [
          {
            "name": "id",
            "title": "Practice id",
            "type": "string",
            "description": "Stable unique identifier for the practice. Cite by id: https://www.aitrace.org/r/practice/{id} resolves to the current page.",
            "format": "uuid",
            "constraints": {
              "required": true
            }
          },
          {
            "name": "company_id",
            "title": "Company id",
            "type": "string",
            "description": "Id of the company the practice belongs to.",
            "format": "uuid",
            "constraints": {
              "required": true
            }
          },
          {
            "name": "category",
            "title": "Category",
            "type": "string",
            "description": "Practice category, one of seven values; \"Other\" is the catch-all.",
            "constraints": {
              "required": true,
              "enum": [
                "creative_generation",
                "productivity_automation",
                "data_analysis",
                "content_moderation",
                "recommendation_system",
                "customer_service",
                "other"
              ]
            }
          },
          {
            "name": "subcategory",
            "title": "Subcategory",
            "type": "string",
            "description": "Optional free-text subcategory."
          },
          {
            "name": "summary",
            "title": "Summary",
            "type": "string",
            "description": "One-sentence summary of the practice.",
            "constraints": {
              "required": true
            }
          },
          {
            "name": "details",
            "title": "Details",
            "type": "string",
            "description": "Longer prose description."
          },
          {
            "name": "products_affected",
            "title": "Products affected",
            "type": "array",
            "description": "Array of product or service names touched by this practice. Empty when none are named."
          },
          {
            "name": "status",
            "title": "Status",
            "type": "string",
            "description": "Editorial status: verified, reported, disputed, or retracted.",
            "constraints": {
              "required": true,
              "enum": [
                "verified",
                "reported",
                "disputed",
                "retracted"
              ]
            }
          },
          {
            "name": "date_practice_started",
            "title": "Date started",
            "type": "string",
            "description": "Earliest known date the practice began. A partial date (a year, or a year and month) is allowed; null when sources do not say."
          },
          {
            "name": "discontinued_at",
            "title": "Discontinued",
            "type": "date",
            "description": "Date the practice was discontinued. Null when still active. Discontinuation is an explicit flag, not a deletion: the entry stays in the record."
          },
          {
            "name": "last_reviewed_at",
            "title": "Last reviewed",
            "type": "datetime",
            "description": "Timestamp of the most recent moderator review of this practice."
          },
          {
            "name": "deployment_scope",
            "title": "Deployment scope",
            "type": "string",
            "description": "Access conditions for the AI system. The value \"unknown\" is the sentinel default and earns zero points in the completeness score. Orthogonal to visibility; never infer one from the other.",
            "constraints": {
              "required": true,
              "enum": [
                "all_users",
                "opt_in",
                "pilot",
                "internal_tool",
                "offered_not_mandated",
                "unknown"
              ]
            }
          },
          {
            "name": "deployment_regions",
            "title": "Deployment regions",
            "type": "string",
            "description": "Free-text geographic scope (examples: \"US only\", \"60+ countries\", \"global\"). Null when sources do not clarify. For scoring purposes, the literal string \"unknown\" is treated the same as null."
          },
          {
            "name": "user_base_affected",
            "title": "User base affected",
            "type": "string",
            "description": "Free-text scale and population affected (example: \"all 500M monthly users\", \"enterprise customers only\"). Null when sources do not clarify. For scoring purposes, the literal string \"unknown\" is treated the same as null."
          },
          {
            "name": "ai_function",
            "title": "AI function",
            "type": "array",
            "description": "Array of AI functions; the primary function is listed first. Sentinel default is [\"other\"]. An array containing only \"other\" earns zero points in the completeness score.",
            "constraints": {
              "required": true
            }
          },
          {
            "name": "ai_input",
            "title": "AI input",
            "type": "string",
            "description": "Free-text description of what the AI system receives as input."
          },
          {
            "name": "ai_output",
            "title": "AI output",
            "type": "string",
            "description": "Free-text description of what the AI system produces."
          },
          {
            "name": "labor_impact_type",
            "title": "Labor impact type",
            "type": "string",
            "description": "Labor consequence of the AI system. Sentinel default is \"unclear\", which earns zero points. Setting \"automates_prior_task\" requires explicit two-sided evidence at the specific company.",
            "constraints": {
              "required": true,
              "enum": [
                "augments_existing",
                "automates_prior_task",
                "new_capability",
                "unclear"
              ]
            }
          },
          {
            "name": "prior_human_process",
            "title": "Prior human process",
            "type": "string",
            "description": "Free-text description of what humans did before the AI system existed. Null when labor_impact_type is new_capability or when sources do not clarify. Populating this field earns its 10 points even when labor_impact_type remains unclear."
