E2ER Standard Explorer
← E2ER · Data model§1 · VISION
The conventions that make research trustworthy were built for work done by people. With AI, a manuscript takes minutes to generate, while checking whether it holds up still depends on an expert reading it closely. E2ER is an open standard that settles the conventions of AI-assisted research in the open.
Every number, citation and statement about prior work in an E2ER run carries a trace to its source. Select an underlined element in the excerpts below, taken unedited from a real run in the repository.
A discipline's methods become skills that any AI system can use. An epidemiologist who knows how confounding hides in registry data writes it down once, and economists and sociologists working with such data gain from it.
A research process is a template of steps that anyone can read, run, adapt or ignore. Judgement written into one template can accumulate across fields.
When two fields approach the same question differently, both templates can run on it and their results can be compared, including where each one breaks.
E2ER is the first implementation of the standard. It ships one complete template, from a research question and data to a paper with a replication package, and draws on a public catalogue of skills published by other research projects. Everything beyond that is open to contribution. See what exists today.
§2 · BUILDING BLOCKS
The standard uses a small, fixed vocabulary. Select a term to see its definition, an example from the current implementation, and its status.
A specialist applies skills in a step; steps arranged in order form a template; a template executed on a researcher's own data and literature is a run; every run ends in an evidence package that anyone can verify.
§3 · THE STANDARD, DRAFT 0.1
The standard specifies how building blocks are described, how their output is checked on every run, how they are tested before others rely on them, and how the community decides what enters and who is credited. It describes building blocks independently of any software, so blocks built with other systems can meet it too.
Every building block states the same fields, so a researcher can judge whether it fits before running it. Skills follow the open Agent Skills format (Anthropic, 2025) and add the research fields below; evidence packages follow established formats for packaging research outputs (Soiland-Reyes et al., 2022).
# Example: description of a skill, draft format 0.1 name: difference-in-differences kind: skill version: 1.2.0 purpose: Specify, estimate and diagnose DiD designs, incl. staggered adoption inputs: panel data description; treatment timing; identification spec outputs: econometric specification; estimation-results record implements: methodological literature the guide follows (DOIs) authors: names, ORCID, contributor roles license: MIT tested_on: evaluation records, each naming data, model and version checks: floor + estimation # checks this block adds to the floor
Verification consists of checks that run automatically on every run. A template may add checks and enforce them more strictly. It may not remove the floor.
| Check | What it establishes | Floor | Status today |
|---|---|---|---|
| Output contracts | Every step produced the artifact it declared, in the declared form | Fixed | In place |
| Execution reliability | Analysis code ran and wrote a parseable, non-empty result | Fixed | In place |
| Numbers | Every number in tables and text matches the output of executed code | Proposed | In place can currently be set to log-only |
| Citations | Every reference resolves to an existing publication via OpenAlex, Semantic Scholar or Crossref | Proposed | In place can currently be set to log-only |
| Verbatim passages | Every claim about a source points to a passage found word for word in that source | Proposed | In place in the literature template |
| Estimation contract | The estimation matches the specification declared before it ran | Template-specific | In place |
In the current implementation the fixed floor is output contracts and execution reliability. Draft 0.1 proposes adding numbers, citations and verbatim passages to the floor, so that no template can publish a result without them.
Evaluation defines how building blocks are tested before others rely on them. Its purpose is to find where a block breaks. It is the centrepiece of the development stage. Open the evaluation protocol.
Governance regulates how building blocks are proposed, reviewed, versioned and credited, and how the standard itself changes. Open the governance process and how contributors are credited.
§4 · TEMPLATES IN PLACE
The empirical template turns a research question and data into a draft paper with a replication package. The literature template turns a folder of PDFs or a Zotero library into verified claims. Other researchers may build better versions of either, and the standard lets the versions be compared on their evaluations.
Steps as declared in pipelines/empirical.toml. Greyed steps do not run in the selected mode.
Every run ends with a compiled paper, an audit export and a structured evidence package (paper, code, data, results, design, reviews) that e2er verify checks offline and without an API key.
Reads a folder of local PDFs or a Zotero library.
A sketch of how composition interacts with the floor. Choose optional steps; the floor checks stay attached whatever you choose.
Illustration of the standard§5 · EVALUATION PROTOCOL
A check tells whether one run was faithful to its inputs. An evaluation tells whether a building block can be trusted, under which conditions, and at which point it fails. Developing and proposing this protocol is the centrepiece of the development stage.
Compare a step or template with known answers, for instance an interview corpus that human coders have already coded.
