Skip to content
Published studies are shown for demonstration purposes, not because they are good or bad research. Demonstrator · items marked Example are invented · what exists today
Search

Templates

Empirical study

By e2er authors

Question and data in, empirical paper out. e2er's default.

In placeValidated template file, chosen per paperempiricaltheoretical
No evaluations yet
Adapt this templateRun it
Anyone can contribute. Improve this template Contribute a template
Input
A research question, your data and your literature
Output
A draft paper with a replication package and a dossier
At the end
When any run ends, e2er builds the PDF, writes the audit trail and the structured export, and pushes to GitHub if you set that up.

Steps

Greyed steps do not run in the selected mode.

  1. 1
    Design, data, estimation and draft
    Plans the paper and dispatches specialists for the literature, data, identification strategy, econometric specification, analysis and drafting.
    Research planLiterature reviewData planIdentification strategyEstimationData and descriptive analysisPaper draft
    specialists
  2. 2
    Improve until it stops getting better
    Further rounds of the strategist, revisiting design and analysis.
    specialists
  3. 3
    Estimation check
    Checks the estimation against the specification declared before it ran. Halts the run on failure.
    check
  4. 4
    Self-critique
    A specialist attacks the paper's own argument and evidence.
    Self-critique
    specialists
  5. 5
    Polish
    Five specialists polish formulas, numbers, institutional detail, equilibria and the bibliography.
    Polish of the formulasPolish of the numbersPolish of the institutional detailPolish of the equilibriaPolish of the bibliography
    specialists, parallel
  6. 6
    Review panel
    Numbers and citations are checked first. Six reviewers (mechanism, technical, literature, data, identification, writing) then score the draft.
    Review of the mechanismTechnical reviewReview of the literatureReview of the dataReview of the identificationReview of the writing
    reviewers, parallel
  7. 7
    Revision
    Revises the draft in response to the reviews, as a full revision and as targeted edits.
    RevisionTargeted corrections
    specialists
  8. 8
    Replication package
    Builds the replication package.
    Replication package
    specialists
Technical details

Template id empirical · file pipelines/empirical.toml, checked against pipeline.schema.json.

StepId in the template fileSpecialists
1. Design, data, estimation and draftinitialidea_developer, literature_scanner, data_architect, identification_strategist, econometrics_specialist, data_analyst, paper_drafter
2. Improve until it stops getting betteriterative
3. Estimation checkestimation_gate
4. Self-critiqueself_attackself_attacker
5. Polishpolishpolish_formula, polish_numerics, polish_institutions, polish_equilibria, polish_bibliography
6. Review panelreviewmechanism_reviewer, technical_reviewer, literature_reviewer, data_reviewer, identification_reviewer, writing_reviewer
7. Revisionrevisionrevisor, patch_revisor
8. Replication packagereplicationreplication_packager

At the end (finalize): compile, audit_export, github_push, structured_export. Modes: single_pass, iterative.

More

Pipeline at a glance

The figures below follow the empirical template from input to output. You can have the run stop for your review after any step.

Input
Research question
your datayour literature (PDFs or Zotero)a model subscription or API key
01 · Design
  1. Strategist plans the paper literature · data · identification · specification
writespaper_plan.mdliterature_review.mdidentification_strategy.mddata_dictionary.json
02 · Analysis
  1. Estimation and first draft Data and descriptive analysis · Estimation · Paper draft
  2. Further strategist rounds iterative mode only
  3. Estimation check halts the run if the estimation departs from the declared specification
writeseconometric_spec.mdestimation_results.jsonpaper_draft.tex
03 · Quality assurance
  1. Self-critique iterative mode only
  2. Polish five specialists in parallel · iterative mode only
  3. Checks, then six reviewers numbers and citations first · one combined score
writesnumber_verification.jsoncitation_integrity.jsonreview_aggregation.json
04 · Delivery
  1. Revision full revision and targeted edits
  2. Replication package Replication package
  3. At the end of every run PDF · audit trail · structured export · GitHub push, if set up
writespaper.pdfreplication/provenance.json
Output
Paper
replication packagestudy folder and dossier that e2er verify can check
Fig. 1. Phases of the empirical template. Steps as pipelines/empirical.toml declares them; green steps are checks.
Self-critique · a specialist attacks the paper's own argument and evidence iterative mode
Polish · formulas, numbers, institutions, equilibria, bibliography iterative mode
numbers and citations are checked before any reviewer reads the draft
MechanismTechnicalIdentificationLiteratureDataWriting
e2er's internal quality review: one score, the weighted average of the six (technical and identification 1.5, data 1.25, mechanism and literature 1, writing 0.75). It decides the revision, applied in order:
  1. Mechanism score below 5 → the analysis is redone and the draft scored again, once
  2. Any reviewer below 4 → no revision
  3. Combined score 6.5 or more → no revision; 5 to below 6.5 → one revision of the text; below 5 → no revision
Fig. 2. Quality-assurance stack. The score follows mechanically from the six scores. Whatever the score, a run that finishes its steps is completed, and the score is reported next to it.
Design
paper_plan.mdliterature_review.mdidentification_strategy.mddata_dictionary.json
Analysis
econometric_spec.mdestimation_results.jsonpaper_draft.tex
Quality assurance
number_verification.jsoncitation_integrity.jsonreview_aggregation.json
Delivery
paper.pdfreplication/provenance.json
Fig. 3. Files handed from one phase to the next. Every file ends up in the study folder and gets a fingerprint in its file list (provenance.json).