          },
          {
            "name": "labor_context",
            "title": "Labor context",
            "type": "string",
            "description": "Free-text nuance about the labor situation that does not fit the enum cleanly (example: \"editors still review before publish\"). Documenting a gap here earns its 5 points even when labor_impact_type is unclear."
          },
          {
            "name": "visibility",
            "title": "Visibility",
            "type": "string",
            "description": "Whose experience includes the AI output. Null is the sentinel and earns zero points. Orthogonal to deployment_scope; both fields must be set independently based on what the sources support.",
            "constraints": {
              "enum": [
                "consumer_facing",
                "internal",
                "both"
              ]
            }
          },
          {
            "name": "completeness_score",
            "title": "Completeness score",
            "type": "integer",
            "description": "Derived 0 to 100 editorial completeness score, maintained automatically whenever the practice is written. Purely additive; zero is a valid score. Sentinel values (\"unknown\", \"unclear\", a sole [\"other\"], null) earn zero points for their respective fields. A low score due to honest unknowns is acceptable. It is never authored by hand and is not an editorial judgment.",
            "constraints": {
              "required": true
            }
          },
          {
            "name": "created_at",
            "title": "Created",
            "type": "datetime",
            "description": "Timestamp the practice record was created.",
            "constraints": {
              "required": true
            }
          },
          {
            "name": "updated_at",
            "title": "Updated",
            "type": "datetime",
            "description": "Timestamp the practice record was most recently updated.",
            "constraints": {
              "required": true
            }
          }
        ],
        "primaryKey": "id",
        "foreignKeys": [
          {
            "fields": [
              "company_id"
            ],
            "reference": {
              "resource": "companies",
              "fields": [
                "id"
              ]
            }
          }
        ],
        "missingValues": [
          ""
        ]
      }
    },
    {
      "name": "evidence",
      "title": "Evidence",
      "description": "One row per cited source. Every claim in a practice is traceable to at least one row here; a published practice has at least one accepted source, and at least one Tier 1 or Tier 2 source.",
      "path": "evidence.csv",
      "profile": "tabular-data-resource",
      "format": "csv",
      "mediatype": "text/csv",
      "encoding": "utf-8",
      "schema": {
        "fields": [
          {
            "name": "id",
            "title": "Evidence id",
            "type": "string",
            "description": "Evidence row unique identifier.",
            "format": "uuid",
            "constraints": {
              "required": true
            }
          },
          {
            "name": "practice_id",
            "title": "Practice id",
            "type": "string",
            "description": "Id of the practice this source supports.",
            "format": "uuid",
            "constraints": {
              "required": true
            }
          },
          {
            "name": "source_type",
            "title": "Source type",
            "type": "string",
            "description": "Type of source: news_article, company_disclosure, regulatory_filing, community_report, academic_paper, social_media_post. Each type maps to a tier.",
            "constraints": {
              "required": true,
              "enum": [
                "company_disclosure",
                "regulatory_filing",
                "news_article",
                "academic_paper",
                "social_media_post",
                "community_report"
              ]
            }
          },
          {
            "name": "source_url",
            "title": "Source URL",
            "type": "string",
            "description": "Canonical URL of the source.",
            "format": "uri",
            "constraints": {
              "required": true
            }
          },
          {
            "name": "archived_url",
            "title": "Archived copy",
            "type": "string",
            "description": "Wayback or archive URL, when captured. Null when the page could not be archived (for example, the publisher blocks archiving or the page was gone before capture).",
            "format": "uri"
          },
          {
            "name": "source_title",
            "title": "Title",
            "type": "string",
            "description": "Title of the article, document, or post.",
            "constraints": {
              "required": true
            }
          },
          {
            "name": "source_publisher",
            "title": "Publisher",
            "type": "string",
            "description": "Publisher or platform hosting the source."
          },
          {
            "name": "source_date",
            "title": "Date published",
            "type": "date",
            "description": "Publication date of the source."
          },
          {
            "name": "excerpt",
            "title": "Excerpt",
            "type": "string",
            "description": "Evidence excerpt relevant to the claim."
          },
          {
            "name": "verified",
            "title": "Moderator verified",
            "type": "boolean",
            "description": "Whether a moderator has manually verified this source. A source is marked moderator-verified only when three conditions are met simultaneously: the source is from the company itself, the URL is on a recognizable official domain, and the content directly confirms the specific practice being documented. This flag is applied at the source level, not the practice level.",
            "constraints": {
              "required": true
            }
          },
          {
            "name": "created_at",
            "title": "Created",
            "type": "datetime",
            "description": "Timestamp the evidence row was created.",
            "constraints": {
              "required": true
            }
          }
        ],
        "primaryKey": "id",
        "foreignKeys": [
          {
            "fields": [
              "practice_id"
            ],
            "reference": {
              "resource": "practices",
              "fields": [
                "id"
              ]
            }
          }
        ],
        "missingValues": [
          ""
        ]
      }
    }
  ]
}