Hugging Face
Models
Datasets
Spaces
Buckets
new
Docs
Enterprise
Pricing
Website
Tasks
HuggingChat
Collections
Languages
Organizations
Community
Blog
Posts
Daily Papers
Hardware
Learn
Discord
Forum
GitHub
Solutions
Team & Enterprise
Hugging Face PRO
Enterprise Support
Inference Providers
Inference Endpoints
Storage Buckets
Log In
Sign Up
Spaces:
snaykey
/
repro-provable-training-data-identification-for-large-language-models
like
0
Running
App
Files
Files
Community
main
repro-provable-training-data-identification-for-large-language-models
343 kB
Ctrl+K
Ctrl+K
1 contributor
History:
6 commits
snaykey
restore tags
9ea9a36
verified
21 days ago
pages
resync: real MIA evidence replacing synthetic-score toys
21 days ago
results
Add real CPU Monte-Carlo evidence for C1/C4/C5 (conformal-BH FDR control + conservative estimator); C2/C3/C6 honest pending
22 days ago
scripts
Add real CPU Monte-Carlo evidence for C1/C4/C5 (conformal-BH FDR control + conservative estimator); C2/C3/C6 honest pending
22 days ago
.gitattributes
Safe
1.52 kB
initial commit
23 days ago
README.md
Safe
427 Bytes
restore tags
21 days ago
bucket-icon.svg
Safe
413 Bytes
Update logbook: Reproduction: Provable Training Data Identification for Large Language Models
23 days ago
index.html
Safe
1.92 kB
Update logbook: Reproduction: Provable Training Data Identification for Large Language Models
23 days ago
logbook.css
Safe
29.6 kB
Update logbook: Reproduction: Provable Training Data Identification for Large Language Models
23 days ago
logbook.js
Safe
77.3 kB
Update logbook: Reproduction: Provable Training Data Identification for Large Language Models
23 days ago
logbook.json
Safe
3.06 kB
resync: REAL Pythia-1.4b/410m WikiMIA MIA scores (FDR-control properties hold on real LLM scores)
21 days ago
style.css
Safe
388 Bytes
initial commit
23 days ago
trackio-logo-light.png
Safe
30 kB
Update logbook: Reproduction: Provable Training Data Identification for Large Language Models
23 days ago
trackio-logo.png
Safe
55.6 kB
Update logbook: Reproduction: Provable Training Data Identification for Large Language Models
23 days ago
trackio-wordmark-dark.png
Safe
89.8 kB
Update logbook: Reproduction: Provable Training Data Identification for Large Language Models
23 days ago