Changes for page Workflows
Last modified by Robert Schaub on 2026/02/08 08:32
Summary
-
Page properties (1 modified, 0 added, 0 removed)
Details
- Page properties
-
- Content
-
... ... @@ -1,15 +1,11 @@ 1 1 = Workflows = 2 - 3 3 FactHarbor workflows are **simple, automated, focused on continuous improvement**. 4 - 5 5 == 1. Core Principles == 6 - 7 7 * **Automated by default**: AI processes everything 8 8 * **Publish immediately**: No centralized approval (removed in V0.9.50) 9 9 * **Quality through monitoring**: Not gatekeeping 10 10 * **Fix systems, not data**: Errors trigger improvements 11 11 * **Human-in-loop**: Only for edge cases and abuse 12 - 13 13 == 2. Claim Submission Workflow == 14 14 15 15 === 2.1 Claim Extraction === ... ... @@ -17,13 +17,11 @@ 17 17 When users submit content (text, articles, web pages), FactHarbor first extracts individual verifiable claims: 18 18 19 19 **Input Types:** 20 - 21 21 * Single claim: "The Earth is flat" 22 22 * Text with multiple claims: "Climate change is accelerating. Sea levels rose 3mm in 2023. Arctic ice decreased 13% annually." 23 23 * URLs: Web pages analyzed for factual claims 24 24 25 25 **Extraction Process:** 26 - 27 27 * LLM analyzes submitted content 28 28 * Identifies distinct, verifiable factual claims 29 29 * Separates claims from opinions, questions, or commentary ... ... @@ -30,13 +30,11 @@ 30 30 * Each claim becomes independent for processing 31 31 32 32 **Output:** 33 - 34 34 * List of claims with context 35 35 * Each claim assigned unique ID 36 36 * Original context preserved for reference 37 37 38 38 This extraction ensures: 39 - 40 40 * Each claim receives focused analysis 41 41 * Multiple claims in one submission are all processed 42 42 * Claims are properly isolated for independent verification ... ... @@ -50,10 +50,9 @@ 50 50 51 51 == 2.5 Claim and Scenario Workflow == 52 52 53 -{{include reference=" Archive.FactHarbor2026\.02\.08.Specification.Diagrams.Claim and Scenario Workflow.WebHome"/}}45 +{{include reference="FactHarbor.Specification.Diagrams.Claim and Scenario Workflow.WebHome"/}} 54 54 55 55 == 3. Automated Analysis Workflow == 56 - 57 57 ``` 58 58 Claim from queue 59 59 ↓ ... ... @@ -73,45 +73,33 @@ 73 73 ``` 74 74 **Timeline**: 10-30 seconds 75 75 **90%+ published automatically** 76 - 77 77 == 3.5 Evidence and Verdict Workflow == 78 - 79 -{{include reference="Archive.FactHarbor 2026\.02\.08.Specification.Diagrams.Evidence and Verdict Workflow.WebHome"/}} 80 - 68 +{{include reference="FactHarbor.Specification.Diagrams.Evidence and Verdict Workflow.WebHome"/}} 81 81 == 4. Publication Workflow == 82 - 83 83 **Standard (90%+)**: Pass quality gates → Publish immediately with confidence scores 84 84 **High Risk (<10%)**: Risk > 80% → Moderator review 85 85 **Low Quality**: Confidence < 40% → Improvement queue → Re-process 86 - 87 87 == 5. User Contribution Workflow == 88 - 89 89 ``` 90 90 Contributor edits → System validates → Applied immediately → Logged → Reputation earned 91 91 ``` 92 92 **No approval required** (Wikipedia model) 93 93 **New contributors** (<50 reputation): Limited to minor edits 94 - 95 95 == 5.5 Quality and Audit Workflow == 96 96 97 -{{include reference=" Archive.FactHarbor2026\.02\.08.Specification.Diagrams.Quality and Audit Workflow.WebHome"/}}81 +{{include reference="FactHarbor.Specification.Diagrams.Quality and Audit Workflow.WebHome"/}} 98 98 99 99 == 6. Flagging Workflow == 100 - 101 101 ``` 102 102 User flags issue → Categorize (abuse/quality) → Automated or manual resolution 103 103 ``` 104 104 **Quality issues**: Add to improvement queue → System fix → Auto re-process 105 105 **Abuse**: Moderator review → Action taken 106 - 107 107 == 7. Moderation Workflow == 108 - 109 109 **Automated pre-moderation**: 95% published automatically 110 110 **Moderator queue**: Only high-risk or flagged content 111 111 **Appeal process**: Different moderator → Governing Team if needed 112 - 113 113 == 8. System Improvement Workflow == 114 - 115 115 **Weekly cycle**: 116 116 ``` 117 117 Monday: Review error patterns ... ... @@ -128,26 +128,18 @@ 128 128 ``` 129 129 New algorithm → Split traffic (90% control, 10% test) → Run 1 week → Compare metrics → Deploy if better 130 130 ``` 131 - 132 132 == 9. Quality Monitoring Workflow == 133 - 134 134 **Continuous**: Every hour calculate metrics, detect anomalies 135 135 **Daily**: Update source track records, aggregate error patterns 136 136 **Weekly**: System improvement cycle, performance review 137 - 138 138 == 10. Source Track Record Workflow == 139 - 140 140 **Initial score**: New source starts at 50 (neutral) 141 141 **Daily updates**: Calculate accuracy, correction frequency, update score 142 142 **Continuous**: All claims using source recalculated when score changes 143 - 144 144 == 11. Re-Processing Workflow == 145 - 146 146 **Triggers**: System improvement deployed, source score updated, new evidence, error fixed 147 147 **Process**: Identify affected claims → Re-run AKEL → Compare → Update if better → Log change 148 - 149 149 == 12. Related Pages == 150 - 151 -* [[Requirements>>Archive.FactHarbor 2026\.02\.08.Specification.Requirements.WebHome]] 152 -* [[Architecture>>Archive.FactHarbor 2026\.02\.08.Specification.Architecture.WebHome]] 153 -* [[Data Model>>Archive.FactHarbor 2026\.02\.08.Specification.Data Model.WebHome]] 122 +* [[Requirements>>FactHarbor.Specification.Requirements.WebHome]] 123 +* [[Architecture>>FactHarbor.Specification.Architecture.WebHome]] 124 +* [[Data Model>>FactHarbor.Specification.Data Model.WebHome]]