---
title: "Reading the Numbers"
description: "Course reference: the metrics any Jev benchmark scorecard reports, one entry each — intuition, formula with worked arithmetic, the failure mode, and the reading rule, all off one 2×2 grid. Written for the software engineer: every metric is anchored to a deployment decision you already own. Data scientists can skip straight to the entries they need."
license: "© 2026 Peripatos · free to read; quoting with credit welcome, reuse by permission. Unofficial educational resource; Jev and TypeSafe are trademarks of TypeSafe AI."
published-date: 2026-10-19
verified-date: 2026-10-19
source: "https://peripatos.dev/courses/jev-fundamentals/references/reading-the-numbers/"
---

You are reading a scorecard and it says κ 0.085, ECE 0.32, F1 66.7%. Whether those numbers praise the model or warn you off is pure reading skill, and this reference is that skill, one metric at a time. Every entry follows the same four lines: **intuition** (the plain-English one-liner and which cells of the grid it reads), **formula and worked toy** (the display equation, numbered and consistent across the whole course), **when it lies** (the failure mode that catches people), and **how to read it** (the rule the benchmark holds itself to). The audience is deliberately the software engineer integrating a judged pipeline — each entry opens with the deployment decision the metric answers, not the statistics. If you already think in confusion matrices, this page is your lookup layer: jump straight to the entry you need.

Everything on this page is arithmetic on four numbers. One frozen toy runs the whole reference: a censor screening files for secrets judged 20 files in one labeled run — 10 carrying secrets, 10 clean. It flagged 8 files, of which 6 were real. It is a _teaching_ toy: the benchmark's real, interval-carrying numbers live in the lessons, and S01E05's report is where they land.

## In this reference

1. [The one grid everything reads from](#grid)
2. [Accuracy](#metric-accuracy)
3. [Precision](#metric-precision)
4. [Recall](#metric-recall)
5. [F1](#metric-f1)
6. [Cut](#metric-cut)
7. [κ and the keep-all signature](#metric-kappa)
8. [Confidence intervals and the tie rule](#metric-intervals)
9. [ECE and calibration](#metric-ece)
10. [MAE and bias](#metric-mae)
11. [Assembling a scorecard row](#scorecard)
12. [Sources & further reading](#sources)

## The one grid everything reads from

The [glossary](/courses/jev-fundamentals/glossary/) defines a **confusion matrix** as the four buckets a binary judgment lands in against truth: hits (true positive), false alarms (false positive), misses (false negative), clean passes (true negative). Every metric below is a different fraction of these four counts — nothing richer ever arrives at a metric, and every dispute between two summary metrics resolves by walking back here:

Table 1. The 2×2 grid this reference is built on. TP + FP + FN + TN = 20.

|   | Actual: secret (positive) | Actual: clean (negative) |
| --- | --- | --- |
| Flagged (predicted positive) | True Positive (TP) = 6 | False Positive (FP) = 2 |
| Passed (predicted negative) | False Negative (FN) = 4 | True Negative (TN) = 8 |

