AI explanation

^{Show image generation prompt} Model: dalle-3
Prompt: Generate an image of a surreal, vibrant landscape split in two halves. On one side stands a row of sleek, stolen cars with blazing headlights, racing through a neon-soaked Tennessee city. The cars leave trails of vivid light behind them as they speed away, creating a sense of frenetic movement and excitement. On the other side, set against a backdrop of an idyllic Belgian countryside, an old-fashioned gas station is surrounded by a queue of patient cars. The station is bathed in a soft, hazy glow, exuding a tranquil atmosphere. In the distance, a group of enigmatic, shadowy figures are depicted siphoning gasoline from a hidden tanker, their sly grins adding an air of mischievousness to the scene. The contrast between the chaotic energy of the stolen cars in Tennessee and the serene, unsuspecting scene in Belgium brings out the stark disparities in the cross-country caper, creating a compelling visual narrative. The depiction should include only scenes, people, and objects, it should not include text or speech bubbles.

---

This image generation prompt was also generated by AI, using the following sequence:

Model: gpt-3.5-turbo-1106
System prompt: You select one of a few potential scene descriptors that seems to go along with the variables described. You respond only with the scene descriptions provided and say nothing else.
User prompt: Here are two variables: Motor vehicle thefts in Tennessee and Gasoline pumped in Belgium. Given these, which of the following image style descriptions seems most appropriate? Pick the one that seems to be related to one of the variables at hand. Please respond with only one of the following potential descriptions: Scalar art Psychedelic A scene from Skyrim a Polaroid photo Psychedelic
ChatGPT: Psychedelic

Model: gpt-3.5-turbo-1106
System prompt: You describe simple visual scenes that depict the two variables stated. You combine both variables into one scene.
User prompt: Please describe a visual scene that prominently depicts both Motor vehicle thefts in Tennessee and Gasoline pumped in Belgium, in the following situation: Gasoline pumped in Belgium increased because as more motor vehicles were stolen in Tennessee, fuel thieves got bolder and started siphoning gas across the Atlantic. They figured it was the perfect crime because who's gonna look for their stolen gas in a whole other continent? So, Tennessee car thefts led to a global gas getaway, leaving Belgians scratching their heads as their fuel mysteriously disappeared. It's a cross-country caper that's driving everyone nuts!. Keep the description simple.
ChatGPT: In Tennessee, a group of thieves swiftly and skillfully hotwired and stole several cars, their engines roaring as they sped away. Meanwhile, across the Atlantic in Belgium, a line of cars patiently queued at a gas station, their owners pumping fuel into their tanks. In the distance, a group of shadowy figures siphoned gasoline from a hidden tanker, their mischievous grins betraying their sneaky intent. The stolen Tennessee cars and the siphoned gasoline eventually converged, creating a cross-country caper that left people puzzled and frustrated on both sides of the Atlantic.

Model: gpt-3.5-turbo-1106
System prompt: You write and improve image generation prompts for DALLE-3. You maintain the same subjects, but enhance the visuals.
User prompt: Please respond with an image generation prompt that would be likely to create an interesting visual using DALLE-3, using the following style: [ Psychedelic ] and depicting this scene: In Tennessee, a group of thieves swiftly and skillfully hotwired and stole several cars, their engines roaring as they sped away. Meanwhile, across the Atlantic in Belgium, a line of cars patiently queued at a gas station, their owners pumping fuel into their tanks. In the distance, a group of shadowy figures siphoned gasoline from a hidden tanker, their mischievous grins betraying their sneaky intent. The stolen Tennessee cars and the siphoned gasoline eventually converged, creating a cross-country caper that left people puzzled and frustrated on both sides of the Atlantic. Keep the visual depiction simple. Do not include any words or speech bubbles.
ChatGPT: Generate an image of a surreal, vibrant landscape split in two halves. On one side stands a row of sleek, stolen cars with blazing headlights, racing through a neon-soaked Tennessee city. The cars leave trails of vivid light behind them as they speed away, creating a sense of frenetic movement and excitement. On the other side, set against a backdrop of an idyllic Belgian countryside, an old-fashioned gas station is surrounded by a queue of patient cars. The station is bathed in a soft, hazy glow, exuding a tranquil atmosphere. In the distance, a group of enigmatic, shadowy figures are depicted siphoning gasoline from a hidden tanker, their sly grins adding an air of mischievousness to the scene. The contrast between the chaotic energy of the stolen cars in Tennessee and the serene, unsuspecting scene in Belgium brings out the stark disparities in the cross-country caper, creating a compelling visual narrative.

---

*Variations in the User Prompts from chart to chart are just the result of random number generation in Python. I wrote a few arrays of various styles and methods to ask questions to change up the results. Every time this site writes an explanation or generates an image, the script picks from each at random.

