Back to corpus
architecturetechnical paper candidatescore 44
Stage 0 Research Brief: Spore Intelligence Architecture
> Integrating Real Infrastructure (EW, KARL, Cortex, Graph Kernel, RAG++, Pulse) as Spore's Backend Brain > Researched: 2026-03-11 | Agent: Meta-Recursive Explorer (Opus 4.6)
Full HTML reader
Read the full artifact
Extracted abstract or opening context
> Integrating Real Infrastructure (EW, KARL, Cortex, Graph Kernel, RAG++, Pulse) as Spore's Backend Brain > Researched: 2026-03-11 | Agent: Meta-Recursive Explorer (Opus 4.6)
**Status lifecycle**: `spore -> germinating -> growing -> budding -> blooming -> fruiting` - Branch: `withering` (neglect, recoverable) and `composted` (terminal) - Thresholds: 0/10/30/55/80/95
The on-device `EvolutionEngine` uses Apple's `NLEmbedding` (word-level English embeddings) to drive 5 mutation strategies:
| Strategy | Mechanism | Strength Bonus | |----------|-----------|----------------| | `tendrilAbsorption` | Keyword overlap from connected spores | +1.5 | | `seasonalMutation` | Spring expands, winter distills | +1.0 | | `maturityRefinement` | Replace weakest keyword with more relevant one | +2.0 | | `hybridVigor` | Cross-pollinate from graft parents | +3.0 | | `spontaneousGrowth` | NLEmbedding nearest-neighbor expansion | +0.5 |
**Mutation probability** is computed per growth cycle: - Base: 15%, capped at 60% - Modifiers: season (spring 1.5x, winter 0.4x), tendril count (+3% each), grafted (+12%), maturity bonus (1.3x for budding/blooming) - Diminishing returns after 10 mutations
Promotion decision
What has to happen next
Promote into a technical note or architecture paper with implementation anchors.
Why this is not always a full paper yet
Corpus pages are public-safe readers for discovered workspace artifacts. They are not automatically final papers. A corpus item becomes a polished paper only after the editable source, evidence checkpoints, references, figures, render path, and release status are attached through the paper schema.