kb/concepts/ bekommt Areas: layout: fuer concept, Area-Titel aus jedem Type-Spec, Schwellen-Empfehlung im lint (schliesst #59)
Files changed: - CHANGES.md - README.md - VERSION - kb/concepts/Ambient Environment Dependency.md - kb/concepts/Anti-Cramming Heuristic.md - kb/concepts/Audit Trail.md - kb/concepts/BM25.md - kb/concepts/Bulk Operations.md - kb/concepts/CI Integration.md - kb/concepts/COLLECTION.md - kb/concepts/CPPC.md - kb/concepts/Checkpoint Audit.md - kb/concepts/Claude Code Auto Mode.md - kb/concepts/Command Round-Trip Integrity.md - kb/concepts/Confidence Scoring.md - kb/concepts/Consolidation Tiers.md - kb/concepts/Content Quality Control.md - kb/concepts/Context Isolation.md - kb/concepts/Contradiction Resolution.md - kb/concepts/Cross-platform Agent Skills.md - kb/concepts/Crystallization.md - kb/concepts/Delete Rather Than Anonymize.md - kb/concepts/Denylist over Allowlist.md - kb/concepts/Detect-Repair Asymmetry.md - kb/concepts/Diff-Reviewable Agent Edits.md - kb/concepts/Dual Licensing by File Plan.md - kb/concepts/Entity Extraction.md - kb/concepts/Episodic Memory.md - kb/concepts/Event-Driven Automation.md - kb/concepts/Filter on Ingest.md - kb/concepts/Forgetting.md - kb/concepts/Graph Traversal.md - kb/concepts/Green Suite Blind Spot.md - kb/concepts/Hooks.md - kb/concepts/Hybrid Search.md - kb/concepts/INDEX.md - kb/concepts/Implementation Spectrum.md - kb/concepts/Index Scaling.md - kb/concepts/Issue Label Scheme.md - kb/concepts/Iteration and Cost Limits.md - kb/concepts/KB Migration.md - kb/concepts/KB Stack Versioning.md - kb/concepts/Knowledge Compounding.md - kb/concepts/Knowledge Graph.md - kb/concepts/LLM Wiki Pattern.md - kb/concepts/Lint Workflow.md - kb/concepts/MCP-Leseserver.md - kb/concepts/Mass-Update Gate.md - kb/concepts/Memory Lifecycle.md - kb/concepts/Mesh Sync.md - kb/concepts/Modbus.md - kb/concepts/Multi-Agent Collaboration.md - kb/concepts/Naming Convention Conflict.md - kb/concepts/OKF Compatibility.md - kb/concepts/Optional Instance Context File.md - kb/concepts/Personalization Plane.md - kb/concepts/Privacy and Governance.md - kb/concepts/Procedural Memory.md - kb/concepts/Publish-Remote Gate.md - kb/concepts/Quality Scoring.md - kb/concepts/Quality and Self-Correction.md - kb/concepts/RAG.md - kb/concepts/Reciprocal Rank Fusion.md - kb/concepts/SSD TRIM.md - kb/concepts/Scale Ceiling.md - kb/concepts/Self-Healing.md - kb/concepts/Semantic Lint Automation.md - kb/concepts/Semantic Memory.md - kb/concepts/Session Orientation.md - kb/concepts/Shared vs Private.md - kb/concepts/Split Merge Reclassify.md - kb/concepts/Split Threshold.md - kb/concepts/Structural Enforcement over Documented Rule.md - kb/concepts/Stub Threshold.md - kb/concepts/Supersession.md - kb/concepts/Three-Layer Architecture.md - kb/concepts/Token Economics.md - kb/concepts/Typed Relationships.md - kb/concepts/User Management.md - kb/concepts/Vector Search.md - kb/concepts/Work Coordination.md - kb/concepts/Workflow Extraction.md - kb/concepts/Workflow Orchestration.md - kb/concepts/Working Memory.md - kb/concepts/Write-Once Frontmatter Fields.md - kb/concepts/architectures/Consolidation Tiers.md - kb/concepts/architectures/Context Isolation.md - kb/concepts/architectures/Cross-platform Agent Skills.md - kb/concepts/architectures/Episodic Memory.md - kb/concepts/architectures/Hybrid Search.md - kb/concepts/architectures/Implementation Spectrum.md - kb/concepts/architectures/Knowledge Graph.md - kb/concepts/architectures/LLM Wiki Pattern.md - kb/concepts/architectures/MCP-Leseserver.md - kb/concepts/architectures/Memory Lifecycle.md - kb/concepts/architectures/OKF Compatibility.md - kb/concepts/architectures/Optional Instance Context File.md - kb/concepts/architectures/Personalization Plane.md - kb/concepts/architectures/Procedural Memory.md - kb/concepts/architectures/RAG.md - kb/concepts/architectures/Scale Ceiling.md - kb/concepts/architectures/Semantic Memory.md - kb/concepts/architectures/Three-Layer Architecture.md - kb/concepts/architectures/Token Economics.md - kb/concepts/architectures/Working Memory.md - kb/concepts/decisions/Delete Rather Than Anonymize.md - kb/concepts/decisions/Denylist over Allowlist.md - kb/concepts/decisions/Diff-Reviewable Agent Edits.md - kb/concepts/decisions/Dual Licensing by File Plan.md - kb/concepts/decisions/Issue Label Scheme.md - kb/concepts/decisions/KB Stack Versioning.md - kb/concepts/decisions/Structural Enforcement over Documented Rule.md - kb/concepts/patterns/Audit Trail.md - kb/concepts/patterns/BM25.md - kb/concepts/patterns/Command Round-Trip Integrity.md - kb/concepts/patterns/Confidence Scoring.md - kb/concepts/patterns/Contradiction Resolution.md - kb/concepts/patterns/Entity Extraction.md - kb/concepts/patterns/Filter on Ingest.md - kb/concepts/patterns/Forgetting.md - kb/concepts/patterns/Graph Traversal.md - kb/concepts/patterns/Mesh Sync.md - kb/concepts/patterns/Quality Scoring.md - kb/concepts/patterns/Reciprocal Rank Fusion.md - kb/concepts/patterns/Self-Healing.md - kb/concepts/patterns/Shared vs Private.md - kb/concepts/patterns/Typed Relationships.md - kb/concepts/patterns/Vector Search.md - kb/concepts/patterns/Work Coordination.md - kb/concepts/problems/Ambient Environment Dependency.md - kb/concepts/problems/Detect-Repair Asymmetry.md - kb/concepts/problems/Green Suite Blind Spot.md - kb/concepts/problems/Naming Convention Conflict.md - kb/concepts/problems/Write-Once Frontmatter Fields.md - kb/concepts/protocols/CPPC.md - kb/concepts/protocols/Modbus.md - kb/concepts/protocols/SSD TRIM.md - kb/concepts/workflows/Anti-Cramming Heuristic.md - kb/concepts/workflows/Bulk Operations.md - kb/concepts/workflows/CI Integration.md - kb/concepts/workflows/Checkpoint Audit.md - kb/concepts/workflows/Claude Code Auto Mode.md - kb/concepts/workflows/Content Quality Control.md - kb/concepts/workflows/Crystallization.md - kb/concepts/workflows/Event-Driven Automation.md - kb/concepts/workflows/Hooks.md - kb/concepts/workflows/Index Scaling.md - kb/concepts/workflows/Iteration and Cost Limits.md - kb/concepts/workflows/KB Migration.md - kb/concepts/workflows/Knowledge Compounding.md - kb/concepts/workflows/Lint Workflow.md - kb/concepts/workflows/Mass-Update Gate.md - kb/concepts/workflows/Multi-Agent Collaboration.md - kb/concepts/workflows/Privacy and Governance.md - kb/concepts/workflows/Publish-Remote Gate.md - kb/concepts/workflows/Quality and Self-Correction.md - kb/concepts/workflows/Semantic Lint Automation.md - kb/concepts/workflows/Session Orientation.md - kb/concepts/workflows/Split Merge Reclassify.md - kb/concepts/workflows/Split Threshold.md - kb/concepts/workflows/Stub Threshold.md - kb/concepts/workflows/Supersession.md - kb/concepts/workflows/User Management.md - kb/concepts/workflows/Workflow Extraction.md - kb/concepts/workflows/Workflow Orchestration.md - kb/index.md - kb/log.md - tools/CONTRACT.md - tools/README.md - tools/chemenu/catalog.py - tools/chemenu/commands/index_build.py - tools/chemenu/lint_core.py - tools/chemenu/tests/conftest.py - tools/chemenu/tests/test_cite_cmd.py - tools/chemenu/tests/test_git_publish.py - tools/chemenu/tests/test_index_build.py - tools/chemenu/tests/test_lint.py - tools/chemenu/tests/test_new_page.py - tools/chemenu/tests/test_provenance.py - tools/chemenu/tests/test_type_resolver.py - tools/chemenu/tests/test_xref.py - types/concept.md - types/type-spec.md
This commit is contained in:
@@ -0,0 +1,169 @@
|
||||
---
|
||||
type: types/concept.md
|
||||
concept_type: pattern
|
||||
tags: [memory, retention, decay, ebbinghaus]
|
||||
created: 2026-07-26
|
||||
modified: 2026-08-29
|
||||
related:
|
||||
- part-of: Memory Lifecycle
|
||||
- see-also: Confidence Scoring
|
||||
- rests-on: Consolidation Tiers
|
||||
sources: [Source - LLM Wiki v2]
|
||||
confidence: 0.90
|
||||
confidence_base: 0.90
|
||||
provenance: sourced
|
||||
summary: Muster zur Wissensbindung, das selten abgerufene Fakten schrittweise zurückstuft, modelliert nach der Ebbinghausschen Vergessenskurve.