I sequence the requests into multiple prompts because I find GPT 3.5 to perform much better with short, well-managed contexts. Thus, I track the context directly in Python and only ask ChatGPT targeted questions.

AI academic paper

Pump It Up: Exploring the Surprising Relationship Between Motor Vehicle Thefts in Tennessee and Gasoline Pumped in Belgium The Journal of Unexpected Correlations in Societal Phenomena Jan 2024

Problem variable:	Which variable has a problem? Motor vehicle thefts in Tennessee Gasoline pumped in Belgium Neither / both
Issue:	What is the issue? The data is incorrect The chart isn't displaying properly There is a typo The source link is incorrect A calculation is wrong Something else
Additional details: Optional
Confirm you are a human:

Data details

Why this works

1. Data dredging: I have 25,153 variables in my database. I compare all these variables against each other to find ones that randomly match up. That's 632,673,409 correlation calculations! This is called “data dredging.” Instead of starting with a hypothesis and testing it, I instead abused the data to see what correlations shake out. It’s a dangerous way to go about analysis, because any sufficiently large dataset will yield strong correlations completely at random.
2. Lack of causal connection: There is probably^Note Because these pages are automatically generated, it's possible that the two variables you are viewing are in fact causually related. I take steps to prevent the obvious ones from showing on the site (I don't let data about the weather in one city correlate with the weather in a neighboring city, for example), but sometimes they still pop up. If they are related, cool! You found a loophole.
   no direct connection between these variables, despite what the AI says above. This is exacerbated by the fact that I used "Years" as the base variable. Lots of things happen in a year that are not related to each other! Most studies would use something like "one person" in stead of "one year" to be the "thing" studied.
3. Observations not independent: For many variables, sequential years are not independent of each other. If a population of people is continuously doing something every day, there is no reason to think they would suddenly change how they are doing that thing on January 1. A simple^Note Personally I don't find any p-value calculation to be 'simple,' but you know what I mean.
   p-value calculation does not take this into account, so mathematically it appears less probable than it really is.

Try it yourself

# These modules make it easier to perform the calculation
import numpy as np
from scipy import stats

# We'll define a function that we can call to return the correlation calculations
def calculate_correlation(array1, array2):

    # Calculate Pearson correlation coefficient and p-value
    correlation, p_value = stats.pearsonr(array1, array2)

    # Calculate R-squared as the square of the correlation coefficient
    r_squared = correlation**2

    return correlation, r_squared, p_value

# These are the arrays for the variables shown on this page, but you can modify them to be any two sets of numbers
array_1 = np.array([485.2,543.6,566.9,542.8,532.9,571.5,613.6,575.9,591,560.3,648.5,647.1,628.6,517.4,460.6,483.9,491.7,458.4,452.9,420.4,423.6,375.1,352.8,309,238.5,233.3,221,200.8,183.2,193.2,197.6,229.2,276.8,304.9,282.4,306.4,297.5,362.3,])
array_2 = np.array([57.9288,62.9699,65.6822,67.7404,66.6027,63.1315,63.3836,67.0273,65.7206,65.7288,65.5863,63.2377,58.6904,58.1562,55.4274,51.8306,50.6082,48.3178,48.7342,44.6066,41.4795,38.589,36.4904,33.3852,32.4438,30.2904,29.2219,28.4126,28.4356,29.8603,31.6603,34.0246,35.9041,40.1671,44.9945,37.6831,45.9616,51.874,])
array_1_name = "Motor vehicle thefts in Tennessee"
array_2_name = "Gasoline pumped in Belgium"

# Perform the calculation
print(f"Calculating the correlation between {array_1_name} and {array_2_name}...")
correlation, r_squared, p_value = calculate_correlation(array_1, array_2)

# Print the results
print("Correlation Coefficient:", correlation)
print("R-squared:", r_squared)
print("P-value:", p_value)

Reuseable content

• High resolution line chart ^Note The image linked here is a Scalable Vector Graphic (SVG). It is the highest resolution that is possible to achieve. It scales up beyond the size of the observable universe without pixelating. You do not need to email me asking if I have a higher resolution image. I do not. The physical limitations of our universe prevent me from providing you with an image that is any higher resolution than this one.
  
  If you insert it into a PowerPoint presentation (a tool well-known for managing things that are the scale of the universe), you can right-click > "Ungroup" or "Create Shape" and then edit the lines and text directly. You can also change the colors this way.
  
  Alternatively you can use a tool like Inkscape.
  
• High resolution line chart, optimized for mobile
• Alternative high resolution line chart
• Scatterplot
• Portable line chart (png)
• Portable line chart (png), optimized for mobile
• Line chart for only Motor vehicle thefts in Tennessee
• Line chart for only Gasoline pumped in Belgium
• AI-generated correlation image
• The spurious research paper: Pump It Up: Exploring the Surprising Relationship Between Motor Vehicle Thefts in Tennessee and Gasoline Pumped in Belgium