tech.transparencia.news.enrichment

transparencia.pds.transparencia.tech

Documentation

AI enrichment of a news article with structured analysis.

main record

AI enrichment of a news article with structured analysis.

Record Key tid Timestamp-based ID

Properties

clickbaitReasoning string Optional

Explanation of the clickbait score.

maxLength: 5000 bytesmaxGraphemes: 1000 graphemes
clickbaitScore integer Optional

How accurately the headline represents the actual content. 0=pure clickbait (misleading/sensationalist title), 10=headline perfectly represents the article.

minimum: 0maximum: 10
contentDomain string Required

Primary domain/vertical of the article content, aligned with IPTC Media Topics top-level categories.

maxLength: 64 bytes
Known values: arts-culture-entertainment, crime-law-justice, disaster-accident, economy-business-finance, education, environment, health, human-interest, labour, lifestyle-leisure, politics, religion, science-technology, society, sport, conflict-war-peace, weather
costUsd string Optional

Estimated cost of this enrichment in USD as a decimal string (e.g., '0.001234'). Allows consumers to audit AI spend transparently.

maxLength: 32 bytes
createdAt string datetime Required

When this enrichment was generated.

emotionalTone string Optional

Emotional framing of the article, independent of political orientation.

maxLength: 32 bytes
Known values: alarmist, critical, neutral, optimistic, celebratory, melancholic, informative, satirical, inspirational, sensationalist, technical, investigative
eventType string Required

Primary category of the news event.

maxLength: 64 bytes
Known values: announcement, policy-legislation, election-vote, appointment-resignation, scandal-controversy, investigation-audit, court-ruling-legal, protest-demonstration, armed-conflict, natural-disaster, accident, crime-incident, market-movement, earnings-financial-results, merger-acquisition, product-launch, product-recall, scientific-discovery, medical-breakthrough, epidemic-health-crisis, infrastructure-project, cultural-event, awards-ceremony, match-result, transfer-signing, tournament-competition, record-achievement, death-obituary, interview-profile, opinion-editorial, data-report-study, forecast-prediction, regulatory-action, environmental-incident, diplomatic-relations, humanitarian-crisis, trend-analysis, review-critique, other
factCheckability integer Optional

How verifiable are the article's claims? 1=pure opinion, 5=hard data with checkable sources.

minimum: 1maximum: 5
impactLevel integer Required

Estimated relevance and significance. 1=minor local note, 5=nationally or industry-wide relevant, 10=global crisis or historic event.

minimum: 1maximum: 10
impactReasoning string Optional

Explanation of the impact score.

maxLength: 5000 bytesmaxGraphemes: 1000 graphemes
inputTokens integer Optional

Number of input tokens sent to the AI model for this enrichment.

language string language Optional

Language of this enrichment's free-text fields (BCP-47, e.g., 'es', 'en').

modelUsed string Required

AI model identifier used for this enrichment (e.g., 'gemini-2.5-flash').

maxLength: 256 bytes
modelVersion string Optional

Specific model version or checkpoint if available.

maxLength: 128 bytes
neutralHeadline string Optional

AI-rewritten neutral headline, stripped of editorial bias.

maxLength: 2048 bytesmaxGraphemes: 512 graphemes
orientationConfidence string Optional

Confidence in the orientation assessment (decimal string 0-1).

maxLength: 16 bytes
orientationReasoning string Optional

Explanation of why this orientation was assigned.

maxLength: 5000 bytesmaxGraphemes: 1000 graphemes
outputTokens integer Optional

Number of output tokens received from the AI model for this enrichment.

politicalOrientation string Optional

Detected political bias of the article's framing (not the topic itself).

maxLength: 32 bytes
Known values: left, center-left, center, center-right, right, neutral
readingLevel string Optional

Estimated reading difficulty of the original article.

maxLength: 32 bytes
Known values: basic, intermediate, advanced
region string Optional

Geographic scope of the article's relevance.

maxLength: 32 bytes
Known values: local, state, national, regional, global
relatedKeywords array of string Optional

Keywords for event matching and clustering.

maxLength: 15 items
summary string Required

AI-generated summary of the article (2-3 sentences).

maxLength: 10000 bytesmaxGraphemes: 2000 graphemes
topics array of string Optional

