ecoCompute Science 2027 invites submissions on resource-aware and resource-reducing computing. The event is held online in the European time zone in summer 2027.
A submission consists of two pages and a runnable artifact. The reviewers execute the artifact.
Submission requirements
The two-page write-up
At most two pages, under five headings, in the following order:
| Section | Content |
|---|---|
| The claim | What the work sets out to show. One or two sentences are sufficient. |
| The method | The setup, the measurement method, the hardware, and the number of runs. |
| The results | The measured values, with variance. State which property is expected to be stable and within what tolerance. |
| Prior work | What exists already, and what this work adds to it or contradicts. |
| Questions for discussion | The questions the authors wish to put to three discussion groups. |
Bullet points are acceptable throughout. Presentational quality is not a criterion for acceptance. The write-up is a guide to the artifact, not the evidence itself.
The artifact
A complete, runnable artifact that enables a reviewer to regenerate the reported results, or otherwise verify the claims, without contacting the authors. An archive file or a container image is sufficient. No hosting platform is required.
The Artifacts page sets out in detail what counts as an artifact, what the step-by-step guide must contain, and how specialised hardware and measurement variance are handled. Authors are asked to read it before submitting.
Tracks
Track 1: Artifact track
The main track, which requires full reproducibility: a reviewer is able to regenerate the reported results from the artifact. Unless stated otherwise, the material on this site describes this track.
Track 2: Industry and impact track
Under development. Details will follow on this page.
Industry work frequently rests on data that cannot leave the organisation, and constructing representative sample data is often not feasible either. The organisers do not wish to exclude such work, nor to present it as reproduced when it has not been.
The intended form is a lower requirement for reproducibility, a higher requirement for applicability, and a mandatory impact artifact. The impact artifact is whatever renders the claimed effect verifiable in principle: the calculation sheet, the measured savings, or the methodology applied to a public configuration. Papers in this track are labelled as such, and their artifact status is published alongside them so that the two tracks are not conflated.
Authors with industry work to submit are invited to contact the organisers. Concrete cases will shape this track more effectively than speculation.
Submissions we particularly encourage
- Negative results. An optimisation that did not yield a benefit, an effect that disappeared once noise was controlled for, or a tool that did not measure what it claimed to measure.
- Replication studies. An unsuccessful attempt to reproduce a published result is a full submission here.
- Methodology and accounting work. Proposals for accounting for oversubscription or effective utilisation are in scope. The artifact is then the method applied to sample configurations, which a reviewer can re-execute and verify.
- Tools and measurement stacks, together with evidence that they perform as described.
Review
A dedicated artifact evaluation committee executes the submissions. The opening days of the review period constitute a kick-the-tires phase: reviewers report any issue that prevents them from starting, and authors are given a short window in which to correct it. Artifacts should not fail on setup problems.
The review outcome and the artifact status are published together with the paper.
The process is set out in full on the Review and Publication page.
Publication
Publication proceeds in two stages:
- Stage one is the two-page write-up together with the artifact. It is reviewed, accepted and presented at the event.
- Stage two is a full paper, written after the event and shepherded by a committee member, who confirms that the claims do not exceed the evidence that was reviewed. The full paper receives a DOI.
Stage two is published in ECEASST, the Electronic Communications of the EASST. It is a diamond open access journal hosted by Berlin Universities Publishing, properly indexed, with no fee for authors or readers. ECEASST provides the submission and reviewing platform for the full papers through to publication. Anna-Lena Lamprecht is responsible for the publication track.
Important dates
| Submission opens | To be announced |
| Submission deadline | To be announced |
| Kick-the-tires window | To be announced |
| Notification | To be announced |
| Event | Summer 2027, online |
| Stage two full paper | After the event, shepherded |
Dates will be published on this page and announced on LinkedIn.
How to submit
The submission system is being set up. Until it is available, enquiries about a prospective submission, or requests to be notified when the system opens, may be sent to science@eco-compute.io.
Questions still under discussion
These questions are genuinely open and are stated here rather than presented as settled. Comments are welcome; please contact the organisers.
- How can artifact review be kept affordable? A cap on the number of submissions, rolling review, an arrangement in which one reviewer produces a working recipe that the others then follow, or AI assistance for the first reproduction pass. Most likely some combination of these.
- Single-blind or fully open review? Artifacts are difficult to anonymise reliably.
- How can non-attendance in capped discussion groups be avoided? Registration free of charge produces high rates of non-attendance. A nominal fee, a short written application, and an invitation model following the example of Dagstuhl are all under consideration.
- Who will serve on the programme and artifact committees? Expressions of interest in reviewing are welcome.