Skip to content

GCRI · Labs

IA nei flussi di lavoro scientifici

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.

01Canvas

Come si svolge il lavoro.

sistemi · intorno a questo temaIllustrativo

Testbed operations

AI in scientific workflows · Field lab coast · Campaign 5

Sensors deployedGCRI · Labs

Sensor deployment

linea costiera illustrativa

BuoyStazioneGaugeMareBands: tidal rangeN

Sensors

S-01 tide940.0Nominal
S-04 salinity760.4Recalibrate
S-07 wave950.1Nominal

Sensor vs reference

Testbed operations: the screen’s structure, terms and states for AI in scientific workflows.Nomi di esempio e valori illustrativi; un progetto, non un registro né un sistema attivo.

Fig.Testbed operations: example names and illustrative values, not a record or a live system.

02La domanda

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.

Meccanismo

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.

Meccanismo

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.

Meccanismo

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.

Meccanismo

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.

03Metodi ed evidenze

How AI in scientific workflows is modelled, measured and tested.

Il modello, le sue ipotesi, i suoi dati e la sua incertezza, nella forma in cui uno scienziato o un ingegnere li verificherebbe. Le strutture seguono metodi pubblicati. I valori rappresentati sono illustrativi, non risultati.

Modello, equazioni e ipotesi

The model structure used for AI in scientific workflows, the assumptions it makes and how each is tested.

Rischio dell'elemento iRi = f(Hi, Ei, Vi, Ci)pericolo, esposizione, vulnerabilità e capacità di risposta
Perdita annua attesaEAL = ∑k pk · Lksu eventi k con probabilità annua pk
Sistemi accoppiatixt+1 = A xt + B ut + εtA carries the couplings, u the shock, ε the error
IpotesiPerché è realizzatoCome viene testato
Pericolo ed esposizione sono indipendenti all'interno di un eventoMantiene trattabile l'integrale delle perditeConfrontare con un adattamento di copula su registrazioni congiunte
Gli accoppiamenti sono lineari vicino al punto di funzionamentoConsente agli shock di propagarsi attraverso APerturbare oltre l'intervallo lineare e confrontare
Le curve di vulnerabilità si trasferiscono da un luogo all'altroLe curve locali sono raramente disponibiliValidare rispetto alle perdite osservate, dove esistono
Input
set di dati versionati con provenienza
Risultati
distribuzioni, mai valori singoli
Codice
pubblicato con la scheda del modello e i test
Riproduzione
stessi dati, codice, ambiente e seed
Formulazioni standard del rischio e dello spazio degli stati; le ipotesi elencate sono tipiche del metodo, dichiarate per la revisione, non risultati.
Principi guida FAIR · GO FAIR e FORCE11W3C PROV · World Wide Web ConsortiumGuidance on consistent treatment of uncertainties · IPCCCEOS Analysis Ready Data · Comitato sui satelliti per l'osservazione della Terra
04In the five domains

AI in scientific workflows changes each domain’s methods.

05Indicatori

Cosa viene misurato e con quale accuratezza.

Ogni indicatore riporta la sua unità, la sua cadenza, il tipo di fonte su cui si basa e l'etichetta di evidenza che un valore riporterebbe. Non sono mostrati valori: un programma li fornisce sotto la propria autorità.

IndicatoreUnitàCadenzaTipo di fonteEtichetta
Held-out evaluation design statedpercent of model-based studiesannualeAudit against the REFORMS checklistOSSERVATO
Code and model weights availablepercent of studies with runnable code and weightsannualeRepository and article auditOSSERVATO
External validationpercent of models tested on data from another site or periodannualeLiterature reviewSTIMATO
Errore di calibrazioneexpected calibration error, dimensionlessper modelHeld-out evaluationOSSERVATO
Performance gap under shiftdifference in the primary metric between internal and external test setsper modelValidation reportsOSSERVATO
AI use disclosurepercent of submissions with a disclosure statementannualeJournal submission recordsDICHIARATO
Contamination checks reportedpercent of benchmark evaluation reportsannualeEvaluation reportsRIPORTATO
06Fonti

Da dove provengono le evidenze.

