Wiki source code of Roles & Publication Modes
Version 1.1 by Robert Schaub on 2025/12/22 14:22
Hide last authors
| author | version | line-number | content |
|---|---|---|---|
 |
1.1 | 1 | = Roles & Publication Modes = **Version:** 0.9.70 **Last Updated:** December 21, 2025 **Status:** CORRECTED - Automation Philosophy Consistent This page defines user roles and publication modes in FactHarbor. == 1. User Roles == === 1.1 Contributors === **Who**: Community members who suggest system improvements **Responsibilities:** |
| 2 | * Participate in sampling audits (analyze patterns, not individual outputs) | ||
| 3 | * Suggest algorithm/prompt improvements based on findings | ||
| 4 | * Document systematic issues observed | ||
| 5 | * Contribute to system improvement discussions **Can:** | ||
| 6 | * Edit published content (changes apply immediately, Wikipedia-style) | ||
| 7 | * Flag quality issues (for sampling audit) | ||
| 8 | * Earn reputation through contributions | ||
| 9 | * Participate in RFC (Request for Comments) processes **Cannot:** | ||
| 10 | * Approve content before publication | ||
| 11 | * Override quality gates | ||
| 12 | * Act as gatekeepers | ||
| 13 | * Manually fix individual AI outputs **Note**: Contributors improve THE SYSTEM, not individual outputs. === 1.2 Trusted Contributors === **Who**: Contributors with proven track record and domain expertise **Responsibilities:** | ||
| 14 | * Same as Contributors, plus: | ||
| 15 | * Review complex algorithm changes | ||
| 16 | * Provide domain expertise on contested claims | ||
| 17 | * Mentor new contributors **Can:** | ||
| 18 | * Everything Contributors can do, plus: | ||
| 19 | * Participate in higher-level system design decisions | ||
| 20 | * Review RFC proposals | ||
| 21 | * Access more detailed system metrics **Cannot:** | ||
| 22 | * Approve content before publication | ||
| 23 | * Override quality gates | ||
| 24 | * Act as gatekeepers **Important**: "Trusted" refers to judgment quality, NOT approval authority. === 1.3 Moderators === **Who**: Team members focused on community health and abuse prevention **Responsibilities:** | ||
| 25 | * Handle abuse, spam, and harassment | ||
| 26 | * Enforce community guidelines | ||
| 27 | * Respond to user reports | ||
| 28 | * Manage bans and appeals **Can:** | ||
| 29 | * Hide abusive content | ||
| 30 | * Ban users for policy violations | ||
| 31 | * Review appeals | ||
| 32 | * Escalate serious issues to Governing Team **Cannot:** | ||
| 33 | * Approve content for publication | ||
| 34 | * Review content quality before publication | ||
| 35 | * Override quality gates for content | ||
| 36 | * Act as editorial gatekeepers **Critical Distinction:** | ||
| 37 | ``` | ||
| 38 | Moderators handle: ABUSE (spam, harassment, violations) | ||
| 39 | Moderators DO NOT handle: CONTENT QUALITY (that's automated) | ||
| 40 | ``` === 1.4 Domain Trusted Contributors (Optional, Task-Specific) === **Who**: Subject matter specialists invited for specific high-stakes disputes **Not a permanent role**: Contacted externally when needed for contested claims in their domain **When used:** | ||
| 41 | * Medical claims with life/safety implications | ||
| 42 | * Legal interpretations with significant impact | ||
| 43 | * Scientific claims with high controversy | ||
| 44 | * Technical claims requiring specialized knowledge **Process:** | ||
| 45 | * Moderator identifies need for expert input | ||
| 46 | * Contact expert externally (don't require them to be users) | ||
| 47 | * Trusted Contributor provides written opinion with sources | ||
| 48 | * Opinion added to claim record | ||
| 49 | * Trusted Contributor acknowledged in claim **Important**: This is CONSULTATION, not APPROVAL. Their opinion is added to the evidence, not used as a gate. **User Needs served**: UN-16 (Expert validation status) == 2. Publication Modes == **Fulfills**: UN-1 (Trust indicators), UN-16 (Review status transparency) FactHarbor uses **TWO publication modes** (not three). Focus is on transparency and confidence scoring, not gatekeeping. === 2.1 Mode 1: Draft-Only === **Status**: Not visible to public **When Used:** | ||
| 50 | * Quality gates failed | ||
| 51 | * Confidence below threshold | ||
| 52 | * Structural integrity issues | ||
| 53 | * Insufficient evidence **What Happens:** | ||
| 54 | * Content remains private | ||
| 55 | * System logs failure reasons | ||
| 56 | * Prompts/algorithms improved based on patterns | ||
| 57 | * Content may be re-processed after improvements **NOT "pending human approval"** - it's blocked because it doesn't meet automated quality standards. === 2.2 Mode 2: AI-Generated (Public) === **Status**: Published and visible to all users **When Used:** | ||
| 58 | * Quality gates passed | ||
| 59 | * Confidence ≥ threshold | ||
| 60 | * Meets structural requirements | ||
| 61 | * Sufficient evidence found **Includes:** | ||
| 62 | * Confidence score displayed (0-100%) | ||
| 63 | * Risk tier badge (A/B/C) | ||
| 64 | * Quality indicators | ||
| 65 | * Clear "AI-Generated" labeling | ||
| 66 | * Sampling audit status **Labels by Risk Tier:** | ||
| 67 | * **Tier A (High Risk):** "⚠️ AI-Generated - High Impact Topic - Seek Professional Advice" | ||
