{"id":"res-col-music-study-abstracts-matrix","audience":"college","category":"research","technique":"grounding","title":"Turn four study abstracts into a one-line-each evidence table","free":false,"task":"For your Psychology 101 lit review on music while studying, you want one line per study from 4 abstracts: exactly 4 numbered lines, each with author and year, the sample size (or \"N not stated\"), and the main finding in under 15 words. Use corrected numbers where a correction exists, and don't claim more than an abstract says. Plain text, nothing else.","materialLabel":"Four abstracts from your search (attached to your prompt automatically)","material":"1. Reilly, M. & Chen, D. (2021). Lyrics and Reading Comprehension. Applied Cognitive Studies.\nAbstract: 120 undergraduates completed reading tests while hearing music with lyrics, instrumental music, or silence. Comprehension scores were lower with lyrical music than with silence. Instrumental music showed no difference from silence.\n\n2. Batista, R. (2019). Study Habits and Background Music: A Campus Survey. Journal of College Learning.\nAbstract: We surveyed 860 students at two universities. 71% reported studying with music. Students who studied with music reported more enjoyment of studying, but their self-reported GPAs did not differ from students who studied in silence.\n\n3. Kowalski, J., Ruiz, A., & Byrne, T. (2022). Tempo and Typing. Human Performance Letters.\nAbstract: Participants (N = 48) transcribed text while hearing slow or fast music. Fast-tempo music increased typing speed but not accuracy.\nCorrection (2023): The final analyzed sample was 44 after four participants were excluded for equipment errors.\n\n4. Mensah, K. (2020). Where Students Choose to Study: Noise in the Library. Library Behavior Review.\nAbstract: This observational study tracked seat choices in a university library over one semester. Students moved away from louder zones during exam weeks. Academic outcomes were not measured.\n\nmy note: lit review draft due Monday, Prof. Asante wants a table first","rules":[{"type":"numberedItems","count":4},{"type":"plainText"}],"mistakes":[{"title":"Using the uncorrected number","why":"The AI copies the first sample size it sees and skips the correction note.","fix":"Add: \"Use corrected numbers where a correction is given.\"","checks":["r0"]},{"title":"Inventing missing details","why":"When an abstract has no sample size, the AI may estimate one or skip the field silently.","fix":"Say: \"If the sample size isn't given, write N not stated.\"","checks":["r0"]},{"title":"Overstating findings","why":"The AI rounds findings up into conclusions, like 'music helps grades', that the abstract never claims.","fix":"Add: \"State only what the abstract says it found.\"","checks":["r1"]},{"title":"Not saying how many","why":"The AI decides the length itself and usually returns more lines, one per study than you can use.","fix":"Be exact: \"exactly 4 numbered lines, one per study.\"","checks":["numberedItems","r2"]},{"title":"Getting markdown back","why":"AI defaults to bold labels and headings, which show up as stray symbols in your notes doc.","fix":"Ask for \"plain text, no bold, no headings.\"","checks":["plainText"]}],"promptHints":[{"label":"Fixes the line shape","patterns":["one line","author.{0,20}year","format","like:?\\s*1\\."]},{"label":"Asks for sample sizes","patterns":["sample","\\bN\\b","participants","not stated"]},{"label":"Handles the correction","patterns":["correct","44"]},{"label":"Keeps findings to the abstract","patterns":["only.{0,30}abstract","(don't|do not) (overstate|add|claim)","only what"]},{"label":"Asks for plain text","patterns":["plain","no bold","no markdown","no formatting","no headings"]}],"hint":"An evidence table is only useful if every cell is accurate. Show the AI the line shape, tell it what to write when a detail is missing, and keep findings to what each abstract says.","rubricLabels":["Sample sizes are 120 for Reilly & Chen, 860 for Batista, 44 for Kowalski (the corrected figure, not 48), and 'N not stated' (or similar) for Mensah","Findings stay within each abstract: Batista is not described as showing music improves grades, and Mensah is not described as measuring grades or learning","Outputs only the 4 numbered lines, one study per line: no intro, no headings or table markup, no synthesis paragraph"]}