Changes for page POC1: Core Workflow with Quality Gates
Last modified by Robert Schaub on 2025/12/24 18:26
From version 3.2
edited by Robert Schaub
on 2025/12/24 18:26
on 2025/12/24 18:26
Change comment:
Update document after refactoring.
Summary
-
Page properties (2 modified, 0 added, 0 removed)
Details
- Page properties
-
- Parent
-
... ... @@ -1,1 +1,1 @@ 1 -Test.FactHarbor V0\.9\.103.Roadmap.WebHome1 +Test.FactHarbor.Roadmap.WebHome - Content
-
... ... @@ -4,6 +4,7 @@ 4 4 5 5 **Success Metric:** <10% hallucination rate, quality gates prevent low-confidence publications 6 6 7 + 7 7 == 1. Overview == 8 8 9 9 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. ... ... @@ -40,6 +40,7 @@ 40 40 * A/B testing 41 41 * Gates 2 & 3 (Evidence relevance, Scenario coherence) 42 42 44 + 43 43 === Experimental Features (POC1) === 44 44 45 45 **Context-Aware Analysis** (Approach 1: Single-Pass Holistic) ... ... @@ -57,7 +57,7 @@ 57 57 * Success criteria: ≥70% accuracy on misleading articles 58 58 * Marked as experimental - doesn't block POC1 success 59 59 60 -**See:** [[Article Verdict Problem>>FactHarbor.Specification.POC.Article-Verdict-Problem]] for complete analysis 62 +**See:** [[Article Verdict Problem>>Test.FactHarbor.Specification.POC.Article-Verdict-Problem]] for complete analysis 61 61 62 62 **Decision:** 63 63 * If ≥70% accuracy → ship in POC2 ... ... @@ -68,7 +68,7 @@ 68 68 69 69 === 3.1 NFR11: Quality Assurance Framework (POC1 Lite Version) === 70 70 71 -**Importance:** CRITICAL - Core POC1 Requirement 73 +**Importance:** CRITICAL - Core POC1 Requirement 72 72 **Fulfills:** AI safety, credibility, prevents embarrassing failures 73 73 74 74 **Specification:** ... ... @@ -100,6 +100,7 @@ 100 100 101 101 **Target:** 0% opinion statements processed as facts 102 102 105 + 103 103 ==== Gate 4: Verdict Confidence Assessment ==== 104 104 105 105 **Purpose:** Only publish verdicts with sufficient evidence and confidence ... ... @@ -113,20 +113,20 @@ 113 113 114 114 **Confidence Tiers:** 115 115 {{code}}HIGH (80-100%): 116 - - ≥3 sources 117 - - ≥0.7 average quality 118 - - ≥80% agreement 119 - 119 + - ≥3 sources 120 + - ≥0.7 average quality 121 + - ≥80% agreement 122 + 120 120 MEDIUM (50-79%): 121 - - ≥2 sources 122 - - ≥0.6 average quality 123 - - ≥60% agreement 124 - 124 + - ≥2 sources 125 + - ≥0.6 average quality 126 + - ≥60% agreement 127 + 125 125 LOW (0-49%): 126 - - ≥2 sources BUT low quality/agreement 127 - 129 + - ≥2 sources BUT low quality/agreement 130 + 128 128 INSUFFICIENT: 129 - - <2 sources → DO NOT PUBLISH{{/code}} 132 + - <2 sources → DO NOT PUBLISH{{/code}} 130 130 131 131 **POC1 Publication Rule:** 132 132 ... ... @@ -135,6 +135,7 @@ 135 135 136 136 **Target:** 0% verdicts published with <2 sources 137 137 141 + 138 138 === 3.2 Modified FR7: Automated Verdicts (Enhanced) === 139 139 140 140 **Enhancement for POC1:** ... ... @@ -145,13 +145,13 @@ 145 145 AKEL Workflow (POC1): 146 146 147 147 1. Extract claims from article 148 - ↓ 152 + ↓ 149 149 2. [GATE 1] Validate each claim is fact-checkable 150 - ↓ (pass claims only) 154 + ↓ (pass claims only) 151 151 3. Generate verdicts for each claim 152 - ↓ 156 + ↓ 153 153 