repository · survival report #5 · 2026-10-12 · method v4 · unranked

QwenLM/qwen-code

In Survival Report #5 (2026-10-12, method v4): 544,888 of 661,978 lines introduced by 567 AI-tagged commits are still at HEAD, 82.3 %. These are counts, not grades. No rank, no colour, no verdict, and no comparison with any other repository on this page. Every number links to the audit bytes behind it and the method and its limits are public.

GitHub · latest.json · badge.svg · Survival Report #5 · all repositories · Atom feed

567AI-tagged commits · of 9,886 661,978lines introduced by them 544,888still attributed to them at HEAD 82.3 %line-weighted 52.6 %median per commit 21 %of introduced lines in the largest commit

Baseline: this repository's untagged lines

Commits with no machine-readable AI signal, human-written, inline-completed or untagged-agent code alike: 9,319 commits, 6,828,369 lines introduced, 4,841,967 still at HEAD (70.9 % line-weighted, 62.4 % median per commit). Age is the time from a commit to HEAD. The baseline was added in method v3 and is unchanged later; definition at causari.dev/method.

Age-matched: AI-tagged lines 82.3 % against untagged lines in the matched age windows 72.4 %, a gap of +9.9 pts, over 5 age windows holding 100 % of the AI-tagged lines.

Line ageAI-taggedcommitsUntaggedcommits
0–30 d90.3 %2585.8 %1,027
30–90 d82.6 %15781.6 %2,203
90–180 d82.3 %10460.2 %1,729
180–365 d49.1 %20551.4 %2,044
365–730 d30.7 %7631.9 %2,316

By agent, in Survival Report #5

Alphabetical. A commit is attributed to the agent its metadata names; one agent per commit. VERIFIED commits only.

AgentCommitsLines introducedStill at HEADLine-weightedCapped
claude-code436515,577425,68882.6 %77.6 %
cursor3091,06282,98491.1 %88.2 %
gemini6913,8084,26730.9 %31.8 %
github-copilot2136,87528,50677.3 %77.2 %
jules31201714.2 %14.2 %
openai-codex84,5363,42675.5 %75.5 %

History across reports

One row per report this repository was measured in, oldest first; each report measured HEAD as of its own date. The line is the line-weighted ratio on a fixed 0 – 100 % axis; each point is one report.

Line-weighted ratio across reports, 0 to 100 %: #2 85.8 %; #3 86.9 %; #4 82.2 %; #5 82.3 %
ReportDateAI-tagged commitsLines introducedStill at HEADLine-weighted
Survival Report #22026-09-23555597,734513,05185.8 %
Survival Report #32026-09-28563659,736573,20686.9 %
Survival Report #42026-10-05565661,284543,89182.2 %
Survival Report #52026-10-12567661,978544,88882.3 %

Reproduce

One command, any machine, no account: the same bytes the report was built from. The exact bytes behind this page are repos/QwenLM__qwen-code.json of Survival Report #5. Open an issue with your JSON if it differs.

re audit QwenLM/qwen-code --json   # method v4, full clone

Badge

Text only, one colour, no red and no green. It follows the latest report and is cached for one hour. badge-dark.svg is the same badge as paper on ink.

AI code survival 82.3 % · causari · #5 AI code survival 82.3 % · causari · #5, paper on ink

README · Markdown
[![AI code survival](https://causari.dev/r/qwenlm/qwen-code/badge.svg)](https://causari.dev/r/qwenlm/qwen-code/)

Coverage

  • Method v4, causari 0.4.1. Detection from commit metadata only; survival from git blame -w -M -C at HEAD.
  • Full clone: yes. Method v4 refuses shallow clones; this row comes from a complete history.
  • Sample: 567 AI-tagged commits; the sample floor is 5. At or above the floor, so the ratio is aggregated into the report.
  • PROBABLE: No PROBABLE commits: every counted commit carries machine-readable AI authorship metadata.
  • Cap: 4,950 lines per commit in this repository; the capped ratio is 76.7 %.
  • .git-blame-ignore-revs: not present in this repository.