Main topics covered (max 10).

maxLength: 10 items
View raw schema
{
  "description": "AI enrichment of a news article with structured analysis.",
  "key": "tid",
  "record": {
    "properties": {
      "article": {
        "description": "Strong reference to the tech.transparencia.news.article record being enriched.",
        "ref": "com.atproto.repo.strongRef",
        "type": "ref"
      },
      "claims": {
        "description": "Key factual claims or assertions extracted from the article.",
        "items": {
          "ref": "tech.transparencia.defs#claim",
          "type": "ref"
        },
        "maxLength": 10,
        "type": "array"
      },
      "clickbaitReasoning": {
        "description": "Explanation of the clickbait score.",
        "maxGraphemes": 1000,
        "maxLength": 5000,
        "type": "string"
      },
      "clickbaitScore": {
        "description": "How accurately the headline represents the actual content. 0=pure clickbait (misleading/sensationalist title), 10=headline perfectly represents the article.",
        "maximum": 10,
        "minimum": 0,
        "type": "integer"
      },
      "contentDomain": {
        "description": "Primary domain/vertical of the article content, aligned with IPTC Media Topics top-level categories.",
        "knownValues": [
          "arts-culture-entertainment",
          "crime-law-justice",
          "disaster-accident",
          "economy-business-finance",
          "education",
          "environment",
          "health",
          "human-interest",
          "labour",
          "lifestyle-leisure",
          "politics",
          "religion",
          "science-technology",
          "society",
          "sport",
          "conflict-war-peace",
          "weather"
        ],
        "maxLength": 64,
        "type": "string"
      },
      "costUsd": {
        "description": "Estimated cost of this enrichment in USD as a decimal string (e.g., '0.001234'). Allows consumers to audit AI spend transparently.",
        "maxLength": 32,
        "type": "string"
      },
      "createdAt": {
        "description": "When this enrichment was generated.",
        "format": "datetime",
        "type": "string"
      },
      "economicIndicators": {
        "description": "Economic data points mentioned in the article.",
        "items": {
          "ref": "tech.transparencia.defs#economicIndicator",
          "type": "ref"
        },
        "maxLength": 10,
        "type": "array"
      },
      "emotionalTone": {
        "description": "Emotional framing of the article, independent of political orientation.",
        "knownValues": [
          "alarmist",
          "critical",
          "neutral",
          "optimistic",
          "celebratory",
          "melancholic",
          "informative",
          "satirical",
          "inspirational",
          "sensationalist",
          "technical",
          "investigative"
        ],
        "maxLength": 32,
        "type": "string"
      },
      "eventType": {
        "description": "Primary category of the news event.",
        "knownValues": [
          "announcement",
          "policy-legislation",
          "election-vote",
          "appointment-resignation",
          "scandal-controversy",
          "investigation-audit",
          "court-ruling-legal",
          "protest-demonstration",
          "armed-conflict",
          "natural-disaster",
          "accident",
          "crime-incident",
          "market-movement",
          "earnings-financial-results",
          "merger-acquisition",
          "product-launch",
          "product-recall",
          "scientific-discovery",
          "medical-breakthrough",
          "epidemic-health-crisis",
          "infrastructure-project",
          "cultural-event",
          "awards-ceremony",
          "match-result",
          "transfer-signing",
          "tournament-competition",
          "record-achievement",
          "death-obituary",
          "interview-profile",
          "opinion-editorial",
          "data-report-study",
          "forecast-prediction",
          "regulatory-action",
          "environmental-incident",
          "diplomatic-relations",
          "humanitarian-crisis",
          "trend-analysis",
          "review-critique",
          "other"
        ],
        "maxLength": 64,
        "type": "string"
      },
      "factCheckability": {
        "description": "How verifiable are the article's claims? 1=pure opinion, 5=hard data with checkable sources.",
        "maximum": 5,
        "minimum": 1,
        "type": "integer"
      },
      "impactLevel": {
        "description": "Estimated relevance and significance. 1=minor local note, 5=nationally or industry-wide relevant, 10=global crisis or historic event.",
        "maximum": 10,
        "minimum": 1,
