MétaCan
ENFR
Menu
Cohort builder

4,299,418 works, Canadian by any of four routes.

Every filter state is a URL; the URL is the query; the query is citable via /q/⟨hash⟩. The page, the API and the export parse the same parameters.

Export CSVExport JSONAPI query

The current cohort, streamed from the database: every work column, the machine labels, the provisional scores, and the per-row validation status. Exports are capped at 100,000 rows. Mints a permanent /q/ link for this exact query. The same filters always produce the same link, whoever asks.

Search term
Year range
→
Sort
Language
Type
Field
Venue
Topic
Domain Adaptation and Few-Shot Learning
Retraction
Abstract
Evidence source
Study design
Label agreement
Label status

Direct Codex and Gemma labels are unvalidated and sparse. Distilled predictions cover the full frame and are also unvalidated. Choose the evidence source explicitly; absence of a direct label is never a negative label.

affaffiliation
fundfunder
venuejournal
aboutaboutness

The four routes compose: require the funder route and exclude affiliation to get the funder-only stratum no affiliation-based frame ever sees.

705 results · 1 filter active ·
Categories
Machine labels · sparse coverage
Evidence
An unlabeled work is unknown, not a negative. Label coverage is reported on every query.
705 works in the cohort · of 4,299,418page 1 of 15

Labels cover 0 of 705 works in this cohort. The rest are unlabeled, which is not a negative label: the label table is sparse today and grows as labeling rounds land.

Distilled predictions cover 705 of 705 works in this cohort. Predictions are machine_predicted_unvalidated teacher distillation outputs. Candidate is the union; consensus is the intersection.

affunlabeled
A survey on semi-supervised learning
2019· article· en· Machine Learning· Computer Science
distilled prediction:candidate · metaepi_narrow+insufficient_payloadconsensus · none
2,562
citations
affunlabeled
Optimization as a Model for Few-Shot Learning
2017· article· en· International Conference on Learning Representations· Computer Science
distilled prediction:candidate · sts+scholarly_communicationconsensus · none
2,447
citations
affunlabeled
Deep learning for AI
2021· article· en· Communications of the ACM· Computer Science
distilled prediction:candidate · metaresearch+open_scienceconsensus · open_science
627
citations
affunlabeled
A Review of Generalized Zero-Shot Learning Methods
2022· review· en· IEEE Transactions on Pattern Analysis and Machine Intelligence· Computer Science
distilled prediction:candidate · metaepi_narrow+insufficient_payloadconsensus · none
396
citations
affunlabeled
Ranking Distillation
2018· article· en· Computer Science
distilled prediction:candidate · noneconsensus · none
165
citations
affunlabeled
k-Sparse Autoencoders
2013· preprint· en· arXiv (Cornell University)· Computer Science
distilled prediction:candidate · metaepi_narrow+insufficient_payloadconsensus · none
148
citations
affunlabeled
Unsupervised Learning via Meta-Learning
2018· preprint· en· arXiv (Cornell University)· Computer Science
distilled prediction:candidate · metaepi_narrow+insufficient_payloadconsensus · none
129
citations
fundno affunlabeled
When Does Contrastive Visual Representation Learning Work?
2022· article· en· 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)· Computer Science
distilled prediction:candidate · metaepi_narrow+insufficient_payloadconsensus · none
98
citations
next →

How this was built: Screen · Findings · About