<svg viewBox="0 0 700 336" style="width:100%;max-width:680px;height:auto;margin:0 auto;display:block;" aria-label="Anatomy of the two-by-two grid: the flagged row sums to the precision denominator, TP plus FP equals 8; the actual-secret column sums to the recall denominator, TP plus FN equals 10; the diagonal sums to accuracy, 14 of 20; kappa reads the same four counts against chance" xmlns="http://www.w3.org/2000/svg"> <style> .rg-bg { fill: var(--surface, #fff); } .rg-box { fill: var(--surface, #fff); stroke: var(--border, #999); stroke-width: 1.5; } .rg-hit { fill: var(--surface, #fff); stroke: var(--accent, #0066cc); stroke-width: 1.8; } .rg-text { fill: var(--ink, #111); font-family: var(--font-ui, sans-serif); font-size: 19px; font-weight: 700; } /* presentation-attribute hexes ride each element beside these classes; readers that strip the style block keep the figure (reader-mode rule, DESIGN.md). NB: no angle brackets inside this block - svg style parses as foreign content, and a literal open-bracket opens a nested element. */ .rg-name { fill: var(--ink, #111); font-family: var(--font-ui, sans-serif); font-size: 13px; font-weight: 700; } .rg-small { fill: var(--ink-muted, #777); font-family: var(--font-ui, sans-serif); font-size: 11px; } .rg-head { fill: var(--ink-muted, #777); font-family: var(--font-ui, sans-serif); font-size: 12px; font-weight: 700; } .rg-bracket { stroke: var(--accent, #0066cc); stroke-width: 1.8; fill: none; } .rg-accent { fill: var(--accent, #0066cc); font-weight: 700; } </style> <text x="270" y="40" text-anchor="middle" class="rg-head" fill="#777">Actual: secret (+)</text> <text x="440" y="40" text-anchor="middle" class="rg-head" fill="#777">Actual: clean (−)</text> <text x="14" y="78" class="rg-name" fill="#111">Flagged</text> <text x="14" y="93" class="rg-small" fill="#777">(predicted +)</text> <text x="14" y="148" class="rg-name" fill="#111">Passed</text> <text x="14" y="163" class="rg-small" fill="#777">(predicted −)</text> <rect x="190" y="56" width="160" height="60" rx="6" class="rg-hit" fill="#fff" stroke="#0066cc"></rect> <text x="270" y="91" text-anchor="middle" class="rg-text" fill="#111">TP = 6</text> <text x="270" y="110" text-anchor="middle" class="rg-small" fill="#777">a hit</text> <rect x="360" y="56" width="160" height="60" rx="6" class="rg-box" fill="#fff" stroke="#999"></rect> <text x="440" y="91" text-anchor="middle" class="rg-text" fill="#111">FP = 2</text> <text x="440" y="110" text-anchor="middle" class="rg-small" fill="#777">a false alarm</text> <rect x="190" y="126" width="160" height="60" rx="6" class="rg-box" fill="#fff" stroke="#999"></rect> <text x="270" y="161" text-anchor="middle" class="rg-text" fill="#111">FN = 4</text> <text x="270" y="180" text-anchor="middle" class="rg-small" fill="#777">a miss</text> <rect x="360" y="126" width="160" height="60" rx="6" class="rg-hit" fill="#fff" stroke="#0066cc"></rect> <text x="440" y="161" text-anchor="middle" class="rg-text" fill="#111">TN = 8</text> <text x="440" y="180" text-anchor="middle" class="rg-small" fill="#777">a clean pass</text> <path class="rg-bracket" fill="none" stroke="#0066cc" d="M 526 56 h 7 v 60 h -7"></path> <text x="540" y="78" class="rg-accent" fill="#0066cc">Precision</text> <text x="540" y="94" class="rg-small" fill="#777">TP + FP = 8</text> <text x="540" y="110" class="rg-small" fill="#777">reads the flagged row</text> <path class="rg-bracket" fill="none" stroke="#0066cc" d="M 190 198 h 7 v 7 h 153 v -7 h 7"></path> <text x="190" y="230" class="rg-accent" fill="#0066cc">Recall</text> <text x="190" y="246" class="rg-small" fill="#777">TP + FN = 10</text> <text x="190" y="262" class="rg-small" fill="#777">reads the actual-secret column</text> <text x="520" y="236" text-anchor="end" class="rg-accent" fill="#0066cc">Accuracy</text> <text x="520" y="252" text-anchor="end" class="rg-small" fill="#777">(6 + 8) of 20</text> <text x="520" y="268" text-anchor="end" class="rg-small" fill="#777">reads the outlined diagonal</text> <text x="350" y="300" text-anchor="middle" class="rg-small" fill="#777">κ uses the same four counts, read against the agreement chance would produce — the κ entry below carries the full reading</text> </svg>

Figure 1. How the three headline cuts read the same grid: precision's denominator is the flagged row of the matrix, recall's is the actual-secret column, and accuracy's is the diagonal.

The counting is the cheap half; the ground-truth column (who _actually_ carried a secret) is the expensive one — the labeling work that makes every metric here possible. Figure 1 lays out the grid's three headline reads; every entry below walks back to it. Four definitions already live in the glossary and are not redefined below: [κ (Cohen's kappa)](/courses/jev-fundamentals/glossary/), [Brier score](/courses/jev-fundamentals/glossary/), the [reliability curve](/courses/jev-fundamentals/glossary/), and [PR-AUC](/courses/jev-fundamentals/glossary/) for threshold-free reading. Equations carry the numbers (1)–(12), _and S01E05 re-displays the same numbers_: a citation travels between this page and the lessons intact — one number, many surfaces. The numbers are stable names, not a reading order: a course page may cite (12) before (7), because the lessons meet formulas in their own narrative order — the number is the identity.

