{"id":"study-lit-review-source-matrix","audience":"college","category":"summarizing","technique":"format","track":"study","title":"Turn three study abstracts into a source matrix","free":false,"task":"You're starting a literature review for your Education class and want a quick source matrix. Get exactly 3 numbered lines, one per study, each in the form 'Author (year): method | finding | limitation', each under 30 words, plain text. Use only the abstracts, including the erratum for Kowalski, and add no analysis.","materialLabel":"The three abstracts (attached to your prompt automatically)","material":"EDUC 3200 - Lit review prep: Does homework help elementary students?\n\nSOURCE 1: Alvarez, R. (2019)\nSurveyed 1,100 parents of 3rd-5th graders about nightly homework time and compared it to report card grades. Found no clear link between homework time and grades. Limitation: grades were self-reported by parents.\n\nSOURCE 2: Kowalski, J. (2021)\nRandomly assigned 12 fourth-grade classrooms to \"math homework\" or \"no homework\" for one semester. Students with homework scored 9 points higher on a math test.\n** ERRATUM (published 2022): the difference was 4 points, not 9; a scoring error inflated the original result. **\nLimitation: only one school district.\n\nSOURCE 3: Mensah, A. (2023)\nInterviewed 30 teachers about why they assign homework. Most said they assign it because parents expect it, not because they believe it raises learning. Limitation: small sample of teachers from two schools.\n\nProf. Bianchi: \"A matrix is for organizing, not arguing. Save your synthesis for the paper.\"\nLit review due Dec 3.","rules":[{"type":"numberedItems","count":3},{"type":"maxWords","max":100},{"type":"plainText"}],"mistakes":[{"title":"Asking for a summary","why":"The AI writes a paragraph per study and compares them, which is the paper's job, not the matrix's.","fix":"Show the shape: \"Author (year): method | finding | limitation\".","checks":["r0"]},{"title":"Not saying how many lines","why":"The AI picks its own number, and it usually picks more lines than you need.","fix":"Be exact: \"Exactly 3 numbered lines.\"","checks":["numberedItems"]},{"title":"Trusting the AI to count words","why":"AI is bad at counting. Ask for a total and it often lands 20% over.","fix":"Cap each part: \"each part under 9 words.\"","checks":["maxWords"]},{"title":"Missing the erratum","why":"The original result and the correction are both in the abstract.","fix":"Add: \"Use the corrected 4-point result for Kowalski.\"","checks":["r1"]},{"title":"Getting analysis","why":"The AI likes to synthesize and conclude.","fix":"Add: \"No analysis or comparison.\"","checks":["r2","plainText"]}],"promptHints":[{"label":"Says how many lines","patterns":["\\b(3|three)\\b.{0,25}line"]},{"label":"Shows the line shape","patterns":["\\|","method.{0,10}finding","like ['\"]","format"]},{"label":"Uses the erratum","patterns":["erratum","4 points","correct"]},{"label":"Rules out analysis","patterns":["no (analysis|synthesis|comparison)","(don't|do not).{0,15}(analy|compar)"]},{"label":"Sets a length limit","patterns":["\\d+\\s*words","word (limit|count)","under \\d+"]}],"hint":"A matrix organizes, it doesn't argue. Show the AI the line shape, point it to the erratum, and rule out analysis.","rubricLabels":["Has 3 lines, one per study, each in the form 'Author (year): method | finding | limitation'","Kowalski's finding uses 4 points (the erratum), not 9","Every detail comes from the abstracts, and there is no analysis, synthesis or comparison across studies"]}