GCRI · Labs
زیرەکی دەستکرد لە کارەکانی زانستیدا
Machine learning now enters science at every step: screening literature, designing experiments, analysing images and sequences, emulating simulations and drafting text. Each use can speed discovery and each can introduce errors that look like findings. This page sets out how models are evaluated for scientific use, where leakage, benchmark overfitting and silent drift arise, and what evidence editors, funders and regulators need before they rely on a model-assisted result.
چۆن کارەکە بەڕێوە دەچێت.
Testbed operations
AI in scientific workflows · Field lab coast · Campaign 5
Sensor deployment
هێڵی کەنارەی نموونەیی
Sensors
| S-01 tide | 94 | 0.0 | Nominal |
| S-04 salinity | 76 | 0.4 | Recalibrate |
| S-07 wave | 95 | 0.1 | Nominal |
Sensor vs reference
وێنەTestbed operations: example names and illustrative values, not a record or a live system.
AI in scientific workflows: how the risk develops.
Model evaluation and scientific assistance. The dossier below sets out how the risk develops, what is measured, where the data come from, how it is modelled and who decides.
Leakage inflates performance
When information from the test set reaches training, through duplicates, shared patients, neighbouring sites or preprocessing fitted on all the data, a model appears more accurate than it is. Leakage has been documented in many fields that adopted machine learning.
Benchmarks get overfitted
Repeated tuning against the same public benchmark selects models that fit its quirks. Gains on a leaderboard can vanish on new data, and contamination of training corpora with benchmark items makes scores hard to interpret.
Drift and distribution shift
Instruments, protocols, populations and software change. A model validated on last year’s data or another lab’s scanner can degrade without any visible error. Monitoring after deployment is part of the evaluation, not an extra.
Generated text and fabricated sources
Language models can produce fluent text, citations and code that are wrong. Unchecked, these errors enter manuscripts, peer reviews and proposals, and spread through citation. Disclosure and verification policies exist because such errors are hard to see.
How AI in scientific workflows is modelled, measured and tested.
مۆدێلەکە، گریمانەکانی، داتاکانی و نادڵنیاییەکەی، بەو شێوەیەی زانا یان ئەندازیارێک دەیپشکنێت. پێکهاتەکان ڕێگا بڵاوکراوەکان دەگرنەبەر. بەهاکانی کێشراو نموونەییە، نەک دۆزینەوە.
مۆدێل، هاوکێشەکان و گریمانەکان
The model structure used for AI in scientific workflows, the assumptions it makes and how each is tested.
Ri = f(Hi, Ei, Vi, Ci)مەترسیدەر، ڕووبەڕووبوون، لاوازی و توانای مامەڵەکردنEAL = ∑k pk · Lkبەسەر ڕووداوەکانی k بە ئەگەری ساڵانەی pkxt+1 = A xt + B ut + εtA carries the couplings, u the shock, ε the error| گریمانە | بۆچی دروست دەکرێت | چۆن تاقی دەکرێتەوە |
|---|---|---|
| مەترسیدەر و ڕووبەڕووبوون لە ناو پێشهاتێکدا سەربەخۆن | ئینتێگراڵی زیان بە ئاسانی دەهێڵێتەوە | بەراورد بکە لەگەڵ گونجاندنی کۆپیولا لەسەر تۆمارە هاوبەشەکان |
| هاوبەستییەکان لە نزیک خاڵی کارکردن هێڵین | ڕێگە دەدات شۆکەکان بڵاو ببنەوە لە A | لە دەرەوەی مەودای هێڵیی شڵەژێنە و بەراورد بکە |
| چەمکەکانی لاوازی لە شوێنێکەوە بۆ شوێنێکی تر دەگوازرێنەوە | چەمکی ناوخۆیی بە دەگمەن بەردەستە | لەگەڵ زیانە چاودێریکراوەکان پشتڕاستی بکەرەوە کە هەن |
- تێکردنەکان
- کۆمەڵە داتای وەشانکراو لەگەڵ ڕەسەنایەتی
- دەرچووەکان
- دابەشبوون، نەک یەک ژمارە
- کۆد
- بڵاوکراوەتەوە لەگەڵ کارتی مۆدێل و تاقیکردنەوەکان
- بەرهەمهێنانەوە
- هەمان داتا، کۆد، ژینگە و تۆو
AI in scientific workflows changes each domain’s methods.
Findings feed the زنجیرەی Methods and Technical. AI use follows NIST’s AI RMF and is disclosed; models carry NS-12 cards under the proposed Nexus Standards.
- Workflow evaluations.