| 68 | * **Tier B (Medium Risk):** "🤖 AI-Generated - May Contain Errors" | ||
| 69 | * **Tier C (Low Risk):** "🤖 AI-Generated" **User Contributions:** | ||
| 70 | * User edits apply immediately (Wikipedia model) | ||
| 71 | * All changes logged and versioned | ||
| 72 | * May be selected for sampling audit | ||
| 73 | * Reputation earned for quality contributions === REMOVED: Mode 3 === **V0.9.50 Decision:** No centralized approval workflow. **Rationale:** | ||
| 74 | * Defeats automation purpose | ||
| 75 | * Creates bottleneck | ||
| 76 | * Inconsistent quality | ||
| 77 | * Not scalable **What Replaced It:** | ||
| 78 | * Better quality gates | ||
| 79 | * Sampling audits for system improvement | ||
| 80 | * Transparent confidence scoring | ||
| 81 | * Risk-based warnings == 3. Content States == === 3.1 Published === **Status**: Visible to all users **Includes:** | ||
| 82 | * AI-generated analyses (default state after passing gates) | ||
| 83 | * User-contributed content | ||
| 84 | * Edited/improved content **Quality Indicators** (displayed with content): | ||
| 85 | * **Confidence Score**: 0-100% (AI's confidence in analysis) | ||
| 86 | * **Source Quality Score**: 0-100% (based on source track record) | ||
| 87 | * **Controversy Flag**: If high dispute/edit activity | ||
| 88 | * **Completeness Score**: % of expected fields filled | ||
| 89 | * **Last Updated**: Date of most recent change | ||
| 90 | * **Edit Count**: Number of revisions | ||
| 91 | * **Review Status**: AI-generated / Enhanced by contributors **Automatic Warnings:** | ||
| 92 | * Confidence < 60%: "Low confidence - use caution" | ||
| 93 | * Source quality < 40%: "Sources may be unreliable" | ||
| 94 | * High controversy: "Disputed - multiple interpretations exist" | ||
| 95 | * Medical/Legal/Safety domain: "Seek professional advice" **User Needs served**: UN-1 (Trust score), UN-9 (Methodology transparency), UN-15 (Evolution timeline), UN-16 (Review status) === 3.2 Hidden === **Status**: Not visible to regular users (only to moderators) **Reasons:** | ||
| 96 | * Spam or advertising | ||
| 97 | * Personal attacks or harassment | ||
| 98 | * Illegal content | ||
| 99 | * Privacy violations | ||
| 100 | * Deliberate misinformation (verified) | ||
| 101 | * Abuse or harmful content **Process:** | ||
| 102 | * Automated detection flags for moderator review | ||
| 103 | * Moderator confirms and hides | ||
| 104 | * Original author notified with reason | ||
| 105 | * Can appeal to board if disputes moderator decision **Note**: Content is hidden, not deleted (for audit trail) == 4. Role Evolution Path == **Contributor Journey:** 1. **Visitor** – Explores platform, reads documentation, may raise questions | ||
| 106 | 2. **New Contributor** – Submits first improvements (typo fixes, small clarifications, new issues) | ||
| 107 | 3. **Contributor** – Contributes regularly and follows project conventions | ||
| 108 | 4. **Trusted Contributor** – Has a track record of high-quality work and reliable judgment | ||
| 109 | 5. **Auditor** – Participates in sampling audits (pattern analysis) | ||
| 110 | 6. **Moderator** – Focuses on behavior, tone, and conflict moderation (not content quality) | ||
| 111 | 7. **Domain Expert** (optional) – Offers domain expertise without changing governance authority **Key Principle**: Low barrier to entry, transparent criteria for advancement, clear separation between content quality (automated) and behavior moderation (human). == 5. Principles == * **Low barrier to entry** for new contributors | ||
| 112 | * **Transparent criteria** for gaining and losing responsibilities | ||
| 113 | * **Clear separation** between content quality (automated) and behavioral moderation (human) | ||
| 114 | * **Documented processes** for escalation and appeal | ||
| 115 | * **No gatekeeping** for content publication | ||
| 116 | * **Immediate application** of contributions (Wikipedia model) == 6. Related Pages == * [[AKEL>>FactHarbor.Specification.AI Knowledge Extraction Layer (AKEL).WebHome]] - AI system | ||
| 117 | * [[Workflows>>FactHarbor.Specification.Workflows.WebHome]] - Process workflows | ||
| 118 | * [[Architecture>>FactHarbor.Specification.Architecture.WebHome]] - System architecture | ||
| 119 | * [[Decision Processes>>FactHarbor.Organisation.Decision-Processes.WebHome]] - Governance | ||
| 120 | * [[Requirements>>FactHarbor.Specification.Requirements.WebHome]] - All requirements **V0.9.70 CHANGES:** **REMOVED:** | ||
| 121 | - All references to "Mode 3" publication | ||
| 122 | - "Contributors validate quality gates" | ||
| 123 | - "Trusted Contributors validate outputs" | ||
| 124 | - "Moderators finalize publication" **CLARIFIED:** | ||
| 125 | - Contributors suggest system improvements (not approve outputs) | ||
| 126 | - Moderators handle abuse only (not content quality) | ||
| 127 | - Trusted Contributors provide consultation (not validation) | ||
| 128 | - Domain experts provide opinions (not approval) | ||
| 129 | - Only 2 publication modes (AI-Generated / Draft-Only) **ADDED:** | ||
| 130 | - Clear role boundaries | ||
| 131 | - Explicit "cannot" lists for each role | ||
| 132 | - Publication mode details | ||
| 133 | - Content state specifications | ||
| 134 |