Changes for page Workflows

Last modified by Robert Schaub on 2025/12/24 20:34

From 1.1 to 2.1 From 7.3 to 7.4

From version 2.1

edited by Robert Schaub
on 2025/12/11 20:16

Change comment: Imported from XAR

To version 7.3

edited by Robert Schaub
on 2025/12/16 20:28

Change comment: Renamed back-links.

Raw
Rendered

Summary

Page properties (1 modified, 0 added, 0 removed)

Details

Page properties

Content

@@ -1,343 +1,410 @@
  = Workflows =
--This chapter defines the core workflows used across the FactHarbor system.
++This page describes the core workflows for content creation, review, and publication in FactHarbor.
--Each workflow describes:
++== Overview ==
--* Purpose
--* Participants
--* Steps
--* Automation vs. manual work
--* (Wherever applicable) linear ASCII flow: a → b → c → d
++FactHarbor workflows support three publication modes with risk-based review:
--Workflows included:
++* **Mode 1 (Draft)**: Internal only, failed quality gates or pending review
++* **Mode 2 (AI-Generated)**: Public with AI-generated label, passed quality gates
++* **Mode 3 (Human-Reviewed)**: Public with human-reviewed status, highest trust
--1. Claim Workflow
--2. Scenario Workflow
--3. Evidence Workflow
--4. Verdict Workflow
--5. Re-evaluation Workflow
--6. Federation Synchronization Workflow
--7. User Role & Review Workflow
--8. AKEL Workflow
--9. Global Trigger Flow
--10. Entity Lifecycle Notes
++Workflows vary by **Risk Tier** (A/B/C) and **Content Type** (Claim, Scenario, Evidence, Verdict).
  ----
--== Claim Workflow ==
++== Claim Submission & Publication Workflow ==
--**Purpose:**
--Transform raw text or input material into a normalized, classified, deduplicated, and versioned claim ready for scenario evaluation.
++=== Step 1: Claim Submission ===
--**Participants:**
--* Contributor
--* AKEL
--* Reviewer
++**Actor**: Contributor or AKEL
--=== Steps ===
++**Actions**:
--**1. Ingestion**
--* User submits text, URL, transcript, or multi-claim content
--* AKEL extracts one or multiple claims
++* Submit claim text
++* Provide initial sources (optional for human contributors, mandatory for AKEL)
++* System assigns initial AuthorType (Human or AI)
--**2. Normalization**
--* Standardizes wording
--* Reduces ambiguity
--* Flags implicit assumptions
++**Output**: Claim draft created
--**3. Classification (AKEL draft → Reviewer confirm)**
--* ClaimType
--* Domain
--* Evaluability
--* SafetyCategory
++=== Step 2: AKEL Processing ===
--**4. Duplicate & Similarity Detection**
--* Embeddings created
--* Similar claims found
--* Reviewer merges, splits, or confirms uniqueness
++**Automated Steps**:
--**5. Version Creation**
--* New ClaimVersion stored
--* Every edit creates a new immutable version
++1. Claim extraction and normalization
++2. Classification (domain, type, evaluability)
++3. Risk tier assignment (A/B/C suggested)
++4. Initial scenario generation
++5. Evidence search
++6. **Contradiction search** (mandatory)
++7. Quality gate validation
--**6. Cluster Assignment**
--* AKEL proposes cluster membership
--* Reviewer confirms
++**Output**: Processed claim with risk tier and quality gate results
--**7. Scenario Linking (optional)**
--* Existing scenarios connected
--* AKEL may propose new drafts
++=== Step 3: Quality Gate Checkpoint ===
--**8. Publication**
--* Claim becomes active and visible
++**Gates Evaluated**:
--**Flow:**
--Ingest → Normalize → Classify → Deduplicate → Cluster → Version → Publish
++* Source quality
++* Contradiction search completion
++* Uncertainty quantification
++* Structural integrity
------
++**Outcomes**:
--== Scenario Workflow ==
++* **All gates pass** → Proceed to Mode 2 publication (if Tier B or C)
++* **Any gate fails** → Mode 1 (Draft), flag for human review
++* **Tier A** → Mode 2 with warnings + auto-escalate to expert queue
--**Purpose:**
--Define the specific analytic contexts needed to evaluate each claim.
++=== Step 4: Publication (Risk-Tier Dependent) ===
--**Participants:**
--* Contributor
--* Reviewer
--* Domain Expert
--* AKEL
++**Tier C (Low Risk)**:
--=== Steps ===
++* **Direct to Mode 2**: AI-generated, public, clearly labeled
++* User can request human review
++* Sampling audit applies
--**1. Scenario Proposal**
--* Drafted by contributor or generated by AKEL
++**Tier B (Medium Risk)**:
