Tables and other media
Totals, denominators, and misleading charts
Check a numeric comparison’s arithmetic, units, population, and visual claim.
Lesson 5 of 6 in the recommended order · About 25 min (estimate)
On this page
Practical AI glossary — terms and common confusions
- Model
- A learned component used to produce a result.
A drafting model is one part of a letter app; it is not the whole app.
- Application
- The software experience around components and services.
A letter app adds accounts, storage, and a Send button.
- Prompt
- Instructions and input supplied for a task.
“Summarize this notice in two bullets” specifies a task and shape, not a truth guarantee.
- Token
- A unit a model processes; it need not be a whole word.
A tokenizer can split a name into pieces; count using the actual system.
- Context
- Information available for the current request.
An earlier attachment may be absent even when its filename is visible.
- Training
- Adjusting a model using examples.
A training log differs from a conversation correction.
- Inference
- Using a trained model to produce a result.
Drafting another sentence does not by itself prove retraining.
- Retrieval
- Selecting material to supply to a task.
A retrieved notice still needs a relevance and date check.
- Embedding
- A numerical representation used to compare or organize items.
A similar search match is a candidate, not proof of the same meaning.
- Tool
- A function an application can call.
A calendar lookup can be read-only; finding an event is different from creating one.
- Agent
- Software that can choose and carry out steps toward a goal.
An agent still needs bounded permissions and checked action receipts.
- Hallucination
- Plausible generated content that is unsupported or false.
An invented opening time needs evidence or removal, even when phrased confidently.
- Evaluation
- Checking results against stated criteria.
Twenty checked examples establish a bounded result, not universal reliability.
- Multimodal
- Working with more than one kind of input or output.
A photo plus text does not prove every small label in the photo was read correctly.
Outcome
Recalculate rates and changes and distinguish respondent percentages from population-wide claims.
Why it matters
Check a numeric comparison’s arithmetic, units, population, and visual claim.
Concept
Start with the question before selecting a denominator. A respondent preference rate uses responses; invitation coverage uses invitations; seat occupancy uses capacity. The same numerator can answer different questions with different denominators. Report which one you used.
Distinguish percentage points from percent change: moving from 40% to 50% is 10 percentage points, while the relative increase is 25% of the original 40%. Charts need matching units, time periods, and clearly labeled scales. A cropped axis can magnify visual differences; describe the actual numbers rather than inferring a dramatic effect from bar height alone.
Worked example
Cedar invited 24 volunteers; 18 replied and 12 preferred morning. Morning preference among respondents is 12/18, about 66.7%. The 12 known morning preferences are 50% of all invitations, but the six nonrespondents remain unknown. Neither rate means all invitees made a choice.
Cedar continuity note: these lessons use separate snapshots—room selection, booking pending, booking confirmed, and later attendance review. Survey responses are preferences, not attendance. Each supplied packet identifies the facts for its own task; do not import a later snapshot into an earlier decision.
Same 12 known preferences, two different questions
One square represents one invited volunteer
| Mark | Group | Count |
|---|---|---|
| M | Known morning preference | 12 |
| R | Other respondents | 6 |
| ? | Nonrespondents: preference unknown | 6 |
Among respondents
Numerator- 12 morning preferences
Denominator- 18 respondents
Rate- 12 / 18 ≈ 66.7%
About two-thirds of respondents preferred morning.
Among all invitees
Numerator- 12 known morning preferences
Denominator- 24 invitees
Rate- 12 / 24 = 50%
Half of all invitees have a known morning preference. The other half is not a single preference group.
Before you check
Write the numerator, denominator, units, and rounding for each rate. For a chart claim, compare its words with the actual values and the scale description.
Practice and fresh transfer
The packets below are fictional and contain the facts needed for these cases. External references are optional background. Judge each response independently: it may be supported, contradicted, or unresolved. Select the passages needed to justify your judgment and write why the distinction matters before revealing feedback.
Assess the response
Use Accept when all material claims are supported. Use Revise when a supplied fact or requirement is contradicted. Use Evidence is insufficient when a key fact cannot be established either way. If a response contains both an unknown and a direct contradiction, choose Revise and explain both problems. Conflicting claims with no established authority remain insufficient; a claim does not become a governing fact merely because a source asserts it.
Some responses are fully supported. Others need correction or more evidence. Judge each on its sources; do not edit a correct answer just to change it.
Your written notes stay in this page and disappear when you leave. Only a self-reviewed completion can be saved to your learning account. These practice checks do not establish independent proficiency.
Practice
Case 1
Consider the proposed response for this fictional Cedar work task. Use the supplied packet and stated requirements.
Source packet
- Source 1
- Survey record: 24 invited, 18 responses, 12 morning choices among responses.
- Source 2
- Question: What fraction of invitees replied?
Response to assess
18 of 24 invitees replied, giving 75% response coverage.
Practice
Case 2
Consider the proposed response for this fictional Cedar work task. Use the supplied packet and stated requirements.
Source packet
- Source 1
- Survey: Of 18 respondents, 12 preferred morning. There were 24 invitees in total.
- Source 2
- Missingness note: Six invitees did not respond.
Response to assess
Two-thirds of all 24 invitees stated a morning preference.
Fresh transfer
Case 3
Consider a fictional before-and-after rate calculation.
Source packet
- Source 1
- Report: Completion rose from 30% to 36%.
- Source 2
- Definitions: Percentage-point change subtracts the two rates; relative percent change divides that difference by the original rate.
Response to assess
The increase is 6 percentage points, equivalent to a 20% relative increase from the original rate.
Fresh transfer
Case 4
Consider a fictional statement about a chart with a cropped axis.
Source packet
- Source 1
- Data: April 98 units; May 100 units.
- Source 2
- Chart note: The vertical axis starts at 97, so the visible bars have heights of 1 and 3 units above the axis baseline.
Response to assess
May’s total is three times April’s total.
Save your self-review
Completion records that you reviewed the cases. Your explanation and transfer performance need a facilitator to establish independent learning.
Sign in with your learning-center account to save completion.
Review the explanation for every case before saving.
Summary and next step
Apply the checklist to a new task. Preserve supported content, explain any change with evidence, and name what remains unresolved. Saving records self-review, not independently demonstrated proficiency. A facilitator must assess the explanation and fresh transfer for human learning evidence.