spb/autoscholar

1---23mode: empirical4discipline: economics5title: "<Working title: an empirical study>"6---78# Research brief — <working title> (empirical)910## 1. Research objective and scope1112- **Question.** <e.g., Does X affect Y in population P over period T?>13- **Hypotheses.** H1: <…>. H0 is a real possibility: a well-identified null result is a valid outcome.14- **Scope and unit of analysis.** <firms/countries/households…; frequency; sample window>.1516## 2. Domain, mode and methodology1718- Discipline: <economics/finance/statistics/…>. Primary mode: empirical.19- Methodology: <OLS/panel FE/DiD/IV/event study/GARCH/ML forecasting…>, chosen because <identification argument>.20- Inference: <clustered/robust SE, bootstrap, multiple-testing policy>.2122## 3. Contribution and novelty2324- <Expected contribution; the 3–5 closest papers to position against.>2526## 4. Literature and source rules2728- Indexes: OpenAlex + Crossref (+ Semantic Scholar). Target ≥ 15 verified sources; must-read: <DOIs>.29- Map every background claim to a verified key.3031## 5. Data3233- **Sources:** <exact dataset/API/series ids, e.g., FRED series XYZ; World Bank indicator ABC; SEC EDGAR filings; public Kaggle/Zenodo DOI>. Only legally usable, documented data; record license and access date.34- **Construction:** <variable definitions, cleaning rules, sample selection, treatment of missing values and outliers>.35- **Size limits:** keep raw + derived data under 200 MB in the workspace (subsample and document if larger).36- No synthetic data unless explicitly allowed here: <allowed/not allowed>.3738## 6. Procedure (pre-registered)39401. Data acquisition and manifest (`data/manifest.json`, SHA-256, license).412. Descriptive statistics table and at least one figure of the raw series/distribution.423. Main specification(s): <exact equations/models, controls, fixed effects, sample>.434. Secondary/exploratory analyses: <…> (label as exploratory).445. Write `code/reproduce.sh` regenerating all tables/figures/metrics from raw inputs; log every run.4546## 7. Baselines, robustness and falsification4748- Robustness: <alternative controls, windows, estimators, placebo/pre-trend tests, leave-one-out, winsorization>.49- Report robustness results that weaken the finding. State what would falsify H1.5051## 8. Reproducibility and artifacts5253- Pinned environment (uv), seeds, `results/experiment-log.jsonl`, `results/metrics.json` with every reported value registered.5455## 9. Manuscript5657- AutoScholar class; tables with units/notes/standard errors; figures with legible axes; 10–20 pages.5859## 10. Review and revision6061- Reviewer focus: identification threats, standard-error validity, data leakage, p-hacking signals, claim-to-evidence gaps.6263## 11. Limitations, ethics, legal6465- <Measurement error, external validity, data license constraints; no personal data.>6667## 12. Acceptance criteria6869- Main specification estimated on the full sample with CIs; ≥ 3 robustness checks; reproduction script regenerates `metrics.json`; ≥ 15 verified citations; limitations stated.70