### Confusion matrix

The four buckets a binary judgment lands in against truth: hits (true positive), false alarms (false positive), misses (false negative), clean passes (true negative). Every metric is an arithmetic view of these four counts.

**Eq. (1)** — N = TP + FN + FP + TN.

**Worked toy:** on Table 1, 6 + 4 + 2 + 8 = 20 — the equation is just the grid audited against the dataset size.

**When it lies:** it doesn't. The matrix is raw ground truth, not a summary; when two summary metrics contradict each other, look back at the four numbers to see what actually happened.

**How to read it:** print the 2×2 beside any summary anyone hands you. Every dispute resolves at the counts — it is the only table on this page that is evidence rather than arithmetic on evidence.

### Accuracy

The share of answers in the right bucket: (hits + clean passes) / everything. All four buckets count alike, so accuracy rewards the lazy judge on a lopsided workload — pair it with recall or precision before believing it.

**Eq. (2)** — Accuracy = (TP + TN) / N.

**Worked toy:** the two correct quadrants hold 6 + 8 = 14 of 20, so accuracy = 14 / 20 = 0.70. Flattened twice: on the balanced 10/10 grid a flag-nothing censor and a flag-everything censor each read exactly 0.50 — one for missing everything, one for crying wolf on every clean file.

**The deployment decision it answers:** none, safely, by itself. If 90% of your test files are clean, a censor hard-coded to say "clean" achieves 90% accuracy while doing zero work — it would pass your accuracy gate outright. The class balance is a fact about your workload, not the model.

**When it lies:** imbalanced workloads reward the lazy or biased judge.

**How to read it:** never alone; on guardrail-shaped workloads (few true positives), read κ and precision/recall instead — and remember the [keep-all signature](#metric-kappa).

### Precision

Of everything flagged, how much was real: hits / (hits + false alarms). It charges every cry of wolf; alone it cannot see the misses — a judge that flags one thing and skips the rest scores 100%. Reads the flagged column of the grid — the flagged pool is the denominator's cost.

**Eq. (3)** — Precision = TP / (TP + FP).

**Worked toy:** the flagged column holds 8 files and 6 of them were real, so precision = 6 / (6 + 2) = 0.75. The denominator is the flag pool — the quadrant the censor itself fills — which is why precision falls as the censor over-flags and rises as it goes quiet.

**The deployment decision it answers:** alert fatigue. If an engineer gets 10 censor alerts a day and 8 are false alarms, they stop trusting the alert queue — low precision is the number that forecasts that.

**The trap:** precision is recall-blind. A censor that flags exactly one file — and happens to get it right — scores a perfect 1.00 while missing the other nine secrets. Precision never sees the quadrant it did not fill.

**How to read it:** report it beside recall, with the flag count named. A precision claim without its denominator (the flagged pool) proves nothing about coverage.

### Recall

Of everything real, what the judge caught: hits / (hits + misses). It charges every miss; alone it rewards the censor that flags everything. Reads the actual-positive row of the grid — the missed-pool is the denominator's cost.

**Eq. (4)** — Recall = TP / (TP + FN).

**Worked toy:** the actual-secret row holds 10 files and the censor caught 6, so recall = 6 / (6 + 4) = 0.60. The denominator is the true-positive pool, so the clean column is invisible to it by construction.

**The deployment decision it answers:** leaked secrets. In security (or compliance) review the false negative is the catastrophic class — the secret that ships. Low recall is the number that forecasts that breach.

**The trap:** recall rewards over-prediction. A censor that flags every file reads a perfect 1.00 while filling the false-positive quadrant; flag-nothing reads 0.00. Neither number says whether the system is operable.

**When it lies:** aggregate recall hides per-kind failure. S01E05's report found one arm blind to a whole secret kind (auth tokens) while its overall recall looked acceptable — keep per-kind recall where the truth matters at the kind level.

**How to read it:** the pair (precision, recall) travels together, never either alone.

### F1

The harmonic mean of precision and recall at one cut — a judge's usefulness in one number that punishes either side falling to zero. Reads the same flagged column and positive row as precision and recall.

**Eq. (5)** — F1 = 2TP / (2TP + FP + FN).

**Worked toy:** both forms on the grid agree — from the counts, F1 = 2 · 6 / (12 + 2 + 4) = 12 / 18 ≈ 0.667; from the pair, 2 · 0.75 · 0.60 / (0.75 + 0.60) = 0.90 / 1.35 ≈ 0.667. That agreement is the harmonic mean's whole point: a judge strong on one side and idle on the other is held to the idle side (100% precision with 0% recall scores 0, not 0.50).