|
||||
---
|
||||
# Forgetting
|
||||
|
||||
**Typ:** Pattern (Wissensspeicherungsverwaltung)
|
||||
|
||||
## Definition
|
||||
|
||||
Forgetting ist der Mechanismus, durch den **Fakten, die einmal wichtig waren, aber seit Monaten nicht aufgerufen oder verstärkt wurden, allmählich aus der Bedeutung im Wiki verschwinden**. Dies implementiert eine Aufbewahrungskurve, die sich von Ebbinghaus' Vergessenskurve aus der kognitiven Psychologie inspiriert.
|
||||
|
||||
Dies ist eine Kernkomponente der Verwaltung des [[Memory Lifecycle]] und stellt sicher, dass das Wiki nicht zu einem lauten Friedhof veralteter Informationen wird.
|
||||
|
||||
## Kernpunkte
|
||||
|
||||
### Das Problem
|
||||
|
||||
Ohne Vergessen:
|
||||
- Jedes Wissensstück wird für immer als gleich wichtig behandelt
|
||||
- Alte, irrelevante Informationen verstopfen das Wiki
|
||||
- Suchergebnisse werden mit veralteten Inhalten verunreinigt
|
||||
- Das Wiki wird zu einer Rumpelkammer
|
||||
|
||||
### Die Lösung
|
||||
|
||||
**Allmähliche Herabstufung** statt Löschung implementieren:
|
||||
|
||||
- Fakten werden **nicht gelöscht** (historischer Datensatz bleibt erhalten)
|
||||
- Fakten werden **in Suche und Synthese herabgestuft**
|
||||
- Herabstufung ist **allmählich** (nicht plötzlich)
|
||||
- Unterschiedliche **Verfallsraten** für verschiedene Wissenstypen
|
||||
|
||||
### Aufbewahrungskurve
|
||||
|
||||
Inspiriert von Ebbinghaus' Vergessenskurve:
|
||||
|
||||
```
|
||||
Vertrauen/Priorität
|
||||
1.0 │ *
|
||||
│ *
|
||||
│ *
|
||||
│ *
|
||||
0.8 │ *
|
||||
│ *
|
||||
│ *
|
||||
│ *
|
||||
0.6 │ *
|
||||
│ *
|
||||
│ *
|
||||
│ *
|
||||
0.4 │ *
|
||||
│ *
|
||||
│*
|
||||
0.2 ┼───────────────────────────────── Zeit
|
||||
0 1m 3m 6m 1j 2j
|
||||
```
|
||||
|
||||
**Grundsatz:** Jede **Verstärkung** (Zugriff, Bestätigung aus neuer Quelle) **setzt die Kurve** für diesen Fakt **zurück**.
