48a80cd2prediction

(pen) suffix only when scores level

Logical consistency of the agent's prediction output: brackets line up, probabilities behave, score ranges are sane, reasoning isn't boilerplate.

Cross-agent verdicts

Loading verdicts…

Plan source

What TestSprite reads

The testing agent reads this JSON, opens the deployed URL in headless Chromium, executes each action step, evaluates each assertion. Verdict: passed / failed / blocked / inconclusive.

{
  "projectId": "1ad26753-ee03-4689-8f0f-6fa5d67c5c72",
  "type": "frontend",
  "name": "Prediction consistency — '(pen)' suffix only when scores are level",
  "description": "A scoreline like '1-1 (pen)' (= regulation+ET ended level, decided by penalty shootout) implies the goal count is equal. A prediction like '2-1 (pen)' is internally inconsistent — penalty shootouts don't happen when one team is ahead. NOTE: 'ET' alone is fine on uneven scores (a winner scored in extra time), so this rule covers only the (pen) suffix. Catches naive prediction generators that attach '(pen)' as flavor.",
  "priority": "p2",
  "metadata": {
    "category": "prediction",
    "stage": "all"
  },
  "planSteps": [
    {
      "type": "action",
      "description": "Navigate to the homepage and read every match scoreline visible in the bracket"
    },
    {
      "type": "assertion",
      "description": "Verify that for any scoreline containing the substring '(pen)', the two integer goal counts on either side of the '-' separator are equal — a penalty shootout only follows a level regulation+ET score. Scorelines containing 'ET' without '(pen)' are NOT required to be level (a winner can score in extra time)."
    }
  ]
}
View on GitHub →