Changes for page Workflows

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

From 7.5 to 7.4

From version 7.4

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

Change comment: Renamed back-links.

To version 1.1

edited by Robert Schaub
on 2025/12/11 16:36

Change comment: Imported from XAR

Raw
Rendered

Summary

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

Details

Page properties

Content

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