Evaluations and datasets · Lesson 4 of 18 · 6 min

Count evaluation records

Record counts help catch accidental truncation or filtering. Reconcile loaded, evaluated, skipped and failed cases so an aggregate score has a trustworthy denominator.

Open the lab Course map

Mastery 0/3Run itExplain itApply it

learner@clairos:~ $

↑ history · Tab complete · Ctrl+C cancel · Esc, Tab to leaveExit 0

Your objectives

Hints are always available. Wrong turns never cost XP.

1
Read the case evidence
Read /opt/ai-lab/cases/aiops-evals-datasets-004.json. Separate the recorded facts from your assumptions.
Hint & worked example
Record counts help catch accidental truncation or filtering. Reconcile loaded, evaluated, skipped and failed cases so an aggregate score has a trustworthy denominator.
The complete case JSON is read successfully.
```
cat /opt/ai-lab/cases/aiops-evals-datasets-004.json
```
Common mistake to avoid: Ignore skipped records when describing coverage.
2
Isolate the deciding signal
Select the skipped field from the case JSON. What does it establish—and what does it not establish?
Hint & worked example
Explain the four skipped records rather than reporting 96 as the original dataset size.
A successful JSON query isolates skipped.
```
jq .skipped /opt/ai-lab/cases/aiops-evals-datasets-004.json
```
Common mistake to avoid: Using a different case or an unrelated signal as the justification.
3
Record your operational decision
Choose the justified code: explain-four-skips, change-without-evidence, or ignore-the-signal. Save that one code followed by a newline in /home/learner/lab/aiops-evals-datasets-004-decision.txt.
Hint & worked example
Explain the four skipped records rather than reporting 96 as the original dataset size.
The decision artifact contains the correct code, not just a matching command in history.
```
printf '%s\n' 'explain-four-skips' > /home/learner/lab/aiops-evals-datasets-004-decision.txt
```
Common mistake to avoid: Ignore skipped records when describing coverage.

Understand the pattern

Record counts help catch accidental truncation or filtering. Reconcile loaded, evaluated, skipped and failed cases so an aggregate score has a trustworthy denominator.

Interpret the evidence

Explain the four skipped records rather than reporting 96 as the original dataset size.

A tempting mistake

Ignore skipped records when describing coverage.

All names, measurements, prices, versions, and thresholds in this exercise are fictional training data. The evidence supports this bounded scenario, not a claim about a live provider.

Worked example and expected result

$ cat /opt/ai-lab/cases/aiops-evals-datasets-004.json

{
  "fixture": "Fictional training data; not a live measurement.",
  "loaded": 100,
  "evaluated": 96,
  "skipped": 4
}

Exit status: 0. The command completed successfully in the training fixture.

$ jq .skipped /opt/ai-lab/cases/aiops-evals-datasets-004.json

Exit status: 0. The command completed successfully in the training fixture.

$ printf '%s\n' 'explain-four-skips' > /home/learner/lab/aiops-evals-datasets-004-decision.txt

(no output; exit 0)

Exit status: 0. The command completed successfully in the training fixture.

Try a variation

Name the assumption that would have to change for “explain-four-skips” to stop being the justified action. Do not silently replace missing evidence with a guess.

Explain it

What does the evidence in “Count evaluation records” justify?Make the change now and gather the missing evidence afterward.Explain the four skipped records rather than reporting 96 as the original dataset size.Ignore skipped records when describing coverage.

Apply it elsewhere

A colleague concludes: “Ignore skipped records when describing coverage.” What should you do?Reject that conclusion; return to the case evidence and its stated limits.Accept it because the training command completed.Treat this fixture as a live measurement.

Keep the momentum.

Complete the lab, then explain and apply the pattern.

Next: Run a baseline evaluation Try an incident drill

Anonymous lesson and mastery progress lasts for this session. Sign in to keep synced lesson XP between sessions; mastery stays device-local. No speed bonus, lost lives, or hint penalties.

Keep learning

Case methodology: evidence, limits, decision