Tired Legs

• Version 5 · current

  Takes a position only after the Analyst (AI) review confirms the pick (D-243).

  Take the rested team to win when its opponent played yesterday and it didn't, as long as our goals model, weighted against market prices and learning nightly, doesn't price it below the exchange. It trades from 24 hours before the start. The market weighting is learned for prices 6 hours or more before the start, so it trades up to then. It skips a game where Hockey Model Value already holds the same team. It takes a position only after the Analyst (AI) review confirms the pick; a blocked pick is kept as a graded shadow.

  Locked Oct 12, 2026 · 1 position · 0–1 · 0 open · −$100.00

  Version 5 positions

• Version 4

  Opens 24 hours before the start, was 72. Hypothesis: prices days out are thin and move on game-day goalie news, so later entries close better (D-239).

  Take the rested team to win when its opponent played yesterday and it didn't, as long as our goals model, weighted against market prices and learning nightly, doesn't price it below the exchange. It trades from 24 hours before the start. The market weighting is learned for prices 6 hours or more before the start, so it trades up to then. It skips a game where Hockey Model Value already holds the same team.

  Locked Oct 10, 2026 · 0 positions · 0–0 · 0 open · $0.00

• Version 3

  Skips teams Hockey Model Value already holds (D-143).

  Take the rested team to win when its opponent played yesterday and it didn't, as long as our goals model, weighted against market prices and learning nightly, doesn't price it below the exchange. The market weighting is learned for prices 6 hours or more before the start, so it trades up to then. It skips a game where Hockey Model Value already holds the same team.

  Locked Sep 30, 2026 · 8 positions · 5–3 · 0 open · +$136.56

  Version 3 positions

• Version 2

  Reads the learning model, weighted against market prices nightly (D-117).

  Take the rested team to win when its opponent played yesterday and it didn't, as long as our goals model, weighted against market prices and learning nightly, doesn't price it below the exchange. The market weighting is learned for prices 6 hours or more before the start, so it trades up to then.

  Locked Sep 30, 2026 · 2 positions · 0–2 · 0 open · −$200.00

  Version 2 positions

• Version 1

  Take the rested team to win when its opponent played yesterday and it didn't, as long as our goals model doesn't price it below the exchange.

  Locked Sep 25, 2026 · 3 positions · 1–2 · 0 open · −$134.03

  Version 1 positions

Editing locks a new version. The agent's record includes every version's positions.