- Disclosed AI use cases.
What is measured, and how well.
Each indicator carries its unit, its cadence, the kind of source behind it and the evidence label a value would carry. No values are shown: a programme supplies them under its own authority.
| Indicator | Unit | Cadence | Source type | ناونیشان |
|---|---|---|---|---|
| Held-out evaluation design stated | percent of model-based studies | annual | Audit against the REFORMS checklist | چاودێریکراو |
| Code and model weights available | percent of studies with runnable code and weights | annual | Repository and article audit | چاودێریکراو |
| External validation | percent of models tested on data from another site or period | annual | Literature review | مەزەندەکراو |
| Calibration error | expected calibration error, dimensionless | per model | Held-out evaluation | چاودێریکراو |
| Performance gap under shift | difference in the primary metric between internal and external test sets | per model | Validation reports | چاودێریکراو |
| AI use disclosure | percent of submissions with a disclosure statement | annual | Journal submission records | DECLARED |
| Contamination checks reported | percent of benchmark evaluation reports | annual | Evaluation reports | REPORTED |
Where the evidence comes from.
Named public datasets and institutional records, each with its licence class. Sources by agreement are used only under their terms and never republished.
| سەرچاوە | What it gives | Licence class |
|---|---|---|
| OpenML | Datasets, tasks and evaluation runs with standardised splits | Open, CC BY |
| Hugging Face Hub model and dataset cards | Documented models and datasets with stated training data and limitations | Licence per model or dataset |
| MLCommons benchmarks | Shared benchmarks and measurement rules for model performance | Open, Apache 2.0 |
| AI Incident Database (Responsible AI Collaborative) | Reported failures and harms of deployed AI سیستەمە | Open, attribution |
| Software Heritage | Archived source code with persistent intrinsic identifiers | Open archive, licence per repository |
| arXiv metadata | Preprints across physics, computing and quantitative biology | Metadata CC0; licence per paper |
| Zenodo (CERN) | Citable deposits of code, models, data and evaluation outputs | Open, licence per record |
Who decides, and what the evidence serves.
Labs prepares evidence. The decisions below are taken by the authorities named, under their own rules, and never by the platform.
| کێ بڕیار دەدات | The question | Evidence this page serves |
|---|---|---|
| Journal editors and reviewers | Whether a model-based claim rests on an evaluation that excludes leakage and tests generalisation | REFORMS or TRIPOD+AI checklist, split design, external validation, code availability |
| Research funders | Whether applicants and reviewers may use generative AI, and on what disclosure terms | Funder policy, disclosure records, documented verification of generated content |
| Medicines and device regulators | Whether an AI component in a medical product is validated for its intended use | Prespecified evaluation, external validation, predetermined change control plan |
| Research integrity offices | Whether an allegation involving fabricated or generated content is substantiated | Provenance of text, data and code; version history; tool logs |
Outputs this topic produces
- Evaluation protocols that fix splits, metrics and baselines before training
- Model cards and datasheets with intended use, limits and known failure modes
- Leakage and contamination audits of model-assisted studies
- Reproducible pipelines with code, weights, environment and data versions archived
What experts ask about AI in research.
- What task is the model doing, and what is it compared against?
- Was the model evaluated on data independent of the data it was trained or tuned on?
- How does performance change when conditions shift away from the training data?
- Can the output be checked by a person or a simpler method, and is it?
- Which steps of the workflow were assisted, and is that disclosed in the result?
Where AI helps and where it misleads.
Machine learning models learn statistical regularities from data. They can be very effective where those regularities are stable and data are plentiful, for example classifying land cover from satellite imagery or emulating a climate model to explore many scenarios. They are weaker where data are sparse, where the system changes over time or where rare events matter most, which describes much of risk science.
Common failure modes are well understood: leakage, where information from the test set reaches training; گۆڕانی دابەشبوون, where conditions in use differ from those in training; shortcut learning, where a model relies on a spurious cue; and overconfident outputs without calibrated uncertainty. Generative models add the risk of fluent but fabricated content, including citations and code that looks correct but is not.
Workflow effects matter as much as model accuracy. When a tool is used at several stages, small errors can accumulate, and reviewers may give automated outputs more trust than they deserve.
How AI tools are evaluated.
- 01
Held-out and out-of-distribution tests
Evaluation on data separated by time, place or source. This is the minimum for any claim of generalisation.
- 02
Baselines
Comparison with simple statistical methods and expert judgement. A complex model that does not beat a simple baseline is not adding value.
- 03
Calibration and uncertainty
Checks that stated confidence matches observed accuracy, using uncertainty quantification.
