Harvard vs. Dartmouth

Research grade

🔬 Research candidateDartmouth at 52%

Matches a rule that looked positive after costs in the short windows of our Oct 22 2026 backtest. The full-year test without hindsight (Oct 26 2026) found no evidence for any of these rules: out of sample they lost money or were noise. A label for a pattern that once looked good, not an edge and not a recommendation.

• + $50k+ behind an 80 %+ consensusNot confirmed. Oct 22 backtest: +10.3 % a trade (n 172), picked after seeing the table. Full year, out of sample: $50k+ on the side −2.7 % (n 641, 95 % CI −7.6 to +2.9); 80 %+ with $50k+ on a favourite +0.4 % (n 1,558, 95 % CI −2.3 to +3.0): no edge.
• · Side priced 50–60¢Full year, out of sample: 0.50–0.70 lost −2.9 % a trade (n 23,546, 95 % CI −3.9 to −1.9).

The rules come from our Oct 22 2026 backtest (one entry per market, held to resolution, after a 1¢ half-spread and Polymarket's taker fees). Our full-year test without hindsight (Oct 26 2026) found none of them profitable out of sample, and the plain consensus lost −3.0 % a trade. The grade describes the market; it is not a forecast, not an edge and not advice.