Skip to Content

Changes for page Automation

Last modified by Robert Schaub on 2025/12/24 20:34
From version 4.1
edited by Robert Schaub
on 2025/12/12 09:32
Change comment: Imported from XAR
To version 7.2
edited by Robert Schaub
on 2025/12/16 20:25
Change comment: Update document after refactoring.

Summary

Details

Page properties
Parent
... ... @@ -1,1 +1,1 @@
1 -FactHarbor.Specification.WebHome
1 +FactHarbor.Archive.FactHarbor.Specification.WebHome
Content
... ... @@ -1,17 +1,18 @@
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 +* Risk-based publication model
7 +* Quality gates for AI-generated content
7 7  * What must remain human-only
8 -* What AI (AKEL) can draft
9 +* 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  
12 -== POC v1 (Fully Automated "Text to Truth Landscape") ==
13 +== POC v1 (AI-Generated Publication Demonstration) ==
13 13  
14 -The goal of POC v1 is to validate the automated reasoning capabilities of the data model without human intervention.
15 +The goal of POC v1 is to validate the automated reasoning capabilities and demonstrate AI-generated content publication.
15 15  
16 16  === Workflow ===
17 17  
... ... @@ -19,93 +19,252 @@
19 19  1. **Deep Analysis (Background)**: The system autonomously performs the full pipeline **before** displaying the text:
20 20  * Extraction & Normalisation
21 21  * Scenario & Sub-query generation
22 -* Evidence retrieval & Verdict computation
23 +* Evidence retrieval with **contradiction search**
24 +* Quality gate validation
25 +* Verdict computation
23 23  1. **Visualisation (Extraction & Marking)**: The system displays the text with claims extracted and marked.
24 24  * **Verdict-Based Coloring**: The extraction highlights (e.g. Orange/Green) are chosen **according to the computed verdict** for each claim.
28 +* **AI-Generated Label**: Clear indication that content is AI-produced
25 25  1. **Inspection**: User clicks a highlighted claim to see the **Reasoning Trail**, showing exactly which evidence and sub-queries led to that verdict.
26 26  
27 27  === Technical Scope ===
28 28  
29 -* **Fully Automated**: No human-in-the-loop for this phase.
30 -* **Structured Sub-Queries**: Logic is generated by decomposing claims into the FactHarbor data model.
31 -* **Latency**: Focus on accuracy of reasoning over real-time speed for v1.
33 +* **AI-Generated Publication**: Content published as Mode 2 (AI-Generated, no prior human review)
34 +* **Quality Gates Active**: All automated quality checks enforced
35 +* **Contradiction Search Demonstrated**: Shows counter-evidence and reservation detection
36 +* **Risk Tier Classification**: POC shows tier assignment (demo purposes)
37 +* **No Human Approval Gate**: Demonstrates scalable AI publication
38 +* **Structured Sub-Queries**: Logic generated by decomposing claims into the FactHarbor data model
32 32  
33 33  ----
34 34  
35 -== Manual vs Automated Responsibilities ==
42 +== Publication Model ==
36 36  
37 -=== Human-Only Tasks ===
44 +FactHarbor implements a risk-based publication model with three modes:
38 38  
39 -These require human judgment, ethics, or contextual interpretation:
46 +=== Mode 1: Draft-Only ===
47 +* Failed quality gates
48 +* High-risk content pending expert review
49 +* Internal review queue only
40 40  
41 -* Definition of key terms in claims
42 -* Approval or rejection of scenarios
43 -* Interpretation of evidence in context
44 -* Final verdict approval
45 -* Governance decisions and dispute resolution
46 -* High-risk domain oversight
47 -* Ethical boundary decisions (especially medical, political, psychological)
51 +=== Mode 2: AI-Generated (Public) ===
52 +* Passed all quality gates
53 +* Risk tier B or C
54 +* Clear AI-generated labeling
55 +* Users can request human review
48 48  
49 -=== Semi-Automated (AI Draft → Human Review) ===
57 +=== Mode 3: Human-Reviewed ===
58 +* Validated by human reviewers/experts
59 +* "Human-Reviewed" status badge
60 +* Required for Tier A content publication
50 50  
51 -AKEL can draft these, but humans must refine/approve:
62 +See [[AKEL page>>FactHarbor.Specification.AI Knowledge Extraction Layer (AKEL).WebHome]] for detailed publication mode descriptions.
52 52  
53 -* Scenario structures (definitions, assumptions, context)
54 -* Evaluation methods
55 -* Evidence relevance suggestions
56 -* Reliability hints
57 -* Verdict reasoning chains
58 -* Uncertainty and limitations
59 -* Scenario comparison explanations
60 -* Suggestions for merging or splitting scenarios
61 -* Draft public summaries
64 +----
62 62  
