Making scientific abstracts easier to understand

With chatGPT’s assistance, I created a simple Discord bot that takes an abstract from a scientific paper as input to the API, and returns something that’s easier to understand.

Example Input Abstract:
"“The stellar companion to the weak-line T Tauri star DI Tau A was first discovered by the lunar occultation technique in 1989 and was subsequently confirmed by a speckle imaging observation in 1991. It has not been detected since, despite being targeted by five different studies that used a variety of methods and spanned more than 20 years. Here, we report the serendipitous rediscovery of DI Tau B during our Young Exoplanets Spectroscopic Survey (YESS). Using radial velocity data from YESS spanning 17 years, new adaptive optics observations from Keck II, and a variety of other data from the literature, we derive a preliminary orbital solution for the system that effectively explains the detection and (almost all of the) non-detection history of DI Tau B. We estimate the dynamical masses of both components, finding that the large mass difference (q ∼0.17) and long orbital period (≳35 years) make DI Tau system a noteworthy and valuable addition to studies of stellar evolution and pre-main-sequence models. With a long orbital period and a small flux ratio (f2/f1) between DI Tau A and B, additional measurements are needed for a better comparison between these observational results and pre-main-sequence models. Finally, we report an average surface magnetic field strength (B¯) for DI Tau A, of ∼0.55 kG, which is unusually low in the context of young active stars.”

“DI Tau A is a weak-line T Tauri star, which is a type of star that is still growing and changing. In 1989, scientists used a special technique called lunar occultation to discover another star that was close to DI Tau A. This other star was called DI Tau B. Scientists then used something called speckle imaging in 1991 to confirm that DI Tau B was really there. But after that, no one could find DI Tau B again, even though they looked for it many times over the next 20 years using different methods. Recently, scientists found DI Tau B again by accident while they were studying something else! They used data from 17 years of observations and some special tools like Keck II and other information from books to figure out how far away DI Tau B is from DI Tau A and how long it takes for them to go around each other in circles (called an orbit). They also figured out how much each star weighs (called mass) and found out that the two stars have very different masses. Finally, they measured the strength of the magnetic field around DI Tau A and found it was unusually low compared to other young stars like it.”

I can do more of these kinds of things – please contact me if interested.

Thanks OpenAI for an awesome tool! I’ve been a computer programmer for 40 years and now I’m becoming a different kind of programmer (some kind of hybrid programmer + prompt engineer). Feels like a superpower.


INPUT: “Galaxy mergers are common processes in the Universe. As a large fraction of galaxies hosts at their centres a central supermassive black hole (SMBH), mergers can lead to the formation of a supermassive black hole binary (SMBHB). The formation of such a binary is more efficient when the SMBHs are embedded in a nuclear star cluster (NSC). NSCs are dense and massive stellar clusters present in the majority of the observed galaxies. Their central densities can reach up to 10^7,M_\odot/{\rm pc}^3 and their masses can be as large as a few 10^7,M_\odot. The direct detection of an SMBHB is observationally challenging. In this work, we illustrate how the large scale structural and dynamical properties of an NSC can help to identify nucleated galaxies that recently went through a merger that possibly led to the formation of a central SMBHB. Our models show that the merger can imprint signatures on the shape, density profile, rotation and velocity structure of the NSC. The strength of the signatures depends on the mass ratio between the SMBHs and on the orbital initial conditions of the merger. In addition, the number of hypervelocity stars produced in the mergers is linked to the SMBHB properties. The merger can also contribute to the formation of the nuclear stellar disc of the galaxy.”

OUTPUT1 describes the abstract in easier terminology:
Galaxy mergers are like when two galaxies crash into each other. They usually have a supermassive black hole at the center, which is like a really big black hole. When two galaxies merge, they can form a supermassive black hole binary, which is like two really big black holes that are close together. To make this happen, the galaxies need to have something called a nuclear star cluster. This is like a really dense and massive group of stars that are in the middle of the galaxy. It’s hard to see these supermassive black hole binaries because they’re so far away and so small. But scientists can look for signs that two galaxies merged recently by looking at how the nuclear star cluster looks and moves. They can also look for things called hypervelocity stars, which are stars that move really fast because of the merger. Finally, mergers can also help form discs of stars around the center of the galaxy.

OUTPUT2 takes OUTPUT1 and creates ten great questions from it:

  1. What is the process of two galaxies merging?
  2. How do scientists detect signs of a recent merger?
  3. What is a nuclear star cluster and how does it affect galaxy mergers?
  4. How do hypervelocity stars form during a merger?
  5. What are the consequences of two galaxies merging?
  6. How long does it take for two galaxies to merge?
  7. Are there any other effects of galaxy mergers besides the formation of supermassive black hole binaries?
  8. What are the chances that two galaxies will merge in our lifetime?
  9. Are there any ways to prevent or slow down galaxy mergers?
  10. Are there any observable differences between galaxies that have merged and those that haven’t?

Fun, but useful?

(All of these examples are API calls, not via chatGPT)