Skip to Content

Changes for page Automation

Last modified by Robert Schaub on 2025/12/24 20:34
From version 2.1
edited by Robert Schaub
on 2025/12/11 21:35
Change comment: Imported from XAR
To version 7.7
edited by Robert Schaub
on 2025/12/16 21:39
Change comment: Renamed back-links.

Summary

Details

Page properties
Parent
... ... @@ -1,1 +1,1 @@
1 -FactHarbor.Specification.WebHome
1 +FactHarbor.Archive.FactHarbor V0\.9\.18.Specification.WebHome
Content
... ... @@ -1,153 +1,296 @@
1 1  = Automation =
2 2  
3 -Automation in FactHarbor amplifies human capability but never replaces human oversight.
4 -All automated outputs require human review before publication.
3 +Automation in FactHarbor amplifies human capability while implementing risk-based oversight.
5 5  
6 6  This chapter defines:
6 +
7 +* Risk-based publication model
8 +* Quality gates for AI-generated content
7 7  * What must remain human-only
8 -* What AI (AKEL) can draft
10 +* What AI (AKEL) can draft and publish
9 9  * What can be fully automated
10 10  * How automation evolves through POC → Beta 0 → Release 1.0
11 11  
14 +== POC v1 (AI-Generated Publication Demonstration) ==
15 +
16 +The goal of POC v1 is to validate the automated reasoning capabilities and demonstrate AI-generated content publication.
17 +
18 +=== Workflow ===
19 +
20 +1. **Input**: User pastes a block of raw text.
21 +1. **Deep Analysis (Background)**: The system autonomously performs the full pipeline **before** displaying the text:
22 +
23 +* Extraction & Normalisation
24 +* Scenario & Sub-query generation
25 +* Evidence retrieval with **contradiction search**
26 +* Quality gate validation
27 +* Verdict computation
28 +
29 +1. **Visualisation (Extraction & Marking)**: The system displays the text with claims extracted and marked.
30 +
31 +* **Verdict-Based Coloring**: The extraction highlights (e.g. Orange/Green) are chosen **according to the computed verdict** for each claim.
32 +* **AI-Generated Label**: Clear indication that content is AI-produced
33 +
34 +1. **Inspection**: User clicks a highlighted claim to see the **Reasoning Trail**, showing exactly which evidence and sub-queries led to that verdict.
35 +
36 +=== Technical Scope ===
37 +
38 +* **AI-Generated Publication**: Content published as Mode 2 (AI-Generated, no prior human review)
39 +* **Quality Gates Active**: All automated quality checks enforced
40 +* **Contradiction Search Demonstrated**: Shows counter-evidence and reservation detection
41 +* **Risk Tier Classification**: POC shows tier assignment (demo purposes)
42 +* **No Human Approval Gate**: Demonstrates scalable AI publication
43 +* **Structured Sub-Queries**: Logic generated by decomposing claims into the FactHarbor data model
44 +
12 12  ----
13 13  
14 -= Manual vs Automated Responsibilities =
47 +== Publication Model ==
15 15  
49 +FactHarbor implements a risk-based publication model with three modes:
50 +
51 +=== Mode 1: Draft-Only ===
52 +
53 +* Failed quality gates
54 +* High-risk content pending expert review
55 +* Internal review queue only
56 +
57 +=== Mode 2: AI-Generated (Public) ===
58 +
59 +* Passed all quality gates
60 +* Risk tier B or C
61 +* Clear AI-generated labeling
62 +* Users can request human review
63 +
64 +=== Mode 3: Human-Reviewed ===
65 +
66 +* Validated by human reviewers/experts
67 +* "Human-Reviewed" status badge
68 +* Required for Tier A content publication
69 +
70 +See [[AKEL page>>FactHarbor.Specification V0\.9\.18.AI Knowledge Extraction Layer (AKEL).WebHome]] for detailed publication mode descriptions.
