Wiki source code of POC2: Robust Quality & Reliability
Last modified by Robert Schaub on 2025/12/22 13:49
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 | |||
| 7 | |||
| 8 | == 1. Overview == | ||
| 9 | |||
| 10 | 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. | ||
| 11 | |||
| 12 | **Key Innovation:** Complete quality validation pipeline catches all categories of errors | ||
| 13 | |||
| 14 | **What We're Proving:** | ||
| |
1.2 | 15 | |
| |
1.1 | 16 | * All 4 quality gates work together effectively |
| 17 | * Evidence deduplication prevents artificial inflation | ||
| 18 | * System maintains quality at larger scale | ||
| 19 | * Quality metrics dashboard provides actionable insights | ||
| 20 | |||
| 21 | == 2. New Requirements == | ||
| 22 | |||
| 23 | === 2.1 NFR11: Complete Quality Assurance Framework === | ||
| 24 | |||
| 25 | **Add Gates 2 & 3** (POC1 had only Gates 1 & 4) | ||
| 26 | |||
| 27 | ==== Gate 2: Evidence Relevance Validation ==== | ||
| 28 | |||
| 29 | **Purpose:** Ensure AI-linked evidence actually relates to the claim | ||
| 30 | |||
| 31 | **Validation Checks:** | ||
| |
1.2 | 32 | |
| |
1.1 | 33 | 1. **Semantic Similarity:** Cosine similarity between claim and evidence embeddings ≥ 0.6 |
| 34 | 2. **Entity Overlap:** At least 1 shared named entity between claim and evidence | ||
| 35 | 3. **Topic Relevance:** Evidence discusses the claim's subject matter (score ≥ 0.5) | ||
| 36 | |||
| 37 | **Action if Failed:** | ||
| |
1.2 | 38 | |
| |
1.1 | 39 | * Discard irrelevant evidence (don't count it) |
| 40 | * If <2 relevant evidence items remain → "Insufficient Evidence" verdict | ||
| 41 | * Log discarded evidence for quality review | ||
| 42 | |||
| 43 | **Target:** 0% of evidence cited is off-topic | ||
| 44 | |||
| 45 | |||
| 46 | ==== Gate 3: Scenario Coherence Check ==== | ||
| 47 | |||
| 48 | **Purpose:** Validate scenarios are logical, complete, and meaningfully different | ||
| 49 | |||
| 50 | **Validation Checks:** | ||
| |
1.2 | 51 | |
| |
1.1 | 52 | 1. **Completeness:** All required fields populated (assumptions, scope, evidence context) |
| 53 | 2. **Internal Consistency:** Assumptions don't contradict each other (score <0.3) | ||
| 54 | 3. **Distinctiveness:** Scenarios are meaningfully different (similarity <0.8) | ||
| 55 | 4. **Minimum Detail:** At least 1 specific assumption per scenario | ||
| 56 | |||
| 57 | **Action if Failed:** | ||
| |
1.2 | 58 | |
| |
1.1 | 59 | * Merge duplicate scenarios |
| 60 | * Flag contradictory assumptions for review | ||
| 61 | * Reduce confidence score by 20% | ||
| 62 | * Do not publish if <2 distinct scenarios | ||
| 63 | |||
| 64 | **Target:** 0% duplicate scenarios, all scenarios internally consistent | ||
| 65 | |||
| 66 | |||
| 67 | === 2.2 FR54: Evidence Deduplication (NEW) === | ||
| 68 | |||
| 69 | **Priority:** HIGH | ||
| 70 | **Fulfills:** Accurate evidence counting, prevents artificial inflation | ||
| 71 | |||
| 72 | **Purpose:** Prevent counting the same evidence multiple times when cited by different sources | ||
| 73 | |||
| 74 | **Problem:** | ||
| |
1.2 | 75 | |
| |
1.1 | 76 | * Wire services (AP, Reuters) redistribute same content |
| 77 | * Different sites cite the same original study | ||
| 78 | * Aggregators copy primary sources | ||
| 79 | * AKEL might count this as "5 sources" when it's really 1 | ||
| 80 | |||
| 81 | **Solution: Content Fingerprinting** | ||
| |
1.2 | 82 | |
| |
1.1 | 83 | * Generate SHA-256 hash of normalized text |
| 84 | * Detect near-duplicates (≥85% similarity) using fuzzy matching | ||
