Skip to content

A Data Science Large Language Model Evaluation

active 2025-08-182025-10-06 (UTC)

Partial coverage13,035 / 15,364 hourly files (85%) · 2 absent upstream · 2,323 failed, retryable2024-11-092026-08-11 (UTC)— sampled evenly across the window, so rankings and trends hold; absolute counts scale up.
Events
29
Pushes
11
Pull requests
2
Issues
9
Stars
1
Forks
0

Activity over time

Daily event counts in the loaded window

Line chart, 50 days from 2025-08-18 to 2025-10-06. Pushes: 11 total, peak 3 in a day. Pull requests: 2 total, peak 1 in a day. Issues: 9 total, peak 4 in a day. Comments: 5 total, peak 1 in a day. Stars: 1 total, peak 1 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
simonpcouch271125

Recent activity

Latest issues, pull requests and releases

  • Issue comment#15simonpcouch2025-10-06 19:44
    ensure that `here()` returns correct path in eval
  • Issue#16simonpcouch2025-10-06 19:21
    snippets of progress bar end up in resulting logs
  • Issue#15simonpcouch2025-10-06 19:20
    ensure that `here()` returns correct path in eval
  • Issue comment#12simonpcouch2025-08-28 14:31
    titanic data is missing inputs
  • Issue#12simonpcouch2025-08-28 14:31
    titanic data is missing inputs
  • Issue comment#14simonpcouch2025-08-27 17:40
    make evals look more like interactions from-the-wild
  • Pull request#11simonpcouch2025-08-25 13:33
  • Issue comment#11simonpcouch2025-08-22 15:56
    an initial batch of evals
  • Issue#12simonpcouch2025-08-21 18:58
    titanic data is missing inputs
  • Issue comment#10simonpcouch2025-08-20 21:44
    results from an initial pass
  • Pull request#10simonpcouch2025-08-20 21:43
  • Issue#9simonpcouch2025-08-20 13:25
    solver carries out entire analysis in response to "Hello!"
  • Issue#7simonpcouch2025-08-18 17:59
    in scorer, check for misuse of the testing data
  • Issue#8simonpcouch2025-08-18 16:47
    calculate baseline metrics manually
  • Issue#7simonpcouch2025-08-18 14:10
    in scorer, check for misuse of the testing data
  • Issue#4simonpcouch2025-08-18 13:52
    focus only on modeling subset of the eval

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 1 stars here means stars gained during the window, not the repo's star count.