Wiki source code of POC2: Robust Quality & Reliability
Version 1.5 by Robert Schaub on 2025/12/21 13:38
Hide last authors
| author | version | line-number | content |
|---|---|---|---|
| |
1.1 | 1 | = POC2: Robust Quality & Reliability = |
| 2 | |||
| 3 | **Phase Goal:** Prove AKEL produces high-quality outputs consistently at scale | ||
| 4 | |||
| 5 | **Success Metric:** <5% hallucination rate, all 4 quality gates operational | ||
| 6 | |||
| |
1.3 | 7 | ---- |
| |
1.1 | 8 | |
| 9 | == 1. Overview == | ||
| 10 | |||
| 11 | POC2 extends POC1 by implementing the full quality assurance framework (all 4 gates), adding evidence deduplication, and processing significantly more test articles to validate system reliability at scale. | ||
| 12 | |||
| 13 | **Key Innovation:** Complete quality validation pipeline catches all categories of errors | ||
| 14 | |||
| 15 | **What We're Proving:** | ||
| |
1.2 | 16 | |
| |
1.1 | 17 | * All 4 quality gates work together effectively |
| 18 | * Evidence deduplication prevents artificial inflation | ||
| 19 | * System maintains quality at larger scale | ||
| 20 | * Quality metrics dashboard provides actionable insights | ||
| 21 | |||
| |
1.3 | 22 | ---- |
| |
1.1 | 23 | |
| 24 | == 2. New Requirements == | ||
| 25 | |||
| 26 | === 2.1 NFR11: Complete Quality Assurance Framework === | ||
| 27 | |||
| 28 | **Add Gates 2 & 3** (POC1 had only Gates 1 & 4) | ||
| 29 | |||
| 30 | ==== Gate 2: Evidence Relevance Validation ==== | ||
| 31 | |||
| 32 | **Purpose:** Ensure AI-linked evidence actually relates to the claim | ||
| 33 | |||
| 34 | **Validation Checks:** | ||
| |
1.2 | 35 | |
| |
1.1 | 36 | 1. **Semantic Similarity:** Cosine similarity between claim and evidence embeddings ≥ 0.6 |
| 37 | 2. **Entity Overlap:** At least 1 shared named entity between claim and evidence | ||
| 38 | 3. **Topic Relevance:** Evidence discusses the claim's subject matter (score ≥ 0.5) | ||
| 39 | |||
| 40 | **Action if Failed:** | ||
| |
1.2 | 41 | |
| |
1.1 | 42 | * Discard irrelevant evidence (don't count it) |
| 43 | * If <2 relevant evidence items remain → "Insufficient Evidence" verdict | ||
| 44 | * Log discarded evidence for quality review | ||
| 45 | |||
| 46 | **Target:** 0% of evidence cited is off-topic | ||
| 47 | |||
| |
1.3 | 48 | ---- |
| |
1.1 | 49 | |
| 50 | ==== Gate 3: Scenario Coherence Check ==== | ||
| 51 | |||
| 52 | **Purpose:** Validate scenarios are logical, complete, and meaningfully different | ||
| 53 | |||
| 54 | **Validation Checks:** | ||
| |
1.2 | 55 | |
| |
1.1 | 56 | 1. **Completeness:** All required fields populated (assumptions, scope, evidence context) |
| 57 | 2. **Internal Consistency:** Assumptions don't contradict each other (score <0.3) | ||
| 58 | 3. **Distinctiveness:** Scenarios are meaningfully different (similarity <0.8) | ||
| 59 | 4. **Minimum Detail:** At least 1 specific assumption per scenario | ||
| 60 | |||
| 61 | **Action if Failed:** | ||
| |
1.2 | 62 | |
| |
1.1 | 63 | * Merge duplicate scenarios |
| 64 | * Flag contradictory assumptions for review | ||
| 65 | * Reduce confidence score by 20% | ||
| 66 | * Do not publish if <2 distinct scenarios | ||
| 67 | |||
| 68 | **Target:** 0% duplicate scenarios, all scenarios internally consistent | ||
| 69 | |||
| |
1.3 | 70 | ---- |
| |
1.1 | 71 | |
| 72 | === 2.2 FR54: Evidence Deduplication (NEW) === | ||
| 73 | |||
| 74 | **Priority:** HIGH | ||
| 75 | **Fulfills:** Accurate evidence counting, prevents artificial inflation | ||
| 76 | |||
| 77 | **Purpose:** Prevent counting the same evidence multiple times when cited by different sources | ||
| 78 | |||
| 79 | **Problem:** | ||
| |
1.2 | 80 | |
| |
1.1 | 81 | * Wire services (AP, Reuters) redistribute same content |
| 82 | * Different sites cite the same original study | ||
| 83 | * Aggregators copy primary sources | ||
| 84 | * AKEL might count this as "5 sources" when it's really 1 | ||
| 85 | |||