Run a template on a published study and compare its results with the original (Brodeur et al., 2025; Kohler et al., 2026).
Vary document length, corpus, data quality or model to locate the point at which output degrades (Laban et al., 2026; Pangakis & Wolken, 2025).
Researchers rate a building block against a shared rubric and report failures. RISE already scores research systems against a published rubric.
A hypothetical coding template, evaluated on transcripts of increasing length. The evaluation record states the length at which agreement with human coders falls below the threshold the template declares.
block: qualitative-coding@0.3.1 test: stress / document length material: interview corpus, 240 transcripts, coded by two humans model: named model and version runs: all runs, incl. failed and aborted ones result: agreement by length band; breaking point where it falls below threshold evaluator: name, ORCID, contributor role "validation" scope: valid for this material; other corpora need their own record
Records include failed and aborted runs, because reporting only successful runs overstates performance (Masters et al., 2026). They are stored in a common format for evaluation results (Batzner et al., 2026).
§6 · GOVERNANCE
Governance decides what others can rely on. The process below is a proposal. Its rules will be settled with the researchers who contribute, starting at the special-issue workshop, following community models such as nf-core (Ewels et al., 2020) and mathlib (The mathlib Community, 2020).
Writes a skill, specialist or template and its description, and keeps it working.
Runs benchmark, reproduction or stress tests and authors the evaluation record.
Reads a submission as a method expert and decides with a maintainer whether it is listed.
Keeps a group of building blocks consistent with the standard and handles new versions.
Decides changes to the standard itself and settles disputes, in public and with written reasons.
Runs templates, reports failures, and may become an evaluator by doing so systematically.
Anyone can propose a change to the standard in a public proposal document, which states the problem, the change and its consequences for existing building blocks. Proposals are discussed openly and decided by the steering group, which publishes the decision and its reasons. Accepted changes receive a version number, and building blocks declare which version they meet.
§7 · ATTRIBUTION AND CREDIT
A standard grows only if contributing pays off for the people who contribute. Scholarly incentives currently reward novel findings and undervalue reproductions, verification and reusable infrastructure (Hanneke et al., 2026). E2ER turns each kind of contribution into something a researcher can list and others can cite.
| Contribution | What the contributor receives | Status |
|---|---|---|
| Write a skill, specialist or template | A persistent identifier and citation for each version; authorship with contributor roles (Brand et al., 2015) | Planned |
| Have a building block used | An automatic citation in every run that uses it, in the paper's references and its replication package (Smith et al., 2016) | Planned |
| Evaluate a building block | Authorship of a citable evaluation record, with the contributor role "validation" | Planned |
| Report a failure | Credit in the building block's change history and in the evaluation it triggers | Planned |
| Review or maintain | Named review and maintenance roles on the building block's record | Planned |
| Publish skills elsewhere | Source, license and maintainers travel with every installed skill | In place |
Select a building block used by a run to see how its authors are credited.
§8 · WHAT EXISTS TODAY
E2ER is open-source software under the MIT license (Hanneke, 2026a). It installs like any other software package and runs on consumer subscriptions to Claude, ChatGPT or Gemini, which lowers the barrier for researchers without research budgets.
| Element | Status | Note |
|---|---|---|
| Empirical and literature templates | In place | First versions, open to better ones |
| Templates as validated files, chosen per paper | In place | A run resumes under the template it started with |
| Checks on every run, with logged verdicts | In place | Fixed floor today: output contracts and execution reliability |
| Evidence package and offline verifier | In place | e2er export, e2er verify |
| Skill catalogue with provenance (RISE) | In place | 168 of 358 skills cannot be redistributed, so E2ER installs from source |
| Browser dashboard: library, skills, template choice | Prototype | On the development branch, not yet released |
| Description format, draft 0.1 | Prototype | Templates follow it; skills and specialists to follow |
| Specialists as files | Planned | Today separate modules with declared inputs and outputs |
| Dossier and author line on every paper | Prototype | e2er publish writes the dossier and adds “with E2ER” and a dossier footnote to the paper; development branch (§9) |
| e2er.org: accounts, publishing, reviewer access | Planned | Database and staging environment built; accounts and publishing follow in October (§9) |
| Evaluation protocol and records | Planned | Stage 2 centrepiece |
| Governance and credit | Planned | To be settled with contributors |
| Templates for qualitative, experimental and theoretical research | Planned | Coding, systematic reviews, survey and experiment design, theory building |
§9 · THE PLATFORM
Researchers run E2ER on their own computers, with their own accounts at the AI providers. When they publish a study, e2er.org receives its description, its dossier and the fingerprints of its files; the files themselves stay on the researcher's computer or in their repository. The platform keeps a public list of studies and building blocks, gives contributors and reviewers their accounts, and credits the authors of a building block each time a study uses it.