Description

Data model
Discipline
Economics
Method family
Empirical (quantitative)Theoretical
Design
not specified
Research stage
ReviewRevision and editingReplicationResearch questionLiterature synthesisData acquisitionResearch designData analysisDrafting
Authors
e2er authors (Software, Methodology)
Usage
1 published study · forked 1 time · Examples: 3 example studies, 3 example forks
Source
e2er repository · pipelines/empirical.toml · @d8fd8ab
Record
template:empirical · JSON

Solid tags are declared by the source or mapped from its terms; dashed tags are inferred by a published rule. Hover a tag for its provenance.

Versions and evaluations

One version, unreleased

One version so far: pipelines/empirical.toml in e2er 0.10.0. No evaluation records exist yet.

Evaluate this template Report a failure
Cite this template
Persistent identifiers planned 
@software{e2erauthors2026e2erempiricalstudytempla,
  title   = {e2er empirical study template},
  author  = {e2er authors},
  year    = {2026},
  note    = {e2er template. Persistent identifier planned},
  url     = {https://e2er.org/templates/empirical}
}

Connectors this template can use

What a run of this template can reach outside your machine, and what each sends out.

Anthropic APILeaves your machine: Prompts, including passages and data summaries OpenRouterLeaves your machine: Prompts, including passages and data summaries Claude CodeLeaves your machine: Prompts, including passages and data summaries CodexLeaves your machine: Prompts, including passages and data summaries GeminiLeaves your machine: Prompts, including passages and data summaries PDF folderLeaves your machine: Nothing leaves your machine Zotero library (local)Leaves your machine: Nothing leaves your machine Zotero Web APILeaves your machine: Queries only OpenAlexLeaves your machine: References or search terms CrossrefLeaves your machine: References or search terms Semantic ScholarLeaves your machine: References or search terms Your data folderLeaves your machine: Nothing leaves your machine FREDLeaves your machine: Queries only Yahoo Finance (yfinance)Leaves your machine: Queries only Global Macro Database (GMD)Leaves your machine: Queries only AlliumLeaves your machine: Queries only Zenodo dataset by DOIplannedLeaves your machine: Queries only Harvard Dataverse dataset by DOIplannedLeaves your machine: Queries only GitHubLeaves your machine: Files, to your own account USGS Earthquake CatalogLeaves your machine: Queries only NASA Exoplanet ArchiveLeaves your machine: Queries only ESA Gaia ArchiveLeaves your machine: Queries only NASA POWERLeaves your machine: Queries only NOAA Climate Data OnlineLeaves your machine: Queries only World Bank Open DataLeaves your machine: Queries only EurostatLeaves your machine: Queries only Our World in DataLeaves your machine: Queries only WHO Global Health ObservatoryLeaves your machine: Queries only Project GutenbergLeaves your machine: Queries only GitHub repository metadataLeaves your machine: Queries only Eurostat GISCO boundariesLeaves your machine: Queries only Natural EarthLeaves your machine: Queries only

Checks on this template

  • ✓Output contracts · Every step produced the artifact it declared, in the declared form
    Required of every template.
  • ✓Execution reliability · Analysis code ran and wrote a parseable, non-empty result
    Required of every template.
  • ○Numbers · Every number in tables and text matches the output of executed code
    Proposed. Proposed for the floor; runs log it but may not block on it.
  • ○Citations · Every reference resolves to an existing publication via OpenAlex, Semantic Scholar or Crossref
    Proposed. Proposed for the floor; runs log it but may not block on it.
  • ○Verbatim passages · Every claim about a source points to a passage found word for word in that source
    Proposed. Proposed for the floor; runs log it but may not block on it.

Runs of this template

No Cash Flows, New Owners: Spot Bitcoin ETFs and the Origins of Co-movementIn place

Use it

Install e2er as described on the Install page, then start a run:

e2er run "<your research question>"

The empirical template is the default. Other template files placed in ./pipelines or ~/.e2er/pipelines appear in the dashboard's new-paper form, from e2er 0.10.0. Get started goes from install to publish.

On e2er.org

Loading…

Report a failurePropose a new version

Discussion

Loading…