**When it lies:** it hides the cut choice. S01E05's worked case: an arm's keep-scores sat under the 0.5 cut so hard F1 read 50% there; the threshold sweep rescued 70% at 0.35; after the answer definitions were corrected the scores separated on their own — 73.1% at the original cut, nothing tuned.

**How to read it:** report F1 at the cut WITH the sweep over cuts — or the operating point is a guess wearing a number.

### Cut

The threshold where a continuous answer becomes a decision: answers at or above it count as "yes". The model owns the probabilities; the cut is yours, and moving it trades recall against precision along the sweep.

**Eq. (6)** — flagi ⇔ scorei ≥ t.

where i runs over a judged run and t is the threshold you own.

**Worked toy:** eight of the 20 scored answers sit at or above the 0.5 cut and get flagged. Push the cut to 0.7: only two true positives remain above it while both false positives now sit below — flags 2, hits 2, precision 1.00, recall 0.20. Nothing about the censor changed between the two reads; only the cut moved, and with it the whole trade you own.

**The deployment decision it answers:** your guardrail thresholds. S01E03's routing thresholds and abstention bands are this line — if you tuned one against a build, the receipt habit (S01E04) protects the match between cut and build.

**How to read it:** never report a cut-bound number without its cut. Sweep before believing any operating point — a sweep is a re-read of captured scores, not a re-run of the benchmark (capture-first makes it free).

### Confidence interval (95%)

The range the same measurement lands in on 95% of repetitions of the data — bootstrapped by resampling the labeled items with replacement, no distribution assumed. Read the interval first: the point is a guess, the interval is its honest size.

**Eq. (7)** — CI95 = [ κ̂ at the 2.5th percentile , κ̂ at the 97.5th percentile ].

where κ̂ is the κ recomputed on one bootstrap resample.

**Worked toy:** resample the toy run's 20 labels at random 10,000 times, recompute κ on each resample, sort, and read the 250th and 9750th values: toy κ = 0.40 lands in [0.15, 0.65]. A model scoring 0.85 on 20 evaluation samples might behave anywhere between roughly 0.60 and 0.95 in deployment — that is what small n means.

**The deployment decision it answers:** how much to trust a short eval before you build on it. Interval width scales with 1/√n: the same κ on 500 items tightens about five-fold. A wide interval is not failure; it is small n speaking — and the honest report prints it.

**When it lies:** narrow intervals from cherry-picked subsets are the dishonest version; a wide one printed plainly is honest.

**How to read it:** never compare points without intervals — and never declare Model A "better" than Model B unless their intervals are fully disjoint. The tie rule below fixes "disjoint" as arithmetic.

### Tie rule

The pre-committed comparison reading: overlapping intervals are ties; only a disjoint interval supports a separation claim. Fixed before the data arrives, so "who won" cannot be re-litigated after.

**Eq. (8)** — separate ⇔ A's high end &lt; B's low end, or B's high end &lt; A's low end.

where A and B are two judges' intervals on the same task.

**Worked toy:** judge A reads 0.40 [0.25, 0.55], judge B reads 0.43 [0.28, 0.58]. A's high end (0.55) sits above B's low end (0.28): the intervals overlap and the reading is a tie — however big the 0.03 gap in B's favor looks in a headline.

**When it lies:** it cannot — what it can do is disappoint. Wide-interval ties answer less than a vendor's launch post wants; that is the rule working, not failing.

**How to read it:** commit the comparison reading before the data arrives (the benchmark's pre-registered rules); the family matters too — S01E05's S1 intervals all overlap, so its arms are a family, not a ranking, and no purchase decision can be priced off the point estimates.

### ECE (expected calibration error)

The weighted gap between claimed confidence and achieved hit rate, binned over the model's own claims. "80% sure" ten times should hit about 8 — ECE prices that distance; it says nothing about accuracy.

**Eq. (9)** — ECE = Σb (nb / N) · |confb − hitb|.

where nb is the count in confidence bin b, N the total answers, confb that bin's average claim, and hitb its achieved hit rate.

