Where My Nerds At?

[Wrestleknownothing]

This one might not be for everyone.

But it be for me. And sometimes that's enough.

Grading The Expected Points Model | Wrestling.Guru

It is time for introspection and to hand out some grades. I Go To Extremes Every year there are outliers. Wrestlers or teams that show up, or not so much. B ...

wrestling.guru

 

[Misalorales]

This one might not be for everyone.

But it be for me. And sometimes that's enough.

Grading The Expected Points Model | Wrestling.Guru

It is time for introspection and to hand out some grades. I Go To Extremes Every year there are outliers. Wrestlers or teams that show up, or not so much. B ...

wrestling.guru

What would you say is the most accurate you could get,or hope to get, your model, realistically? Trying to predict a 33 man bracket and all of the various data within them is insanity. Doing it 10 separate times is something else entirely! Love the work, thanks for all you do.

 

[gimb14]

1 seeds outperformed expected. penn state typically outperforms expected. penn state had 7 1 seeds. makes sense.

also, that title...

 

[Wrestleknownothing]

What would you say is the most accurate you could get,or hope to get, your model, realistically? Trying to predict a 33 man bracket and all of the various data within them is insanity. Doing it 10 separate times is something else entirely! Love the work, thanks for all you do.

I think I would need to have access to much more granular data like what Track has. Go down to the individual action level across the whole season and build from there. There is a guy on intermat called Pablo who is doing it at the match results level for the whole season (kinda like wrestlestat's Elo), but not yet at the individual action level. He isn't yet predicting scores so it is hard to measure, but it looks interesting.

 

[Misalorales]

I think I would need to have access to much more granular data like what Track has. Go down to the individual action level across the whole season and build from there. There is a guy on intermat called Pablo who is doing it at the match results level for the whole season (kinda like wrestlestat's Elo), but not yet at the individual action level. He isn't yet predicting scores so it is hard to measure, but it looks interesting.

I distrust A.I, especially with sports data, but do you think utilizing it in conjunction with your database would supercharge your model or ability to refine said model? It feels like at some point in the future that's the way no?

 

[Wrestleknownothing]

I distrust A.I, especially with sports data, but do you think utilizing it in conjunction with your database would supercharge your model or ability to refine said model? It feels like at some point in the future that's the way no?

It is important to distinguish between the sub-categories of AI.

Large language models (what everyone is using when doing internet queries) handle unstructured data very well. Especially when there is no one correct answer. They work really well as editors and style coaches for written documents. They work really well for summaries. And they work well to assist with starting points for coding. But they still do particularly poorly at finding a single correct answer in a sea of wrong answers (sports trivia being a prime example). I have been waiting for them to get better at wrestling stats now that @cowcards has created his invaluable resource, but it has not happened yet.

And when it comes to math LLMs used to make very basic mistakes (did not carry digits) on basic math (since fixed), but when it comes to complex math they tend to punt. For example, I tested ChatGPT (and soon I will be testing Claude) recently by asking it to perform the algebraic expansion I use for calculating the odds of 0-10 AAs - a solved problem with a known equation. Rather than produce the results it produced the Python code you would use to get the results. Not what I asked for, but closely related as long as you have the ability to run Python code.

Machine learning models, on the other hand, can do particularly well at optimizations like what I am doing. The key is picking the right one, or picking the right agent to pick the right one. And there are a lot of technologies that fit in this sub-category. Even a simple linear regression is part of AI. So I can say with a straight face that when I do my surface optimizations I am already using AI.

The other issue is that the data I am using is very structured, and so far, pretty basic. With structured data you only need to go down the more sophisticated machine learning technique route when it gets more granular and sophisticated.

 

[Stevej]

This one might not be for everyone.

But it be for me. And sometimes that's enough.

Grading The Expected Points Model | Wrestling.Guru

It is time for introspection and to hand out some grades. I Go To Extremes Every year there are outliers. Wrestlers or teams that show up, or not so much. B ...

wrestling.guru

Fascinating reading and fantastic work! Thanks so much for sharing this with us!

 

[Wrestleknownothing]

also, that title...

"The most difficult thing in life is to know yourself." - Thales of Miletus

 

[Psalm 1 guy]

Was your "Penn 'We Ain't The Field' State adjustment" accurate this year? I would imagine Penn State having seven #1 seeds limited this points adjustment. I am curious to see if Penn State can top their 40.5 Bonus points at next year's NCAA tournament. I know there were 1.5 Bonus points left on the table by MM (.5 for missing a tech by a TD where he rode much of the match and not gaining the Major against Hepner), but I am not sure of the other wrestlers. Since I had guessed that Penn State would score 42 Bonus points, MM kept me from the perfect guess : )

 

[pawrstlersinpa]

I distrust A.I, especially with sports data, but do you think utilizing it in conjunction with your database would supercharge your model or ability to refine said model? It feels like at some point in the future that's the way no?

