Last modified by Robert Schaub on 2025/12/24 09:59

From version 1.1
edited by Robert Schaub
on 2025/12/23 18:19
Change comment: Imported from XAR
To version 2.2
edited by Robert Schaub
on 2025/12/24 09:59
Change comment: Update document after refactoring.

Summary

Details

Page properties
Parent
... ... @@ -1,1 +1,1 @@
1 -Test.FactHarbor.Roadmap.WebHome
1 +Test.FactHarbor V0\.9\.100 incremental.Roadmap.WebHome
Content
... ... @@ -15,6 +15,7 @@
15 15  
16 16  * AKEL can reliably extract factual claims from articles
17 17  * AKEL can generate credible verdicts with proper evidence
18 +* **AKEL can assess article credibility beyond simple claim averaging** (context-aware analysis)
18 18  * Quality gates prevent hallucinations and low-confidence outputs
19 19  * Fully automated approach is viable
20 20  
... ... @@ -40,6 +40,31 @@
40 40  * A/B testing
41 41  * Gates 2 & 3 (Evidence relevance, Scenario coherence)
42 42  
44 +
45 +=== Experimental Features (POC1) ===
46 +
47 +**Context-Aware Analysis** (Approach 1: Single-Pass Holistic)
48 +
49 +**Goal:** Test if AI can detect when an article's overall credibility differs from the average of its claim verdicts (e.g., accurate facts but misleading conclusion).
50 +
51 +**Implementation:**
52 +* Enhanced AI prompt to evaluate logical structure
53 +* AI identifies article's main argument
54 +* AI assesses if conclusion follows from evidence
55 +* Article verdict may differ from claim average
56 +
57 +**Testing:**
58 +* 30-article test set (10 straightforward, 10 misleading, 10 complex)
59 +* Success criteria: ≥70% accuracy on misleading articles
60 +* Marked as experimental - doesn't block POC1 success
61 +
62 +**See:** [[Article Verdict Problem>>Test.FactHarbor.Specification.POC.Article-Verdict-Problem]] for complete analysis
63 +
64 +**Decision:**
65 +* If ≥70% accuracy → ship in POC2
66 +* If 50-70% → try weighted aggregation approach
67 +* If <50% → defer to POC2 with different approach
68 +
43 43  == 3. Requirements ==
44 44  
45 45  === 3.1 NFR11: Quality Assurance Framework (POC1 Lite Version) ===