Skip to Content

Changes for page FAQ

Last modified by Robert Schaub on 2026/02/08 08:32
From version 1.2
edited by Robert Schaub
on 2026/02/08 08:28
Change comment: Renamed back-links.
To version 1.1
edited by Robert Schaub
on 2026/01/20 21:40
Change comment: Imported from XAR

Summary

Details

Page properties
Content
... ... @@ -1,20 +1,13 @@
1 1  = Frequently Asked Questions (FAQ) =
2 -
3 3  Common questions about FactHarbor's design, functionality, and approach.
4 -
5 5  == 1. How do claims get evaluated in FactHarbor? ==
6 -
7 7  === 1.1 User Submission ===
8 -
9 9  **Who**: Anyone can submit claims
10 10  **Process**: User submits claim text + source URLs
11 11  **Speed**: Typically <20 seconds to verdict
12 -
13 13  === 1.2 AKEL Processing (Automated) ===
14 -
15 15  **What**: AI Knowledge Extraction Layer analyzes claim
16 16  **Steps**:
17 -
18 18  * Parse claim into testable components
19 19  * Extract evidence from provided sources
20 20  * Score source credibility
... ... @@ -23,12 +23,9 @@
23 23  * Publish automatically
24 24  **Authority**: AKEL makes all content decisions
25 25  **Scale**: Can process millions of claims
26 -
27 27  === 1.3 Continuous Improvement (Human Role) ===
28 -
29 29  **What**: Humans improve the system, not individual verdicts
30 30  **Activities**:
31 -
32 32  * Monitor aggregate performance metrics
33 33  * Identify systematic errors
34 34  * Propose algorithm improvements
... ... @@ -36,11 +36,8 @@
36 36  * Test changes before deployment
37 37  **NOT**: Reviewing individual claims for approval
38 38  **Focus**: Fix the system, not the data
39 -
40 40  === 1.4 Exception Handling ===
41 -
42 42  **When AKEL flags for review**:
43 -
44 44  * Low confidence verdict
45 45  * Detected manipulation attempt
46 46  * Unusual pattern requiring attention
... ... @@ -49,19 +49,14 @@
49 49  * Takes action on abuse/manipulation
50 50  * Proposes detection improvements
51 51  * Does NOT override verdicts
52 -
53 53  === 1.5 Why This Model Works ===
54 -
55 55  **Scale**: Automation handles volume humans cannot
56 56  **Consistency**: Same rules applied uniformly
57 57  **Transparency**: Algorithms can be audited
58 58  **Improvement**: Systematic fixes benefit all claims
59 -
60 60  == 2. What prevents FactHarbor from becoming another echo chamber? ==
61 -
62 62  FactHarbor includes multiple safeguards against echo chambers and filter bubbles:
63 63  **Mandatory Contradiction Search**:
64 -
65 65  * AI must actively search for counter-evidence, not just confirmations
66 66  * System checks for echo chamber patterns in source clusters
67 67  * Flags tribal or ideological source clustering
... ... @@ -82,19 +82,16 @@
82 82  * Multiple independent nodes with different perspectives
83 83  * No single entity controls "the truth"
84 84  * Cross-node contradiction detection
85 -
86 86  == 3. How does FactHarbor handle claims that are "true in one context but false in another"? ==
87 -
88 88  This is exactly what FactHarbor is designed for:
89 89  **Scenarios capture contexts**:
90 -
91 91  * Each scenario defines specific boundaries, definitions, and assumptions
92 92  * The same claim can have different verdicts in different scenarios
93 93  * Example: "Coffee is healthy" depends on:
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?)
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?)
98 98  **Truth Landscape**:
99 99  * Shows all scenarios and their verdicts side-by-side
100 100  * Users see *why* interpretations differ
... ... @@ -103,11 +103,8 @@
103 103  * Every scenario states its assumptions clearly
104 104  * Users can compare how changing assumptions changes conclusions
105 105  * Makes context-dependence visible, not hidden
106 -
107 107  == 4. What makes FactHarbor different from traditional fact-checking sites? ==
108 -
109 109  **Traditional Fact-Checking**:
110 -
111 111  * Binary verdicts: True / Mostly True / False
112 112  * Single interpretation chosen by fact-checker
113 113  * Often hides legitimate contextual differences
... ... @@ -119,11 +119,8 @@
119 119  * **Version history**: Shows how understanding evolves
120 120  * **Contradiction search**: Actively seeks opposing evidence
121 121  * **Federated**: No single authority controls truth
122 -
123 123  == 5. How do you prevent manipulation or coordinated misinformation campaigns? ==
124 -
125 125  **Quality Gates**:
126 -
127 127  * Automated checks before AI-generated content publishes
128 128  * Source quality verification
129 129  * Mandatory contradiction search
... ... @@ -146,12 +146,9 @@
146 146  * No single point of control
147 147  * Cross-node contradiction detection
148 148  * Trust model prevents malicious node influence
149 -
150 150  == 6. What happens when new evidence contradicts an existing verdict? ==
151 -
152 152  FactHarbor is designed for evolving knowledge:
153 153  **Automatic Re-evaluation**:
154 -
155 155  1. New evidence arrives
156 156  2. System detects affected scenarios and verdicts
157 157  3. AKEL proposes updated verdicts
... ... @@ -159,7 +159,6 @@
159 159  5. New verdict version published
160 160  6. Old versions remain accessible
161 161  **Version History**:
162 -
163 163  * Every verdict has complete history
164 164  * Users can see "as of date X, what did we know?"
165 165  * Timeline shows how understanding evolved
... ... @@ -171,12 +171,9 @@
171 171  * Users following claims are notified of updates
172 172  * Can compare old vs new verdicts
