Skip to Content
Last modified by Robert Schaub on 2025/12/22 14:33
From version 1.2
edited by Robert Schaub
on 2025/12/22 14:32
Change comment: Update document after refactoring.
To version 1.3
edited by Robert Schaub
on 2025/12/22 14:32
Change comment: Renamed back-links.

Summary

Details

Page properties
Content
... ... @@ -1,4 +1,7 @@
1 -= POC1: Core Workflow with Quality Gates = **Phase Goal:** Prove AKEL can produce credible, quality outputs without manual intervention **Success Metric:** <10% hallucination rate, quality gates prevent low-confidence publications == 1. Overview == POC1 validates that the core AKEL workflow (Article → Claims → Verdicts) can produce trustworthy fact-checking analyses automatically. This phase implements **2 critical quality gates** to prevent low-quality outputs from being published. **Key Innovation:** Quality validation BEFORE publication, not after **What We're Proving:**
1 += POC1: Core Workflow with Quality Gates =
2 +
3 + **Phase Goal:** Prove AKEL can produce credible, quality outputs without manual intervention **Success Metric:** <10% hallucination rate, quality gates prevent low-confidence publications == 1. Overview == POC1 validates that the core AKEL workflow (Article → Claims → Verdicts) can produce trustworthy fact-checking analyses automatically. This phase implements **2 critical quality gates** to prevent low-quality outputs from being published. **Key Innovation:** Quality validation BEFORE publication, not after **What We're Proving:**
4 +
2 2  * AKEL can reliably extract factual claims from articles
3 3  * AKEL can generate credible verdicts with proper evidence
4 4  * Quality gates prevent hallucinations and low-confidence outputs
... ... @@ -15,29 +15,28 @@
15 15  * Security hardening
16 16  * A/B testing
17 17  * Gates 2 & 3 (Evidence relevance, Scenario coherence) == 3. Requirements == === 3.1 NFR11: Quality Assurance Framework (POC1 Lite Version) === **Priority:** CRITICAL - Core POC1 Requirement **Fulfills:** AI safety, credibility, prevents embarrassing failures **Specification:** AKEL must validate outputs before displaying to users. POC1 implements a **2-gate subset** of the full NFR11 framework. ==== Gate 1: Claim Validation ==== **Purpose:** Ensure extracted claims are factual assertions, not opinions or predictions **Validation Checks:**
21 +
18 18  1. **Factual Statement Test:** Can this be verified with evidence?
19 19  2. **Opinion Detection:** Contains hedging language? ("I think", "probably", "best", "worst")
20 20  3. **Specificity Score:** Contains concrete details? (names, numbers, dates, locations)
21 21  4. **Future Prediction Test:** Makes claims about future events? **Pass Criteria:**
22 -{{code}}
23 -- isFactual: true
26 +{{code}}- isFactual: true
24 24  - opinionScore: ≤ 0.3
25 25  - specificityScore: ≥ 0.3
26 -- claimType: FACTUAL
27 -{{/code}} **Action if Failed:**
29 +- claimType: FACTUAL{{/code}} **Action if Failed:**
30 +
28 28  * Flag as "Non-verifiable: Opinion/Prediction/Ambiguous"
29 29  * Do NOT generate scenarios or verdicts
30 30  * Display explanation to user **Target:** 0% opinion statements processed as facts ==== Gate 4: Verdict Confidence Assessment ==== **Purpose:** Only publish verdicts with sufficient evidence and confidence **Validation Checks:**
34 +
31 31  1. **Evidence Count:** Minimum 2 independent sources
32 32  2. **Source Quality:** Average reliability ≥ 0.6 (on 0-1 scale)
33 33  3. **Evidence Agreement:** % supporting vs. contradicting ≥ 0.6
34 34  4. **Uncertainty Factors:** Count of hedging statements in reasoning **Confidence Tiers:**
35 -{{code}}
36 -HIGH (80-100%): - ≥3 sources - ≥0.7 average quality - ≥80% agreement MEDIUM (50-79%): - ≥2 sources - ≥0.6 average quality - ≥60% agreement LOW (0-49%): - ≥2 sources BUT low quality/agreement INSUFFICIENT: - <2 sources → DO NOT PUBLISH
37 -{{/code}} **POC1 Publication Rule:**
39 +{{code}}HIGH (80-100%): - ≥3 sources - ≥0.7 average quality - ≥80% agreement MEDIUM (50-79%): - ≥2 sources - ≥0.6 average quality - ≥60% agreement LOW (0-49%): - ≥2 sources BUT low quality/agreement INSUFFICIENT: - <2 sources → DO NOT PUBLISH{{/code}} **POC1 Publication Rule:**
40 +
38 38  * Minimum **MEDIUM** confidence required
39 -* Blocked verdicts show "Insufficient Evidence" message **Target:** 0% verdicts published with <2 sources === 3.2 Modified FR7: Automated Verdicts (Enhanced) === **Enhancement for POC1:** After AKEL generates a verdict, it must pass through the quality validation pipeline: {{code}}
40 -AKEL Workflow (POC1): 1. Extract claims from article ↓
