附件A
对阵抽签
全卡组的获胜机会模型会对每场战斗进行评分，然后将您的平局与实时元面板进行比较 - 公平的匹配实际上会向您提供的卡组，并按实际游戏频率进行加权。
机密 - 案件档案 #481
匹配机制在针对你？数字作证。输入玩家标签。获取证据。建立你的案件*。
从文件中随机拉出一个毫无戒心的玩家。
* 法庭不予受理。在部落聊天中具有毁灭性。
附件A
全卡组的获胜机会模型会对每场战斗进行评分，然后将您的平局与实时元面板进行比较 - 公平的匹配实际上会向您提供的卡组，并按实际游戏频率进行加权。
附件B
根据您的连胜记录每场比赛，并标记新的牌组变化。如果在你攀登时获胜机会恰好下降，那么时机本身就是证据。
附件C
标准化水平差距仍然是支持证据。如果水平均匀，则该因素自动失去影响。
附录D
单独的技能得分根据模型预测的获胜机会来衡量结果：50 表示您按牌行事，较高表示手牌正在发挥作用。
案例服务台现场直播
481 记录文件
A tag report is the way in. These are the rest of the tools built on the same model.
Deck Lab
Build a deck and score all 8 cards together against the live meta panel, then let the model try swaps — each one re-scored as a complete deck, so only changes that lift the whole deck surface.
Model rankings
The decks the model rates highest right now, for ranked and for Trophy Road, with their measured win rates.
Card explorer
Per-card usage, win rate, counters and synergies — and the decks currently carrying each card.
Public board
Every report on file, the luckiest and unluckiest of the day, and what other players make of them.
Data Lab
The correlations behind the model: what actually moves a win rate, and what only looks like it does.
Rigged Royale Pro
Higher daily allowances, full-catalog swap searches, score history, and the upgrade path planner.
Developer API
The same model behind every page, as REST endpoints: deck scoring, matchups, meta panels. Interactive docs and keys live in your account.
每次访问都会将未见过的战斗合并到玩家的历史中。一份报告分析了最新的 200 可用的 1v1 战斗，其中包括证据加权因素，当证据不足时，信心会趋于中性；排位、天梯、军团战、赛事等模式也可以单独进行。团战除外。