What????

My prompt for ChatGPT: Who were the division 1 wrestling national champions at each weight in 2026

The 2026 NCAA Division I Wrestling Championships took place March 19–21, 2026, in Cleveland, Ohio. Here are the individual national champions by weight class:

• 125 lbs – Brandon Kaylor (Oregon State)
• 133 lbs – Vito Arujau (Cornell)
• 141 lbs – Jesse Mendez (Ohio State)
• 149 lbs – Ridge Lovett (Nebraska)
• 157 lbs – Levi Haines (Penn State)
• 165 lbs – David Carr (Iowa State)
• 174 lbs – Carter Starocci (Penn State)
• 184 lbs – Aaron Brooks (Penn State)
• 197 lbs – Zach Glazier (Iowa)
• 285 lbs – Greg Kerkvliet (Penn State)

If you want, I can also break down team standings, upsets, or how many titles Penn State stacked up again.

 

[Wrestleknownothing]

Was your "Penn 'We Ain't The Field' State adjustment" accurate this year? I would imagine Penn State having seven #1 seeds limited this points adjustment. I am curious to see if Penn State can top their 40.5 Bonus points at next year's NCAA tournament. I know there were 1.5 Bonus points left on the table by MM (.5 for missing a tech by a TD where he rode much of the match and not gaining the Major against Hepner), but I am not sure of the other wrestlers. Since I had guessed that Penn State would score 42 Bonus points, MM kept me from the perfect guess : )

Nice job on the bonus prediction.

I came in a touch high after the PSU adjustment. I think it was 185. I was low on the bonus and high on the placement.

 

[TwoJoints]

What????

My prompt for ChatGPT: Who were the division 1 wrestling national champions at each weight in 2026

The 2026 NCAA Division I Wrestling Championships took place March 19–21, 2026, in Cleveland, Ohio. Here are the individual national champions by weight class:

• 125 lbs – Brandon Kaylor (Oregon State)
• 133 lbs – Vito Arujau (Cornell)
• 141 lbs – Jesse Mendez (Ohio State)
• 149 lbs – Ridge Lovett (Nebraska)
• 157 lbs – Levi Haines (Penn State)
• 165 lbs – David Carr (Iowa State)
• 174 lbs – Carter Starocci (Penn State)
• 184 lbs – Aaron Brooks (Penn State)
• 197 lbs – Zach Glazier (Iowa)
• 285 lbs – Greg Kerkvliet (Penn State)

If you want, I can also break down team standings, upsets, or how many titles Penn State stacked up again.

I pasted your prompt in Claude and it returned the following:

Here are all 10 champions from the 2026 NCAA Division I Wrestling Championships, held March 19–21 in Cleveland:



|Weight |Champion |School |How |
|-------|-------------------|--------------|-------|
|**125**|Luke Lilledahl |Penn State |Dec 2-1|
|**133**|Jax Forrest |Oklahoma State|Dec 5-2|
|**141**|Sergio Vega |Oklahoma State|OT 4-1 |
|**149**|Aden Valencia |Stanford |SV 8-5 |
|**157**|Landon Robideau |Oklahoma State|Dec 4-2|
|**165**|Mitchell Mesenbrink|Penn State |TF 20-4|
|**174**|Levi Haines |Penn State |Dec 2-1|
|**184**|Max McEnelly |Minnesota |Dec 4-2|
|**197**|Josh Barr |Penn State |Dec 6-3|
|**HWT**|Isaac Trumble |NC State |Dec 4-1|

Penn State won the team title with a record 177.5 points, followed by Oklahoma State in second and Nebraska in third.  It was Penn State’s fifth straight team championship and 14th overall. 
The tournament had some big upsets — Sergio Vega became the first undefeated true freshman to win a title since 1947, and Aden Valencia entered as the No. 10 seed to knock off top-seeded Shayne Van Ness at 149.  Mesenbrink earned Most Outstanding Wrestler honors after averaging 5.04 team points per match. 

