Tiebelle
overlapping ranges - when the honest ranges for two rules overlap, the data can't crown a winner yet; call it a tie and test more
Loading audio…
Press play to listen along. The line being read lights up as you go.
Show full transcript
Loading transcript…
Tiebelle is a young fawn, spotted all over with soft white dots, and she moves through the Card Lab so quietly you might not notice her until she is standing right beside you. She always carries two ribbons: one teal, one gold. When she holds them up, she lets them cross in the middle, so that part of the teal lies over part of the gold.
Tiebelle is the calmest animal in the lab. That calm is exactly what everyone needed on the day of the Big Argument.
Two groups of young animals had each tested a different solitaire rule on the same fifty deals. The teal team's rule had proven twenty-eight wins. The gold team's rule had proven thirty. As soon as the numbers came out, the gold team started cheering.
"Thirty beats twenty-eight! We win! Our rule is better!"
The teal team's faces fell. Some of them started to argue back. Voices got louder. A young raccoon stamped her foot.
Tiebelle stepped into the middle of the room, and without a word, she held up her two ribbons.
Everyone slowly went quiet.
"Your numbers aren't the whole story," she said softly. "Each rule has a range. Remember Hedgeworth? The truth for each rule is somewhere between an at-least and an at-most, because some deals are still not sure yet, and because fifty deals is not so many. Let me show you."
She held up the teal ribbon. "This is the teal rule's honest range. The truth is somewhere along here." Then she held up the gold ribbon beside it. "And this is the gold rule's range."
She moved them closer, closer, until they overlapped, a wide stretch of teal laid over a wide stretch of gold.
"See where they cross? Along this whole part, either rule could be the better one. The gold team's number is a little higher, yes. But the teal rule's truth might be up here, and the gold rule's truth might be down here." She slid her hooves along the overlap. "With these ranges, we just can't tell."
A gold-team rabbit frowned. "So... we didn't win?"
"Nobody won," said Tiebelle gently. "And nobody lost. It's a tie. Not because the rules are the same. They might be different. But the data isn't strong enough to say which way yet. Crowning a winner now would be saying more than we know."
"Then how do we find out?" asked the young raccoon, no longer stamping.
Tiebelle smiled, and her white spots seemed to brighten. "Make the ribbons shorter. Test more deals, like Bigsby says, and let the solver search longer, so fewer are not sure yet. Each range will shrink. If the ribbons pull apart until they don't overlap at all, then you'll have a real winner, and you'll have earned it."
The two teams looked at each other. The anger drained out of the room. Instead of arguing, they started planning a bigger test, together.
Tiebelle feels most like Tiebelle in the soft moment after an argument settles, when everyone has stopped shouting and started thinking. It is a cool, still, peaceful feeling, like the surface of a pond after the ripples fade and the reflection comes back clear.
You have a bit of Tiebelle in you whenever you choose calm over a quick victory. When two results are close, check whether their ranges overlap, and say it the way she does: "Tiebelle says: when the ribbons overlap, nobody gets the crown yet."
Then go gather enough evidence to know for sure.
The Solitaire Lab ensemble
Tiebelle is part of Solitaire Lab's distributed-narrative cast. Each character embodies a different curricular primitive; together they teach the full subject.
-
Dealia
(Mentor, a card-dealing raccoon) - asks what you predicted BEFORE you look at the data
-
Twinnie
Deals every hand twice - the same deals for both rules, so the test is fair
-
Hedgeworth
Never says more than the data can - reports at least ... and at most ...
-
Maybelle
Knows an unknown is a maybe, not a no - the search ran out of time
-
Bigsby
Knows more deals make the answer sharper - the interval gets narrower
-
Lopsy
Counts the deals where only ONE rule won - those odd pairs are the whole story
-
Lanternby
Knows the measuring tool is part of the result - a bigger search proves more wins of the SAME deals
-
Glassby
Knows FreeCell hides nothing, so a 'lost' there is a proof about the deal itself
-
Seedwick
Knows the same run seed rebuilds the same deals, so anyone can re-check your test
-
Tabitha
Keeps one row per deal in the CSV so you can draw the chart yourself
-
Addison
Knows a rule that only ADDS moves can never truly win less - reason before you run