Skip to Content

Changes for page FAQ

Last modified by Robert Schaub on 2026/02/08 08:32
From version 1.1
edited by Robert Schaub
on 2026/01/20 21:40
Change comment: Imported from XAR
To version 1.5
edited by Robert Schaub
on 2026/02/08 08:31
Change comment: Update document after refactoring.

Summary

Details

Page properties
Parent
... ... @@ -1,1 +1,1 @@
1 -FactHarbor.Specification.WebHome
1 +Archive.FactHarbor 2026\.02\.08.Specification.WebHome
Content
... ... @@ -1,13 +1,20 @@
1 1  = Frequently Asked Questions (FAQ) =
2 +
2 2  Common questions about FactHarbor's design, functionality, and approach.
4 +
3 3  == 1. How do claims get evaluated in FactHarbor? ==
6 +
4 4  === 1.1 User Submission ===
8 +
5 5  **Who**: Anyone can submit claims
6 6  **Process**: User submits claim text + source URLs
7 7  **Speed**: Typically <20 seconds to verdict
12 +
8 8  === 1.2 AKEL Processing (Automated) ===
14 +
9 9  **What**: AI Knowledge Extraction Layer analyzes claim
10 10  **Steps**:
17 +
11 11  * Parse claim into testable components
12 12  * Extract evidence from provided sources
13 13  * Score source credibility
... ... @@ -16,9 +16,12 @@
16 16  * Publish automatically
17 17  **Authority**: AKEL makes all content decisions
18 18  **Scale**: Can process millions of claims
26 +
19 19  === 1.3 Continuous Improvement (Human Role) ===
28 +
20 20  **What**: Humans improve the system, not individual verdicts
21 21  **Activities**:
31 +
22 22  * Monitor aggregate performance metrics
23 23  * Identify systematic errors
24 24  * Propose algorithm improvements
... ... @@ -26,8 +26,11 @@
26 26  * Test changes before deployment
27 27  **NOT**: Reviewing individual claims for approval
28 28  **Focus**: Fix the system, not the data
39 +
29 29  === 1.4 Exception Handling ===
41 +
30 30  **When AKEL flags for review**:
43 +
31 31  * Low confidence verdict
32 32  * Detected manipulation attempt
33 33  * Unusual pattern requiring attention
... ... @@ -36,14 +36,19 @@
36 36  * Takes action on abuse/manipulation
37 37  * Proposes detection improvements
38 38  * Does NOT override verdicts
52 +
39 39  === 1.5 Why This Model Works ===
54 +
40 40  **Scale**: Automation handles volume humans cannot
41 41  **Consistency**: Same rules applied uniformly
42 42  **Transparency**: Algorithms can be audited
43 43  **Improvement**: Systematic fixes benefit all claims
59 +
44 44  == 2. What prevents FactHarbor from becoming another echo chamber? ==
61 +
45 45  FactHarbor includes multiple safeguards against echo chambers and filter bubbles:
46 46  **Mandatory Contradiction Search**:
64 +
47 47  * AI must actively search for counter-evidence, not just confirmations
48 48  * System checks for echo chamber patterns in source clusters
49 49  * Flags tribal or ideological source clustering
... ... @@ -64,16 +64,19 @@
64 64  * Multiple independent nodes with different perspectives
65 65  * No single entity controls "the truth"
66 66  * Cross-node contradiction detection
85 +
67 67  == 3. How does FactHarbor handle claims that are "true in one context but false in another"? ==
87 +
68 68  This is exactly what FactHarbor is designed for:
69 69  **Scenarios capture contexts**:
90 +
70 70  * Each scenario defines specific boundaries, definitions, and assumptions
71 71  * The same claim can have different verdicts in different scenarios
72 72  * Example: "Coffee is healthy" depends on:
73 - ** Definition of "healthy" (reduces disease risk? improves mood? affects specific conditions?)
74 - ** Population (adults? pregnant women? people with heart conditions?)
75 - ** Consumption level (1 cup/day? 5 cups/day?)
76 - ** Time horizon (short-term? long-term?)
94 +** Definition of "healthy" (reduces disease risk? improves mood? affects specific conditions?)
95 +** Population (adults? pregnant women? people with heart conditions?)
96 +** Consumption level (1 cup/day? 5 cups/day?)