--**2. Completion of Required Fields**
--Must include:
--* Definitions
--* Assumptions
--* ContextBoundary
--* EvaluationMethod
--* SafetyClass
--* VersionMetadata
++* **Direct to Mode 2**: AI-generated, public, clearly labeled
++* Higher audit sampling rate
++* High-engagement content may auto-escalate
--**3. Safety Interception (AKEL)**
--Flags:
--* non-falsifiable structures
--* pseudoscientific assumptions
--* unsafe contexts
++**Tier A (High Risk)**:
--**4. Redundancy & Conflict Check**
--* Similar scenarios merged
--* Contradictions flagged
++* **Mode 2 with warnings**: AI-generated, public, prominent disclaimers
++* **Auto-escalated** to expert review queue
++* User warnings displayed
++* Highest audit sampling rate
--**5. Reviewer Validation**
--Ensures clarity, neutrality, and methodological validity.
++=== Step 5: Human Review (Optional for B/C, Escalated for A) ===
--**6. Expert Approval (mandatory for high-risk domains)**
++**Triggers**:
--**7. Version Storage**
--* Each revision = new ScenarioVersion
++* User requests review
++* Audit flags issues
++* High engagement (Tier B)
++* Automatic (Tier A)
--**Flow:**
--Draft → Validate → Safety Check → Review → Expert Approval → Version → Activate
++**Process**:
++1. Reviewer/Expert examines claim
++2. Validates quality gates
++3. Checks contradiction search results
++4. Assesses risk tier appropriateness
++5. Decision: Approve, Request Changes, or Reject
++
++**Outcomes**:
++
++* **Approved** → Mode 3 (Human-Reviewed)
++* **Changes Requested** → Back to contributor or AKEL for revision
++* **Rejected** → Rejected status with reasoning
++
  ----
--== Evidence Workflow ==
++== Scenario Creation Workflow ==
--**Purpose:**
--Structure, classify, validate, version, and link evidence to scenarios.
++=== Step 1: Scenario Generation ===
--**Participants:**
--* Contributor
--* Reviewer
--* Domain Expert
--* AKEL
++**Automated (AKEL)**:
--=== Steps ===
++* Generate scenarios for claim
++* Define boundaries, assumptions, context
++* Identify evaluation methods
--**1. Evidence Submission**
--* File, dataset, URL, or extracted text
++**Manual (Expert/Reviewer)**:
--**2. Metadata Extraction (AKEL)**
--* EvidenceType
--* Category
--* Provenance
--* Study design
--* ExtractionMethod
--* ReliabilityHints
++* Create custom scenarios
++* Refine AKEL-generated scenarios
++* Add domain-specific nuances
--**3. Relevance Check**
--Reviewer verifies which scenarios the evidence applies to.
++=== Step 2: Scenario Validation ===
--**4. Reliability Assessment**
--* AKEL proposes reliability
--* Reviewer confirms
--* Expert review for complex papers
++**Quality Checks**:
--**5. ScenarioEvidenceLink Creation**
--Each link stores:
--* relevance score
--* justification
--* evidence version
++* Completeness (definitions, boundaries, assumptions clear)
++* Relevance to claim
++* Evaluability
++* No circular logic
--**6. Versioning**
--* Any update = new EvidenceVersion
++**Risk Tier Assignment**:
--**Flow:**
--Submit → Extract Metadata → Evaluate Relevance → Score Reliability → Link → Version
++* Inherits from parent claim
++* Can be overridden by expert if scenario increases/decreases risk
++=== Step 3: Scenario Publication ===
++
++**Mode 2 (AI-Generated)**:
++
++* Tier B/C scenarios can publish immediately
++* Subject to sampling audits
++
++**Mode 1 (Draft)**:
++
++* Tier A scenarios default to draft
++* Require expert validation for Mode 2 or Mode 3
++
  ----
--== Verdict Workflow ==
++== Evidence Evaluation Workflow ==
--**Purpose:**
--Generate likelihood estimates per scenario based on evidence and scenario structure.
++=== Step 1: Evidence Search & Retrieval ===
--**Participants:**
--* AKEL (drafts)
--* Reviewer
--* Domain Expert
++**AKEL Actions**:
--=== Steps ===
++* Search academic databases, reputable media
++* **Mandatory contradiction search** (counter-evidence, reservations)
++* Extract metadata (author, date, publication, methodology)
++* Assess source reliability
--**1. Evidence Aggregation**
--Collect relevant evidence versions.
++**Quality Requirements**:
--**2. Draft Verdict Generation (AKEL)**
--Outputs:
--* likelihood range
--* uncertainty factors
--* conflict detection
--* sensitivity analysis
++* Primary sources preferred
++* Diverse perspectives included
