Skip to Content

Changes for page Workflows

Last modified by Robert Schaub on 2026/02/08 08:26
From version 1.1
edited by Robert Schaub
on 2025/12/18 12:03
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
... ... @@ -1,18 +1,59 @@
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 ==
14 +
15 +=== 2.1 Claim Extraction ===
16 +
17 +When users submit content (text, articles, web pages), FactHarbor first extracts individual verifiable claims:
18 +
19 +**Input Types:**
20 +
21 +* Single claim: "The Earth is flat"
22 +* Text with multiple claims: "Climate change is accelerating. Sea levels rose 3mm in 2023. Arctic ice decreased 13% annually."
23 +* URLs: Web pages analyzed for factual claims
24 +
25 +**Extraction Process:**
26 +
27 +* LLM analyzes submitted content
28 +* Identifies distinct, verifiable factual claims
29 +* Separates claims from opinions, questions, or commentary
30 +* Each claim becomes independent for processing
31 +
32 +**Output:**
33 +
34 +* List of claims with context
35 +* Each claim assigned unique ID
36 +* Original context preserved for reference
37 +
38 +This extraction ensures:
39 +
40 +* Each claim receives focused analysis
41 +* Multiple claims in one submission are all processed
42 +* Claims are properly isolated for independent verification
43 +* Context is preserved for accurate interpretation
44 +
10 10  ```
11 11  User submits → Duplicate detection → Categorization → Processing queue → User receives ID
12 12  ```
13 13  **Timeline**: Seconds
14 14  **No approval needed**
50 +
51 +== 2.5 Claim and Scenario Workflow ==
52 +
53 +{{include reference="FactHarbor.Specification.Diagrams.Claim and Scenario Workflow.WebHome"/}}
54 +
15 15  == 3. Automated Analysis Workflow ==
56 +
16 16  ```
17 17  Claim from queue
18 18  ↓
... ... @@ -32,29 +32,45 @@
32 32  ```
33 33  **Timeline**: 10-30 seconds
34 34  **90%+ published automatically**
76 +
35 35  == 3.5 Evidence and Verdict Workflow ==
78 +
36 36  {{include reference="FactHarbor.Specification.Diagrams.Evidence and Verdict Workflow.WebHome"/}}
80 +
37 37  == 4. Publication Workflow ==
82 +
38 38  **Standard (90%+)**: Pass quality gates → Publish immediately with confidence scores
39 39  **High Risk (<10%)**: Risk > 80% → Moderator review
40 40  **Low Quality**: Confidence < 40% → Improvement queue → Re-process
86 +
41 41  == 5. User Contribution Workflow ==
88 +
42 42  ```
43 43  Contributor edits → System validates → Applied immediately → Logged → Reputation earned
44 44  ```
45 45  **No approval required** (Wikipedia model)
46 46  **New contributors** (<50 reputation): Limited to minor edits
94 +
95 +== 5.5 Quality and Audit Workflow ==
96 +
97 +{{include reference="FactHarbor.Specification.Diagrams.Quality and Audit Workflow.WebHome"/}}
98 +
47 47  == 6. Flagging Workflow ==
100 +
48 48  ```
49 49  User flags issue → Categorize (abuse/quality) → Automated or manual resolution
50 50  ```
51 51  **Quality issues**: Add to improvement queue → System fix → Auto re-process
52 52  **Abuse**: Moderator review → Action taken
106 +
53 53  == 7. Moderation Workflow ==
108 +
54 54  **Automated pre-moderation**: 95% published automatically
55 55  **Moderator queue**: Only high-risk or flagged content
56 56  **Appeal process**: Different moderator → Governing Team if needed
112 +
57 57  == 8. System Improvement Workflow ==
114 +
58 58  **Weekly cycle**:
59 59  ```
60 60  Monday: Review error patterns
... ... @@ -71,18 +71,26 @@
71 71  ```
72 72  New algorithm → Split traffic (90% control, 10% test) → Run 1 week → Compare metrics → Deploy if better
73 73  ```
131 +
74 74  == 9. Quality Monitoring Workflow ==
133 +
75 75  **Continuous**: Every hour calculate metrics, detect anomalies
76 76  **Daily**: Update source track records, aggregate error patterns
77 77  **Weekly**: System improvement cycle, performance review
137 +
78 78  == 10. Source Track Record Workflow ==
139 +
79 79  **Initial score**: New source starts at 50 (neutral)
80 80  **Daily updates**: Calculate accuracy, correction frequency, update score
81 81  **Continuous**: All claims using source recalculated when score changes
143 +
82 82  == 11. Re-Processing Workflow ==
145 +
83 83  **Triggers**: System improvement deployed, source score updated, new evidence, error fixed
84 84  **Process**: Identify affected claims → Re-run AKEL → Compare → Update if better → Log change
148 +
85 85  == 12. Related Pages ==
150 +
86 86  * [[Requirements>>FactHarbor.Specification.Requirements.WebHome]]
87 -* [[Architecture>>FactHarbor.Specification.Architecture.WebHome]]
152 +* [[Architecture>>Archive.FactHarbor.Specification.Architecture.WebHome]]
88 88  * [[Data Model>>FactHarbor.Specification.Data Model.WebHome]]