Set di dati pubblici e registri istituzionali specifici, ciascuno con la sua classe di licenza. Le fonti soggette ad accordo sono utilizzate solo alle relative condizioni e mai ripubblicate.

FonteCosa fornisceClasse di licenza
OpenMLDatasets, tasks and evaluation runs with standardised splitsOpen, CC BY
Hugging Face Hub model and dataset cardsDocumented models and datasets with stated training data and limitationsLicence per model or dataset
MLCommons benchmarksShared benchmarks and measurement rules for model performanceOpen, Apache 2.0
AI Incident Database (Responsible AI Collaborative)Reported failures and harms of deployed AI sistemiAperto, attribuzione
Software HeritageArchived source code with persistent intrinsic identifiersOpen archive, licence per repository
arXiv metadataPreprints across physics, computing and quantitative biologyMetadata CC0; licence per paper
Zenodo (CERN)Citable deposits of code, models, data and evaluation outputsOpen, licence per record
07Decisioni

Chi decide, e a cosa servono le evidenze.

Laboratori prepares evidence. The decisions below are taken by the authorities named, under their own rules, and never by the platform.

Chi decideLa domandaEvidenze fornite da questa pagina
Journal editors and reviewersWhether a model-based claim rests on an evaluation that excludes leakage and tests generalisationREFORMS or TRIPOD+AI checklist, split design, external validation, code availability
Finanziatori della ricercaWhether applicants and reviewers may use generative AI, and on what disclosure termsFunder policy, disclosure records, documented verification of generated content
Medicines and device regulatorsWhether an AI component in a medical product is validated for its intended usePrespecified evaluation, external validation, predetermined change control plan
Research integrity officesWhether an allegation involving fabricated or generated content is substantiatedProvenance of text, data and code; version history; tool logs

Output prodotti da questo argomento

  • 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
08Questioni centrali

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?
09Meccanismi e fattori

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; spostamento di distribuzione, 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.

10Metodi e dati

How AI tools are evaluated.

  1. 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.

  2. 02

    Baselines

    Comparison with simple statistical methods and expert judgement. A complex model that does not beat a simple baseline is not adding value.

  3. 03

    Calibration and uncertainty

    Checks that stated confidence matches observed accuracy, using quantificazione dell'incertezza.

  4. 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.

12Where this page’s references

Where this page’s references lead.

Gli organismi e i documenti alla luce dei quali si legge questa pagina. Stato ed edizioni cambiano; ogni link porta all'organismo emittente.

13Domande

Domande e risposte.

What is data leakage?
Any route by which information about the test data influences training or model selection. It makes reported performance higher than the model will achieve on genuinely new data.
Is a high benchmark score enough to publish a method?
Not on its own. Reviewers increasingly expect external validation, uncertainty on the score, ablations and an account of how the benchmark was protected from contamination.
Can a generative AI tool be listed as an author?
COPE and the ICMJE say no, because authorship carries accountability a tool cannot hold. Use of such tools is disclosed in the methods or acknowledgements, under the journal’s policy.
Why publish model weights and code?
So others can rerun the evaluation, test on new data and find errors. Where weights cannot be shared, for privacy or safety, a controlled access route and a stated reason are the accepted alternative.
Does Labs use generative AI to write findings?
Any assisted step is designed to be disclosed. Findings are the responsibility of named researchers, who check every generated claim, citation and line of code.
Can Labs evaluate a commercial AI model?
A model can be evaluated under a published protocol. The result describes performance on the tested task and is not an endorsement or approval.
Why compare with simple baselines?
Because complex models often appear impressive on benchmarks but add little over a well-chosen simple method on real research data.
RapportiContribuisci

Contribuisci con evidenze da questa pagina.

Rapporti 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.

GCRILaboratoriEvidenze di LabsMetodi e aspetti tecnici
Laboratori

Porta un metodo, un set di dati o una domanda.

Informazioni e richieste sono aperte oggi. Una richiesta riceve un riferimento e indica il passo successivo; candidature, pagamenti, assegnazioni di calcolo e registrazioni si aprono solo quando esistono il team, le condizioni e la capacità di revisione.