++* Echo chambers flagged
++* Conflicting evidence acknowledged
--**3. Reasoning Draft**
--Structured explanation chain generated by AKEL.
++=== Step 2: Evidence Summarization ===
--**4. Reviewer Validation**
--Ensures logic, evidence fit, no hallucinations.
++**AKEL Generates**:
--**5. Expert Review**
--Required for:
--* medicine
--* psychology
--* engineering
--* political misinformation
--* controversial or risky domains
++* Summary of evidence
++* Relevance assessment
++* Reliability score
++* Limitations and caveats
++* Conflicting evidence summary
--**6. Verdict Storage**
--* Every update creates a new VerdictVersion
++**Quality Gate**: Structural integrity, source quality
--**Flow:**
--Aggregate → Draft Verdict → Draft Explanation → Review → Expert Approval → Version
++=== Step 3: Evidence Review ===
++**Reviewer/Expert Validates**:
++
++* Accuracy of summaries
++* Appropriateness of sources
++* Completeness of contradiction search
++* Reliability assessments
++
++**Outcomes**:
++
++* **Mode 2**: Evidence summaries published as AI-generated
++* **Mode 3**: After human validation
++* **Mode 1**: Failed quality checks or pending expert review
++
  ----
--== Re-evaluation Workflow ==
++== Verdict Generation Workflow ==
--**Purpose:**
--Keep verdicts current when evidence or scenarios change.
++=== Step 1: Verdict Computation ===
--=== Trigger Types ===
++**AKEL Computes**:
--* Evidence updated, disputed, retracted
--* Scenario assumptions changed
--* Claim reclassification
--* AKEL contradiction detection
--* Federation sync
++* Verdict across scenarios
++* Confidence scores
++* Uncertainty quantification
++* Key assumptions
++* Limitations
--=== Steps ===
++**Inputs**:
--**1. Trigger Detection**
--Re-evaluation engine receives event.
++* Claim text
++* Scenario definitions
++* Evidence assessments
++* Contradiction search results
--**2. Impact Analysis**
--Find affected:
--* scenarios
--* evidence links
--* verdicts
++=== Step 2: Verdict Validation ===
--**3. AKEL Draft Re-calculation**
--New:
--* likelihood
--* reasoning
--* uncertainty
++**Quality Gates**:
--**4. Reviewer Validation**
--**5. Expert Review** (high-risk)
--**6. Version Storage**
++* All four gates apply (source, contradiction, uncertainty, structure)
++* Reasoning chain must be traceable
++* Assumptions must be explicit
--**Flow:**
--Trigger → Analyze → Recompute → Review → Expert → Version
++**Risk Tier Check**:
++* Tier A: Always requires expert validation for Mode 3
++* Tier B: Mode 2 allowed, audit sampling
++* Tier C: Mode 2 default
++
++=== Step 3: Verdict Publication ===
++
++**Mode 2 (AI-Generated Verdict)**:
++
++* Clear labeling with confidence scores
++* Uncertainty disclosure
++* Links to reasoning trail
++* User can request expert review
++
++**Mode 3 (Expert-Validated Verdict)**:
++
++* Human reviewer/expert stamp
++* Additional commentary (optional)
++* Highest trust level
++
  ----
--== Federation Synchronization Workflow ==
++== Audit Workflow ==
--**Purpose:**
--Exchange structured data between nodes.
++=== Step 1: Audit Sampling Selection ===
--=== Steps ===
--1. Detect version changes
--1. Build bundle (diff + Merkle tree + signatures)
--1. Push to peers
--1. Validate lineage + hashes
--1. Resolve conflicts (merge or branch)
--1. Optional re-evaluation
++**Stratified Sampling**:
--**Flow:**
--Change → Bundle → Push → Validate → Merge/Fork → Update
++* Risk tier priority (A > B > C)
++* Low confidence scores
++* High traffic content
++* Novel topics
++* User flags
++**Sampling Rates** (Recommendations):
++
++* Tier A: 30-50%
++* Tier B: 10-20%
++* Tier C: 5-10%
++
++=== Step 2: Audit Execution ===
++
++**Auditor Actions**:
++
++1. Review sampled AI-generated content
++2. Validate quality gates were properly applied
++3. Check contradiction search completeness
++4. Assess reasoning quality
++5. Identify errors or hallucinations
++
++**Audit Outcome**:
++
++* **Pass**: Content remains in Mode 2, logged as validated
++* **Fail**: Content flagged for review, system improvement triggered
++
++=== Step 3: Feedback Loop ===
++
++**System Improvements**:
++
++* Failed audits analyzed for patterns
++* AKEL parameters adjusted
++* Quality gates refined
++* Risk tier assignments recalibrated
++
++**Transparency**:
++
++* Audit statistics published periodically
