Skip to Content

Changes for page Specification

Last modified by Robert Schaub on 2025/12/24 20:33
From version 11.1
edited by Robert Schaub
on 2025/12/12 19:37
Change comment: Imported from XAR
To version 8.1
edited by Robert Schaub
on 2025/12/12 08:32
Change comment: Imported from XAR

Summary

Details

Page properties
Content
... ... @@ -1,4 +1,4 @@
1 -{{warning title="Version 0.8ae (Draft)"}}
1 +{{warning title="Version 0.8x (Delta Update)"}}
2 2  This document describes the **Specification** of FactHarbor. It is a working draft.
3 3  {{/warning}}
4 4  
... ... @@ -6,39 +6,17 @@
6 6  
7 7  This section defines the technical architecture, data models, and functional requirements of FactHarbor.
8 8  
9 -== Mission ==
10 -
11 -**FactHarbor brings clarity and transparency to a world full of unclear, controversial, and misleading information by shedding light on the context, assumptions, and evidence behind claims — empowering people to better understand and judge wisely.**
12 -
13 -== Purpose ==
14 -
15 -Modern society faces a deep informational crisis:
16 -* Misinformation spreads faster than corrections.
17 -* High-quality evidence is buried under noise.
18 -* Meanings shift depending on context — but this is rarely made explicit.
19 -* Users lack tools to understand *why* information conflicts.
20 -* Claims are evaluated without clearly defined assumptions.
21 -
22 -FactHarbor introduces structure, transparency, and comparative reasoning. It provides:
23 -* Multiple valid scenarios for ambiguous claims.
24 -* Transparent assumptions, definitions, and boundaries.
25 -* Full evidence provenance.
26 -* Likelihood-based verdicts (one per scenario).
27 -* Versioning and temporal change tracking.
28 -* Hybrid AI–human collaboration.
29 -
30 30  == Core Concepts ==
31 31  
32 -* **Claim**: A statement needing structured interpretation.
33 -* **Scenario**: Definitions, assumptions, boundaries, and context.
34 -* **Evidence**: Information supporting or contradicting a scenario.
35 -* **Verdict**: Likelihood estimate based on weighted evidence **for a specific scenario**.
36 -* **Summary View**: User-facing overview.
37 -* **AKEL**: AI subsystem for drafting and assistance (human supervised).
38 -* **Federation**: Decentralized nodes hosting datasets.
39 -* **Truth Landscape**: The aggregation of multiple scenario-dependent verdicts showing where a claim is plausible.
40 -* **Time Evolution**: Versioning of all entities allowing historical views.
11 +FactHarbor structures reasoning about claims into transparent, inspectable steps:
41 41  
13 +* **Claims and Claim Clusters** – people submit real-world statements; similar phrasings are grouped.
14 +* **Scenarios** – each claim is evaluated under clearly defined contexts (assumptions, definitions, boundaries).
15 +* **Evidence** – sources and data are collected and linked to specific scenarios.
16 +* **Verdicts** – **There is no single verdict for a claim.** Instead, there is a distinct verdict for **each scenario** against which the claim is evaluated.
17 +* **Truth Landscape** – the aggregation of these multiple scenario-dependent verdicts shows where (under which assumptions) a claim is plausible and where it is not.
18 +* **Time Evolution** – all important entities (claims, scenarios, evidence links, verdicts) are versioned.
19 +
42 42  == Functional Lifecycle ==
43 43  
44 44  The system follows a six-step lifecycle:
... ... @@ -46,7 +46,7 @@
46 46  1. **Claim submission**: Automatic extraction and normalisation; Cluster detection.
47 47  2. **Scenario building**: Clarifying definitions and assumptions; AI proposals with human approval.
48 48  3. **Evidence handling**: AI-assisted retrieval; Human assessment of reliability; Explicit scenario linking.
49 -4. **Verdict creation**: AI-generated draft verdicts; Human refinement; Reasoning explanations.
27 +4. **Verdict creation**: AI-generated draft verdicts **per scenario**; Human refinement; Reasoning explanations.
50 50  5. **Public presentation**: Concise summaries; Truth Landscape comparison; Deep dives.
51 51  6. **Time evolution**: Versioning of all entities; Re-evaluation triggers when evidence changes.
52 52