Forecast
Facebook Twitter
  • Embed
  • Copy Link
    •
  • Approval
  • Set Reminder
  • Share private question
  • Unsubscribe from question
  • View Metaculus Prediction
  • {{qctrl.question.communityIsHidden ? 'Show' : 'Hide'}} Community Prediction
    •

    Your submission is now in Draft mode.

    Once it's ready, please submit your draft for review by our team of Community Moderators. Thank you!

    Submit Essay

    Once you submit your essay, you can no longer edit it.

    Pending

    This content now needs to be approved by community moderators.

    Submitted

    This essay was submitted and is waiting for review.

    What percentage of theorems will be proven by an RL model in the HOList benchmark by end of 2019?

    Created by ghabs on {{qctrl.question.created_time | dateStr}}
    Published by ghabs {{"onDate" | translate:({date: (qctrl.question.publish_time | dateStr)})}}

    Question

    The HOList Leaderboard, recently released by researchers at Google, is a benchmark test for automated theorem provers.

    Plausibly, if an automated model can prove theorems in a novel way that humans have not, it points to their use in advanced scientific inquiry.

    As of May 27th, 2019, the current leader in the RL category has proven 36.55% of the theorems in the HOList dataset.

    By end of 2019, what percentage of theorems will be proven by an RL model in the HOList benchmark?

    The resolution criteria will be the publicly reported HOList benchmark website.

    Categories:
    Benchmarks
    Drivers of progress – Algorithms

    Make a Prediction

    Prediction

    Note: this question resolved before its original close time. All of your predictions came after the resolution, so you did not gain (or lose) any points for it.

    Note: this question resolved before its original close time. You earned points up until the question resolution, but not afterwards.

    Current points depend on your prediction, the community's prediction, and the result. Your total earned points are averaged over the lifetime of the question, so predict early to get as many points as possible! See the FAQ.