Year 10 · 85 minutes · Retrieval
Can a cut in the wrong place change what an assistant finds?
Retrieval systems often split documents into chunks and score each against a query. This lab uses a transparent lexical overlap score over word sets. Chunk size and overlap determine whether a fact stays with its qualifier and how much irrelevant text enters the context. Larger chunks can retain context but dilute relevance. This is not semantic embedding search; a paraphrase with no shared words can fail.
Print the supplied reserve document with word indices and three queries. Rehearse the lexical scorer and qualifier markers. Explain the overlap constraint: overlap must be smaller than chunk size.
Find a claim and its qualifier in a passage. Useful earlier investigations: y6-context Use pairs for investigation, with operator/reviewer swaps after each comparison. Keep individual predictions, journals and a short oral defence so group work does not hide understanding.
Australian Curriculum Version 9 · Digital Technologies: AC9TDI10P06, AC9TDI10P08. 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.
Place a paper boundary between an opening time and its wet-weather exception.
Ask: “Would the first piece alone support an unconditional answer?”
Listen for: “No, the exception is missing.”
Predict the top chunk and qualifier coverage before changing chunk size.
Ask: “What remains fixed while we test this policy?”
Listen for: “Document, query and scoring formula.”
Adjust chunk size and overlap; inspect cut positions, lexical scores, retrieved words and context cost. Compare the same three queries.
Ask: “Did a higher score guarantee complete evidence?”
Listen for: “No, the qualifier may be in another chunk.”
Run the query using different wording with little lexical overlap.
Ask: “Can better chunking fix a scorer that does not recognise synonyms?”
Listen for: “Not necessarily; that is a retrieval representation limit.”
Choose size and overlap, record coverage and cost for all queries and state a failure case. Propose sentence-aware boundaries on paper.
Ask: “Why not simply retrieve the whole document?”
Listen for: “It increases cost and can include irrelevant or conflicting text.”
Include exact chunk IDs and relevant passages.
Ask: “What would another evaluator need to reproduce this?”
Listen for: “The document, queries, scorer and chunk settings.”
Larger chunks always retrieve better.
Move a boundary with the query fixed. Predict whether the retrieved passage retains both a fact and its qualifier.
A paraphrased query with no shared keywords can fail regardless of chunk size because the scorer is lexical.
Choose a chunk/overlap policy using a fixed three-query suite; report complete-evidence recall and context word cost.
Ask learners to reproduce one overlap score and point to the exact qualifier. Do not accept top-hit score as a substitute for evidence completeness.
Use a short document and two queries; provide a keyword intersection table before computing scores independently.
Implement sentence-aware splitting in the hardware extension and compare it against fixed windows without changing the test queries.
A chunking policy with query-level retrieval evidence, costs and a failure case.
Only supplied fictional documents are indexed. No uploads, network retrieval or private school documents are used.
Compare four overlap policies for a synthetic reserve document using CPU segmentation and GPU lexical query scoring. Change chunk size and measure retrieved word cost and qualifier completeness. Repeated chunks test throughput, not document diversity.
| Criterion | Beginning | Secure | Extending |
|---|---|---|---|
| Retrieval mechanism | Treats chunking as formatting | Connects boundaries to scored passages | Distinguishes scorer limits from boundary limits |
| Policy evaluation | Optimises one query | Compares fixed queries and cost | Reports qualifier recall and a reproducible failure |
Australian Curriculum Version 9 · Digital Technologies
References: AC9TDI10P06, AC9TDI10P08. Read the current source (checked 2026-09-07).
Evidence to assess: A chunking policy with query-level retrieval evidence, costs and a failure case.
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: Find a claim and its qualifier in a passage. 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.
Split documents into overlapping word windows and rank lexical query overlap; inspect each top chunk with its source.
Starting parameters: Query = rain tours, Words per chunk = 8, Overlap words = 2
Ranked by lexical overlap. Compare qualifiers in the top two chunks with the complete sources.
| document | start | passage | score |
|---|---|---|---|
| Visitor guide | 1 | Tours leave at nine. When rain is heavy, | 2 |
| Visitor guide | 7 | is heavy, tours are cancelled. | 1 |
| Ticket guide | 1 | Entry costs eight dollars. Children enter free on | 0 |
| Ticket guide | 7 | free on Sundays. | 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 document: Visitor guide; start: 1; passage: Tours leave at nine. When rain is heavy,; score: 2.” 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, document: Visitor guide; start: 1; passage: Tours leave at nine. When rain is heavy,; score: 2. I can trace it using this mechanism: Split documents into overlapping word windows and rank lexical query overlap; inspect each top chunk with its source. 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: Author a small source corpus and query. Compare chunk boundaries and record which qualifiers survive retrieval. Require the original and changed evidence and this boundary: Lexical retrieval is not semantic understanding and can separate a qualifier from a claim.
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.