repository · survival report #4 · 2026-10-05 · method v3 · unranked

openai/codex

In Survival Report #4 (2026-10-05, method v3): 109,054 of 183,908 lines introduced by 364 AI-tagged commits are still at HEAD, 59.3 %. 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 #4 · all repositories · Atom feed

364AI-tagged commits · of 11,843 183,908lines introduced by them 109,054still attributed to them at HEAD 59.3 %line-weighted 58.3 %median per commit 6 %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: 11,479 commits, 3,726,152 lines introduced, 2,202,474 still at HEAD (59.1 % line-weighted, 61.8 % median per commit). Age is the time from a commit to HEAD. Method v3; definition at causari.dev/method.

Age-matched: AI-tagged lines 59.4 % against untagged lines of the same age 54.4 %, a gap of +5.0 pts, over 2 age windows holding 100 % of the AI-tagged lines.

Line ageAI-taggedcommitsUntaggedcommits
0–30 d—081.4 %1,550
30–90 d—077.1 %2,319
90–180 d63.8 %19763.6 %2,604
180–365 d54.1 %16343.5 %3,515
365–730 d19.4 %418.0 %1,491

By agent, in Survival Report #4

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

AgentCommitsLines introducedStill at HEADLine-weightedCapped
claude-code102,2501,09048.4 %48.4 %
github-copilot323013157.0 %57.0 %
openai-codex351181,428107,83359.4 %58.9 %

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 %: #1 59.6 %; #2 59.6 %; #3 59.4 %; #4 59.3 %
ReportDateAI-tagged commitsLines introducedStill at HEADLine-weighted
Survival Report #12026-09-20364183,908109,67459.6 %
Survival Report #22026-09-23364183,908109,63759.6 %
Survival Report #32026-09-28364183,908109,29159.4 %
Survival Report #42026-10-05364183,908109,05459.3 %

Reproduce

One command, any machine, no account: the same bytes the report was built from. The exact bytes behind this page are repos/openai__codex.json of Survival Report #4. Open an issue with your JSON if it differs.

re audit openai/codex --json   # method v3, 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 59.3 % · causari · #4 AI code survival 59.3 % · causari · #4, paper on ink

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

Coverage

  • Method v3, causari 0.3.0. Detection from commit metadata only; survival from git blame -w -M -C at HEAD.
  • Full clone: yes. Method v3 refuses shallow clones; this row comes from a complete history.
  • Sample: 364 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: 1,874 lines per commit in this repository; the capped ratio is 58.7 %.
  • .git-blame-ignore-revs: not present in this repository.