Aliveness and competence come apart; Haiku outranks Opus in forced-choice aesthetic comparisons despite lower baseline.

{
  "doc": "battery.md",
  "context": "Alexander mirror method reveals smaller models produce rougher, more alive responses; competence (rubric) ≠ aliveness (aesthetic).",
  "norm_label": "Aliveness and competence come apart; Haiku outranks Opus in forced-choice aesthetic comparisons despite lower baseline.",
  "graphify_id": "finding_aliveness_decouples",
  "source_file": "battery.md",
  "imported_from": "/tmp/koan-debug/battery/graph.json",
  "extracted_type": "finding",
  "source_location": "Abstract, §8.1-8.2",
  "graphify_file_type": "finding"
}