Skip to Content

Changes for page Workflows

Last modified by Robert Schaub on 2026/02/08 08:25
From version 1.3
edited by Robert Schaub
on 2026/01/20 20:26
Change comment: Renamed back-links.
To version 1.1
edited by Robert Schaub
on 2025/12/24 10:21
Change comment: Imported from XAR

Summary

Details

Page properties
Parent
... ... @@ -1,1 +1,1 @@
1 -Test.FactHarbor V0\.9\.100.Specification.WebHome
1 +FactHarbor.Specification.WebHome
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
... ... @@ -30,18 +30,17 @@
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
43 43  * Context is preserved for accurate interpretation
44 44  
37 +
45 45  ```
46 46  User submits → Duplicate detection → Categorization → Processing queue → User receives ID
47 47  ```
... ... @@ -53,7 +53,6 @@
53 53  {{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  ↓
... ... @@ -73,25 +73,18 @@
73 73  ```
74 74  **Timeline**: 10-30 seconds
75 75  **90%+ published automatically**
76 -
77 77  == 3.5 Evidence and Verdict Workflow ==
78 -
79 79  {{include reference="FactHarbor.Specification.Diagrams.Evidence and Verdict Workflow.WebHome"/}}
80 -
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 97  {{include reference="FactHarbor.Specification.Diagrams.Quality and Audit Workflow.WebHome"/}}
... ... @@ -98,21 +98,16 @@
98 98  
99 99  
100 100  == 6. Flagging Workflow ==
101 -
102 102  ```
103 103  User flags issue → Categorize (abuse/quality) → Automated or manual resolution
104 104  ```
105 105  **Quality issues**: Add to improvement queue → System fix → Auto re-process
106 106  **Abuse**: Moderator review → Action taken
107 -
108 108  == 7. Moderation Workflow ==
109 -
110 110  **Automated pre-moderation**: 95% published automatically
111 111  **Moderator queue**: Only high-risk or flagged content
112 112  **Appeal process**: Different moderator → Governing Team if needed
113 -
114 114  == 8. System Improvement Workflow ==
115 -
116 116  **Weekly cycle**:
117 117  ```
118 118  Monday: Review error patterns
... ... @@ -129,26 +129,18 @@
129 129  ```
130 130  New algorithm → Split traffic (90% control, 10% test) → Run 1 week → Compare metrics → Deploy if better
131 131  ```
132 -
133 133  == 9. Quality Monitoring Workflow ==
134 -
135 135  **Continuous**: Every hour calculate metrics, detect anomalies
136 136  **Daily**: Update source track records, aggregate error patterns
137 137  **Weekly**: System improvement cycle, performance review
138 -
139 139  == 10. Source Track Record Workflow ==
140 -
141 141  **Initial score**: New source starts at 50 (neutral)
142 142  **Daily updates**: Calculate accuracy, correction frequency, update score
143 143  **Continuous**: All claims using source recalculated when score changes
144 -
145 145  == 11. Re-Processing Workflow ==
146 -
147 147  **Triggers**: System improvement deployed, source score updated, new evidence, error fixed
148 148  **Process**: Identify affected claims → Re-run AKEL → Compare → Update if better → Log change
149 -
150 150  == 12. Related Pages ==
151 -
152 152  * [[Requirements>>FactHarbor.Specification.Requirements.WebHome]]
153 -* [[Architecture>>Archive.FactHarbor.Specification.Architecture.WebHome]]
125 +* [[Architecture>>FactHarbor.Specification.Architecture.WebHome]]
154 154  * [[Data Model>>FactHarbor.Specification.Data Model.WebHome]]