EU ETS installation net-short
Retrospective research on whether an EU ETS installation's annual verified emissions exceed its free allocation. The intended prediction cutoff and historical registry availability remain assumptions in this current-snapshot panel.
Versioned research data. Read the suitability requirements before interpreting scores.
Suitability and evaluation
Retained for retrospective model-development research with documented timing limitations. Later evaluation rows expose earlier outcomes; predictions require restricted access.
Supported uses: Retrospective train/validation model-development experiments under the documented timing and selection limitations; Final evaluation only under a protocol that isolates holdout data from development and prevents later rows influencing earlier predictions
Not supported: Claims of verified real-time or operational forecasting validity; Treating development/validation scores as untouched final-test results; Forecasting scores from unrestricted cross-row access to this artifact
- Historical feature availability
- assumed
- Training-label timing
- unverified
- Data vintage
- current snapshot
- Row selection
- unverified
- Required evaluation access
- chronological
Cross-row audit: recovery demonstrated. Independent operator-commissioned audit; predictions frozen before labels were opened; holdouts sealed; two AUC implementations in exact agreement
The labeled eval split is development/validation data. Isolate final holdout data from development and prevent later rows influencing earlier predictions. Published data is not a secure hidden test service.
- join (installation, t) -> (installation, t+1): the next row's net_short_l1 is T's label
- The labelled holdout is presumed to carry the same self-answering structure by construction; it was never opened by the audit and must be treated as compromisable by the same join class.
- Historical feature/label availability at the declared instant is assumed from current snapshots, not verified against release vintages.
- The current scorer passes the complete feature frame to predict_proba; prediction-time isolation is instructed but not mechanically enforced, so any framework score on these files is gameable.
Corrections to historical documentation
- Public site page, Hub card and repository README must state the restricted suitability once rendered; no frozen package bytes change.
Reviewed 2026-10-24. Applies to this artifact; original data and tags are preserved.
At a glance
| Question | Retrospective research on whether an EU ETS installation's annual verified emissions exceed its free allocation. The intended prediction cutoff and historical registry availability remain assumptions in this current-snapshot panel. |
|---|---|
| Field | Environment and climate policy / binary-classification |
| Rows | 188,205 |
| Documented splits | 3 |
| This version | v2026.10 |
| Released | 2026-10-22 |
| Evaluation ROC AUC | 0.9199 |
| Artifact | 3540ad2180d8df8a9ff39f5f6c1326c5e487ed20e28f189b9528eeb71f799f66 |
Get this dataset
How to load it
from datasets import load_dataset
ds = load_dataset('earino/eutl-installation-net-short', revision='v2026.10')
The version links and checksums identify this artifact. Exclude the labelled holdout from the agent's workspace when running an evaluation.
What is inside 
| Split | Rows | Positive labels |
|---|---|---|
| eval | 24,322 | 18,002 (74.02%) |
| holdout | 22,151 | 15,993 (72.20%) |
| train | 141,732 | 64,528 (45.53%) |
Files and checksums
| Download | Bytes | SHA-256 |
|---|---|---|
| meta.json | 2,810 | b0e54387f5a5348dc381989a61f017248412c2c5f8220ad9f8a8f032735aa152 |
| private-holdout.csv | 1,507,248 | 1c694e5e6b0bc0b329c5934e24037fb7229326ffac1806db6e0655fe0439de9b |
| public-eval.csv | 1,660,374 | 0d9f35d5393734a9a63457890a9c4177418199b2cae458b36a8687fdbd4253ab |
| public-train.csv | 9,421,952 | c7f23c557d9605c92ba787d199922a1978f712f9b1069926ac5d63236331e903 |
| quality.json | 10,270 | 88222d66bfd02aa5f768791e5d8d8803822b3b63f21d4d2e6397c9b638bef87b |
Release notes · 2026-10-22
This release ships 188,205 installation-years from the EU emissions trading system, covering compliance years 2006 through 2025. The panel is built from the European Commission's Union Registry public extracts: 617,448 rows over 23,748 installations across 32 registries, restricted to the years where both the year's allocation and the previous year's emissions are known.
The intended decision point is 30 April of compliance year t, using prior-year emissions and year-t allocation. Those values come from current registry extracts; this release does not verify their original publication dates, revision histories, or availability at every historical cutoff. The outcome is year-t verified emissions exceeding year-t free allocation.
The recorded baseline achieved 0.9199 validation ROC AUC under the original runner protocol, compared with a tested calendar-only rule at 0.527 and a prior-year net-position rule at 0.8671. These are comparisons with those references, not evidence that later-row access is safe or that historical availability has been verified.
The splits are temporal: train years 2006 through 2019, evaluation 2020 through 2022, holdout 2023 through 2025. The labelled holdout ships with the release and stays outside any evaluated agent's workspace.
Recorded structural checks and baselines
PASSED Gate 1.4.0.
baseline only, through the runner's own contract. No agent or harness comparison was run, and none is implied.
These historical checks do not establish availability at each prediction time or protection against every shortcut. Scores below describe the recorded protocol.
Limits
The positive base rate rises over time - 45.5 percent in train, 74.0 in evaluation, 72.2 in holdout - because the free-allocation share fell while the cap declined. Read every score against the documented per-year prevalence.
The single column margin_t alone reaches an AUC near 0.90 under the gate's one-column sweep: the intended one-line rule nearly solves the task, so a model must beat it honestly rather than rediscover it.
Exact emission-allocation ties are labelled 0 and counted (4,224 rows); the label source values are excluded from every shipped file.
The panel ends at 2025 because the extract carries no numeric verified emissions for later years at the snapshot date.
No claim of real-time or operational forecasting validity: historical feature and label availability at the prediction instant is assumed from a current source snapshot, not verified against release vintages.
The labeled eval split is development/validation. Final holdout scoring requires prediction-time access restrictions; the original scorer provided the complete feature frame. Downloadable holdout labels must stay outside model development.
Source, licences, and citation
European Commission, Directorate-General for Climate Action - Union Registry public extracts (EUTL), operators_yearly_activity daily extract, https://union-registry-data.ec.europa.eu/report/eu-registry-data-download, vintage of 2026-10-22. Contains Commission-owned content licensed under CC BY 4.0.
Source: CC-BY-4.0. Compilation: CC0-1.0. Code and documentation: MIT.
Our contribution - the installation-year row selection and eligibility frame, the derived net-short label, the settlement-lagged feature derivations, the temporal partition, and the packaging - is dedicated to the public domain under CC0-1.0. The dedication covers only our contribution: the underlying Union Registry public extracts keep their own designation and remain subject to the Commission's CC BY 4.0 reuse terms, whose attribution condition carries through to every copy of the derived data. Nothing here relicenses the source or presents CC0 as the source's terms.
Suggested citation
European Commission, Directorate-General for Climate Action. Union Registry Public Website, EUTL public extracts: operators' yearly activity data (daily extract). https://union-registry-data.ec.europa.eu/report/eu-registry-data-download. Licensed under CC BY 4.0 (Commission reuse policy). Derived dataset: EU ETS installation net-short prediction task (not a Commission official product).