71 +
72 +----
73 +
74 +== Risk Tiers and Automation Levels ==
75 +
76 +=== Tier A (High Risk) ===
77 +
78 +* **Domains**: Medical, legal, elections, safety, security
79 +* **Automation**: AI can draft, human review required for "Human-Reviewed" status
80 +* **AI publication**: Allowed with prominent disclaimers and warnings
81 +* **Audit rate**: Recommendation: 30-50%
82 +
83 +=== Tier B (Medium Risk) ===
84 +
85 +* **Domains**: Complex policy, science, causality claims
86 +* **Automation**: AI can draft and publish (Mode 2)
87 +* **Human review**: Optional, audit-based
88 +* **Audit rate**: Recommendation: 10-20%
89 +
90 +=== Tier C (Low Risk) ===
91 +
92 +* **Domains**: Definitions, established facts, historical data
93 +* **Automation**: AI publication default
94 +* **Human review**: On request or via sampling
95 +* **Audit rate**: Recommendation: 5-10%
96 +
97 +----
98 +
16 16  == Human-Only Tasks ==
17 17  
18 -These require human judgment, ethics, or contextual interpretation:
101 +These require human judgment and cannot be automated:
19 19  
20 -* Definition of key terms in claims
21 -* Approval or rejection of scenarios
22 -* Interpretation of evidence in context
23 -* Final verdict approval
24 -* Governance decisions and dispute resolution
25 -* High-risk domain oversight
26 -* Ethical boundary decisions (especially medical, political, psychological)
103 +* **Ethical boundary decisions** (especially medical, political, psychological harm assessment)
104 +* **Dispute resolution** between conflicting expert opinions
105 +* **Governance policy** setting and enforcement
106 +* **Final authority** on Tier A "Human-Reviewed" status
107 +* **Audit system oversight** and quality standard definition
108 +* **Risk tier policy** adjustments based on societal context
27 27  
28 -== Semi-Automated (AI Draft → Human Review) ==
110 +----
29 29  
30 -AKEL can draft these, but humans must refine/approve:
112 +== AI-Draft with Audit (Semi-Automated) ==
31 31  
32 -* Scenario structures (definitions, assumptions, context)
33 -* Evaluation methods
34 -* Evidence relevance suggestions
35 -* Reliability hints
36 -* Verdict reasoning chains
37 -* Uncertainty and limitations
38 -* Scenario comparison explanations
39 -* Suggestions for merging or splitting scenarios
40 -* Draft public summaries
114 +AKEL drafts these; humans validate via sampling audits:
41 41  
116 +* **Scenario structures** (definitions, assumptions, context)
117 +* **Evaluation methods** and reasoning chains
118 +* **Evidence relevance** assessment and ranking
119 +* **Reliability scoring** and source evaluation
120 +* **Verdict reasoning** with uncertainty quantification
121 +* **Contradiction and reservation** identification
122 +* **Scenario comparison** explanations
123 +* **Public summaries** and accessibility text
124 +
125 +Most Tier B and C content remains in AI-draft status unless:
126 +
127 +* Users request human review
128 +* Audits identify errors
129 +* High engagement triggers review
130 +* Community flags issues
131 +
132 +----
133 +
42 42  == Fully Automated Structural Tasks ==
43 43  
44 44  These require no human interpretation:
45 45  
46 -* Claim normalization
47 -* Duplicate & cluster detection (vector embeddings)
48 -* Evidence metadata extraction
49 -* Basic reliability heuristics
50 -* Contradiction detection
51 -* Re-evaluation triggers
52 -* Batch layout generation (diagrams, summaries)
53 -* Federation integrity checks
138 +* **Claim normalization** (canonical form generation)
139 +* **Duplicate detection** (vector embeddings, clustering)
140 +* **Evidence metadata extraction** (dates, authors, publication info)
141 +* **Basic reliability heuristics** (source reputation scoring)
142 +* **Contradiction detection** (conflicting statements across sources)
143 +* **Re-evaluation triggers** (new evidence, source updates)
144 +* **Layout generation** (diagrams, summaries, UI presentation)
145 +* **Federation integrity checks** (cross-node data validation)
54 54  
55 55  ----
56 56  
57 -= Automation Roadmap =
149 +== Quality Gates (Automated) ==
58 58  
59 -Automation increases with maturity.
