Research processes anyone can read, run and adapt
A template arranges steps into a complete research process. Each step names the specialists it runs and the checks it must pass. Researchers can use, adapt or ignore the templates that others publish, and the floor of checks stays attached whatever they change.
Empirical study
Question and data in, empirical paper out. e2er's default.
In A research question, your data and your literature. Out A draft paper with a replication package and a dossier.
1 published study · forked 1 time · Examples: 3 example studies, 3 example forks No evaluations yetEmpirical study, pre-registered
The empirical template with the researcher in it: a design review, a pre-registration frozen before any estimation, and a review of the draft.
In A research question, your data and your literature. Out A draft paper with a frozen pre-registration, a replication package and a dossier.
forked 1 time No evaluations yetEvent study in finance
A fork of the empirical template for abnormal-return event studies around announcements: it checks the estimation window and overlapping events before estimation.
In A research question, event dates, daily returns and your literature. Out A draft paper with cumulative abnormal returns, a frozen pre-registration, a replication package and a dossier.
not used in published research yet · Examples: 4 example studies No evaluations yetReplication of a published study
Computational reproduction of a published study from its Zenodo replication package: fetch and verify the package, plan, run it in a Docker sandbox, and compare every reported number with what the rerun produced.
In A Zenodo record (its DOI) and, if you have it, the published paper as PDF. Out A reproduction report and the dossier.
not used in published research yet No evaluations yetDescriptive data study
Question and data in, a checked description of the data out: the sample and its filters, summary statistics, distributions and associations, figures re-read from the data. A data check stops the run on missing units, duplicate rows, unexplained gaps or missing coverage before anything is computed.
In A research question and data. Out A checked description of the data (the sample, summary statistics, distributions, associations, figures re-read from the data) as a draft paper with a dossier.
not used in published research yet No evaluations yetMap a research field
Map a research field: retrieve its papers from OpenAlex, compute the main path of its citation network (SPC weights, key routes), test it on alternative boundaries, and draw the field by year in lanes named as questions, with a reading list, network exports and a short field review.
In A research field: its topic, and the journals it publishes in if you know them. Out A map of the field by year in lanes named as questions, a reading list, network exports and a short field review.
not used in published research yet No evaluations yetPolicy evaluation (difference-in-differences)
What a policy changed, by difference-in-differences: the design (treatment timing, comparison group, estimator) is checked against the data before estimation, and the event study, pre-trends test and placebo or sensitivity analysis after it.
In A question about what a policy changed, and a panel with the treatment timing. Out Difference-in-differences estimates with the event study, a pre-trends test and a placebo or sensitivity analysis, as a draft paper with a dossier.
not used in published research yet No evaluations yetSpatial analysis
How a variable varies across regions or places: maps from the data and recorded boundaries, Moran's I with permutation inference recomputed by e2er, optional local clusters (LISA), with the boundaries' source, CRS and weights checked before the analysis.
In A question about how a variable varies across places, data by region and their boundaries. Out Maps, Moran's I with permutation inference and optional local clusters, as a draft paper with a dossier.
not used in published research yet No evaluations yetSystematic review and meta-analysis
A systematic review with a random-effects meta-analysis, following PRISMA 2020: a protocol fixed before the search, a recorded OpenAlex search, screening with a reason for every exclusion, open-access full texts, extraction in which every number is traced to its page and quote, a meta-analysis by e2er's own code (tau^2, I^2, prediction interval, Egger's test, trim and fill, leave-one-out) or a plain narrative synthesis when too few studies can be pooled, and a PRISMA flow diagram.
In A review question. Out A systematic review following PRISMA 2020: protocol, recorded search, screening, extraction traced to quotes, a random-effects meta-analysis or a narrative synthesis, forest, funnel and flow diagrams.
not used in published research yet · Examples: 1 example study 1 evaluation 9 of 10 runs completed ExampleText analysis
A corpus in, counts and models of its language out: term frequencies, key terms (log-likelihood with the log ratio), collocations, dictionary and sentiment measures with a hand-checked sample, topic models with their stability across seeds, change over time. The corpus design and preprocessing are fixed before the corpus is built; e2er recounts every number from the corpus.
In A question about language and a corpus: books from Project Gutenberg or your own texts. Out Term frequencies, key terms, collocations, dictionary measures with a hand-checked sample and topic models, every number recounted from the corpus, as a draft paper with a dossier.
not used in published research yet No evaluations yetTime series and forecasting
A series in, its trend, seasonality, models and forecasts out. The forecast setup and its hold-out are frozen before any model is fitted; every model is judged on the hold-out against naive baselines, with errors recomputed by e2er and forecasts given with intervals. Optional pre-registration of the setup.
