Skip to Content
Last modified by Robert Schaub on 2026/02/08 08:12
From version 6.1
edited by Robert Schaub
on 2026/01/02 10:06
Change comment: There is no comment for this version
To version 8.1
edited by Robert Schaub
on 2026/01/02 10:13
Change comment: There is no comment for this version

Summary

Details

Page properties
Content
... ... @@ -1,4 +1,4 @@
1 -= FactHarbor POC1 Architecture Analysis =
1 += FactHarbor POC1 Architecture Analysis 1.Jan.26 =
2 2  
3 3  **Version:** 2.6.17
4 4  **Analysis Date:** January 2026
... ... @@ -94,8 +94,121 @@
94 94  
95 95  == 2. ERD Data Model (Current POC1 Implementation) ==
96 96  
97 +**Data Objects ERD**
98 +
97 97  {{mermaid}}
98 98  erDiagram
101 + ARTICLE ||--o{ CLAIM : "contains"
102 + ARTICLE ||--|| ARTICLE_VERDICT : "has"
103 + CLAIM ||--|| CLAIM_VERDICT : "has"
104 + CLAIM ||--o{ CLAIM : "depends on"
105 + CLAIM_VERDICT }o--o{ EVIDENCE : "supported by"
106 + SOURCE ||--o{ EVIDENCE : "provides"
107 + ARTICLE ||--o{ SOURCE : "references"
108 +
109 + ARTICLE {
110 + string id PK "Unique identifier (job ID)"
111 + string inputType "text | url"
112 + string inputValue "Original URL or text"
113 + string articleThesis "Main argument/thesis"
114 + string detectedInputType "question | claim | article"
115 + boolean isQuestion "True if input is a question"
116 + datetime createdAt "Analysis timestamp"
117 + datetime updatedAt "Last update"
118 + json distinctProceedings "Legal proceedings if any"
119 + boolean hasMultipleProceedings "Multi-proceeding flag"
120 + string proceedingContext "Context for proceedings"
121 + json logicalFallacies "Detected fallacies array"
122 + boolean isPseudoscience "Pseudoscience detection"
123 + string_array pseudoscienceCategories "Categories if detected"
124 + int llmCalls "Total LLM API calls"
125 + json searchQueries "All search queries performed"
126 + string schemaVersion "e.g. 2.6.17"
127 + }
128 +
129 + CLAIM {
130 + string id PK "SC1, SC2, C1, etc."
131 + string articleId FK "Parent article"
132 + string text "The claim statement"
133 + string type "legal | procedural | factual | evaluative"
134 + string claimRole "attribution | source | timing | core"
135 + string_array dependsOn "IDs of prerequisite claims"
136 + string_array keyEntities "Named entities in claim"
137 + boolean isCentral "Is this a central claim?"
138 + string relatedProceedingId "Linked proceeding if any"
139 + int startOffset "Position in original text"
140 + int endOffset "End position in original text"
141 + string approximatePosition "Descriptive position"
142 + }
143 +
144 + CLAIM_VERDICT {
145 + string id PK "Same as claim ID"
146 + string claimId FK "Reference to claim"
147 + string llmVerdict "WELL-SUPPORTED | PARTIALLY-SUPPORTED | UNCERTAIN | REFUTED"
148 + string verdict "True | Mostly True | Leaning True | Unverified | Leaning False | Mostly False | False"
149 + int confidence "0-100 LLM confidence"
150 + int truthPercentage "0-100 calibrated truth score"
151 + string riskTier "A (high) | B (medium) | C (low)"
152 + string reasoning "Explanation of verdict"
153 + string_array supportingFactIds "Evidence IDs supporting this"
154 + boolean dependencyFailed "True if prerequisite failed"
155 + string_array failedDependencies "Which deps failed"
156 + string highlightColor "green | light-green | yellow | orange | dark-orange | red | dark-red"
157 + boolean isPseudoscience "Pseudoscience flag"
158 + string escalationReason "Why verdict was escalated"
159 + }
160 +
161 + ARTICLE_VERDICT {
162 + string id PK "Same as article ID"
163 + string articleId FK "Reference to article"
164 + string llmArticleVerdict "Original LLM verdict"
165 + int llmArticleConfidence "Original LLM confidence"
166 + string articleVerdict "True | Mostly True | Leaning True | Unverified | Leaning False | Mostly False | False"
167 + int articleTruthPercentage "0-100 calibrated score"
168 + string articleVerdictReason "Why verdict differs from claims avg"
169 + int claimsAverageTruthPercentage "Average of claim verdicts"
170 + string claimsAverageVerdict "7-point average verdict"
171 + int claimsTotal "Total claims analyzed"
172 + int claimsSupported "Claims with truth >= 72%"
173 + int claimsUncertain "Claims with truth 43-71%"
174 + int claimsRefuted "Claims with truth < 43%"
175 + int centralClaimsTotal "Number of central claims"
176 + int centralClaimsSupported "Central claims supported"
177 + }
178 +
179 + EVIDENCE {
180 + string id PK "S1-F1, S1-F2 format"
181 + string sourceId FK "Reference to source"
182 + string claimId FK "Optional: specific claim this supports"
183 + string fact "The factual statement extracted"
184 + string category "legal_provision | evidence | expert_quote | statistic | event | criticism"
185 + string specificity "high | medium"
186 + string sourceExcerpt "Original text excerpt"
187 + string relatedProceedingId "Linked proceeding if any"
188 + boolean isContestedClaim "Is this a contested assertion"
189 + string claimSource "Who made contested claim"
190 + }
191 +
192 + SOURCE {
193 + string id PK "S1, S2, etc."
194 + string articleId FK "Parent article"
195 + string url "Full URL"
196 + string title "Page/document title"
197 + string domain "Extracted domain"
198 + int trackRecordScore "0-100 reliability score or null"
199 + string fullText "Extracted content"
200 + datetime fetchedAt "When content was fetched"
201 + string category "news | academic | government | legal"
202 + boolean fetchSuccess "True if fetch succeeded"
203 + string searchQuery "Which query found this"
204 + string mimeType "text/html | application/pdf"
205 + }
206 +{{/mermaid}}
207 +
208 +**Data Usage ERD**
209 +
210 +{{mermaid}}
211 +erDiagram
99 99   JOB ||--o{ JOB_EVENT : "has"
100 100   JOB ||--|| ANALYSIS_RESULT : "produces"
101 101   ANALYSIS_RESULT ||--o{ CLAIM_VERDICT : "contains"