Changes for page FactHarbor POC1 Architecture Analysis 1.Jan.26

Summary

• Page properties (2 modified, 0 added, 0 removed)

Details

Page properties

Title

...	...	@@ -1,1 +1,1 @@
1		-FactHarbor POC1 Architecture Analysis
	1	+POC1 Architecture Analysis - 1.Jan.26

Content

...	...	@@ -1,5 +1,6 @@
1		-= FactHarbor POC1 Architecture Analysis 1.Jan.26 =
	1	+= FactHarbor POC1 Architecture Analysis =
2	2
	3	+
3	3	**Version:** 2.6.17
4	4	**Analysis Date:** January 2026
5	5	**Document Purpose:** Technical diagrams, gap analysis, and optimization recommendations
...	...	@@ -92,123 +92,12 @@
92	92
93	93	----
94	94
	96	+
95	95	== 2. ERD Data Model (Current POC1 Implementation) ==
96	96
97		-**Data Objects ERD**
98	98
99	99	{{mermaid}}
100	100	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
212	212	JOB ||--o{ JOB_EVENT : "has"
213	213	JOB ||--|| ANALYSIS_RESULT : "produces"
214	214	ANALYSIS_RESULT ||--o{ CLAIM_VERDICT : "contains"
...	...	@@ -298,8 +298,10 @@
298	298
299	299	----
300	300
	191	+
301	301	== 3. Overall Architecture with Interactions ==
302	302
	194	+
303	303	{{mermaid}}
304	304	flowchart TB
305	305	subgraph Client["🖥️ Client Layer"]
...	...	@@ -395,10 +395,14 @@
395	395
396	396	----
397	397
	290	+
398	398	== 4. Specification vs Implementation Gap Analysis ==
399	399
	293	+
	294	+
400	400	=== 4.1 Data Model Gaps ===
401	401
	297	+
402	402	| Specification Entity | POC1 Status | Gap Description |
403	403	|-|-|-|
404	404	| **Claim** | ⚠️ Partial | No persistent storage; claims exist only in JSON result. Missing: `status`, `confidence_score`, `risk_score`, `completeness_score`, `version`, `views`, `edit_count` |
...	...	@@ -426,6 +426,7 @@
426	426
427	427	=== 4.3 Architecture Gaps ===
428	428
	325	+
429	429	| Spec Requirement | POC1 Status | Gap Description |
430	430	| |-|-|
431	431	| **Three-Layer Architecture** | ✅ Implemented | Interface (Next.js) → Processing (AKEL) → Data (SQLite) |
...	...	@@ -438,6 +438,7 @@
438	438
439	439	=== 4.4 Publication & Review Gaps ===
440	440
	338	+
441	441	| Spec Feature | POC1 Status | Gap Description |
442	442	| |-|-|
443	443	| **Risk Tier Publication Rules** | ❌ Missing | All results published immediately regardless of tier |
...	...	@@ -447,10 +447,14 @@
447	447
448	448	----
449	449
	348	+
450	450	== 5. Optimization Recommendations ==
451	451
	351	+
	352	+
452	452	=== 5.1 Cost Optimizations ===
453	453
	355	+
454	454	{{mermaid}}
455	455	pie title Current LLM Cost Distribution (Estimated per Analysis)
456	456	"Step 1: Understand" : 15
...	...	@@ -468,6 +468,7 @@
468	468
469	469	=== 5.2 Timing Optimizations ===
470	470
	373	+
471	471	{{mermaid}}
472	472	gantt
473	473	title Current Analysis Timeline (Typical)
...	...	@@ -503,6 +503,7 @@
503	503
504	504	=== 5.3 Priority Recommendations ===
505	505
	409	+
506	506	1. **HIGH PRIORITY - Implement Claim Caching**
507	507	- Cache claim verdicts by content hash
508	508	- Reduces costs for repeated/similar claims
...	...	@@ -520,10 +520,14 @@
520	520
521	521	----
522	522
	427	+
523	523	== 6. Separated Verdict Architecture Proposal ==
524	524
	430	+
	431	+
525	525	=== 6.1 Current Architecture ===
526	526
	434	+
527	527	{{mermaid}}
528	528	flowchart LR
529	529	subgraph Current["Current: Monolithic Analysis"]
...	...	@@ -539,8 +539,10 @@
539	539	- No caching of individual claim verdicts
540	540	- Article verdict tightly coupled to claim extraction
541	541
	450	+
542	542	=== 6.2 Proposed Separated Architecture ===
543	543
	453	+
544	544	{{mermaid}}
545	545	flowchart TB
546	546	subgraph Input["Input Processing"]
...	...	@@ -593,8 +593,10 @@
593	593	class CONTEXT,ARTICLE_VERDICT dynamic
594	594	{{/mermaid}}
595	595
	506	+
596	596	=== 6.3 Benefits Analysis ===
597	597
	509	+
598	598	| Benefit | Impact | Rationale |
599	599	|-| |-|
600	600	| **Cost Reduction** | 40-70% for repeated claims | Many articles share common claims (e.g., "COVID vaccines are safe") |
...	...	@@ -642,8 +642,11 @@
642	642
643	643	----
644	644
	557	+
645	645	== 7. Summary ==
646	646
	560	+
	561	+
647	647	=== Current State ===
648	648
649	649	- POC1 implements core AKEL pipeline successfully
...	...	@@ -651,6 +651,7 @@
651	651	- Multiple LLM providers supported
652	652	- No persistent claim storage or caching
653	653
	569	+
654	654	=== Key Gaps from Specification ===
655	655
656	656	- No scenario extraction
...	...	@@ -659,6 +659,7 @@
659	659	- No source track record updates
660	660	- No review queue
661	661
	578	+
662	662	=== Recommended Next Steps ===
663	663
664	664	1. Implement claim caching layer