Year 4 · 60 minutes · Robustness
Why can an unchanged model stop working?
Our classifier was fitted to synthetic readings under one light condition. A new light condition adds an offset to measurements without changing object labels. The frozen model now sees different numbers. Correcting a known sensor offset can restore some predictions, but a single correction does not fix every kind of environmental change.
Prepare paired readings for the same synthetic objects under two light settings. Mark the original training threshold. Explain that subtracting a known offset is a simplified calibration procedure.
Keep a test rule fixed while changing one environmental condition. Useful earlier investigations: y1-sensor, y3-holdout Use pairs with predictor/operator roles. Swap after the first comparison. Each learner draws or writes their own explanation using one exact case.
Australian Curriculum Version 9 · Digital Technologies: AC9TDI4K01, AC9TDI4P05. Selected aspects only. This activity contributes evidence; it does not cover the full descriptor or achievement standard. A programming descriptor is not claimed for merely moving controls. ACARA AI curriculum connection · V9 Technologies These are planning connections, not ACARA endorsement or exhaustive descriptor alignment.
Show its old and new readings without changing its label.
Ask: “Did the object type change, or its measurement?”
Listen for: “Its measurement changed.”
Predict which side of the frozen threshold an offset object reaches.
Ask: “Which parts of the system are frozen?”
Listen for: “The model and the true object labels.”
Move the lighting offset and watch paired readings and error counts update. Save baseline and shifted states.
Ask: “Which errors appeared first as the offset increased?”
Listen for: “Objects closest to the old threshold.”
Use the edge case in which bright objects shift more than dark ones.
Ask: “Can subtracting one number fix unequal shifts?”
Listen for: “No, some objects need a different correction.”
Estimate an offset from a known reference, apply it and evaluate every fixed object. State what the correction assumes.
Ask: “What evidence would tell us to stop using this correction?”
Listen for: “Different residual errors across the range.”
Record condition, correction, error counts and limitation.
Ask: “Was yesterday’s test wrong?”
Listen for: “It described yesterday’s conditions, not every future one.”
A model that worked yesterday will work tomorrow.
Add a positive lighting offset with the classifier frozen. Predict which labelled objects cross its boundary.
A brightness-dependent change cannot be removed by subtracting a single constant offset.
Calibrate against a reference and report residual errors under uniform and non-uniform shifts.
Ask which quantity changed and which remained fixed. If a learner says the model learned from the shifted objects, point out that the model parameters were frozen.
Use three objects and an integer offset; slide a paper strip beneath a fixed threshold.
Add a separate scale correction and test whether two reference points resolve an affine shift.
A sensor calibration field note with paired readings and residual errors.
The lagoon data are invented. Do not use the model for environmental monitoring or decisions about swimming conditions.
Apply uniform and value-dependent shifts to a frozen model over thousands of measurements. Sweep offsets, control the correction, and compare raw and corrected error rates.
| Criterion | Beginning | Secure | Extending |
|---|---|---|---|
| Shift diagnosis | Calls every error a bad model | Identifies changed input measurements | Distinguishes uniform and non-uniform shift |
| Correction evidence | Tunes until one object works | Checks all fixed objects | States calibration assumptions and failure conditions |
Australian Curriculum Version 9 · Digital Technologies
References: AC9TDI4K01, AC9TDI4P05. Read the current source (checked 2026-09-07).
Evidence to assess: A sensor calibration field note with paired readings and residual errors.
Selected aspects only. This activity contributes evidence; it does not cover the full descriptor or achievement standard. A programming descriptor is not claimed for merely moving controls. Moderate the supplied illustrative responses against your school unit and current achievement standard.
These are planning estimates to test with your class. A short session develops one supported claim; it does not compress the whole senior project.
| Stage | 45 minute focus | 60 minute investigation |
|---|---|---|
| Readiness and prediction | 0–5 | 0–5 |
| Trace the supplied example | 5–13 | 5–15 |
| Author and run cases | 13–25 | 15–35 |
| Counterexample and redesign | 25–35 | 35–45 |
| Explain and discuss | 35–42 | 45–55 |
| Export and handover | 42–45 | 55–60 |
For a longer project, use three 50-minute sessions. Session 1 (0–50): readiness, model, hypothesis and initial cases. Export a project and record the next test. Session 2 (50–100): reopen, check settings, author counterexamples and revise the design. Export the changed project and identify unresolved evidence. Session 3 (100–150): independent peer test, final artefact, individual explanation and moderation. If using two 60-minute sessions, stop at minute 60 after saving the first comparison; use 60–120 for redesign, independent test and defence.
Entry check: Keep a test rule fixed while changing one environmental condition. Ask the learner to demonstrate it before choosing the level of support.
Preparation: allow about 15 minutes to run the starter, print the cards and check a project can be reopened. This estimate has not yet been measured in a classroom pilot.
Read the entry question aloud, model one row, and label the units. Offer the case table as a large-print sheet. Keep mathematical derivations optional until the learner can explain the comparison.
For one device, use a projector: one pair predicts, one operates, and the class records on paper. Swap roles after the first comparison. For individual access, support keyboard controls and a written table equivalent to each visual. Learners may explain orally or with an annotated diagram. Never require personal data, a recorded voice, or a photograph.
Mixed readiness: if the entry check is difficult, use the linked prerequisite and the first two case cards; retain the same central question. If secure, ask the learner to design an unseen test and state which explanation it could disprove.
Keep the classification rule fixed and multiply the same object scores by a changed environment factor.
Starting parameters: Boundary = 0.5, Light multiplier = 1
TP 2; FP 0; FN 0; TN 2.
| case | score | actual | predicted | outcome | cost |
|---|---|---|---|---|---|
| 1 | 0.3 | False | False | TN | 0 |
| 2 | 0.6 | True | True | TP | 0 |
| 3 | 0.8 | True | True | TP | 0 |
| 4 | 0.2 | False | False | TN | 0 |
These are authored examples, not work collected from children. Assess reasoning using the lesson rubric, not whether the first prediction was correct.
Beginning: “It worked because the result looks right.” This identifies no exact case, control or measurement. Ask the learner to point to one row and say what happened.
Developing: “In the first case I recorded case: 1; score: 0.3; actual: False; predicted: False; outcome: TN; cost: 0.” This cites evidence, but does not yet explain how the result follows from the rule. Ask the learner to trace the relevant step.
Secure: “For the first supplied case, case: 1; score: 0.3; actual: False; predicted: False; outcome: TN; cost: 0. I can trace it using this mechanism: Keep the classification rule fixed and multiply the same object scores by a changed environment factor. My result supports a claim about these supplied cases. It does not establish that the same result holds outside them.” Look for an accurate trace, the actual settings and a bounded claim; accept equivalent oral or visual evidence.
Extending: The learner constructs and reruns a new case, reports whether the first explanation survives, and defends a revised design. Use this concrete challenge: Design a light-shift test and separate changing the sensor environment from changing the rule. Require the original and changed evidence and this boundary: This isolates one artificial environmental change; real shifts can affect many features.
Moderation: first assess independently against each lesson criterion. Compare the exact trace or artefact that led to your judgement. Resolve differences using evidence, not polished language. Keep each learner's individual explanation even when the artefact was produced in a group.