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 7.2
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
... ... @@ -1,153 +1,271 @@
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  
13 +== POC v1 (AI-Generated Publication Demonstration) ==
14 +
15 +The goal of POC v1 is to validate the automated reasoning capabilities and demonstrate AI-generated content publication.
16 +
17 +=== Workflow ===
18 +
19 +1. **Input**: User pastes a block of raw text.
20 +1. **Deep Analysis (Background)**: The system autonomously performs the full pipeline **before** displaying the text:
21 +* Extraction & Normalisation
22 +* Scenario & Sub-query generation
23 +* Evidence retrieval with **contradiction search**
24 +* Quality gate validation
25 +* Verdict computation
26 +1. **Visualisation (Extraction & Marking)**: The system displays the text with claims extracted and marked.
27 +* **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
29 +1. **Inspection**: User clicks a highlighted claim to see the **Reasoning Trail**, showing exactly which evidence and sub-queries led to that verdict.
30 +
31 +=== Technical Scope ===
32 +
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
39 +
12 12  ----
13 13  
14 -= Manual vs Automated Responsibilities =
42 +== Publication Model ==
15 15  
44 +FactHarbor implements a risk-based publication model with three modes:
45 +
46 +=== Mode 1: Draft-Only ===
47 +* Failed quality gates
48 +* High-risk content pending expert review
49 +* Internal review queue only
50 +
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
56 +
57 +=== Mode 3: Human-Reviewed ===
58 +* Validated by human reviewers/experts
59 +* "Human-Reviewed" status badge
60 +* Required for Tier A content publication
61 +
62 +See [[AKEL page>>FactHarbor.Specification.AI Knowledge Extraction Layer (AKEL).WebHome]] for detailed publication mode descriptions.
63 +
64 +----
65 +
66 +== Risk Tiers and Automation Levels ==
67 +
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 +
16 16  == Human-Only Tasks ==
17 17  
18 -These require human judgment, ethics, or contextual interpretation:
90 +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)
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
27 27  
28 -== Semi-Automated (AI Draft → Human Review) ==
99 +----
29 29  
30 -AKEL can draft these, but humans must refine/approve:
101 +== 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
103 +AKEL drafts these; humans validate via sampling audits:
41 41  
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 +
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
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)
54 54  
55 55  ----
56 56  
57 -= Automation Roadmap =
137 +== Quality Gates (Automated) ==
58 58  
59 -Automation increases with maturity.
139 +Before AI-draft publication (Mode 2), content must pass:
60 60  
61 -== POC (Low Automation) ==
141 +1. **Source Quality Gate**
142 + * Primary sources verified
143 + * Citations complete and accessible
144 + * Source reliability scored
62 62  
63 -=== Automated ===
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:**
64 64  * Claim normalization
65 -* Light scenario templates
200 +* Scenario template generation
66 66  * Evidence metadata extraction
67 -* Simple verdict drafts (internal only)
202 +* Simple verdict drafts
203 +* **AI-generated publication** (Mode 2, with quality gates)
204 +* **Contradiction search**
205 +* **Risk tier assignment**
68 68  
69 -=== Human ===
70 -* All scenario definitions
71 -* Evidence interpretation
72 -* Verdict creation
73 -* Governance
207 +**Human:**
208 +* High-risk content validation (Tier A)
209 +* Sampling audits across all tiers
210 +* Quality standard refinement
211 +* Governance decisions
74 74  
75 -== Beta 0 (Medium Automation) ==
213 +=== Beta 0 (Enhanced Automation) ===
76 76  
77 -=== Automated ===
78 -* Detailed scenario drafts
79 -* Evidence reliability scoring
215 +**Automated:**
216 +* Detailed scenario generation
217 +* Advanced evidence reliability scoring
80 80  * Cross-scenario comparisons
81 -* Contradiction detection (local + remote nodes)
82 -* Internal Truth Landscape drafts
219 +* Multi-source contradiction detection
220 +* Internal Truth Landscape generation
221 +* **Increased AI-draft coverage** (more Tier B content)
83 83  
84 -=== Human ===
85 -* Scenario approval
86 -* 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 -== Release 1.0 (High Automation) ==
229 +=== Release 1.0 (High Automation) ===
89 89  
90 -=== Automated ===
91 -* Full scenario generation (definitions, assumptions, boundaries)
92 -* Evidence relevance scoring and ranking
93 -* Bayesian verdict scoring across scenario sets
231 +**Automated:**
232 +* Full scenario generation (comprehensive)
233 +* Bayesian verdict scoring across scenarios
94 94  * Multi-scenario summary generation
95 -* Anomaly detection across nodes
96 -* AKEL-assisted federated synchronization
235 +* Anomaly detection across federated nodes
236 +* AKEL-assisted cross-node synchronization
237 +* **Most Tier B and all Tier C** auto-published
97 97  
98 -=== Human ===
99 -* Final approval of all scenarios and verdicts
100 -* Ethical decisions
101 -* Oversight and conflict resolution
239 +**Human:**
240 +* Tier A oversight (still required)
241 +* Strategic audits (lower sampling rates, higher value)
242 +* Ethical decisions and policy
243 +* Conflict resolution
102 102  
103 103  ----
104 104  
105 -= Automation Levels =
247 +== Automation Levels Diagram ==
106 106  
107 -== Level 0 — Human-Centric (POC) ==
108 -AI is purely advisory, nothing auto-published.
249 +{{include reference="Test.FactHarborV09.Specification.Diagrams.Automation Level.WebHome"/}}
109 109  
110 -== Level 1 — Assisted (Beta 0) ==
111 -AI drafts structures; humans approve each part.
251 +----
112 112  
113 -== Level 2 — Structured (Release 1.0) ==
114 -AI produces near-complete drafts; humans refine.
253 +== Automation Roadmap Diagram ==
115 115  
116 -== Level 3 — Distributed Intelligence (Future) ==
117 -Nodes exchange embeddings, contradiction alerts, and scenario templates.
118 -Humans still approve everything.
255 +{{include reference="Test.FactHarborV09.Specification.Diagrams.Automation Roadmap.WebHome"/}}
119 119  
120 120  ----
121 121  
122 -= Automation Matrix =
259 +== Manual vs Automated Matrix ==
123 123  
124 -== Always Human ==
125 -* Final verdict approval
126 -* Scenario validity
127 -* Ethical decisions
128 -* Dispute resolution
261 +{{include reference="Test.FactHarborV09.Specification.Diagrams.Manual vs Automated matrix.WebHome"/}}
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
137 -
138 -== Mixed ==
139 -* Definitions of ambiguous terms
140 -* Boundary choices
141 -* Assumption evaluation
142 -* Evidence selection
143 -* Verdict reasoning
144 -
145 145  ----
146 146  
147 -= Diagram References =
265 +== Related Pages ==
148 148  
149 -{{include reference="FactHarbor.Specification.Diagrams.Automation Roadmap.WebHome"/}}
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]]
150 150  
151 -{{include reference="FactHarbor.Specification.Diagrams.Automation Level.WebHome"/}}
152 -
153 -{{include reference="FactHarbor.Specification.Diagrams.Manual vs Automated matrix.WebHome"/}}