Merge branch 'main' of https://huggingface.co/spaces/CONDA-Workshop/Data-Contamination-Report into pr/9

.gitignore

@@ -1,2 +1,3 @@
 *.pyc
-*.json
+*.json
+*.lock

README.md

@@ -1,5 +1,5 @@
 ---
-title: 🐍💨 Data Contamination Report
+title: 🐍💨 Data Contamination Database
 emoji: 🏭
 colorFrom: green
 colorTo: blue

contamination_report.csv

@@ -18,6 +18,13 @@ samsum;;GPT-3.5;model;;;74.00;model-based;https://arxiv.org/abs/2311.06233;8
 EdinburghNLP/xsum;;GPT-4;model;;;95.00;model-based;https://arxiv.org/abs/2311.06233;8
 EdinburghNLP/xsum;;GPT-3.5;model;;;79.00;model-based;https://arxiv.org/abs/2311.06233;8
 
+allenai/ai2_arc;;CommonCrawl;corpus;;;28.7;data-based;https://arxiv.org/abs/2310.17589;5
+tau/commonsense_qa;;CommonCrawl;corpus;;1.6;;data-based;https://arxiv.org/abs/2310.17589;5
+winogrande;;CommonCrawl;corpus;;1.1;;data-based;https://arxiv.org/abs/2310.17589;5
+ceval/ceval-exam;;CommonCrawl;corpus;;45.8;;data-based;https://arxiv.org/abs/2310.17589;5
+Rowan/hellaswag;;CommonCrawl;corpus;;12.4;;data-based;https://arxiv.org/abs/2310.17589;5
+cais/mmlu;;CommonCrawl;corpus;;;29.1;data-based;https://arxiv.org/abs/2310.17589;5
+
 conll2003;;GPT-3.5;model;100.0;100.0;100.0;model-based;https://hitz-zentroa.github.io/lm-contamination/blog/;7
 nyu-mll/glue;mnli;GPT-3.5;model;100.0;100.0;;model-based;https://hitz-zentroa.github.io/lm-contamination/blog/;7
 rajpurkar/squad_v2;;GPT-3.5;model;100.0;100.0;;model-based;https://hitz-zentroa.github.io/lm-contamination/blog/;7
@@ -446,24 +453,35 @@ zest;;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
 zest;;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
  
  
-imdb;;GPT-4;model;100.0;;0.0;model-based;https://arxiv.org/pdf/2308.08493;3
-imdb;;GPT-3.5;model;0.0;;0.0;model-based;https://arxiv.org/pdf/2308.08493;3
+imdb;;GPT-4;model;100.0;;0.0;model-based;https://arxiv.org/abs/2308.08493;3
+imdb;;GPT-3.5;model;0.0;;0.0;model-based;https://arxiv.org/abs/2308.08493;3
  
-ag_news;;GPT-4;model;100.0;;100.0;model-based;https://arxiv.org/pdf/2308.08493;3
-ag_news;;GPT-3.5;model;0.0;;0.0;model-based;https://arxiv.org/pdf/2308.08493;3
+ag_news;;GPT-4;model;100.0;;100.0;model-based;https://arxiv.org/abs/2308.08493;3
+ag_news;;GPT-3.5;model;0.0;;0.0;model-based;https://arxiv.org/abs/2308.08493;3
  
-yelp_review_full;;GPT-4;model;0.0;;0.0;model-based;https://arxiv.org/pdf/2308.08493;3
-yelp_review_full;;GPT-3.5;model;0.0;;0.0;model-based;https://arxiv.org/pdf/2308.08493;3
+yelp_review_full;;GPT-4;model;0.0;;0.0;model-based;https://arxiv.org/abs/2308.08493;3
+yelp_review_full;;GPT-3.5;model;0.0;;0.0;model-based;https://arxiv.org/abs/2308.08493;3
  
-nyu-mll/glue;rte;GPT-4;model;100.0;;0.0;model-based;https://arxiv.org/pdf/2308.08493;3
-nyu-mll/glue;rte;GPT-3.5;model;0.0;;0.0;model-based;https://arxiv.org/pdf/2308.08493;3
+nyu-mll/glue;rte;GPT-4;model;100.0;;0.0;model-based;https://arxiv.org/abs/2308.08493;3
+nyu-mll/glue;rte;GPT-3.5;model;0.0;;0.0;model-based;https://arxiv.org/abs/2308.08493;3
  
-nyu-mll/glue;wnli;GPT-4;model;100.0;;100.0;model-based;https://arxiv.org/pdf/2308.08493;3
-nyu-mll/glue;wnli;GPT-3.5;model;0.0;;0.0;model-based;https://arxiv.org/pdf/2308.08493;3
+nyu-mll/glue;wnli;GPT-4;model;100.0;;100.0;model-based;https://arxiv.org/abs/2308.08493;3
+nyu-mll/glue;wnli;GPT-3.5;model;0.0;;0.0;model-based;https://arxiv.org/abs/2308.08493;3
  
-samsum;;GPT-4;model;0.0;;0.0;model-based;https://arxiv.org/pdf/2308.08493;3
-samsum;;GPT-3.5;model;0.0;;0.0;model-based;https://arxiv.org/pdf/2308.08493;3
+samsum;;GPT-4;model;0.0;;0.0;model-based;https://arxiv.org/abs/2308.08493;3
+samsum;;GPT-3.5;model;0.0;;0.0;model-based;https://arxiv.org/abs/2308.08493;3
  
-EdinburghNLP/xsum;;GPT-4;model;0.0;;100.0;model-based;https://arxiv.org/pdf/2308.08493;3
-EdinburghNLP/xsum;;GPT-3.5;model;0.0;;100.0;model-based;https://arxiv.org/pdf/2308.08493;3
- 
+EdinburghNLP/xsum;;GPT-4;model;0.0;;100.0;model-based;https://arxiv.org/abs/2308.08493;3
+EdinburghNLP/xsum;;GPT-3.5;model;0.0;;100.0;model-based;https://arxiv.org/abs/2308.08493;3
+
+bigbio/mednli;;GPT-4;model;0.0;0.0;0.0;model-based;https://arxiv.org/abs/2308.08493;8
+bigbio/mednli;;GPT-3.5;model;0.0;0.0;0.0;model-based;https://arxiv.org/abs/2308.08493;8
+
+RadNLI;;GPT-4;model;0.0;0.0;0.0;model-based;https://arxiv.org/abs/2308.08493;8
+RadNLI;;GPT-3.5;model;0.0;0.0;0.0;model-based;https://arxiv.org/abs/2308.08493;8
+
+
+openai_humaneval;;EleutherAI/pile;corpus;;;12.2;data-based;https://arxiv.org/abs/2403.04811;12
+mbpp;;EleutherAI/pile;corpus;;;3.6;data-based;https://arxiv.org/abs/2403.04811;12
+openai_humaneval;;bigcode/the-stack;corpus;;;18.9;data-based;https://arxiv.org/abs/2403.04811;12
+mbpp;;bigcode/the-stack;corpus;;;20.8;data-based;https://arxiv.org/abs/2403.04811;12