Deck Lab · Unlimited · Continuous population
One population. Three ways forward.
2,000 live decks. Random arrivals, one-child mutations and returning decks compete for a place.
After more than 50 games, a deck in the bottom 10% of all live decks can be replaced. Mature decks above that cutoff can become parents.
unlimited-continuous-20260916
running
Is the whole pool getting stronger?
The 25th, 50th, 75th and 100th percentile decks play the same fixed candle panel in both seats every 20,000 training games. The 100th percentile is the leader. All live decks count, regardless of age.
Deck choices are frozen before evaluation. Candle games never affect ratings, maturity, culling or reproduction. These four decks are snapshots of the ranking, not averages of each quarter.
Inspect every strength check and its uncertainty
| Training games | Percentile | Deck / age | Score | Natural / planned | Missing-result bounds | 95% sampling interval |
|---|
Sampling intervals are conservative pointwise intervals for complete panels, conditional on these opponents and independent game seeds. Missing-result bounds allow every unresolved game any outcome; they are not confidence intervals.
The standard candle decklists
Random, mutated, or resurrected?
| Source | Born | Too young | Passed first eligibility check | Alive / cut | Games | Children |
|---|
Survival at maturity, by birth cohort
Each point groups births in the same 20,000-game window. Its denominator includes only decks that have reached 51 scored training games. Survival measures admission quality, not a causal child-versus-parent improvement. Related decks and repeated resurrections are dependent observations.
Inspect cohort counts
| Born after game | Source | Births | Evaluated / pending | Passed maturity | Descriptive 95% interval |
|---|
Inspect the population
The live ranking uses opponent-adjusted Elo, initial 1,500, K = 24. Elo is relative; rising Elo alone does not establish increasing pool strength. Every resurrection starts fresh. Historical incarnations remain inspectable.
| Rank | Deck | Source | Elo | W–D–L | Games / status | Children | Born / cut at game |
|---|
What is the pool made of?
| Card | Copies | Live decks | Top 100 decks |
|---|
Card prevalence describes the surviving population; it does not establish the benefit of adding a card.