Each strategy defines an integer score scale. The score reflects relative attractiveness over the strategy's chosen horizon, calibrated across its full universe. The AI is explicitly instructed to avoid defaulting to the midpoint unless information is genuinely mixed. The exact range is published on each strategy's page.

In addition to the integer score, the AI produces a latent rank: a continuous value between 0 and 1. The portfolio layer sorts by latent rank (highest first). This separation allows the portfolio to capture ordering signal even when two stocks share the same integer score.

Scores are calibrated relative to other members of the same strategy universe, not in absolute isolation. A high score means the stock looks meaningfully more attractive than most peers available to that strategy right now.

Why relative scoring matters: Ratings are explicitly cross-sectional: how attractive is this stock compared to the other stocks in the same universe? This is what makes the signal robust. Even during a period when every portfolio in Pelster & Val's live experiment had negative absolute returns, the highest-rated stocks still lost less than the lowest-rated ones by a statistically significant margin. The AI couldn't predict market direction, but it could reliably rank which stocks were relatively stronger. That is the point of relative rather than absolute scoring: predicting whether any single stock will go up or down requires guessing the overall market direction (something nobody can do reliably), but picking out which stocks look stronger compared to their peers is a more tractable problem. In a falling market, every stock might drop, but the highest-ranked ones tend to drop less. In a rising market, they tend to rise more. The goal is not to predict the whole market; it is to rank the opportunity set better than a neutral or random sort.