4. [GATE 4] Validate verdict has sufficient evidence 154 - ↓ (pass verdicts only) 158 + ↓ (pass verdicts only) 155 155 5. Display to user 156 156 157 157 Failed claims/verdicts: ... ... @@ -176,22 +176,23 @@ 176 176 177 177 {{code}} 178 178 Analysis Summary: 179 - Total Claims Found: 5 180 - Verifiable Claims: 3 181 - Non-verifiable (Opinion): 1 182 - Non-verifiable (Prediction): 1 183 - 184 - Verdicts Generated: 3 185 - High Confidence: 1 186 - Medium Confidence: 2 187 - Insufficient Evidence: 0 188 - 189 - Evidence Sources: 12 total 190 - Average Source Quality: 0.73 191 - 192 - Quality Score: 8.5/10 183 + Total Claims Found: 5 184 + Verifiable Claims: 3 185 + Non-verifiable (Opinion): 1 186 + Non-verifiable (Prediction): 1 187 + 188 + Verdicts Generated: 3 189 + High Confidence: 1 190 + Medium Confidence: 2 191 + Insufficient Evidence: 0 192 + 193 + Evidence Sources: 12 total 194 + Average Source Quality: 0.73 195 + 196 + Quality Score: 8.5/10 193 193 {{/code}} 194 194 199 + 195 195 == 4. Success Criteria == 196 196 197 197 POC1 is considered **SUCCESSFUL** if: ... ... @@ -234,6 +234,7 @@ 234 234 235 235 **Only proceed to POC2 if all success criteria met** 236 236 242 + 237 237 == 6. Architecture Notes == 238 238 239 239 **POC1 Simplified Architecture:** ... ... @@ -240,8 +240,8 @@ 240 240 241 241 {{code}} 242 242 User Input → AKEL Processing → Quality Gates → Display 243 - (claim extraction (Gates 1 & 4) 244 - + verdicts) 249 + (claim extraction (Gates 1 & 4) 250 + + verdicts) 245 245 {{/code}} 246 246 247 247 **vs. Full System (Future):** ... ... @@ -259,15 +259,16 @@ 259 259 * 2 gates instead of 4 260 260 * No review queue 261 261 262 -**See:** [[Architecture>>FactHarbor pre10 V0\.9\.70.Specification.Architecture.WebHome]] for details 268 +**See:** [[Architecture>>Test.FactHarbor pre10 V0\.9\.70.Specification.Architecture.WebHome]] for details 263 263 270 + 264 264 == Related Pages == 265 265 266 -* [[Roadmap Overview>>FactHarbor pre10 V0\.9\.70.Roadmap.WebHome]] - All phases 267 -* [[POC2 Requirements>>FactHarbor pre10 V0\.9\.70.Roadmap.POC2.WebHome]] - Next phase 268 -* [[Requirements>>FactHarbor pre10 V0\.9\.70.Specification.Requirements.WebHome]] - Full system requirements 269 -* [[Architecture>>FactHarbor pre10 V0\.9\.70.Specification.Architecture.WebHome]] - System architecture 270 -* [[NFR11 Full Specification>>FactHarbor.Specification.Requirements.WebHome#NFR11]] - Complete quality framework 273 +* [[Roadmap Overview>>Test.FactHarbor pre10 V0\.9\.70.Roadmap.WebHome]] - All phases 274 +* [[POC2 Requirements>>Test.FactHarbor pre10 V0\.9\.70.Roadmap.POC2.WebHome]] - Next phase 275 +* [[Requirements>>Test.FactHarbor pre10 V0\.9\.70.Specification.Requirements.WebHome]] - Full system requirements 276 +* [[Architecture>>Test.FactHarbor pre10 V0\.9\.70.Specification.Architecture.WebHome]] - System architecture 277 +* [[NFR11 Full Specification>>Test.FactHarbor.Specification.Requirements.WebHome#NFR11]] - Complete quality framework 271 271 272 -**Document Status:** ✅ POC1 Specification Complete - Ready for Implementation 279 +**Document Status:** ✅ POC1 Specification Complete - Ready for Implementation 273 273 **Version:** V0.9.70