| 85 | * Track which sources cited each unique piece of evidence | ||
| 86 | * Display provenance chain to user | ||
| 87 | |||
| 88 | **Target:** Duplicate detection >95% accurate, evidence counts reflect reality | ||
| 89 | |||
| 90 | |||
| 91 | === 2.3 NFR13: Quality Metrics Dashboard (Internal) === | ||
| 92 | |||
| 93 | **Priority:** HIGH | ||
| 94 | **Fulfills:** Real-time quality monitoring during development | ||
| 95 | |||
| 96 | **Dashboard Metrics:** | ||
| |
1.2 | 97 | |
| |
1.1 | 98 | * Claim processing statistics |
| 99 | * Gate performance (pass/fail rates for each gate) | ||
| 100 | * Evidence quality metrics | ||
| 101 | * Hallucination rate tracking | ||
| 102 | * Processing performance | ||
| 103 | |||
| 104 | **Target:** Dashboard functional, all metrics tracked, exportable | ||
| 105 | |||
| 106 | |||
| 107 | == 3. Success Criteria == | ||
| 108 | |||
| 109 | **✅ Quality:** | ||
| |
1.2 | 110 | |
| |
1.1 | 111 | * Hallucination rate <5% (target: <3%) |
| 112 | * Average quality rating ≥8.0/10 | ||
| 113 | * 0 critical failures (publishable falsities) | ||
| 114 | * Gates correctly identify >95% of low-quality outputs | ||
| 115 | |||
| 116 | **✅ All 4 Gates Operational:** | ||
| |
1.2 | 117 | |
| |
1.1 | 118 | * Gate 1: Claim validation working |
| 119 | * Gate 2: Evidence relevance filtering working | ||
| 120 | * Gate 3: Scenario coherence checking working | ||
| 121 | * Gate 4: Verdict confidence assessment working | ||
| 122 | |||
| 123 | **✅ Evidence Deduplication:** | ||
| |
1.2 | 124 | |
| |
1.1 | 125 | * Duplicate detection >95% accurate |
| 126 | * Evidence counts reflect reality | ||
| 127 | * Provenance tracked correctly | ||
| 128 | |||
| 129 | **✅ Metrics Dashboard:** | ||
| |
1.2 | 130 | |
| |
1.1 | 131 | * All metrics implemented and tracking |
| 132 | * Dashboard functional and useful | ||
| 133 | * Alerts trigger appropriately | ||
| 134 | |||
| 135 | == 4. Architecture Notes == | ||
| 136 | |||
| 137 | **POC2 Enhanced Architecture:** | ||
| 138 | |||
| 139 | {{code}} | ||
| 140 | Input → AKEL Processing → All 4 Quality Gates → Display | ||
| 141 | (claims + scenarios (1: Claim validation | ||
| 142 | + evidence linking 2: Evidence relevance | ||
| 143 | + verdicts) 3: Scenario coherence | ||
| 144 | 4: Verdict confidence) | ||
| 145 | {{/code}} | ||
| 146 | |||
| 147 | **Key Additions from POC1:** | ||
| |
1.2 | 148 | |
| |
1.1 | 149 | * Scenario generation component |
| 150 | * Evidence deduplication system | ||
| 151 | * Gates 2 & 3 implementation | ||
| 152 | * Quality metrics collection | ||
| 153 | |||
| 154 | **Still Simplified vs. Full System:** | ||
| |
1.2 | 155 | |
| |
1.1 | 156 | * Single AKEL orchestration (not multi-component pipeline) |
| 157 | * No review queue | ||
| 158 | * No federation architecture | ||
| 159 | |||
| |
1.6 | 160 | **See:** [[Architecture>>Test.FactHarbor pre10 V0\.9\.70.Specification.Architecture.WebHome]] for details |
| |
1.1 | 161 | |
| 162 | |||
| 163 | == Related Pages == | ||
| 164 | |||
| |
1.3 | 165 | * [[POC1>>Test.FactHarbor pre10 V0\.9\.70.Roadmap.POC1.WebHome]] - Previous phase |
| |
1.2 | 166 | * [[Beta 0>>Test.FactHarbor pre10 V0\.9\.70.Roadmap.Beta0.WebHome]] - Next phase |
| |
1.5 | 167 | * [[Roadmap Overview>>Test.FactHarbor pre10 V0\.9\.70.Roadmap.WebHome]] |
| |
1.6 | 168 | * [[Architecture>>Test.FactHarbor pre10 V0\.9\.70.Specification.Architecture.WebHome]] |
| |
1.1 | 169 | |
| 170 | **Document Status:** ✅ POC2 Specification Complete - Waiting for POC1 Completion | ||
| 171 | **Version:** V0.9.70 |