- 04
Provenance and disclosure
A record of which model, version and prompts or settings were used at each step, so the workflow can be re-run or audited.
Benchmark scores rarely transfer directly to a new research setting, and a model’s behaviour can change between versions. Evaluation is repeated when either the task or the model changes.
How it is studied, and what the methods cannot say.
- 01زیرەکی دەستکرد و فێربوونی ماشێنAssisted screening for systematic reviews · Surrogate models to guide experimentsApplied here
- 02ژماردنی نادڵنیایی و پشتڕاستکردنەوەی مۆدێلMeasurement uncertainty budgets · Sensitivity analysis of simulation modelsApplied here
- 03ئەگەر و ئامارSample size and power planning · Meta-analysis with bias assessmentApplied here
- 04دەرهێنانی هۆکاری و هەڵسەنگاندنی کاریگەریRandomised pilots and stepped rollouts · Quasi-experimental programme evaluationApplied here
- 05ئەندازیاری سیستەمەکانRequirements to verification traceability · Stage-gate readiness reviewsApplied here
Where this page’s references lead.
ئەو لەش و بەڵگەنامانەی ئەم لاپەڕەیەیان لەگەڵ دەخوێنرێتەوە. دۆخ و وەشانەکان دەگۆڕێن؛ هەر بەستەرێک دەچێتە لای لەشی دەرکەر.
پرسیار و وەڵام.
What is data leakage?
Is a high benchmark score enough to publish a method?
Can a generative AI tool be listed as an author?
Why publish model weights and code?
Does Labs use generative AI to write findings?
Can Labs evaluate a commercial AI model?
Why compare with simple baselines?
لەم لاپەڕەیەوە بەڵگە پێشکەش بکە.
Reports is the Consortium’s quarterly publication. What you know about this subject can become evidence, a case or a correction in the next edition, credited to you and published under CC BY 4.0 where it is your own work.
- ئیمەیڵدەروازەی GW-GCRIلەم لاپەڕەیەوە بینێرەبەڵگە، ڕاستکردنەوە، بابەت، ڕێگا، پێداچوونەوە، وەرگێڕان یان تێکردنی پڕۆفایل. بە نیشانەی ئەم لاپەڕەیە دەگات، بۆ ئەوەی دەستکاریکەری خاوەنەکەی وەریبگرێت.
- Zenodoتەکیەی کراوەدایبنێ و بیدە بە کۆمەڵگاتۆماری خۆت لە Zenodo بە ORCID iD ی خۆت بڵاو بکەرەوە، پاشان لەوێ بیدە بە کۆمەڵگای Reports. سەرپەرشتیارەکان پێداچوونەوەی بۆ دەکەن؛ DOI هەر هی تۆیە.
- ReportsGCRIهەموو ڕێگاکانی بەشداری ببینەجۆرەکانی بەشداری، هەریەکە چۆن پێداچوونەوەی بۆ دەکرێت، چ ناوبردنێک وەردەگریت، مۆڵەتەکە و ئەوەی هەرگیز وەرناگیرێت.
هەرگیز داتای کەسی، وردەکاریی هەستیاری ژێرخان یان هیچ شتێک مەنێرە کە مافی بڵاوکردنەوەت نییە. بەشدارییەک پێش بەکارهێنان پێداچوونەوەی بۆ دەکرێت؛ ناردنی ماف نابەخشێت بە نووسەرایەتی یان بەڕێوەبردنی ڕاگەیاندن، و پاڵپشتی دارایی هەرگیز دۆزینەوەیەک ناکڕێت.
ڕێگایەک، کۆمەڵە داتایەک یان پرسیارێک بهێنە.
زانیاری و پرسیار ئەمڕۆ کراوەن. پرسیارێک ژمارەی ئاماژەی پێدەدرێت و هەنگاوی دواتر دیاری دەکات؛ داواکاری، پارەدان، تەرخانکردنی کۆمپیوتەر و تۆمارکردن تەنیا کاتێک دەکرێنەوە کە تیم، مەرج و توانای پێداچوونەوەیان هەبێت.
بەڵگەنامە یاساییەکان.
نەخشە، داتا و وێنەکانی ئەم ماڵپەڕە بۆ ناوەڕۆک و زانیاریی گشتی پیشان دراون. ئامۆژگاری، پێشبینی یان ئاگادارکردنەوە نین؛ سنوورەکانی زانیارییەکە لە ڕەتکردنەوەی بەرپرسیارێتی و ئاگاداریی داتادا دەستنیشان کراون.