{
  "note": "Every revision that changed a published number. Newest first. Dates are the day the corrected data went live.",
  "entries": [
    {
      "date": "2026-10-24",
      "title": "Role families: a single-tier classifier was sorting 21.5% of rows into \"other\"",
      "kind": "classification",
      "what_broke": "The role-family bucket came from one rule list that tested `engineer` first. Sales Engineer, Solutions Engineer and Support Engineer were therefore counted as engineering, and the bare word `data` pulled data-center technicians into data/ML.",
      "fix": "Four tiers: disambiguation, then specific titles, then generic words, then broad engineering words. 21 unit tests cover the traps (Technical Account Manager must not become sales; Senior Accountant must not become sales).",
      "numbers": [
        ["engineering share", "39.7%", "27.4%"],
        ["other share", "21.5%", "8.5%"],
        ["remote vs on-site gap, engineering", "-11.5%", "-6.2%"]
      ]
    },
    {
      "date": "2026-10-24",
      "title": "Per-company publication rate divided two different things",
      "kind": "statistics",
      "what_broke": "The rate was computed as paid rows in the CSV divided by open postings on the board. Those are different populations, and the CSV is sampled, so one company reported a 105.9% publication rate.",
      "fix": "Numerator and denominator now come from the same de-duplicated population. Companies with fewer than 25 open postings are left out of the table instead of producing a meaningless percentage.",
      "numbers": [
        ["companies in the table", "n/a", "146"],
        ["companies with 40+ postings publishing no salary", "n/a", "11"]
      ]
    },
    {
      "date": "2026-10-24",
      "title": "Currency conversion used a hardcoded table of ten currencies",
      "kind": "data",
      "what_broke": "Anything outside USD/EUR/GBP/CNY and six more came back as \"no salary\". Filtering by salary then deleted those postings, so the filter reported \"this job has no pay\" when the truth was \"we could not convert it\".",
      "fix": "Live rates for 166 currencies from open.er-api.com, cached 24 hours, with the snapshot timestamp stored in every row and in the run summary. Unconvertible currencies stay null instead of being guessed.",
      "numbers": [
        ["postings with a salary", "7,984", "8,004"],
        ["rows hidden by the salary filter", "~1,170", "0"]
      ]
    },
    {
      "date": "2026-10-24",
      "title": "Greenhouse publish date was actually the last-edit date",
      "kind": "dates",
      "what_broke": "The pipeline read updated_at because created_at does not exist in Greenhouse responses. A 2024 evergreen role edited for a typo looked like it was posted today, which also broke the \"only new jobs\" mode.",
      "fix": "Read first_published, fall back to created_at, then updated_at. Documented per board on the freshness page, because each board exposes a different date field.",
      "numbers": [
        ["postings older than 180 days, Greenhouse", "0.0%", "14.5%"],
        ["median posting age, all boards", "22 days", "51 days"]
      ]
    },
    {
      "date": "2026-10-23",
      "title": "De-duplication ignored location and deleted 17% of real postings",
      "kind": "dedupe",
      "what_broke": "Rows were merged on company + title. The same title in Dublin, Singapore and Chicago is three different jobs, so about 17% of the dataset disappeared. A normal de-duplication rate on a multi-board scrape is 1-3%.",
      "fix": "The key is company + normalized title + normalized location. Hyphens are normalized too, otherwise US-Chicago and us chicago stay apart.",
      "numbers": [
        ["share removed by de-duplication", "17.4%", "1.4%"],
        ["postings with a salary", "6,833", "7,984"],
        ["median salary", "$204,750", "$200,000"]
      ]
    },
    {
      "date": "2026-10-24",
      "title": "Site moved off a host that disallowed crawling",
      "kind": "infrastructure",
      "what_broke": "The static host served a platform-injected robots.txt with Disallow: / on the bare path while our own file appeared under any query string. Every URL answered 200, so nothing looked wrong, but crawlers that respect robots.txt never entered.",
      "fix": "Moved to GitHub Pages under a path that serves our own robots.txt, and added an automated crawlability check that compares the bare path against a cache-busted one and fails if a sitemap entry points at another host."
    }
  ]
}