{
  "schemaVersion": "data-lab-evaluation/1",
  "released": "2026-10-21",
  "status": "Descriptive evaluation record; not a new validation sample",
  "records": [
    {
      "id": "london-qualifications-assessment-v2",
      "study": "London regional baseline and qualifications",
      "href": "/data-lab/london-qualifications#validation",
      "modelRelease": "london-qualifications-reproducible-v1",
      "population": "33 London authorities; 133 authorities supply the national anchor",
      "unit": "Authority × calendar year",
      "outcome": "Police-reported personal-injury collisions",
      "exposure": "DfT all-motor miles; actual assessment-year exposure",
      "training": "Expanding training from 2018; 2020–2021 outcomes excluded; training-only transforms and nested baseline selection",
      "evaluation": "2023–2025 temporal assessment, 99 rows; 2025 borough holdout, 33 rows; central-pair exclusion, 93 rows",
      "priorUse": "All assessment outcomes inspected before this release. V2 protocol amended after V1 results. None of these assessments is fresh confirmation.",
      "overlap": "Temporal training windows overlap. Borough holdout excludes held-out authority outcomes but retains its available lagged predictor history. Geographic dependence remains.",
      "selection": "Original seven baseline candidates; six social representations. No phase-two candidate selection or threshold tuning.",
      "metrics": [
        "Poisson deviance (lower)",
        "Deviance gain against named comparator (higher)",
        "Observed / expected (target 1)",
        "Exposure-weighted absolute rate error per 100,000 miles (lower)"
      ],
      "uncertainty": "399 paired bootstrap draws; 395 complete and 4 failed, unreplaced. Marginal intervals; no multiplicity or neighbouring-borough adjustment.",
      "sensitivities": "Five refitted mileage scenarios; ±20% uniform changes and total-preserving Inner/Outer reallocations. Diagnostic assumptions, not estimated exposure errors.",
      "decision": "Exploratory regional baseline candidate; no social block passes every original gate. Pricing approval absent.",
      "nextEvidence": "A prospectively frozen specification and genuinely uninspected period or external geography, followed by human actuarial validation.",
      "source": "/research/london-qualifications/v1/study-specification.json",
      "checks": "/research/london-qualifications/v1/validation.json",
      "referenceRows": 99,
      "independentCurrentVehicles": null,
      "sources": [
        {
          "path": "lib/london-flagship.json",
          "sha256": "dc35a3e1c1e04a9500b4b96bc272500f7c52f6d8cd6db344d3106fe5da97230f"
        },
        {
          "path": "/research/london-qualifications/v1/predictions.csv",
          "sha256": "d83a656f8c3d06e4b4227447714efcc31c6c85a579e7507b6f4178d329371cca"
        }
      ]
    },
    {
      "id": "price-anchor-evaluation-v2",
      "study": "Original-price car valuation",
      "href": "/data-lab/car-valuation",
      "modelRelease": "price-anchor-shape-v1",
      "population": "UK petrol/diesel research vehicles; current tool accepts ages 1–15",
      "unit": "Historical listing record; public feedback report is not a verified unique vehicle",
      "outcome": "Historical asking price; feedback distinguishes asking, sale and professional value",
      "exposure": "Not applicable; age, mileage and original price are model inputs",
      "training": "66,081 historical petrol/diesel asking-price records; assumed 2020 observation cohort; no verified historical original-price anchors",
      "evaluation": "Historical family-transfer experiment: 2,761 older cars from 10 families; near-new asking prices proxy original prices. Current independent vehicle evaluation set: 0.",
      "priorUse": "Historical experiment previously inspected; no winning variant selected from that test. Public reports default to prior-use unknown.",
      "overlap": "Exact advert dates and verified unique-vehicle identity unavailable. Public submissions can duplicate or self-select; analytical deduplication does not establish independence.",
      "selection": "Grouped, pooled and fixed 15% annual comparator reported separately on the historical experiment. No automatic recalibration from feedback.",
      "metrics": [
        "Historical median absolute percentage error: grouped 10.11%, pooled 9.37%, fixed comparator 16.07%",
        "Feedback: median signed and absolute percentage difference, separately by evidence type and cohort"
      ],
      "uncertainty": "Original-price input sensitivity only; no calibrated individual prediction interval or current coverage claim.",
      "sensitivities": "Original-price bounds; age and mileage through frozen curves. Market index stays at the 19 October 2026 snapshot.",
      "decision": "Research test only. Zero independently validated current vehicles in the released evidence; quote mode remains blocked.",
      "nextEvidence": "Reviewed, matched original-price and current-price evidence with sampling, date alignment and development-use separation. Keep collection exports for later independent validation.",
      "source": "/valuation/price-anchor/SERVICE.txt",
      "checks": "/valuation/price-anchor/model.json",
      "referenceRows": 2761,
      "independentCurrentVehicles": 0,
      "sources": [
        {
          "path": "/valuation/price-anchor/model.json",
          "sha256": "c40b225cf5164176395a51bb3e8f500ff9d388cce2e6233a6cce6e1c7a2ba8b3"
        },
        {
          "path": "/valuation/price-anchor/market-index.json",
          "sha256": "621747ae06cfb04c4dacb5e369b3a56d47b3f77be9b7002e9788a84a5809374f"
        }
      ]
    }
  ]
}