++* Patterns shared with community
++* System improvements documented
++
  ----
--== User Role & Review Workflow ==
++== Mode Transition Workflow ==
--**Purpose:**
--Ensure correctness, neutrality, safety, and resistance to manipulation.
++=== Mode 1 → Mode 2 ===
--=== Steps ===
++**Requirements**:
--**1. Submission**
--Claim / scenario / evidence / verdict.
++* All quality gates pass
++* Risk tier B or C (or A with warnings)
++* Contradiction search completed
--**2. Auto-check (AKEL)**
--Flags unsafe content, contradictions, format issues.
++**Trigger**: Automatic upon quality gate validation
--**3. Reviewer Validation**
++=== Mode 2 → Mode 3 ===
--**4. Expert Validation**
--Required for sensitive domains.
++**Requirements**:
--**5. Moderator Oversight**
--Triggered by suspicious behavior.
++* Human reviewer/expert validation
++* Quality standards confirmed
++* For Tier A: Expert approval required
++* For Tier B/C: Reviewer approval sufficient
--**Flow:**
--Submit → Auto-check → Review → Expert → Moderator (if needed)
++**Trigger**: Human review completion
++=== Mode 3 → Mode 1 (Demotion) ===
++
++**Rare - Only if**:
++
++* New evidence contradicts verdict
++* Error discovered in reasoning
++* Source retraction
++
++**Process**:
++
++1. Content flagged for re-evaluation
++2. Moved to draft (Mode 1)
++3. Re-processed through workflow
++4. Reason for demotion documented
++
  ----
--== AKEL Workflow ==
++== User Actions Across Modes ==
--**Purpose:**
--Support extraction, drafting, structuring, and contradiction detection.
++=== On Mode 1 (Draft) Content ===
--=== Stages ===
++**Contributors**:
--**A — Input Understanding:**
--Extraction, normalization, classification.
++* Edit their own drafts
++* Submit for review
--**B — Scenario Drafting:**
--Definitions, boundaries, assumptions.
++**Reviewers/Experts**:
--**C — Evidence Processing:**
--Retrieval, summarization, ranking.
++* View and comment
++* Request changes
++* Approve for Mode 2 or Mode 3
--**D — Verdict Drafting:**
--Likelihood, explanations, uncertainties.
++=== On Mode 2 (AI-Generated) Content ===
--**E — Safety & Integrity:**
--Contradictions, hallucination detection.
++**All Users**:
--**F — Human Approval:**
--Reviewer and/or expert.
++* Read and use content
++* Request human review
++* Flag for expert attention
++* Provide feedback
--**Flow:**
--Input → Drafts → Integrity → Human Approval
++**Reviewers/Experts**:
++* Validate for Mode 3 transition
++* Edit and refine
++* Adjust risk tier if needed
++
++=== On Mode 3 (Human-Reviewed) Content ===
++
++**All Users**:
++
++* Read with highest confidence
++* Still can flag if new evidence emerges
++
++**Reviewers/Experts**:
++
++* Update if needed
++* Trigger re-evaluation if new evidence
++
  ----
--== Global Trigger Flow (Cascade) ==
++== Diagram References ==
--Trigger Sources:
--* Claim change
--* Scenario change
--* Evidence change
--* Verdict contradiction
--* Federation update
--* AKEL model improvements
++=== Claim and Scenario Lifecycle (Overview) ===
--**Cascade Flow:**
--Trigger → Dependency Graph → Re-evaluation → Updated Verdicts
++{{include reference="FactHarbor.Archive.FactHarbor V0\.9\.23 Lost Data.Organisation.Diagrams.Claim and Scenario Lifecycle (Overview).WebHome"/}}
++=== Claim and Scenario Workflow ===
++
++{{include reference="FactHarbor.Archive.FactHarbor V0\.9\.23 Lost Data.Specification.Diagrams.Claim and Scenario Workflow.WebHome"/}}
++
++=== Evidence and Verdict Workflow ===
++
++{{include reference="Test.FactHarborV09.Specification.Diagrams.Evidence and Verdict Workflow.WebHome"/}}
++
++=== Quality and Audit Workflow ===
++
++{{include reference="Test.FactHarborV09.Specification.Diagrams.Quality and Audit Workflow.WebHome"/}}
++
++
++
++{{include reference="Test.FactHarborV09.Specification.Diagrams.Manual vs Automated matrix.WebHome"/}}
++
++----
++
++== Related Pages ==
++
++* [[AKEL (AI Knowledge Extraction Layer)>>FactHarbor.Specification.AI Knowledge Extraction Layer (AKEL).WebHome]]
++* [[Automation>>FactHarbor.Specification.Automation.WebHome]]
++* [[Requirements (Roles)>>FactHarbor.Specification.Requirements.WebHome]]
++* [[Governance>>FactHarbor.Organisation.Governance]]

Changes for page Workflows

Summary

Details

Applications

Navigation

Need help?