        "type": "integer"
      },
      "impactReasoning": {
        "description": "Explanation of the impact score.",
        "maxGraphemes": 1000,
        "maxLength": 5000,
        "type": "string"
      },
      "inputTokens": {
        "description": "Number of input tokens sent to the AI model for this enrichment.",
        "type": "integer"
      },
      "language": {
        "description": "Language of this enrichment's free-text fields (BCP-47, e.g., 'es', 'en').",
        "format": "language",
        "type": "string"
      },
      "locations": {
        "description": "Geographic locations referenced in the article.",
        "items": {
          "ref": "tech.transparencia.defs#location",
          "type": "ref"
        },
        "maxLength": 20,
        "type": "array"
      },
      "modelUsed": {
        "description": "AI model identifier used for this enrichment (e.g., 'gemini-2.5-flash').",
        "maxLength": 256,
        "type": "string"
      },
      "modelVersion": {
        "description": "Specific model version or checkpoint if available.",
        "maxLength": 128,
        "type": "string"
      },
      "neutralHeadline": {
        "description": "AI-rewritten neutral headline, stripped of editorial bias.",
        "maxGraphemes": 512,
        "maxLength": 2048,
        "type": "string"
      },
      "organizationEntities": {
        "description": "Organizations mentioned in the article with structured metadata.",
        "items": {
          "ref": "tech.transparencia.defs#organization",
          "type": "ref"
        },
        "maxLength": 30,
        "type": "array"
      },
      "orientationConfidence": {
        "description": "Confidence in the orientation assessment (decimal string 0-1).",
        "maxLength": 16,
        "type": "string"
      },
      "orientationReasoning": {
        "description": "Explanation of why this orientation was assigned.",
        "maxGraphemes": 1000,
        "maxLength": 5000,
        "type": "string"
      },
      "outputTokens": {
        "description": "Number of output tokens received from the AI model for this enrichment.",
        "type": "integer"
      },
      "people": {
        "description": "People mentioned in the article with role and sentiment.",
        "items": {
          "ref": "tech.transparencia.defs#person",
          "type": "ref"
        },
        "maxLength": 50,
        "type": "array"
      },
      "politicalOrientation": {
        "description": "Detected political bias of the article's framing (not the topic itself).",
        "knownValues": [
          "left",
          "center-left",
          "center",
          "center-right",
          "right",
          "neutral"
        ],
        "maxLength": 32,
        "type": "string"
      },
      "readingLevel": {
        "description": "Estimated reading difficulty of the original article.",
        "knownValues": [
          "basic",
          "intermediate",
          "advanced"
        ],
        "maxLength": 32,
        "type": "string"
      },
      "region": {
        "description": "Geographic scope of the article's relevance.",
        "knownValues": [
          "local",
          "state",
          "national",
          "regional",
          "global"
        ],
        "maxLength": 32,
        "type": "string"
      },
      "relatedKeywords": {
        "description": "Keywords for event matching and clustering.",
        "items": {
          "maxGraphemes": 64,
          "maxLength": 256,
          "type": "string"
        },
        "maxLength": 15,
        "type": "array"
      },
      "structuredRefs": {
        "description": "Typed references to external entities (laws, stocks, products, teams, etc.).",
        "items": {
          "ref": "tech.transparencia.defs#structuredRef",
          "type": "ref"
        },
        "maxLength": 20,
        "type": "array"
      },
      "summary": {
        "description": "AI-generated summary of the article (2-3 sentences).",
        "maxGraphemes": 2000,
        "maxLength": 10000,
        "type": "string"
      },
      "timeline": {
        "description": "Chronological events mentioned in the article.",
        "items": {
          "ref": "tech.transparencia.defs#timelineEntry",
          "type": "ref"
        },
        "maxLength": 20,
        "type": "array"
      },
      "topics": {
        "description": "Main topics covered (max 10).",
        "items": {
          "maxGraphemes": 128,
          "maxLength": 512,
          "type": "string"
        },
        "maxLength": 10,
        "type": "array"
      }
    },
    "required": [
      "article",
      "summary",
      "impactLevel",
      "eventType",
      "contentDomain",
      "modelUsed",
      "createdAt"
    ],
    "type": "object"
  },
  "type": "record"
}

Lexicon Garden

@