**Worked toy:** one judge answers 20 times. Ten answers claim 0.8 and seven hit — that bin over-claims by |0.8 − 0.7| = 0.1; ten claim 0.3 and four hit — a 0.1 gap again. Each bin pays its gap, weighted by its share of the answers: the toy reads ECE = 0.10, systematic over-prediction of confidence.

**The deployment decision it answers:** is the band router load-bearing? S01E03's routing bands act on the model's own claims — if the claims do not predict the hits, the band routes on nothing and every threshold you set on confidence is fiction. The benchmark gates band routing on a pre-registered bar: ECE ≤ 0.15 on both answer types, resolved conservatively (both must pass).

**The real caution, for calibration of your reading:** S01E05's quiet-confabulation finding — wrong answers that still claimed 0.43–0.54 confidence on every arm. ECE below the bar is necessary, never sufficient: wrong-and-confident is the failure mode a band router trusts most.

**When it lies:** few bins or few items make ECE noisy — read it beside the reliability curve; and it prices the claims' gap only, never correctness (a precise-but-wrong judge scores 0 while being useless).

**How to read it:** gate the band router on it; keep the Brier score as the companion (both live in the glossary).

### MAE (mean absolute error) and bias

MAE — the average size of an error, ignoring direction, on scale answers. Absolute errors cannot cancel: two opposite errors still pay full price. **Bias** — the signed average error: positive leans consistently over, negative consistently under. MAE prices the size; bias names the direction of the lean.

**Eq. (10)** — MAE = (1/n) · Σ |ŷi − yi|.

where ŷi is prediction i, yi its truth, and n the number of scale answers.

**Eq. (11)** — Bias = (1/n) · Σ (ŷi − yi).

**Worked toy:** a three-item urgency toy with truths (1, 1, 1). Judge A answers (2, 0, 1): errors +1, −1, 0 — the signed average would cancel to 0 and hide all of it, the absolute average reads 2/3. Judge B answers (2, 2, 1): errors +1, +1, 0, leaning +0.67 — over-predicting urgency on every item. Same MAE, opposite deployments.

**The deployment decision it answers:** which countermeasure to ship. A leaning judge tightens downward; an eager one (positive bias) needs thresholds raised, a sluggish one (negative) lowered — the sign chooses the fix; MAE alone cannot even name the problem.

**The real case, for calibration of your reading:** S01E05's urgency column printed both — 0.53/+0.37 on an eager small arm, 0.65/−0.39 on a sluggish one, 0.36/+0.22 on the hosted reference. Same magnitude, opposite fixes.

**When it lies:** a near-zero bias can hide two opposite sub-populations that cancel — break the groups before trusting the aggregate.

**How to read it:** the pair travels together: MAE for size, bias for direction, never one instead of the other.

### κ (Cohen's kappa) and the keep-all signature

κ — [rater agreement beyond chance](/courses/jev-fundamentals/glossary/) — is the standard instrument for judge-vs-human agreement on binary verdicts; the **keep-all signature** is the fingerprint of a judge that filters nothing: pass-rate at the workload's shape with κ at exactly 0, because chance agreement absorbs an unfiltered funnel.

**Eq. (12)** — κ = (po − pe) / (1 − pe).

where po is observed agreement and pe what chance alone would agree to given the workload's shape.

**Worked toy:** the toy's flag-nothing censor keeps every file. Of its 20 judgments the 10 correct keeps are its only agreements: po = 10/20 = 0.50, and chance explains exactly 0.50 of it — the subtraction leaves κ = 0.000 while accuracy read 50% and looked like a judge doing its job.

**The deployment decision it answers:** does the funnel filter at all? A curation funnel that keeps everything has no operating cost advantage over no funnel; a pass rate alone cannot tell you — a low keep-rate could equally mean a tight, useful sieve or an over-eager one.

**The real case, for calibration of your reading:** on S01E05's 23-keep/29-split workload, one small arm kept all 52 items: observed agreement 23/52 ≈ 0.44, chance agreement 0.44, κ = 0.000 — the signature in the wild, one ten-thousandth from its definition. Another arm's κ read 0.085 beside a 47-of-52 keep rate: barely past the funnel, not judgment.

**When it lies:** conversely — a near-zero κ on an imbalanced workload is the signature's _neighborhood_, not automatically its verdict; read the keep-rate next to it before calling a model lazy.

**How to read it:** pass-rate and κ together, on imbalanced workloads instead of accuracy. The pair, one arithmetic step apart, is the lazy-judge detector.

