Skip to Content

Changes for page Workflows

Last modified by Robert Schaub on 2026/02/08 08:26
From version 4.1
edited by Robert Schaub
on 2025/12/24 21:53
Change comment: Imported from XAR
To version 4.2
edited by Robert Schaub
on 2026/01/20 20:25
Change comment: Renamed back-links.

Summary

Details

Page properties
Content
... ... @@ -1,11 +1,15 @@
1 1  = Workflows =
2 +
2 2  FactHarbor workflows are **simple, automated, focused on continuous improvement**.
4 +
3 3  == 1. Core Principles ==
6 +
4 4  * **Automated by default**: AI processes everything
5 5  * **Publish immediately**: No centralized approval (removed in V0.9.50)
6 6  * **Quality through monitoring**: Not gatekeeping
7 7  * **Fix systems, not data**: Errors trigger improvements
8 8  * **Human-in-loop**: Only for edge cases and abuse
12 +
9 9  == 2. Claim Submission Workflow ==
10 10  
11 11  === 2.1 Claim Extraction ===
... ... @@ -13,11 +13,13 @@
13 13  When users submit content (text, articles, web pages), FactHarbor first extracts individual verifiable claims:
14 14  
15 15  **Input Types:**
20 +
16 16  * Single claim: "The Earth is flat"
17 17  * Text with multiple claims: "Climate change is accelerating. Sea levels rose 3mm in 2023. Arctic ice decreased 13% annually."
18 18  * URLs: Web pages analyzed for factual claims
19 19  
20 20  **Extraction Process:**
26 +
21 21  * LLM analyzes submitted content
22 22  * Identifies distinct, verifiable factual claims
23 23  * Separates claims from opinions, questions, or commentary
... ... @@ -24,11 +24,13 @@
24 24  * Each claim becomes independent for processing
25 25  
26 26  **Output:**
33 +
27 27  * List of claims with context
28 28  * Each claim assigned unique ID
29 29  * Original context preserved for reference
30 30  
31 31  This extraction ensures:
39 +
32 32  * Each claim receives focused analysis
33 33  * Multiple claims in one submission are all processed
34 34  * Claims are properly isolated for independent verification
... ... @@ -45,6 +45,7 @@
45 45  {{include reference="FactHarbor.Specification.Diagrams.Claim and Scenario Workflow.WebHome"/}}
46 46  
47 47  == 3. Automated Analysis Workflow ==
56 +
48 48  ```
49 49  Claim from queue
50 50  ↓
... ... @@ -64,33 +64,45 @@
64 64  ```
65 65  **Timeline**: 10-30 seconds
66 66  **90%+ published automatically**
76 +
67 67  == 3.5 Evidence and Verdict Workflow ==
78 +
68 68  {{include reference="FactHarbor.Specification.Diagrams.Evidence and Verdict Workflow.WebHome"/}}
80 +
69 69  == 4. Publication Workflow ==
82 +
70 70  **Standard (90%+)**: Pass quality gates → Publish immediately with confidence scores
71 71  **High Risk (<10%)**: Risk > 80% → Moderator review
72 72  **Low Quality**: Confidence < 40% → Improvement queue → Re-process
86 +
73 73  == 5. User Contribution Workflow ==
88 +
74 74  ```
75 75  Contributor edits → System validates → Applied immediately → Logged → Reputation earned
76 76  ```
77 77  **No approval required** (Wikipedia model)
78 78  **New contributors** (<50 reputation): Limited to minor edits
94 +
79 79  == 5.5 Quality and Audit Workflow ==
80 80  
81 81  {{include reference="FactHarbor.Specification.Diagrams.Quality and Audit Workflow.WebHome"/}}
82 82  
83 83  == 6. Flagging Workflow ==
100 +
84 84  ```
85 85  User flags issue → Categorize (abuse/quality) → Automated or manual resolution
86 86  ```
87 87  **Quality issues**: Add to improvement queue → System fix → Auto re-process
88 88  **Abuse**: Moderator review → Action taken
106 +
89 89  == 7. Moderation Workflow ==
108 +
90 90  **Automated pre-moderation**: 95% published automatically
91 91  **Moderator queue**: Only high-risk or flagged content
92 92  **Appeal process**: Different moderator → Governing Team if needed
112 +
93 93  == 8. System Improvement Workflow ==
114 +
94 94  **Weekly cycle**:
95 95  ```
96 96  Monday: Review error patterns
... ... @@ -107,18 +107,26 @@
107 107  ```
108 108  New algorithm → Split traffic (90% control, 10% test) → Run 1 week → Compare metrics → Deploy if better
109 109  ```
131 +
110 110  == 9. Quality Monitoring Workflow ==
133 +
111 111  **Continuous**: Every hour calculate metrics, detect anomalies
112 112  **Daily**: Update source track records, aggregate error patterns
113 113  **Weekly**: System improvement cycle, performance review
137 +
114 114  == 10. Source Track Record Workflow ==
139 +
115 115  **Initial score**: New source starts at 50 (neutral)
116 116  **Daily updates**: Calculate accuracy, correction frequency, update score
117 117  **Continuous**: All claims using source recalculated when score changes
143 +
118 118  == 11. Re-Processing Workflow ==
145 +
119 119  **Triggers**: System improvement deployed, source score updated, new evidence, error fixed
120 120  **Process**: Identify affected claims → Re-run AKEL → Compare → Update if better → Log change
148 +
121 121  == 12. Related Pages ==
150 +
122 122  * [[Requirements>>FactHarbor.Specification.Requirements.WebHome]]
123 -* [[Architecture>>FactHarbor.Specification.Architecture.WebHome]]
152 +* [[Architecture>>Archive.FactHarbor.Specification.Architecture.WebHome]]
124 124  * [[Data Model>>FactHarbor.Specification.Data Model.WebHome]]