151 +Before AI-draft publication (Mode 2), content must pass:
60 60  
61 -== POC (Low Automation) ==
153 +1. **Source Quality Gate**
62 62  
63 -=== Automated ===
64 -* Claim normalization
65 -* Light scenario templates
66 -* Evidence metadata extraction
67 -* Simple verdict drafts (internal only)
155 +* Primary sources verified
156 +* Citations complete and accessible
157 +* Source reliability scored
68 68  
69 -=== Human ===
70 -* All scenario definitions
71 -* Evidence interpretation
72 -* Verdict creation
73 -* Governance
159 +2. **Contradiction Search Gate** (MANDATORY)
74 74  
75 -== Beta 0 (Medium Automation) ==
161 +* Counter-evidence actively sought
162 +* Reservations and limitations identified
163 +* Bubble detection (echo chambers, conspiracy theories)
164 +* Diverse perspective verification
76 76  
77 -=== Automated ===
78 -* Detailed scenario drafts
79 -* Evidence reliability scoring
80 -* Cross-scenario comparisons
81 -* Contradiction detection (local + remote nodes)
82 -* Internal Truth Landscape drafts
166 +3. **Uncertainty Quantification Gate**
83 83  
84 -=== Human ===
85 -* Scenario approval
86 -* Final verdict validation
168 +* Confidence scores calculated
169 +* Limitations stated
170 +* Data gaps disclosed
87 87  
88 -== Release 1.0 (High Automation) ==
172 +4. **Structural Integrity Gate**
89 89  
90 -=== Automated ===
91 -* Full scenario generation (definitions, assumptions, boundaries)
92 -* Evidence relevance scoring and ranking
93 -* Bayesian verdict scoring across scenario sets
94 -* Multi-scenario summary generation
95 -* Anomaly detection across nodes
96 -* AKEL-assisted federated synchronization
174 +* No hallucinations detected
175 +* Logic chain valid
176 +* References verifiable
97 97  
98 -=== Human ===
99 -* Final approval of all scenarios and verdicts
100 -* Ethical decisions
101 -* Oversight and conflict resolution
178 +See [[AKEL page>>FactHarbor.Specification V0\.9\.18.AI Knowledge Extraction Layer (AKEL).WebHome]] for detailed quality gate specifications.
102 102  
103 103  ----
104 104  
105 -= Automation Levels =
182 +== Audit System ==
106 106  
107 -== Level 0 — Human-Centric (POC) ==
108 -AI is purely advisory, nothing auto-published.
184 +Instead of reviewing all AI output, systematic sampling audits ensure quality:
109 109  
110 -== Level 1 — Assisted (Beta 0) ==
111 -AI drafts structures; humans approve each part.
186 +=== Stratified Sampling ===
112 112  
113 -== Level 2 — Structured (Release 1.0) ==
114 -AI produces near-complete drafts; humans refine.
188 +* Risk tier (A > B > C sampling rates)
189 +* Confidence scores (low confidence → more audits)
190 +* Traffic/engagement (popular content audited more)
191 +* Novelty (new topics/claim types prioritized)
192 +* User flags and disagreement signals
115 115  
116 -== Level 3 — Distributed Intelligence (Future) ==
117 -Nodes exchange embeddings, contradiction alerts, and scenario templates.
118 -Humans still approve everything.
194 +=== Continuous Improvement Loop ===
119 119  
196 +Audit findings improve:
197 +
198 +* Query templates
199 +* Source reliability weights
200 +* Contradiction detection algorithms
201 +* Risk tier assignment rules
202 +* Bubble detection heuristics
203 +
204 +=== Transparency ===
205 +
206 +* Audit statistics published
207 +* Accuracy rates by tier reported
208 +* System improvements documented
209 +
120 120  ----
121 121  
122 -= Automation Matrix =
212 +== Automation Roadmap ==
123 123  
124 -== Always Human ==
125 -* Final verdict approval
126 -* Scenario validity
127 -* Ethical decisions
128 -* Dispute resolution
214 +Automation capabilities increase with system maturity while maintaining quality oversight.
