Skip to Content

Wiki source code of Workflows

Last modified by Robert Schaub on 2025/12/24 21:53
Show last authors
1 = Workflows =
2 FactHarbor workflows are **simple, automated, focused on continuous improvement**.
3 == 1. Core Principles ==
4 * **Automated by default**: AI processes everything
5 * **Publish immediately**: No centralized approval (removed in V0.9.50)
6 * **Quality through monitoring**: Not gatekeeping
7 * **Fix systems, not data**: Errors trigger improvements
8 * **Human-in-loop**: Only for edge cases and abuse
9 == 2. Claim Submission Workflow ==
10
11 === 2.1 Claim Extraction ===
12
13 When users submit content (text, articles, web pages), FactHarbor first extracts individual verifiable claims:
14
15 **Input Types:**
16 * Single claim: "The Earth is flat"
17 * Text with multiple claims: "Climate change is accelerating. Sea levels rose 3mm in 2023. Arctic ice decreased 13% annually."
18 * URLs: Web pages analyzed for factual claims
19
20 **Extraction Process:**
21 * LLM analyzes submitted content
22 * Identifies distinct, verifiable factual claims
23 * Separates claims from opinions, questions, or commentary
24 * Each claim becomes independent for processing
25
26 **Output:**
27 * List of claims with context
28 * Each claim assigned unique ID
29 * Original context preserved for reference
30
31 This extraction ensures:
32 * Each claim receives focused analysis
33 * Multiple claims in one submission are all processed
34 * Claims are properly isolated for independent verification
35 * Context is preserved for accurate interpretation
36
37 ```
38 User submits → Duplicate detection → Categorization → Processing queue → User receives ID
39 ```
40 **Timeline**: Seconds
41 **No approval needed**
42
43 == 2.5 Claim and Scenario Workflow ==
44
45 {{include reference="FactHarbor.Specification.Diagrams.Claim and Scenario Workflow.WebHome"/}}
46
47 == 3. Automated Analysis Workflow ==
48 ```
49 Claim from queue
50 ↓
51 Evidence gathering (AKEL)
52 ↓
53 Source evaluation (track record check)
54 ↓
55 Scenario generation
56 ↓
57 Verdict synthesis
58 ↓
59 Risk assessment
60 ↓
61 Quality gates (confidence > 40%? risk < 80%?)
62 ↓
63 Publish OR Flag for improvement
64 ```
65 **Timeline**: 10-30 seconds
66 **90%+ published automatically**
67 == 3.5 Evidence and Verdict Workflow ==
68 {{include reference="FactHarbor.Specification.Diagrams.Evidence and Verdict Workflow.WebHome"/}}
69 == 4. Publication Workflow ==
70 **Standard (90%+)**: Pass quality gates → Publish immediately with confidence scores
71 **High Risk (<10%)**: Risk > 80% → Moderator review
72 **Low Quality**: Confidence < 40% → Improvement queue → Re-process
73 == 5. User Contribution Workflow ==
74 ```
75 Contributor edits → System validates → Applied immediately → Logged → Reputation earned
76 ```
77 **No approval required** (Wikipedia model)
78 **New contributors** (<50 reputation): Limited to minor edits
79 == 5.5 Quality and Audit Workflow ==
80
81 {{include reference="FactHarbor.Specification.Diagrams.Quality and Audit Workflow.WebHome"/}}
82
83 == 6. Flagging Workflow ==
84 ```
85 User flags issue → Categorize (abuse/quality) → Automated or manual resolution
86 ```
87 **Quality issues**: Add to improvement queue → System fix → Auto re-process
88 **Abuse**: Moderator review → Action taken
89 == 7. Moderation Workflow ==
90 **Automated pre-moderation**: 95% published automatically
91 **Moderator queue**: Only high-risk or flagged content
92 **Appeal process**: Different moderator → Governing Team if needed
93 == 8. System Improvement Workflow ==
94 **Weekly cycle**:
95 ```
96 Monday: Review error patterns
97 Tuesday-Wednesday: Develop fixes
98 Thursday: Test improvements
99 Friday: Deploy & re-process
100 Weekend: Monitor metrics
101 ```
102 **Error capture**:
103 ```
104 Error detected → Categorize → Root cause → Improvement queue → Pattern analysis
105 ```
106 **A/B Testing**:
107 ```
108 New algorithm → Split traffic (90% control, 10% test) → Run 1 week → Compare metrics → Deploy if better
109 ```
110 == 9. Quality Monitoring Workflow ==
111 **Continuous**: Every hour calculate metrics, detect anomalies
112 **Daily**: Update source track records, aggregate error patterns
113 **Weekly**: System improvement cycle, performance review
114 == 10. Source Track Record Workflow ==
115 **Initial score**: New source starts at 50 (neutral)
116 **Daily updates**: Calculate accuracy, correction frequency, update score
117 **Continuous**: All claims using source recalculated when score changes
118 == 11. Re-Processing Workflow ==
119 **Triggers**: System improvement deployed, source score updated, new evidence, error fixed
120 **Process**: Identify affected claims → Re-run AKEL → Compare → Update if better → Log change
121 == 12. Related Pages ==
122 * [[Requirements>>FactHarbor.Specification.Requirements.WebHome]]
123 * [[Architecture>>FactHarbor.Specification.Architecture.WebHome]]
124 * [[Data Model>>FactHarbor.Specification.Data Model.WebHome]]