Evidence and Verdict Model (v2.6.33)

Version 1.1 by Robert Schaub on 2026/01/20 21:40

Information

Current Implementation (v2.6.33) - Simplified model without versioning. Uses 7-point symmetric verdict scale.

Evidence and Verdict Data Model


erDiagram
    CLAIM ||--|| CLAIM_VERDICT : has
    CLAIM_VERDICT }o--o{ FACT : supported_by
    FACT }o--|| SOURCE : from

    CLAIM {
        string id PK
        string text
        string type
        string claimRole
        boolean isCentral
        string_array dependsOn
    }

    CLAIM_VERDICT {
        string id PK
        string claimId FK
        string verdict
        int truthPercentage
        int confidence
        string explanation
        string_array supportingFactIds
        string_array opposingFactIds
        string contestationStatus
        float harmPotential
    }

    FACT {
        string id PK
        string sourceId FK
        string text
        string quote
        string relevance
        boolean supports
        string extractedContext
    }

    SOURCE {
        string id PK
        string name
        string domain
        string url
        float reliabilityScore
        string bias
        string factualReporting
    }

Verdict Generation Flow


flowchart TB
    subgraph Research[Research Phase]
        FACTS[Collected Facts]
        SOURCES[Source Metadata]
    end

    subgraph Analysis[Analysis]
        WEIGHT[Weight Evidence by source reliability]
        CONTEST[Check Contestation doubted vs contested]
        HARM[Assess Harm Potential]
    end

    subgraph Verdict[Verdict Generation]
        CALC[Calculate Truth Percentage]
        MAP[Map to 7-point Scale]
        CONF[Assign Confidence]
    end

    subgraph Output[Result]
        CLAIM_V[Claim Verdict]
        ARTICLE_V[Article Verdict]
    end

    FACTS --> WEIGHT
    SOURCES --> WEIGHT
    WEIGHT --> CONTEST
    CONTEST --> HARM
    HARM --> CALC
    CALC --> MAP
    MAP --> CONF
    CONF --> CLAIM_V
    CLAIM_V --> ARTICLE_V

7-Point Verdict Scale

 Verdict  Truth % Range  Description
 TRUE  86-100%  Claim is well-supported by evidence
 MOSTLY-TRUE  72-85%  Largely accurate with minor caveats
 LEANING-TRUE  58-71%  More evidence supports than contradicts
 MIXED  43-57% (high conf)  Roughly equal evidence both ways
 UNVERIFIED  43-57% (low conf)  Insufficient evidence to determine
 LEANING-FALSE  29-42%  More evidence contradicts than supports
 MOSTLY-FALSE  15-28%  Largely inaccurate
 FALSE  0-14%  Claim is refuted by evidence

Contestation Status

  • Doubted: Evidence is weak, uncertain, or ambiguous
  • Contested: Strong evidence exists on both sides

Source Reliability

Source reliability scores come from external MBFC (Media Bias/Fact Check) bundle:

  • Pre-loaded reliability scores for known sources
  • Configurable via source-reliability.ts