Every paper produced with E2ER names E2ER once, next to its authors, and a footnote on its first page links to the study's dossier. The dossier lists each step of the run in order, the specialist and model that carried it out, the file it produced and the checks it passed or failed, together with the exact version of every template, specialist and skill involved. Its address is the SHA-256 hash of its content, so any later change to the record would change the address. In the showcase run the dossier lists 20 steps, including the check that rejected the first draft because it contained two tables typed into the text.
% paper.tex of the showcase run, as written by e2er publish \author{Björn Hanneke with E2ER\thanks{This paper was produced with E2ER. Its dossier lists every step of the run, the files each step produced, and the template, specialists, skills, connectors and AI models used, pinned to their exact versions: \url{https://e2er.org/d/c46711b0dc073e96}.}}
The dossier leaves the paper itself out, because the paper carries the dossier's address. Anyone can recompute the address from the published document; the page for each dossier does so in the browser. Preview: the showcase dossier.
E2ER is local software that researchers use with their own AI accounts. The platform has no field that accepts an AI key, and publishing sends only the description of a study.
| Stays on the researcher's machine | Goes to the AI provider the researcher chose | Goes to e2er.org on publishing |
|---|---|---|
| Data files, the literature library and its PDFs, the run database, AI keys and subscriptions | Prompts, including data summaries and the passages a specialist reads | The study's description, its dossier, the SHA-256 fingerprint of each file, contributors and their roles |
Before sending, the command line removes local paths and refuses to publish if any text resembles a key; a dry run prints the exact request and changes nothing.
Researchers sign in with ORCID or GitHub, or with an email address and password. Password recovery uses single-use links that expire after 30 minutes and sign out every session. The command line signs in by showing a code that the researcher approves in the browser.
Editors receive one access code per manuscript. The code opens a workspace without a name or email address, in which reviewers can try publishing and contributing on sample records that are deleted when the code expires.
Every study, building block, contribution, check and dossier is a row in one SQLite database, held in the European Union. The analytics form a star schema of views over these tables, and every figure on the platform is the result of a named query that is published with its SQL, so anyone can rerun it on the exported database. Dossiers, study versions and building-block versions cannot be changed once written; a withdrawn study keeps its versions citable.
The full data model, with every table and the analytics.
| Phase | Scope | Status |
|---|---|---|
| 0 Foundations | Domain, database in the EU, schema, import of the current registry, staging environment | In progress |
| 1 Figures from queries | Every figure computed by a published query; database available for download | October 2026 |
| 2 Accounts | Sign-in with ORCID, GitHub or email, password recovery, roles, reviewer access codes | October 2026 |
| 3 Command line | Sign-in from the command line, publishing, study status, dossiers for private studies | October 2026 |
| 4 Checks at the source | Checks run at the pinned commit of a study's repository and in GitHub Actions; publishing from a local folder in the browser | Early 2027 |
| 5 Contributions | Submissions and the review queue of §6, comments and failure reports, data export and account deletion | Early 2027 |
§10 · RELATED WORK AND EXISTING PROJECTS
Filter by what a project provides. Marks are our reading of each project's own description.
| Project | Describes blocks | Checks content | Evaluates blocks | Shared governance | For AI agents | Social science |
|---|
● provides ◐ partly ○ does not ◌ planned
§11 · REVIEW CRITERIA
§12 · TRY IT
Repository: github.com/bhanneke/E2ER-project (MIT). Skill catalogue: github.com/bhanneke/RISE.
The dashboard pages for the library and skills and the renamed commands are on the development branch and ship with the next release.