63 -=== Fully Automated Structural Tasks ===
66 +== Risk Tiers and Automation Levels ==
64 64  
68 +=== Tier A (High Risk) ===
69 +* **Domains**: Medical, legal, elections, safety, security
70 +* **Automation**: AI can draft, human review required for "Human-Reviewed" status
71 +* **AI publication**: Allowed with prominent disclaimers and warnings
72 +* **Audit rate**: Recommendation: 30-50%
73 +
74 +=== Tier B (Medium Risk) ===
75 +* **Domains**: Complex policy, science, causality claims
76 +* **Automation**: AI can draft and publish (Mode 2)
77 +* **Human review**: Optional, audit-based
78 +* **Audit rate**: Recommendation: 10-20%
79 +
80 +=== Tier C (Low Risk) ===
81 +* **Domains**: Definitions, established facts, historical data
82 +* **Automation**: AI publication default
83 +* **Human review**: On request or via sampling
84 +* **Audit rate**: Recommendation: 5-10%
85 +
86 +----
87 +
88 +== Human-Only Tasks ==
89 +
90 +These require human judgment and cannot be automated:
91 +
92 +* **Ethical boundary decisions** (especially medical, political, psychological harm assessment)
93 +* **Dispute resolution** between conflicting expert opinions
94 +* **Governance policy** setting and enforcement
95 +* **Final authority** on Tier A "Human-Reviewed" status
96 +* **Audit system oversight** and quality standard definition
97 +* **Risk tier policy** adjustments based on societal context
98 +
99 +----
100 +
101 +== AI-Draft with Audit (Semi-Automated) ==
102 +
103 +AKEL drafts these; humans validate via sampling audits:
104 +
105 +* **Scenario structures** (definitions, assumptions, context)
106 +* **Evaluation methods** and reasoning chains
107 +* **Evidence relevance** assessment and ranking
108 +* **Reliability scoring** and source evaluation
109 +* **Verdict reasoning** with uncertainty quantification
110 +* **Contradiction and reservation** identification
111 +* **Scenario comparison** explanations
112 +* **Public summaries** and accessibility text
113 +
114 +Most Tier B and C content remains in AI-draft status unless:
115 +* Users request human review
116 +* Audits identify errors
117 +* High engagement triggers review
118 +* Community flags issues
119 +
120 +----
121 +
122 +== Fully Automated Structural Tasks ==
123 +
65 65  These require no human interpretation:
66 66  
126 +* **Claim normalization** (canonical form generation)
127 +* **Duplicate detection** (vector embeddings, clustering)
128 +* **Evidence metadata extraction** (dates, authors, publication info)
129 +* **Basic reliability heuristics** (source reputation scoring)
130 +* **Contradiction detection** (conflicting statements across sources)
131 +* **Re-evaluation triggers** (new evidence, source updates)
132 +* **Layout generation** (diagrams, summaries, UI presentation)
133 +* **Federation integrity checks** (cross-node data validation)
134 +
135 +----
136 +
137 +== Quality Gates (Automated) ==
138 +
139 +Before AI-draft publication (Mode 2), content must pass:
140 +
141 +1. **Source Quality Gate**
142 + * Primary sources verified
143 + * Citations complete and accessible
144 + * Source reliability scored
145 +
146 +2. **Contradiction Search Gate** (MANDATORY)
147 + * Counter-evidence actively sought
148 + * Reservations and limitations identified
149 + * Bubble detection (echo chambers, conspiracy theories)
150 + * Diverse perspective verification
151 +
152 +3. **Uncertainty Quantification Gate**
153 + * Confidence scores calculated
154 + * Limitations stated
155 + * Data gaps disclosed
156 +
157 +4. **Structural Integrity Gate**
158 + * No hallucinations detected
159 + * Logic chain valid
160 + * References verifiable
161 +
162 +See [[AKEL page>>FactHarbor.Specification.AI Knowledge Extraction Layer (AKEL).WebHome]] for detailed quality gate specifications.
163 +
164 +----
165 +
166 +== Audit System ==
167 +
168 +Instead of reviewing all AI output, systematic sampling audits ensure quality:
169 +
170 +=== Stratified Sampling ===
171 +* Risk tier (A > B > C sampling rates)
172 +* Confidence scores (low confidence → more audits)
173 +* Traffic/engagement (popular content audited more)
174 +* Novelty (new topics/claim types prioritized)
175 +* User flags and disagreement signals
176 +
177 +=== Continuous Improvement Loop ===
178 +Audit findings improve:
179 +* Query templates
180 +* Source reliability weights
181 +* Contradiction detection algorithms
182 +* Risk tier assignment rules
183 +* Bubble detection heuristics
184 +
185 +=== Transparency ===
186 +* Audit statistics published
187 +* Accuracy rates by tier reported
188 +* System improvements documented