173 173  * Can see which evidence changed conclusions
174 -
175 175  == 7. Who can submit claims to FactHarbor? ==
176 -
177 177  **Anyone** - even without login:
178 178  **Readers** (no login required):
179 -
180 180  * Browse and search all published content
181 181  * Submit text for analysis
182 182  * New claims added automatically unless duplicates exist
... ... @@ -187,7 +187,6 @@
187 187  * Suggest scenarios
188 188  * Participate in discussions
189 189  **Workflow**:
190 -
191 191  1. User submits text (as Reader or Contributor)
192 192  2. AKEL extracts claims
193 193  3. Checks for existing duplicates
... ... @@ -196,12 +196,9 @@
196 196  6. Generates scenarios (draft)
197 197  7. Runs quality gates
198 198  8. Publishes as AI-Generated (Mode 2) if passes
199 -
200 200  == 8. What are "risk tiers" and why do they matter? ==
201 -
202 202  Risk tiers determine review requirements and publication workflow:
203 203  **Tier A (High Risk)**:
204 -
205 205  * **Domains**: Medical, legal, elections, safety, security, major financial
206 206  * **Publication**: AI can publish with warnings, expert review required for "AKEL-Generated" status
207 207  * **Audit rate**: Recommendation 30-50%
... ... @@ -220,11 +220,8 @@
220 220  * AKEL suggests tier based on domain, keywords, impact
221 221  * Moderators and Trusted Contributors can override
222 222  * Risk tiers reviewed based on audit outcomes
223 -
224 224  == 9. How does federation work and why is it important? ==
225 -
226 226  **Federation Model**:
227 -
228 228  * Multiple independent FactHarbor nodes
229 229  * Each node has own database, AKEL, governance
230 230  * Nodes exchange claims, scenarios, evidence, verdicts
... ... @@ -236,7 +236,6 @@
236 236  * **Specialization**: Domain-focused nodes (health, energy, etc.)
237 237  * **Trust diversity**: Multiple perspectives, not single truth source
238 238  **How Nodes Exchange Data**:
239 -
240 240  1. Local node creates versions
241 241  2. Builds signed bundle
242 242  3. Pushes to trusted neighbor nodes
... ... @@ -244,16 +244,12 @@
244 244  5. Accept or branch versions
245 245  6. Local re-evaluation if needed
246 246  **Trust Model**:
247 -
248 248  * Trusted nodes → auto-import
249 249  * Neutral nodes → import with review
250 250  * Untrusted nodes → manual only
251 -
252 252  == 10. Can experts disagree in FactHarbor? ==
253 -
254 254  **Yes - and that's a feature, not a bug**:
255 255  **Multiple Scenarios**:
256 -
257 257  * Trusted Contributors can create different scenarios with different assumptions
258 258  * Each scenario gets its own verdict
259 259  * Users see *why* experts disagree (different definitions, boundaries, evidence weighting)
... ... @@ -270,12 +270,9 @@
270 270  * Different nodes can have different expert conclusions
271 271  * Cross-node branching allowed
272 272  * Users can see how conclusions vary across nodes
273 -
274 274  == 11. What prevents AI from hallucinating or making up facts? ==
275 -
276 276  **Multiple Safeguards**:
277 277  **Quality Gate 4: Structural Integrity**:
278 -
279 279  * Fact-checking against sources
280 280  * No hallucinations allowed
281 281  * Logic chain must be valid and traceable
... ... @@ -298,12 +298,9 @@
298 298  * Tier A marked as highest risk
299 299  * Audit sampling catches errors
300 300  * Community can flag issues
301 -
302 302  == 12. How does FactHarbor make money / is it sustainable? ==
303 -
304 304  [ToDo: Business model and sustainability to be defined]
305 305  Potential models under consideration:
306 -
307 307  * Non-profit foundation with grants and donations
308 308  * Institutional subscriptions (universities, research organizations, media)
309 309  * API access for third-party integrations
... ... @@ -310,37 +310,25 @@
310 310  * Premium features for power users
311 311  * Federated node hosting services
312 312  Core principle: **Public benefit** mission takes priority over profit.
313 -
314 314  == 13. Related Pages ==
315 -
316 316  * [[Requirements (Roles)>>FactHarbor.Specification.Requirements.WebHome]]
317 317  * [[AKEL (AI Knowledge Extraction Layer)>>FactHarbor.Specification.AI Knowledge Extraction Layer (AKEL).WebHome]]
318 318  * [[Automation>>FactHarbor.Specification.Automation.WebHome]]
319 319  * [[Federation & Decentralization>>FactHarbor.Specification.Federation & Decentralization.WebHome]]
320 -* [[Mission & Purpose>>Archive.FactHarbor 2026\.02\.08.Organisation.Core Problems FactHarbor Solves.WebHome]]
321 -
266 +* [[Mission & Purpose>>FactHarbor.Organisation.Core Problems FactHarbor Solves.WebHome]]
322 322  == 20. Glossary / Key Terms ==
323 -
324 324  === Phase 0 vs POC v1 ===
325 -
326 326  These terms refer to the same stage of FactHarbor's development:
327 -
328 328  * **Phase 0** - Organisational perspective: Pre-alpha stage with founder-led governance
329 329  * **POC v1** - Technical perspective: Proof of Concept demonstrating AI-generated publication
330 330  Both describe the current development stage where the platform is being built and initially validated.
331 -
332 332  === Beta 0 ===
333 -
334 334  The next development stage after POC, featuring:
335 -
336 336  * External testers
337 337  * Basic federation experiments
338 338  * Enhanced automation
339 -
340 340  === Release 1.0 ===
341 -
342 342  The first public release featuring:
343 -
344 344  * Full federation support
345 345  * 2000+ concurrent users
346 346  * Production-grade infrastructure