In A research question and a series. Out Its trend, seasonality, models and forecasts with intervals, every model judged on a hold-out frozen before fitting, as a draft paper with a dossier.
not used in published research yet No evaluations yetLiterature
Turns a folder of PDFs or a Zotero library into verified claims.
In A folder of local PDFs or a Zotero library. Out A searchable library of claims, each tied to a verbatim passage.
not used in published research yet No evaluations yetQualitative coding
Codes interview or document corpora with several specialists and reports agreement with human coders.
In A text corpus and a codebook. Out Coded corpus with agreement statistics.
not used in published research yet · Examples: 1 example study 2 evaluations 58 of 72 runs completed ExampleSurvey and experiment design
Designs surveys and experiments and pre-registers them before data collection.
In A research question and constraints. Out Instrument and pre-registration.
not used in published research yet · Examples: 1 example study No evaluations yetPaper review
Six reviewer specialists each score a paper from one angle, in parallel, after a number check and a citation check; their weighted average is the internal quality review score.
In A paper with the result files and bibliography it was written from. Out Six reviewer reports and one score of 0 to 10.
not used in published research yet No evaluations yetcoarse: AI referee report
An open-source multi-agent system that reviews an academic paper like a referee and writes a report with overall feedback and detailed comments that quote the paper.
In A paper as PDF, LaTeX, Markdown, DOCX, HTML or EPUB. Out paper_review.md: overall feedback (4 to 6 issues) and 20 or more detailed comments.
not used in published research yet No evaluations yetTheory construction (E2ET theory lab)
Cross-disciplinary IS theory generation via bisociation: 60 disciplinary personas across 8 tiers in an iterative loop that converges on propositions, constructs and a research agenda.
In A raw phenomenon seed. Out A theory brief: propositions, constructs, mechanisms, boundary conditions, theory type and a research agenda.
not used in published research yet · Examples: 3 example studies No evaluations yetStaggered difference-in-differences (economics)
A fork of the empirical template for policy evaluations with staggered adoption: it adds a pre-trend check and requires a heterogeneity-robust estimator when treatment timing varies.
In A research question, a unit-by-period panel with treatment dates, and your literature. Out A draft paper with event-study figures, a replication package and a dossier.
not used in published research yet · Examples: 6 example studies No evaluations yetRegression discontinuity for platform policies (information systems)
A fork of the empirical template for thresholds set by platforms, such as rating cut-offs or eligibility rules: it adds a manipulation test at the cut-off and a bandwidth sensitivity check.
In A research question, user- or item-level data with the running variable, and your literature. Out A draft paper with RD plots, a replication package and a dossier.
not used in published research yet · Examples: 5 example studies No evaluations yetShift-share instrumental variables (economics)
A fork of the empirical template for shift-share designs: it adds first-stage strength diagnostics and a balance check on exposure shares.
In A research question, regional or industry panel data with exposure shares, and your literature. Out A draft paper with first-stage tables, a replication package and a dossier.
not used in published research yet No evaluations yetGrounded theory with the Gioia method
Builds a grounded model from interviews by moving from informant-centric concepts to researcher-centric themes and aggregate dimensions, following Gioia, Corley and Hamilton (2013).
In Interview transcripts or field notes, and your literature. Out A data structure figure, a grounded model and the coded corpus.
not used in published research yet · Examples: 4 example studies No evaluations yetTheory construction as disciplined imagination
Generates many heterogeneous conjectures about a problem and selects among them with criteria declared in advance, following Weick (1989).
In A problem statement and your literature. Out A selected set of conjectures with the reasons for their selection, and boundary conditions.
not used in published research yet · Examples: 3 example studies No evaluations yetCompose a template
Choose optional steps and see how the floor checks stay attached.
The floor every template inherits
A template may add checks and enforce them more strictly. It may not remove the floor.
| Check | What it establishes | Floor |
|---|---|---|
| Output contracts | Every step produced the artifact it declared, in the declared form | Fixed |
| Execution reliability | Analysis code ran and wrote a parseable, non-empty result | Fixed |
| Numbers | Every number in tables and text matches the output of executed code | Proposed |
| Citations | Every reference resolves to an existing publication via OpenAlex, Semantic Scholar or Crossref | Proposed |
| Verbatim passages | Every claim about a source points to a passage found word for word in that source | Proposed |
In the current implementation the fixed floor is output contracts and execution reliability. Draft 0.1 proposes adding numbers, citations and verbatim passages. The standard, draft 0.1.