§13 · ROADMAP
REFERENCES
Anthropic. (2025). Agent Skills [Open specification]. https://agentskills.io
Batzner, J., Nelaturu, S. H., Stachura, D., Kornilova, A., Crall, J., et al. (2026). Every Eval Ever: A unifying schema and community repository for AI evaluation results (arXiv:2606.14516). https://doi.org/10.48550/arXiv.2606.14516
Binkyte, R., et al. (2026). Inspectable AI for science: A research object approach to generative AI governance (arXiv:2604.11261). https://doi.org/10.48550/arXiv.2604.11261
Brand, A., Allen, L., Altman, M., Hlava, M., & Scott, J. (2015). Beyond authorship: Attribution, contribution, collaboration, and credit. Learned Publishing, 28(2), 151–155. https://doi.org/10.1087/20150211
Brodeur, A., Sung, S. Y., Miguel, E., Vilhuber, L., & Hoces de la Guardia, F. (2025). Assessing reproducibility in economics using standardized crowd-sourced analysis (NBER Working Paper No. 33753). https://doi.org/10.3386/w33753
Crusoe, M. R., Abeln, S., Iosup, A., Amstutz, P., Chilton, J., Tijanić, N., Ménager, H., Soiland-Reyes, S., et al. (2022). Methods included: Standardizing computational reuse and portability with the Common Workflow Language. Communications of the ACM, 65(6), 54–63. https://doi.org/10.1145/3486897
Ewels, P. A., Peltzer, A., Fillinger, S., Patel, H., Alneberg, J., Wilm, A., Garcia, M. U., Di Tommaso, P., et al. (2020). The nf-core framework for community-curated bioinformatics pipelines. Nature Biotechnology, 38(3), 276–278. https://doi.org/10.1038/s41587-020-0439-x
Hanneke, B. (2026a). E2ER: End-to-end researcher (Version 0.8.1) [Computer software]. Zenodo. https://doi.org/10.5281/zenodo.20452754
Hanneke, B. (2026b). RISE: Research information systems engineering [Software repository]. https://github.com/bhanneke/RISE
Hanneke, B., Hering, F., Pfeiffer, J., Reijers, H., & Hinz, O. (2026). Academic publishing in the age of generative AI. Business & Information Systems Engineering, 68(4), 729–737. https://doi.org/10.1007/s12599-026-01013-0
Kassis, T., Agarwal, V., He, Y., Patel, D., Brueckner, A. M., et al. (2026). Scientific Agent Skills: A library of procedural knowledge for research agents (arXiv:2609.00065). https://doi.org/10.48550/arXiv.2609.00065
Kohler, B., Zollikofer, D., Einsiedler, J., Hoyle, A., & Ash, E. (2026). Read the paper, write the code: Agentic reproduction of social-science results (arXiv:2604.21965). https://doi.org/10.48550/arXiv.2604.21965
Laban, P., Schnabel, T., & Neville, J. (2026). LLMs corrupt your documents when you delegate (arXiv:2604.15597). https://doi.org/10.48550/arXiv.2604.15597
Lu, C., Lu, C., Lange, R. T., Yamada, Y., Hu, S., Foerster, J., Ha, D., & Clune, J. (2026). Towards end-to-end automation of AI research. Nature, 651(8107), 914–919. https://doi.org/10.1038/s41586-026-10265-5
Masters, C., Liu, Z., & Albrecht, S. V. (2026). Rollout cards: A reproducibility standard for agent research (arXiv:2605.12131). https://doi.org/10.48550/arXiv.2605.12131
The mathlib Community. (2020). The Lean mathematical library. In Proceedings of the 9th ACM SIGPLAN International Conference on Certified Programs and Proofs (pp. 367–381). https://doi.org/10.1145/3372885.3373824
Pangakis, N., & Wolken, S. (2025). Keeping humans in the loop: Human-centered automated annotation with generative AI. Proceedings of the International AAAI Conference on Web and Social Media, 19, 1471–1492. https://doi.org/10.1609/icwsm.v19i1.35883
Smith, A. M., Katz, D. S., Niemeyer, K. E., & FORCE11 Software Citation Working Group. (2016). Software citation principles. PeerJ Computer Science, 2, e86. https://doi.org/10.7717/peerj-cs.86
Soiland-Reyes, S., Sefton, P., Crosas, M., Castro, L. J., Coppens, F., Fernández, J. M., Garijo, D., Grüning, B., et al. (2022). Packaging research artefacts with RO-Crate. Data Science, 5(2), 97–138. https://doi.org/10.3233/DS-210053
Souza, R., Gueroudji, A., DeWitt, S., Rosendo, D., Ghosal, T., et al. (2025). PROV-AGENT: Unified provenance for tracking AI agent interactions in agentic workflows (arXiv:2508.02866). https://doi.org/10.48550/arXiv.2508.02866
Yamada, Y., Lange, R. T., Lu, C., Hu, S., Lu, C., Foerster, J., Clune, J., & Ha, D. (2025). The AI Scientist-v2: Workshop-level automated scientific discovery via agentic tree search (arXiv:2504.08066). https://doi.org/10.48550/arXiv.2504.08066
Zhang, Y. (2026). Vibe researching as wolf coming: Can AI agents with skills replace or augment social scientists? (arXiv:2602.22401). https://doi.org/10.48550/arXiv.2602.22401