| 86 | **Solution: Content Fingerprinting** | ||
| |
1.2 | 87 | |
| |
1.1 | 88 | * Generate SHA-256 hash of normalized text |
| 89 | * Detect near-duplicates (≥85% similarity) using fuzzy matching | ||
| 90 | * Track which sources cited each unique piece of evidence | ||
| 91 | * Display provenance chain to user | ||
| 92 | |||
| 93 | **Target:** Duplicate detection >95% accurate, evidence counts reflect reality | ||
| 94 | |||
| |
1.3 | 95 | ---- |
| |
1.1 | 96 | |
| 97 | === 2.3 NFR13: Quality Metrics Dashboard (Internal) === | ||
| 98 | |||
| 99 | **Priority:** HIGH | ||
| 100 | **Fulfills:** Real-time quality monitoring during development | ||
| 101 | |||
| 102 | **Dashboard Metrics:** | ||
| |
1.2 | 103 | |
| |
1.1 | 104 | * Claim processing statistics |
| 105 | * Gate performance (pass/fail rates for each gate) | ||
| 106 | * Evidence quality metrics | ||
| 107 | * Hallucination rate tracking | ||
| 108 | * Processing performance | ||
| 109 | |||
| 110 | **Target:** Dashboard functional, all metrics tracked, exportable | ||
| 111 | |||
| |
1.3 | 112 | ---- |
| |
1.1 | 113 | |
| 114 | == 3. Success Criteria == | ||
| 115 | |||
| 116 | **✅ Quality:** | ||
| |
1.2 | 117 | |
| |
1.1 | 118 | * Hallucination rate <5% (target: <3%) |
| 119 | * Average quality rating ≥8.0/10 | ||
| 120 | * 0 critical failures (publishable falsities) | ||
| 121 | * Gates correctly identify >95% of low-quality outputs | ||
| 122 | |||
| 123 | **✅ All 4 Gates Operational:** | ||
| |
1.2 | 124 | |
| |
1.1 | 125 | * Gate 1: Claim validation working |
| 126 | * Gate 2: Evidence relevance filtering working | ||
| 127 | * Gate 3: Scenario coherence checking working | ||
| 128 | * Gate 4: Verdict confidence assessment working | ||
| 129 | |||
| 130 | **✅ Evidence Deduplication:** | ||
| |
1.2 | 131 | |
| |
1.1 | 132 | * Duplicate detection >95% accurate |
| 133 | * Evidence counts reflect reality | ||
| 134 | * Provenance tracked correctly | ||
| 135 | |||
| 136 | **✅ Metrics Dashboard:** | ||
| |
1.2 | 137 | |
| |
1.1 | 138 | * All metrics implemented and tracking |
| 139 | * Dashboard functional and useful | ||
| 140 | * Alerts trigger appropriately | ||
| 141 | |||
| |
1.3 | 142 | ---- |
| |
1.1 | 143 | |
| 144 | == 4. Architecture Notes == | ||
| 145 | |||
| 146 | **POC2 Enhanced Architecture:** | ||
| 147 | |||
| 148 | {{code}} | ||
| 149 | Input → AKEL Processing → All 4 Quality Gates → Display | ||
| 150 | (claims + scenarios (1: Claim validation | ||
| 151 | + evidence linking 2: Evidence relevance | ||
| 152 | + verdicts) 3: Scenario coherence | ||
| 153 | 4: Verdict confidence) | ||
| 154 | {{/code}} | ||
| 155 | |||
| 156 | **Key Additions from POC1:** | ||
| |
1.2 | 157 | |
| |
1.1 | 158 | * Scenario generation component |
| 159 | * Evidence deduplication system | ||
| 160 | * Gates 2 & 3 implementation | ||
| 161 | * Quality metrics collection | ||
| 162 | |||
| 163 | **Still Simplified vs. Full System:** | ||
| |
1.2 | 164 | |
| |
1.1 | 165 | * Single AKEL orchestration (not multi-component pipeline) |
| 166 | * No review queue | ||
| 167 | * No federation architecture | ||
| 168 | |||
| 169 | **See:** [[Architecture>>Test.FactHarbor.Specification.Architecture.WebHome]] for details | ||
| 170 | |||
| |
1.3 | 171 | ---- |
| |
1.1 | 172 | |
| 173 | == Related Pages == | ||
| 174 | |||
| |
1.3 | 175 | * [[POC1>>FactHarbor.Archive.FactHarbor delta for V0\.9\.70.Roadmap.POC1.WebHome]] - Previous phase |
| |
1.2 | 176 | * [[Beta 0>>FactHarbor.Archive.FactHarbor delta for V0\.9\.70.Roadmap.Beta0.WebHome]] - Next phase |
| |
1.5 | 177 | * [[Roadmap Overview>>FactHarbor.Archive.FactHarbor delta for V0\.9\.70.Roadmap.WebHome]] |
| |
1.1 | 178 | * [[Architecture>>Test.FactHarbor.Specification.Architecture.WebHome]] |
| 179 | |||
| |
1.3 | 180 | ---- |
| |
1.1 | 181 | |
| 182 | **Document Status:** ✅ POC2 Specification Complete - Waiting for POC1 Completion | ||
| 183 | **Version:** V0.9.70 |