GCRI · Labs
과학 워크플로의 AI
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.
일이 진행되는 방식.
Testbed operations
AI in scientific workflows · Field lab coast · Campaign 5
Sensor deployment
예시 해안선
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
그림Testbed 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.
모형, 그 가정, 데이터, 불확실성을 과학자나 엔지니어가 확인할 형태로 제시합니다. 구조는 발행된 방법을 따릅니다. 제시된 값은 예시이며 결과가 아닙니다.
모형, 방정식 및 가정
The model structure used for AI in scientific workflows, the assumptions it makes and how each is tested.
Ri = f(Hi, Ei, Vi, Ci)재해, 노출, 취약성, 대처 역량EAL = ∑k pk · Lk연간 확률이 pkxt+1 = A xt + B ut + εtA carries the couplings, u the shock, ε the error| 가정 | 만드는 이유 | 시험 방법 |
|---|---|---|
| 한 사건 안에서 재해와 노출은 서로 독립적임 | 손실 적분을 다루기 쉽게 유지함 | 결합 기록에 적합한 코퓰러와 비교 |
| 결합은 운전점 근처에서 선형이다 | 충격이 A를 통해 전파되게 함 | 선형 범위를 넘어 섭동을 주고 비교하십시오 |
| 취약성 곡선은 장소 간에 옮겨 쓸 수 있다 | 지역 곡선은 거의 없다 | 관측된 손실이 있는 곳에서는 이에 대해 검증 |
- 투입 자료
- 출처 정보가 있는 버전 관리 데이터세트
- 산출물
- 분포이며 결코 단일 숫자가 아님
- 코드
- 모델 카드 및 시험과 함께 공개
- 재현
- 같은 데이터, 코드, 환경과 시드
AI in scientific workflows changes each domain’s methods.
Findings feed the 방법 및 기술 시리즈. 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.
측정되는 것과 그 정확도.
각 지표에는 단위, 주기, 그 뒤의 출처 종류, 값에 붙을 근거 표시가 있습니다. 값은 표시하지 않습니다. 값은 프로그램이 자체 권한으로 제공합니다.
| 지표 | 단위 | 주기 | 출처 유형 | 라벨 |
|---|---|---|---|---|
| Held-out evaluation design stated | percent of model-based studies | 연간 | Audit against the REFORMS checklist | 관측 |
| Code and model weights available | percent of studies with runnable code and weights | 연간 | Repository and article audit | 관측 |
| External validation | percent of models tested on data from another site or period | 연간 | Literature review | 추정 |
| 보정 오차 | expected calibration error, dimensionless | per model | Held-out evaluation | 관측 |
| Performance gap under shift | difference in the primary metric between internal and external test sets | per model | Validation reports | 관측 |
| AI use disclosure | percent of submissions with a disclosure statement | 연간 | Journal submission records | 신고됨 |
| Contamination checks reported | percent of benchmark evaluation reports | 연간 | Evaluation reports | 보고됨 |
근거의 출처.
이름이 명시된 공개 데이터셋과 기관 기록으로, 각각 라이선스 등급이 있습니다. 협약에 따른 출처는 그 조건에 따라서만 사용하며 결코 재게시하지 않습니다.
| 출처 | 제공하는 것 | 라이선스 등급 |
|---|---|---|
| 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 시스템 | 공개, 출처 표시 |
| 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 |
누가 결정하며 근거는 무엇에 쓰이는지.
랩 prepares evidence. The decisions below are taken by the authorities named, under their own rules, and never by the platform.
| 결정 주체 | 질문 | 이 페이지가 제공하는 근거 |
|---|---|---|
| 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 |
| 연구 재원 제공 기관 | 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 |
이 주제가 생산하는 산출물
- 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; 분포 변화, 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 불확실성 정량화.
- 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.
연구되는 방식과 방법이 말할 수 없는 것.
Where this page’s references lead.
이 페이지를 읽을 때 기준이 되는 기구와 문서. 상태와 판은 바뀌며, 각 링크는 발행 기구로 연결됩니다.
질문과 답변.
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?
이 페이지에서 증거를 기여하십시오.
보고서 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.
- 이메일게이트웨이 GW-GCRI이 페이지에서 보내기증거, 정정, 사례, 방법, 검토, 번역 또는 프로필 입력 자료. 이 페이지의 태그가 붙어 도착하므로, 이를 담당하는 편집자가 받게 됩니다.
- Zenodo개방형 예치기탁하고 커뮤니티에 제출하기ORCID iD로 Zenodo에 직접 기록을 게시한 뒤, 그곳의 Reports 커뮤니티에 제출하십시오. 큐레이터가 검토하며, DOI는 귀하의 것으로 남습니다.
- 보고서GCRI모든 기여 방법 보기기여 유형, 각각의 검토 방식, 받게 되는 크레디트, 라이선스, 그리고 절대 받지 않는 것.
개인정보, 민감한 인프라 세부 정보, 공유할 권리가 없는 자료는 절대 보내지 마십시오. 기여물은 사용 전에 검토됩니다. 기여물을 보낸다고 해서 저작자 지위나 편집 권한이 부여되지 않으며, 후원으로 조사 결과를 얻을 수 없습니다.
방법, 데이터세트 또는 질문을 가져오십시오.
정보와 문의는 오늘부터 열려 있습니다. 문의에는 참조 번호가 부여되고 다음 단계가 안내됩니다. 신청, 결제, 컴퓨팅 할당, 등록은 해당 팀, 약관, 심사 역량이 갖추어졌을 때만 열립니다.
법률 문서.
이 사이트의 지도, 데이터와 그림은 맥락과 일반 정보로 제시됩니다. 조언, 예보 또는 경보가 아니며, 정보의 한계는 면책 고지와 데이터 고지에 나와 있습니다.