finding
active
finding:g2-5-fl-capital-efficiency-0-23G2.5-FL capital efficiency η=0.23
very low efficiency; spends aggressively but extracts little score
Source paper
extracted_from(2026) · Robert Müller · Clemens Müller
Neighborhood — ranked by edge-count
Claims (2)
claim
- core interpretive claim about what separates strong from weak play
- summary claim linking measured traits to outcomes
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- G2.5-FL has extremely low points per coin spent, indicating poor resource use.
- code agent with high efficiency, close to top LLMs
- ratio of final score to gross outflow, measuring points per coin spent
- Per-game score divided by gross outflow, measuring points per coin spent.
- Score per gross outflow of money; η > 1 means more than one point per coin spent.
- highest overbid frequency observed
- Much higher cost per quartet due to waste.
- failure to condition action choice on resource state