 

[Wrestleknownothing]

I pasted your prompt in Claude and it returned the following:

Here are all 10 champions from the 2026 NCAA Division I Wrestling Championships, held March 19–21 in Cleveland:



|Weight |Champion |School |How |
|-------|-------------------|--------------|-------|
|**125**|Luke Lilledahl |Penn State |Dec 2-1|
|**133**|Jax Forrest |Oklahoma State|Dec 5-2|
|**141**|Sergio Vega |Oklahoma State|OT 4-1 |
|**149**|Aden Valencia |Stanford |SV 8-5 |
|**157**|Landon Robideau |Oklahoma State|Dec 4-2|
|**165**|Mitchell Mesenbrink|Penn State |TF 20-4|
|**174**|Levi Haines |Penn State |Dec 2-1|
|**184**|Max McEnelly |Minnesota |Dec 4-2|
|**197**|Josh Barr |Penn State |Dec 6-3|
|**HWT**|Isaac Trumble |NC State |Dec 4-1|

Penn State won the team title with a record 177.5 points, followed by Oklahoma State in second and Nebraska in third.  It was Penn State’s fifth straight team championship and 14th overall. 
The tournament had some big upsets — Sergio Vega became the first undefeated true freshman to win a title since 1947, and Aden Valencia entered as the No. 10 seed to knock off top-seeded Shayne Van Ness at 149.  Mesenbrink earned Most Outstanding Wrestler honors after averaging 5.04 team points per match. 

I only count four mistakes.

 

[Col]

First @Wrestleknownothing great analysis! However, in my mind the issue is not settled. There are a number of assumptions you have to make in order to do this kind of analysis. Here these include things such as the lack of scoring is not based on the current wrestlers being better defensively than before, worse offensively than before, or much closer to being evenly matched so that counter takedowns are much more effective than before. If any of these assumptions (or others) are incorrect it could explain why the 3 pt takedown has not generated the results intended.
Next the 3 pt takedown was not the only rule change to be implemented. Things such as what is a takedown, interlocking fingers, and what appears to be a non-enforcement of stalling (among other changes) potentially had an affect as well. Potentially there was a change that is directly linked to the 3 pt takedown (in other words is a dependent not independent variable) which would further complicate the situation.
I think the assumptions are valid, but some of the rule changes have had a bigger impact than the 3 pt takedown. Overall I would say the conclusion is that given the other rule changes the 3 pt takedown has not been able to increase the scoring as intended... leaving open the possibility that if some of the rules are changed it might.
Once again thanks for doing this... no one else that I know of is making the factual analysis to help people understand what actually is happening

 

[Wrestleknownothing]

First @Wrestleknownothing great analysis! However, in my mind the issue is not settled. There are a number of assumptions you have to make in order to do this kind of analysis. Here these include things such as the lack of scoring is not based on the current wrestlers being better defensively than before, worse offensively than before, or much closer to being evenly matched so that counter takedowns are much more effective than before. If any of these assumptions (or others) are incorrect it could explain why the 3 pt takedown has not generated the results intended.
Next the 3 pt takedown was not the only rule change to be implemented. Things such as what is a takedown, interlocking fingers, and what appears to be a non-enforcement of stalling (among other changes) potentially had an affect as well. Potentially there was a change that is directly linked to the 3 pt takedown (in other words is a dependent not independent variable) which would further complicate the situation.
I think the assumptions are valid, but some of the rule changes have had a bigger impact than the 3 pt takedown. Overall I would say the conclusion is that given the other rule changes the 3 pt takedown has not been able to increase the scoring as intended... leaving open the possibility that if some of the rules are changed it might.
Once again thanks for doing this... no one else that I know of is making the factual analysis to help people understand what actually is happening

Thanks, Col. I agree that there are other factors involved that I have not controlled for.

When I was thinking about offense and defensive changes, though, and how that feeds into changes in takedowns, I viewed those as evolutionary processes that play out over time. The change in 0 or 1 TD matches between 2023 and 2024 was not the result of an evolutionary process. It was more like flipping a switch. The change is big enough that you need to look at equally big overnight changes as the cause.

In addition to the 3-pt TD there is the finger grabbing change, but I believe that happened after 2024 (correct me if I am wrong there). I don't even know where to begin with "what is a TD?". The definition has gone back and forth over time. And stalling enforcement is an age old problem (I cited a reference to it from the 1920's earlier).

So while I agree that all of that plays a role, I think (without proving it) that the biggest culprit, by far, is the 3-pt TD.

 

[WPIALBrwnPSU]

All I want to know is if this test is going to be open book and which damn book?

 

[CropDuster507]

I’m gone for a couple months and you guys start becoming refined…