Catalog — the map of everything

doctor (492)

A one-off study — its numbers below are exactly what the run reported.

edge_hunt (232)

A one-off study — its numbers below are exactly what the run reported.

Leaderboards (127)

Ranks every backtested model by skill against the bookmaker's closing prices — the fairest single scoreboard we have.

observatory (124)

A one-off study — its numbers below are exactly what the run reported.

gap_filter_fit (9)

A one-off study — its numbers below are exactly what the run reported.

weather_paper (1)

A one-off study — its numbers below are exactly what the run reported.

maker_paper (1)

A one-off study — its numbers below are exactly what the run reported.

revalidate (4)

A one-off study — its numbers below are exactly what the run reported.

matrix_holdout (2)

A one-off study — its numbers below are exactly what the run reported.

tennis_lab (3)

A one-off study — its numbers below are exactly what the run reported.

sure_thing (1)

A one-off study — its numbers below are exactly what the run reported.

subset_check (1)

A one-off study — its numbers below are exactly what the run reported.

forward_scoreboard (3)

A one-off study — its numbers below are exactly what the run reported.

edge_parlay (2)

A one-off study — its numbers below are exactly what the run reported.

edge_doubles (2)

A one-off study — its numbers below are exactly what the run reported.

v2_filters (1)

A one-off study — its numbers below are exactly what the run reported.

proven_retro (2)

A one-off study — its numbers below are exactly what the run reported.

season_watch (1)

A one-off study — its numbers below are exactly what the run reported.

matrix_backtest (8)

The tournament: every prediction engine × every betting rule × every staking policy, replayed season by season with each season restarting from $1000. Finds which COMBINATIONS survive, not just which models predict.

day_mode (2)

A one-off study — its numbers below are exactly what the run reported.

season_mode (2)

A one-off study — its numbers below are exactly what the run reported.

bayes_replay (3)

A one-off study — its numbers below are exactly what the run reported.

dutch_backtest (1)

A one-off study — its numbers below are exactly what the run reported.

relational (4)

Side-vs-side questions: does the team better at X actually get more Y? Tested for every factor × every countable outcome, conditioned on how big the X advantage was.

gap_intel (4)

Dissects every disagreement between our models and the market: who was right in which situations, whether two engines agreeing means anything, and whether a classifier can predict when OUR side of the gap wins.

scorer_model (3)

A one-off study — its numbers below are exactly what the run reported.

book_profile (1)

A one-off study — its numbers below are exactly what the run reported.

ref_lines (2)

A one-off study — its numbers below are exactly what the run reported.

regime_alerts (1)

A one-off study — its numbers below are exactly what the run reported.

hazard_curves (1)

A one-off study — its numbers below are exactly what the run reported.

wc_retro (1)

A one-off study — its numbers below are exactly what the run reported.

soft_retro (1)

A one-off study — its numbers below are exactly what the run reported.

motivation (1)

A one-off study — its numbers below are exactly what the run reported.

Factor experiments (60)

Asks which pre-match factors drive one specific outcome, using a walk-forward model and permutation importance.

market_misses (2)

A one-off study — its numbers below are exactly what the run reported.

line_movement (2)

Compares opening and closing odds over 20+ years: when a price shortens (steam), is that information already fully absorbed by kickoff, or does following the move still pay?

portfolio_backtest (2)

A one-off study — its numbers below are exactly what the run reported.

lead_lag (1)

A one-off study — its numbers below are exactly what the run reported.

Discovery sweeps (6)

Theory-free sweep: correlates every pre-match factor with every outcome, corrects for the thousands of tests, and keeps only effects stable in every era.

Cross-sport laws (3)

Measures the same abstract effect (fatigue, momentum, rest) independently in each sport. Patterns that replicate across unrelated sports are laws, not quirks.

Strategy sweeps (1)

Tries thousands of betting rules on old seasons, then judges the winners ONLY on years they never saw. Survivors are candidate strategies; everything else was luck.

Each bets its own $1000 paper bankroll daily. Scoreboard →

Match winner settles on 90 minutes; “to advance” includes extra time and penalties — different questions, different markets. Player props settle from Kalshi's own results.