97 +** Time horizon (short-term? long-term?)
77 77  **Truth Landscape**:
78 78  * Shows all scenarios and their verdicts side-by-side
79 79  * Users see *why* interpretations differ
... ... @@ -82,8 +82,11 @@
82 82  * Every scenario states its assumptions clearly
83 83  * Users can compare how changing assumptions changes conclusions
84 84  * Makes context-dependence visible, not hidden
106 +
85 85  == 4. What makes FactHarbor different from traditional fact-checking sites? ==
108 +
86 86  **Traditional Fact-Checking**:
110 +
87 87  * Binary verdicts: True / Mostly True / False
88 88  * Single interpretation chosen by fact-checker
89 89  * Often hides legitimate contextual differences
... ... @@ -95,8 +95,11 @@
95 95  * **Version history**: Shows how understanding evolves
96 96  * **Contradiction search**: Actively seeks opposing evidence
97 97  * **Federated**: No single authority controls truth
122 +
98 98  == 5. How do you prevent manipulation or coordinated misinformation campaigns? ==
124 +
99 99  **Quality Gates**:
126 +
100 100  * Automated checks before AI-generated content publishes
101 101  * Source quality verification
102 102  * Mandatory contradiction search
... ... @@ -119,9 +119,12 @@
119 119  * No single point of control
120 120  * Cross-node contradiction detection
121 121  * Trust model prevents malicious node influence
149 +
122 122  == 6. What happens when new evidence contradicts an existing verdict? ==
151 +
123 123  FactHarbor is designed for evolving knowledge:
124 124  **Automatic Re-evaluation**:
154 +
125 125  1. New evidence arrives
126 126  2. System detects affected scenarios and verdicts
127 127  3. AKEL proposes updated verdicts
... ... @@ -129,6 +129,7 @@
129 129  5. New verdict version published
130 130  6. Old versions remain accessible
131 131  **Version History**:
162 +
132 132  * Every verdict has complete history
133 133  * Users can see "as of date X, what did we know?"
134 134  * Timeline shows how understanding evolved
... ... @@ -140,9 +140,12 @@
140 140  * Users following claims are notified of updates
141 141  * Can compare old vs new verdicts
142 142  * Can see which evidence changed conclusions
174 +
143 143  == 7. Who can submit claims to FactHarbor? ==
176 +
144 144  **Anyone** - even without login:
145 145  **Readers** (no login required):
179 +
146 146  * Browse and search all published content
147 147  * Submit text for analysis
148 148  * New claims added automatically unless duplicates exist
... ... @@ -153,6 +153,7 @@
153 153  * Suggest scenarios
154 154  * Participate in discussions
155 155  **Workflow**:
190 +
156 156  1. User submits text (as Reader or Contributor)
157 157  2. AKEL extracts claims
158 158  3. Checks for existing duplicates
... ... @@ -161,9 +161,12 @@
161 161  6. Generates scenarios (draft)
162 162  7. Runs quality gates
163 163  8. Publishes as AI-Generated (Mode 2) if passes
199 +
164 164  == 8. What are "risk tiers" and why do they matter? ==
201 +
165 165  Risk tiers determine review requirements and publication workflow:
166 166  **Tier A (High Risk)**:
204 +
167 167  * **Domains**: Medical, legal, elections, safety, security, major financial
168 168  * **Publication**: AI can publish with warnings, expert review required for "AKEL-Generated" status
169 169  * **Audit rate**: Recommendation 30-50%
... ... @@ -182,8 +182,11 @@
182 182  * AKEL suggests tier based on domain, keywords, impact
183 183  * Moderators and Trusted Contributors can override
184 184  * Risk tiers reviewed based on audit outcomes
223 +
185 185  == 9. How does federation work and why is it important? ==
225 +
186 186  **Federation Model**:
227 +
187 187  * Multiple independent FactHarbor nodes
188 188  * Each node has own database, AKEL, governance
189 189  * Nodes exchange claims, scenarios, evidence, verdicts
... ... @@ -195,6 +195,7 @@
195 195  * **Specialization**: Domain-focused nodes (health, energy, etc.)