## Assembling a scorecard row

A scorecard row is not a list of six numbers; it is a production order. Read it in four passes, and let the pass structure — not the number order — decide what you believe:

Table 2. Assembling a scorecard row: the question each column answers and its reading rule.

| column | the question it answers | its reading rule |
| --- | --- | --- |
| κ with 95% CI | judgment past the workload's shape? | interval first; overlaps tie |
| accuracy | how often right, raw? | never alone; pair with recall or precision |
| precision / recall (or F1) | flags mean something / catches the real ones? | always paired; at the chosen cut |
| ECE (Brier companion) | probabilities load-bearing? | the band-as-router rule stands here |
| MAE / bias | scale error size and direction? | sign = deployment posture |
| unknown-rate / conf-wrong | abstains where it should; confidence honest? | the honesty pair, read together |

The first pass (κ + CI) decides whether the row is readable at all: a keep-all signature or a family of overlapping intervals means there is no ranking to read further down, only a description. Only a row that survives that pass earns the per-task precision/recall reading in second place; the calibration pair (ECE + honesty) gates what you may automate; the MAE/bias pair sets your countermeasure.

**Beyond two rows.** The toy grid is binary — every entry above divides one flagged axis and one true axis in half. The season's S1 task is already one grade up: three classes (act, review, unknown), which the benchmark reads the multi-class way — the same precision/recall arithmetic run once per class, then averaged equally across classes (macro-averaging), so a large healthy class cannot drown a small collapsing one. The reading rules survive the upgrade unchanged: the average is the summary, the per-class lines are the finding, which is why S3's weak-cell column, not its aggregate, tells you which harm a particular arm misreads in production.

> **🧭 Practice** A censor flags 8 of 10 real secrets and also flags 3 of 20 clean files. Compute precision, recall, accuracy, and F1 by hand from this reference — then name the reading rule each number needs. Step-by-step solution (expand only after trying it yourself) Fill the grid first. The dataset is 30 files: 10 secrets, 20 clean. Flagged-and-real: TP = 8. Flagged-and-clean: FP = 3. Real-but-passed: FN = 10 − 8 = 2. Clean-and-passed: TN = 20 − 3 = 17. Check: 8 + 3 + 2 + 17 = 30. (Every metric is arithmetic on these four counts.) Precision (3) = TP / (TP + FP) = 8 / (8 + 3) = 8/11 ≈ 0.73. Reading rule: report it beside recall, with the flag count named. Recall (4) = TP / (TP + FN) = 8 / (8 + 2) = 0.80. Reading rule: never alone — pair it with precision. Accuracy (2) = (TP + TN) / N = (8 + 17) / 30 = 25/30 ≈ 0.83. Reading rule: never read alone — two-thirds of the files are clean, so the workload leans in the censor's favor; check κ. F1 (5) = 2TP / (2TP + FP + FN) = 16 / (16 + 3 + 2) = 16/21 ≈ 0.76. Reading rule: report at the chosen cut, with the sweep over cuts.

## Sources & further reading

- [Cohen's κ (1960)](https://en.wikipedia.org/wiki/Cohen%27s_kappa) · Wikipedia · encyclopedia article · verified 2026-10-16
  A coefficient of agreement for nominal scales — the original paper, JASA 55(282); the Wikipedia page links it.
- [McNemar's test (1947)](https://en.wikipedia.org/wiki/McNemar%27s_test) · Wikipedia · encyclopedia article · verified 2026-10-16
  The paired-flip statistic for before/after judgments; also carried by the glossary.
- [Guo et al. (2017), On Calibration of Modern Neural Networks](https://arxiv.org/abs/1706.04599) · arXiv · preprint · verified 2026-10-16
  ECE and the reliability diagram, the calibration pair used here.
- [Brier (1950)](https://en.wikipedia.org/wiki/Brier_score) · Wikipedia · encyclopedia article · verified 2026-10-16
  Verification of forecasts expressed in terms of probability — the Brier score's origin (Monthly Weather Review 78(1)).

## See also

- [🎓 S01E05: The Local Benchmark — Tying It All Together](/courses/jev-fundamentals/s01e05-local-benchmark/)
- [📖 Jev Glossary](/courses/jev-fundamentals/glossary/)
---

Source: [Reading the Numbers](https://peripatos.dev/courses/jev-fundamentals/references/reading-the-numbers/), Peripatos — free to read; reuse by permission.