|
||||
|
||||
### Verfallsraten nach Wissenstyp
|
||||
|
||||
| Wissenstyp | Verfallsrate | Begründung |
|
||||
|----------------|------------|-----------|
|
||||
| Architekturentscheidungen | Sehr langsam (1% alle 6 Monate) | Langzeitwirkung, ändern sich selten |
|
||||
| Systemkonfigurationen | Langsam (1% pro Monat) | Stabil, aber kann sich ändern |
|
||||
| Bug-Berichte | Schnell (5% pro Monat) | Vorübergehend, oft behoben |
|
||||
| Notizen aus Meetings | Schnell (5% pro Monat) | Zeitkritischer Kontext |
|
||||
| Forschungsergebnisse | Mittel (2% pro Monat) | Kann veraltet werden |
|
||||
| Best Practices | Sehr langsam (1% alle 3 Monate) | Im Laufe der Zeit bewährt |
|
||||
|
||||
### Implementierung
|
||||
|
||||
**Zu verfolgene Metadaten:**
|
||||
```yaml
|
||||
last_accessed: YYYY-MM-DD
|
||||
last_reinforced: YYYY-MM-DD # Zugriff oder Bestätigung neuer Quelle
|
||||
creation_date: YYYY-MM-DD
|
||||
knowledge_type: [architecture|config|bug|meeting|research|best-practice]
|
||||
current_priority: 0.XX # 0.0-1.0
|
||||
```
|
||||
|
||||
**Verfallsberechnung:**
|
||||
```
|
||||
months_since_reinforcement = (today - last_reinforced).months
|
||||
decay_rate = get_decay_rate(knowledge_type)
|
||||
priority = max(0.2, initial_priority - (months_since_reinforcement * decay_rate))
|
||||
```
|
||||
|
||||
**Verstärkungsauslöser:**
|
||||
- Seite wird aufgerufen/gelesen
|
||||
- Neue Quelle bestätigt die Information
|
||||
- Mensch verstärkt explizit
|
||||
- Verwandte Information wird aufgerufen
|
||||
|
||||
### Integration mit anderen Mechanismen
|
||||
|
||||
**Mit [[Confidence Scoring]]:**
|
||||
- Vergessen beeinträchtigt **Priorität** in der Suche
|
||||
- Vertrauens-Scoring beeinträchtigt **Zuverlässigkeit** des Fakts
|
||||
- Beide funktionieren zusammen: niedrig-vertrauen, niedrig-priorität Fakten erscheinen zuletzt
|
||||
|
||||
**Mit [[Consolidation Tiers]]:**
|
||||
- Höhere Tiers haben **langsamere Verfallsraten**
|
||||
- Prozedurales Gedächtnis (Tier 4) kann **keinen Verfall** haben
|
||||
- Arbeitsgedächtnis (Tier 1) hat **schnellsten Verfall**
|
||||
|
||||
**Mit [[Supersession]]:**
|
||||
- Verdrängte Fakten **verfallen sofort** auf Mindestpriorität
|
||||
- Aber werden **zu historischen Referenzen bewahrt**
|
||||
|
||||
### Suchintegration
|
||||
|
||||
Fakten mit niedrigerer Priorität:
|
||||
- Erscheinen **später** in Suchergebnissen
|
||||
- Werden **mit geringerer Wahrscheinlichkeit** in die Synthese einbezogen
|
||||
- Erfordern **explizitere** Abfragen zum Auftauchen
|
||||
- Können **unterhalb eines bestimmten Schwellenwerts verborgen** sein (konfigurierbar)
|
||||
|
||||
## Vorteile
|
||||
|
||||
- **Relevanz:** Benutzer sehen zuerst die wichtigsten Informationen
|
||||
- **Sauberkeit:** Wiki wird nicht mit alten Informationen verstopft
|
||||
- **Erhaltung:** Historische Informationen sind noch zugänglich
|
||||
- **Anpassungsfähigkeit:** Wiki entwickelt sich mit sich ändernden Bedürfnissen
|
||||
- **Effizienz:** Suche und Synthese sind effizienter
|
||||
|
||||
## Wann zu verwenden
|
||||
|
||||
- Jedes Wiki, das im Laufe der Zeit wachsen soll
|
||||
- Bereiche mit sich entwickelndem Wissen
|
||||
- Situationen, in denen sich die Relevanz von Informationen ändert
|
||||
- Große Wissensdatenbanken
|
||||
|
||||
## Wann NICHT zu verwenden
|
||||
|
||||
- Kleine, statische Wikis
|
||||
- Bereiche, in denen alle Informationen gleich wichtig sind
|
||||
- Situationen, in denen historische Vollständigkeit entscheidend ist
|
||||
|
||||
## Verwandte Concepts
|
||||
|
||||
- [[Supersession]] - Umgang mit veralteten Informationen
|
||||
- [[LLM Wiki Pattern]] - Gesamtmuster
|
||||
|
||||
## Siehe auch
|
||||
|
||||
- [[Event-Driven Automation]] (für automatisiertes Verstärkungstracking)
|
||||
- [[Quality and Self-Correction]] (für verwandte Qualitätsmechanismen)
|
||||
|
||||
<!-- wikitool:links -->
|
||||
## Beziehungen
|
||||
|
||||
- **part-of:** [[Memory Lifecycle]]
|
||||
- **see-also:** [[Confidence Scoring]]
|
||||
- **rests-on:** [[Consolidation Tiers]]
|
||||
<!-- /wikitool:links -->
|
||||
Reference in New Issue
Block a user