189 +
190 +----
191 +
192 +== Automation Roadmap ==
193 +
194 +Automation capabilities increase with system maturity while maintaining quality oversight.
195 +
196 +=== POC (Current Focus) ===
197 +
198 +**Automated:**
67 67  * Claim normalization
68 -* Duplicate & cluster detection (vector embeddings)
200 +* Scenario template generation
69 69  * Evidence metadata extraction
70 -* Basic reliability heuristics
71 -* Contradiction detection
72 -* Re-evaluation triggers
73 -* Batch layout generation (diagrams, summaries)
74 -* Federation integrity checks
202 +* Simple verdict drafts
203 +* **AI-generated publication** (Mode 2, with quality gates)
204 +* **Contradiction search**
205 +* **Risk tier assignment**
75 75  
76 -== Automation Roadmap ==
207 +**Human:**
208 +* High-risk content validation (Tier A)
209 +* Sampling audits across all tiers
210 +* Quality standard refinement
211 +* Governance decisions
77 77  
78 -Automation increases with maturity.
213 +=== Beta 0 (Enhanced Automation) ===
79 79  
80 -=== POC (Low Automation) ===
81 -* **Automated**: Claim normalization, Light scenario templates, Metadata extraction, Internal drafts.
82 -* **Human**: All scenario definitions, Evidence interpretation, Verdict creation, Governance.
215 +**Automated:**
216 +* Detailed scenario generation
217 +* Advanced evidence reliability scoring
218 +* Cross-scenario comparisons
219 +* Multi-source contradiction detection
220 +* Internal Truth Landscape generation
221 +* **Increased AI-draft coverage** (more Tier B content)
83 83  
84 -=== Beta 0 (Medium Automation) ===
85 -* **Automated**: Detailed scenario drafts, Evidence reliability scoring, Cross-scenario comparisons, Contradiction detection.
86 -* **Human**: Scenario approval, Final verdict validation.
223 +**Human:**
224 +* Tier A final approval
225 +* Audit sampling (continued)
226 +* Expert validation of complex domains
227 +* Quality improvement oversight
87 87  
88 88  === Release 1.0 (High Automation) ===
89 -* **Automated**: Full scenario generation, Evidence relevance ranking, Bayesian verdict scoring, Anomaly detection, Federation sync.
90 -* **Human**: Final approval, Ethical decisions, Oversight.
91 91  
92 -== Automation Levels ==
231 +**Automated:**
232 +* Full scenario generation (comprehensive)
233 +* Bayesian verdict scoring across scenarios
234 +* Multi-scenario summary generation
235 +* Anomaly detection across federated nodes
236 +* AKEL-assisted cross-node synchronization
237 +* **Most Tier B and all Tier C** auto-published
93 93  
94 -* **Level 0 — Human-Centric (POC)**: AI is purely advisory, nothing auto-published.
95 -* **Level 1 — Assisted (Beta 0)**: AI drafts structures; humans approve each part.
96 -* **Level 2 — Structured (Release 1.0)**: AI produces near-complete drafts; humans refine.
97 -* **Level 3 — Distributed Intelligence (Future)**: Nodes exchange embeddings and alerts; humans still approve.
239 +**Human:**
240 +* Tier A oversight (still required)
241 +* Strategic audits (lower sampling rates, higher value)
242 +* Ethical decisions and policy
243 +* Conflict resolution
98 98  
99 -== Automation Matrix ==
245 +----
100 100  
101 -* **Always Human**: Final verdict, Scenario validity, Ethics, Disputes.
102 -* **Mostly AI**: Normalization, Clustering, Metadata, Heuristics, Alerts.
103 -* **Mixed**: Definitions, Boundaries, Assumptions, Reasoning.
247 +== Automation Levels Diagram ==
104 104  
105 -== Diagram References ==
249 +{{include reference="Test.FactHarborV09.Specification.Diagrams.Automation Level.WebHome"/}}
106 106  
107 -{{include reference="FactHarbor.Specification.Diagrams.Automation Roadmap.WebHome"/}}
251 +----
108 108  
109 -{{include reference="FactHarbor.Specification.Diagrams.Automation Level.WebHome"/}}
253 +== Automation Roadmap Diagram ==
110 110  
111 -{{include reference="FactHarbor.Specification.Diagrams.Manual vs Automated matrix.WebHome"/}}
255 +{{include reference="Test.FactHarborV09.Specification.Diagrams.Automation Roadmap.WebHome"/}}
256 +
257 +----
258 +
259 +== Manual vs Automated Matrix ==
260 +
261 +{{include reference="Test.FactHarborV09.Specification.Diagrams.Manual vs Automated matrix.WebHome"/}}
262 +
263 +----
264 +
265 +== Related Pages ==
266 +
267 +* [[AKEL (AI Knowledge Extraction Layer)>>FactHarbor.Specification.AI Knowledge Extraction Layer (AKEL).WebHome]]
268 +* [[Requirements (Roles)>>FactHarbor.Specification.Requirements.WebHome]]
269 +* [[Workflows>>FactHarbor.Specification.Workflows.WebHome]]
270 +* [[Governance>>FactHarbor.Organisation.Governance]]
271 +