Skip to Content
Last modified by Robert Schaub on 2025/12/24 20:30
From version 1.1
edited by Robert Schaub
on 2025/12/16 21:42
Change comment: Imported from XAR
To version 2.2
edited by Robert Schaub
on 2025/12/17 18:07
Change comment: Update document after refactoring.

Summary

Details

Page properties
Parent
... ... @@ -1,1 +1,1 @@
1 -FactHarbor.Specification.WebHome
1 +FactHarbor.Archive.FactHarbor 0\.9\.40.Specification.WebHome
Content
... ... @@ -1,6 +1,6 @@
1 1  = AKEL — AI Knowledge Extraction Layer =
2 2  
3 -AKEL is FactHarbor's automated intelligence subsystem.
3 +AKEL is FactHarbor's automated intelligence subsystem.
4 4  Its purpose is to reduce human workload, enhance consistency, and enable scalable knowledge processing — **without ever replacing human judgment**.
5 5  
6 6  AKEL outputs are marked with **AuthorType = AI** and published according to risk-based review policies (see Publication Modes below).
... ... @@ -47,20 +47,20 @@
47 47  == 3. Inputs and Outputs ==
48 48  
49 49  === 3.1 Inputs ===
50 -* User-submitted claims or evidence
51 -* Uploaded documents
52 -* URLs or citations
53 -* External LLM API (optional)
50 +* User-submitted claims or evidence
51 +* Uploaded documents
52 +* URLs or citations
53 +* External LLM API (optional)
54 54  * Embeddings (from local or federated peers)
55 55  
56 56  === 3.2 Outputs (publication mode varies by risk tier) ===
57 -* ClaimVersion (draft or AI-generated)
58 -* ScenarioVersion (draft or AI-generated)
59 -* EvidenceVersion (summary + metadata, draft or AI-generated)
60 -* VerdictVersion (draft, AI-generated, or human-reviewed)
61 -* Contradiction alerts
57 +* ClaimVersion (draft or AI-generated)
58 +* ScenarioVersion (draft or AI-generated)
59 +* EvidenceVersion (summary + metadata, draft or AI-generated)
60 +* VerdictVersion (draft, AI-generated, or human-reviewed)
61 +* Contradiction alerts
62 62  * Reservation and limitation notices
63 -* Re-evaluation proposals
63 +* Re-evaluation proposals
64 64  * Updated embeddings
65 65  
66 66  
... ... @@ -113,7 +113,7 @@
113 113  ```
114 114  
115 115  
116 -== 5. Risk Tiers ==
116 +== 5. Risk tiers ==
117 117  
118 118  AKEL assigns risk tiers to all content to determine appropriate review requirements:
119 119  
... ... @@ -124,10 +124,10 @@
124 124  **Publication policy:**
125 125  * Human review REQUIRED before "Human-Reviewed" status
126 126  * AI-generated content MAY be published but:
127 - ** Clearly flagged as AI-draft with prominent disclaimer
128 - ** May have limited visibility
129 - ** Auto-escalated to expert review queue
130 - ** User warnings displayed
127 + ** Clearly flagged as AI-draft with prominent disclaimer
128 + ** May have limited visibility
129 + ** Auto-escalated to expert review queue
130 + ** User warnings displayed
131 131  
132 132  **Audit rate:** Recommendation: 30-50% of published AI-drafts sampled in first 6 months
133 133  
... ... @@ -235,11 +235,11 @@
235 235  1. System selects content for audit based on sampling strategy
236 236  2. Human auditor reviews AI-generated content against quality standards
237 237  3. Auditor validates or corrects:
238 - * Claim extraction accuracy
239 - * Scenario appropriateness
240 - * Evidence relevance and interpretation
241 - * Verdict reasoning
242 - * Contradiction search completeness
238 + * Claim extraction accuracy
239 + * Scenario appropriateness
240 + * Evidence relevance and interpretation
241 + * Verdict reasoning
242 + * Contradiction search completeness
243 243  4. Audit outcome recorded (pass/fail + detailed feedback)
244 244  5. Failed audits trigger immediate content review
245 245  6. Audit results feed back into system improvement
... ... @@ -271,18 +271,18 @@
271 271  
272 272  In Release 1.0+, AKEL participates in cross-node knowledge alignment:
273 273  
274 -* Shares embeddings
275 -* Exchanges canonicalized claim forms
276 -* Exchanges scenario templates
277 -* Sends + receives contradiction alerts
274 +* Shares embeddings
275 +* Exchanges canonicalized claim forms
276 +* Exchanges scenario templates
277 +* Sends + receives contradiction alerts
278 278  * Shares audit findings (with privacy controls)
279 -* Never shares model weights
279 +* Never shares model weights
280 280  * Never overrides local governance
281 281  
282 282  Nodes may choose trust levels for AKEL-related data:
283 283  
284 -* Trusted nodes: auto-merge embeddings + templates
285 -* Neutral nodes: require reviewer approval
284 +* Trusted nodes: auto-merge embeddings + templates
285 +* Neutral nodes: require reviewer approval
286 286  * Untrusted nodes: fully manual import
287 287  
288 288  
... ... @@ -293,8 +293,8 @@
293 293  1. AKEL generates content and publishes as AI-draft (Mode 2) or keeps as draft (Mode 1)
294 294  2. Reviewers inspect content in review queue
295 295  3. Reviewers validate quality gates were correctly applied
296 -4. Experts validate high-risk (Tier A) or domain-specific outputs
297 -5. Moderators finalize "Human-Reviewed" publication
296 +4. Experts validate high-risk (Tier A) or domain-specific outputs
297 +5. Moderators finalize "Human-Reviewed" publication
298 298  6. Version numbers increment, full history preserved
299 299  
300 300  **Note:** Most AI-generated content (Tier B and C) can remain in Mode 2 (AI-Generated) indefinitely. Human review is optional for these tiers unless users or audits flag issues.