42 +* Blocked verdicts show "Insufficient Evidence" message **Target:** 0% verdicts published with <2 sources === 3.2 Modified FR7: Automated Verdicts (Enhanced) === **Enhancement for POC1:** After AKEL generates a verdict, it must pass through the quality validation pipeline: {{code}}AKEL Workflow (POC1): 1. Extract claims from article ↓
41 41  2. [GATE 1] Validate each claim is fact-checkable ↓ (pass claims only)
42 42  3. Generate verdicts for each claim ↓
43 43  4. [GATE 4] Validate verdict has sufficient evidence ↓ (pass verdicts only)
... ... @@ -44,15 +44,12 @@
44 44  5. Display to user Failed claims/verdicts:
45 45  - Store in database with failure reason
46 46  - Display explanatory message to user
47 -- Log for quality metrics tracking
48 -{{/code}} **Updated Verdict States:**
49 +- Log for quality metrics tracking{{/code}} **Updated Verdict States:**
49 49  * PUBLISHED - Passed all gates
50 50  * INSUFFICIENT_EVIDENCE - Failed Gate 4
51 51  * NON_FACTUAL_CLAIM - Failed Gate 1
52 52  * PROCESSING - In progress
53 -* ERROR - System failure === 3.3 Modified FR4: Analysis Summary (Enhanced) === **Enhancement for POC1:** Analysis Summary must now display quality metadata: {{code}}
54 -Analysis Summary: Total Claims Found: 5 Verifiable Claims: 3 Non-verifiable (Opinion): 1 Non-verifiable (Prediction): 1 Verdicts Generated: 3 High Confidence: 1 Medium Confidence: 2 Insufficient Evidence: 0 Evidence Sources: 12 total Average Source Quality: 0.73 Quality Score: 8.5/10
55 -{{/code}} == 4. Success Criteria == POC1 is considered **SUCCESSFUL** if: **✅ Functional:**
54 +* ERROR - System failure === 3.3 Modified FR4: Analysis Summary (Enhanced) === **Enhancement for POC1:** Analysis Summary must now display quality metadata: {{code}}Analysis Summary: Total Claims Found: 5 Verifiable Claims: 3 Non-verifiable (Opinion): 1 Non-verifiable (Prediction): 1 Verdicts Generated: 3 High Confidence: 1 Medium Confidence: 2 Insufficient Evidence: 0 Evidence Sources: 12 total Average Source Quality: 0.73 Quality Score: 8.5/10{{/code}} == 4. Success Criteria == POC1 is considered **SUCCESSFUL** if: **✅ Functional:**
56 56  * Processes diverse test articles without crashes
57 57  * Generates verdicts for all factual claims
58 58  * Blocks all non-factual claims (0% pass through)
... ... @@ -70,18 +70,13 @@
70 70  * Clear path to POC2 defined == 5. Decision Gates == **POC1 → POC2 Decision:** * **IF** hallucination rate >10% → Pause, improve prompts before POC2
71 71  * **IF** majority of claims non-processable → Rethink claim extraction approach
72 72  * **IF** quality gates too strict (excessive blocking) → Adjust thresholds
73 -* **IF** quality gates too loose (hallucinations pass) → Tighten criteria **Only proceed to POC2 if all success criteria met** == 6. Architecture Notes == **POC1 Simplified Architecture:** {{code}}
74 -User Input → AKEL Processing → Quality Gates → Display (claim extraction (Gates 1 & 4) + verdicts)
75 -{{/code}} **vs. Full System (Future):** {{code}}
76 -Input → Claim Extractor → Scenario Generator → Evidence Linker → Verdict Generator → All 4 Gates → Review Queue → Publication
77 -{{/code}} **POC1 Acceptable Simplifications:**
72 +* **IF** quality gates too loose (hallucinations pass) → Tighten criteria **Only proceed to POC2 if all success criteria met** == 6. Architecture Notes == **POC1 Simplified Architecture:** {{code}}User Input → AKEL Processing → Quality Gates → Display (claim extraction (Gates 1 & 4) + verdicts){{/code}} **vs. Full System (Future):** {{code}}Input → Claim Extractor → Scenario Generator → Evidence Linker → Verdict Generator → All 4 Gates → Review Queue → Publication{{/code}} **POC1 Acceptable Simplifications:**
78 78  * Single AKEL call (not multi-component pipeline)
79 79  * No scenarios (implicit in verdicts)
80 80  * Basic evidence linking
81 81  * 2 gates instead of 4
82 82  * No review queue **See:** [[Architecture>>Test.FactHarbor.Specification.Architecture.WebHome]] for details == Related Pages == * [[Roadmap Overview>>Test.FactHarbor.Roadmap.WebHome]] - All phases
83 -* [[POC2 Requirements>>Test.FactHarbor.Roadmap.POC2.WebHome]] - Next phase
78 +* [[POC2 Requirements>>Test.FactHarbor pre12 V0\.9\.70.Roadmap.POC2.WebHome]] - Next phase
84 84  * [[Requirements>>Test.FactHarbor.Specification.Requirements.WebHome]] - Full system requirements
85 85  * [[Architecture>>Test.FactHarbor.Specification.Architecture.WebHome]] - System architecture
86 86  * [[NFR11 Full Specification>>Test.FactHarbor.Specification.Requirements.WebHome#NFR11]] - Complete quality framework **Document Status:** ✅ POC1 Specification Complete - Ready for Implementation **Version:** V0.9.70
87 -