196 196  * **Trust diversity**: Multiple perspectives, not single truth source
197 197  **How Nodes Exchange Data**:
239 +
198 198  1. Local node creates versions
199 199  2. Builds signed bundle
200 200  3. Pushes to trusted neighbor nodes
... ... @@ -202,12 +202,16 @@
202 202  5. Accept or branch versions
203 203  6. Local re-evaluation if needed
204 204  **Trust Model**:
247 +
205 205  * Trusted nodes → auto-import
206 206  * Neutral nodes → import with review
207 207  * Untrusted nodes → manual only
251 +
208 208  == 10. Can experts disagree in FactHarbor? ==
253 +
209 209  **Yes - and that's a feature, not a bug**:
210 210  **Multiple Scenarios**:
256 +
211 211  * Trusted Contributors can create different scenarios with different assumptions
212 212  * Each scenario gets its own verdict
213 213  * Users see *why* experts disagree (different definitions, boundaries, evidence weighting)
... ... @@ -224,9 +224,12 @@
224 224  * Different nodes can have different expert conclusions
225 225  * Cross-node branching allowed
226 226  * Users can see how conclusions vary across nodes
273 +
227 227  == 11. What prevents AI from hallucinating or making up facts? ==
275 +
228 228  **Multiple Safeguards**:
229 229  **Quality Gate 4: Structural Integrity**:
278 +
230 230  * Fact-checking against sources
231 231  * No hallucinations allowed
232 232  * Logic chain must be valid and traceable
... ... @@ -249,9 +249,12 @@
249 249  * Tier A marked as highest risk
250 250  * Audit sampling catches errors
251 251  * Community can flag issues
301 +
252 252  == 12. How does FactHarbor make money / is it sustainable? ==
303 +
253 253  [ToDo: Business model and sustainability to be defined]
254 254  Potential models under consideration:
306 +
255 255  * Non-profit foundation with grants and donations
256 256  * Institutional subscriptions (universities, research organizations, media)
257 257  * API access for third-party integrations
... ... @@ -258,25 +258,37 @@
258 258  * Premium features for power users
259 259  * Federated node hosting services
260 260  Core principle: **Public benefit** mission takes priority over profit.
313 +
261 261  == 13. Related Pages ==
315 +
262 262  * [[Requirements (Roles)>>FactHarbor.Specification.Requirements.WebHome]]
263 -* [[AKEL (AI Knowledge Extraction Layer)>>FactHarbor.Specification.AI Knowledge Extraction Layer (AKEL).WebHome]]
264 -* [[Automation>>FactHarbor.Specification.Automation.WebHome]]
317 +* [[AKEL (AI Knowledge Extraction Layer)>>Archive.FactHarbor 2026\.02\.08.Specification.AI Knowledge Extraction Layer (AKEL).WebHome]]
318 +* [[Automation>>Archive.FactHarbor 2026\.02\.08.Specification.Automation.WebHome]]
265 265  * [[Federation & Decentralization>>FactHarbor.Specification.Federation & Decentralization.WebHome]]
266 -* [[Mission & Purpose>>FactHarbor.Organisation.Core Problems FactHarbor Solves.WebHome]]
320 +* [[Mission & Purpose>>Archive.FactHarbor 2026\.02\.08.Organisation.Core Problems FactHarbor Solves.WebHome]]
321 +
267 267  == 20. Glossary / Key Terms ==
323 +
268 268  === Phase 0 vs POC v1 ===
325 +
269 269  These terms refer to the same stage of FactHarbor's development:
327 +
270 270  * **Phase 0** - Organisational perspective: Pre-alpha stage with founder-led governance
271 271  * **POC v1** - Technical perspective: Proof of Concept demonstrating AI-generated publication
272 272  Both describe the current development stage where the platform is being built and initially validated.
331 +
273 273  === Beta 0 ===
333 +
274 274  The next development stage after POC, featuring:
335 +
275 275  * External testers
276 276  * Basic federation experiments
277 277  * Enhanced automation
339 +
278 278  === Release 1.0 ===
341 +
279 279  The first public release featuring:
343 +
280 280  * Full federation support
281 281  * 2000+ concurrent users
282 282  * Production-grade infrastructure