129 129  
130 -== Mostly AI (Human Validation Needed) ==
131 -* Claim normalization
132 -* Clustering
133 -* Evidence metadata
134 -* Reliability heuristics
135 -* Scenario drafts
136 -* Contradiction detection
216 +=== POC (Current Focus) ===
137 137  
138 -== Mixed ==
139 -* Definitions of ambiguous terms
140 -* Boundary choices
141 -* Assumption evaluation
142 -* Evidence selection
143 -* Verdict reasoning
218 +**Automated:**
144 144  
220 +* Claim normalization
221 +* Scenario template generation
222 +* Evidence metadata extraction
223 +* Simple verdict drafts
224 +* **AI-generated publication** (Mode 2, with quality gates)
225 +* **Contradiction search**
226 +* **Risk tier assignment**
227 +
228 +**Human:**
229 +
230 +* High-risk content validation (Tier A)
231 +* Sampling audits across all tiers
232 +* Quality standard refinement
233 +* Governance decisions
234 +
235 +=== Beta 0 (Enhanced Automation) ===
236 +
237 +**Automated:**
238 +
239 +* Detailed scenario generation
240 +* Advanced evidence reliability scoring
241 +* Cross-scenario comparisons
242 +* Multi-source contradiction detection
243 +* Internal Truth Landscape generation
244 +* **Increased AI-draft coverage** (more Tier B content)
245 +
246 +**Human:**
247 +
248 +* Tier A final approval
249 +* Audit sampling (continued)
250 +* Expert validation of complex domains
251 +* Quality improvement oversight
252 +
253 +=== Release 1.0 (High Automation) ===
254 +
255 +**Automated:**
256 +
257 +* Full scenario generation (comprehensive)
258 +* Bayesian verdict scoring across scenarios
259 +* Multi-scenario summary generation
260 +* Anomaly detection across federated nodes
261 +* AKEL-assisted cross-node synchronization
262 +* **Most Tier B and all Tier C** auto-published
263 +
264 +**Human:**
265 +
266 +* Tier A oversight (still required)
267 +* Strategic audits (lower sampling rates, higher value)
268 +* Ethical decisions and policy
269 +* Conflict resolution
270 +
145 145  ----
146 146  
147 -= Diagram References =
273 +== Automation Levels Diagram ==
148 148  
149 -{{include reference="FactHarbor.Specification.Diagrams.Automation Roadmap.WebHome"/}}
275 +{{include reference="FactHarbor.Archive.FactHarbor V0\.9\.23 Lost Data.Specification.Diagrams.Automation Level.WebHome"/}}
150 150  
151 -{{include reference="FactHarbor.Specification.Diagrams.Automation Level.WebHome"/}}
277 +----
152 152  
153 -{{include reference="FactHarbor.Specification.Diagrams.Manual vs Automated matrix.WebHome"/}}
279 +== Automation Roadmap Diagram ==
280 +
281 +{{include reference="FactHarbor.Archive.FactHarbor V0\.9\.23 Lost Data.Specification.Diagrams.Automation Roadmap.WebHome"/}}
282 +
283 +----
284 +
285 +== Manual vs Automated Matrix ==
286 +
287 +{{include reference="FactHarbor.Archive.FactHarbor V0\.9\.23 Lost Data.Specification.Diagrams.Manual vs Automated matrix.WebHome"/}}
288 +
289 +----
290 +
291 +== Related Pages ==
292 +
293 +* [[AKEL (AI Knowledge Extraction Layer)>>FactHarbor.Specification V0\.9\.18.AI Knowledge Extraction Layer (AKEL).WebHome]]
294 +* [[Requirements (Roles)>>FactHarbor.Specification.Requirements.WebHome]]
295 +* [[Workflows>>FactHarbor.Specification.Workflows.WebHome]]
296 +* [[Governance>>FactHarbor.Organisation.Governance]]