test

README.md

@@ -5,7 +5,7 @@ colorFrom: green
 colorTo: blue
 sdk: gradio
 python_version: 3.11
-sdk_version: 4.36.0
+sdk_version: 4.19.1
 app_file: app.py
 app_port: 7860
 fullWidth: true

contamination_report.csv

@@ -6,9 +6,6 @@ Anagrams 1;;GPT-3;;model;;3.0;;data-based;https://arxiv.org/abs/2005.14165;13
 
 Anagrams 2;;GPT-3;;model;;7.0;;data-based;https://arxiv.org/abs/2005.14165;13
 
-CodeForces2305;;GPT-3.5-turbo;0613;model;;;0.0;model-based;https://arxiv.org/abs/2402.15938;28
-CodeForces2305;;GPT-3.5-turbo;1106;model;;;0.0;model-based;https://arxiv.org/abs/2402.15938;28
-
 Cycled Letters;;GPT-3;;model;;1.0;;data-based;https://arxiv.org/abs/2005.14165;13
 
 EdinburghNLP/xsum;;GPT-3.5;;model;0.0;;100.0;model-based;https://arxiv.org/abs/2308.08493;3
@@ -20,9 +17,6 @@ EdinburghNLP/xsum;;allenai/c4;;corpus;;;15.49;data-based;https://arxiv.org/abs/2
 
 EleutherAI/hendrycks_math;;GPT-4;;model;100.0;;;data-based;https://arxiv.org/abs/2303.08774;11
 
-HumanEval_R;;GPT-3.5-turbo;0613;model;;;9.76;model-based;https://arxiv.org/abs/2402.15938;28
-HumanEval_R;;GPT-3.5-turbo;1106;model;;;10.97;model-based;https://arxiv.org/abs/2402.15938;28
-
 RadNLI;;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
 
@@ -149,20 +143,6 @@ facebook/anli;test_r2;GPT-3;;model;;;18.0;data-based;https://arxiv.org/abs/2005.
 
 facebook/anli;test_r3;GPT-3;;model;;;16.0;data-based;https://arxiv.org/abs/2005.14165;13
 
-facebook/flores;;Claude 3 Opus;;model;;100.0;;model-based;https://arxiv.org/abs/2404.13813;29
-facebook/flores;;bigscience/bloomz;;model;;100.0;;data-based;https://aclanthology.org/2023.acl-long.891/;20
-facebook/flores;;bigscience/bloomz-1b1;;model;;100.0;;data-based;https://aclanthology.org/2023.acl-long.891/;20
-facebook/flores;;bigscience/bloomz-1b7;;model;;100.0;;data-based;https://aclanthology.org/2023.acl-long.891/;20
-facebook/flores;;bigscience/bloomz-3b;;model;;100.0;;data-based;https://aclanthology.org/2023.acl-long.891/;20
-facebook/flores;;bigscience/bloomz-560m;;model;;100.0;;data-based;https://aclanthology.org/2023.acl-long.891/;20
-facebook/flores;;bigscience/bloomz-7b1;;model;;100.0;;data-based;https://aclanthology.org/2023.acl-long.891/;20
-facebook/flores;;bigscience/mt0-base;;model;;100.0;;data-based;https://aclanthology.org/2023.acl-long.891/;20
-facebook/flores;;bigscience/mt0-large;;model;;100.0;;data-based;https://aclanthology.org/2023.acl-long.891/;20
-facebook/flores;;bigscience/mt0-small;;model;;100.0;;data-based;https://aclanthology.org/2023.acl-long.891/;20
-facebook/flores;;bigscience/mt0-xl;;model;;100.0;;data-based;https://aclanthology.org/2023.acl-long.891/;20
-facebook/flores;;bigscience/mt0-xxl;;model;;100.0;;data-based;https://aclanthology.org/2023.acl-long.891/;20
-facebook/flores;;bigscience/xP3;;corpus;;100.0;;data-based;https://aclanthology.org/2023.acl-long.891/;20
-
 gigaword;;EleutherAI/pile;;corpus;;;1.18;data-based;https://arxiv.org/abs/2310.20707;2
 gigaword;;allenai/c4;;corpus;;;0.15;data-based;https://arxiv.org/abs/2310.20707;2
 gigaword;;oscar-corpus/OSCAR-2301;;corpus;;;0.36;data-based;https://arxiv.org/abs/2310.20707;2
@@ -170,13 +150,8 @@ gigaword;;togethercomputer/RedPajama-Data-V2;;corpus;;;2.82;data-based;https://a
 
 gsm8k;;BAAI/Aquila2-34B;;model;;;100.0;model-based;https://huggingface.co/BAAI/Aquila2-34B/blob/main/README.md;21
 gsm8k;;BAAI/AquilaChat2-34B;;model;;;100.0;model-based;https://huggingface.co/BAAI/AquilaChat2-34B/blob/main/README.md;21
-gsm8k;;EleutherAI/llemma_34b;;model;;;0.15;data-based;https://openreview.net/forum?id=4WnqRR915j;23
-gsm8k;;EleutherAI/llemma_7b;;model;;;0.15;data-based;https://openreview.net/forum?id=4WnqRR915j;23
-gsm8k;;EleutherAI/proof-pile-2;;corpus;;;0.15;data-based;https://openreview.net/forum?id=4WnqRR915j;23
 gsm8k;;GPT-4;;model;100.0;;1.0;data-based;https://arxiv.org/abs/2303.08774;11
 gsm8k;;GPT-4;;model;79.00;;;model-based;https://arxiv.org/abs/2311.06233;8
-gsm8k;;Qwen/Qwen-14B;;model;0.5;;;model-based;https://arxiv.org/abs/2404.18824;27
-gsm8k;;Qwen/Qwen-1_8B;;model;12.8;;0.075;model-based;https://arxiv.org/abs/2404.18824;27
 
 head_qa;en;EleutherAI/pile;;corpus;;;5.11;data-based;https://arxiv.org/abs/2310.20707;2
 head_qa;en;allenai/c4;;corpus;;;5.22;data-based;https://arxiv.org/abs/2310.20707;2
@@ -188,18 +163,6 @@ health_fact;;allenai/c4;;corpus;;;7.53;data-based;https://arxiv.org/abs/2310.207
 health_fact;;oscar-corpus/OSCAR-2301;;corpus;;;3.4;data-based;https://arxiv.org/abs/2310.20707;2
 health_fact;;togethercomputer/RedPajama-Data-V2;;corpus;;;18.7;data-based;https://arxiv.org/abs/2310.20707;2
 
-hendrycks/competition_math;;BAAI/Aquila2-34B;;model;3.366;;1.166;model-based;https://arxiv.org/abs/2404.18824;27
-hendrycks/competition_math;;BAAI/Aquila2-7B;;model;1;;0.133;model-based;https://arxiv.org/abs/2404.18824;27
-hendrycks/competition_math;;EleutherAI/llemma_34b;;model;;;7.72;data-based;https://openreview.net/forum?id=4WnqRR915j;23
-hendrycks/competition_math;;EleutherAI/llemma_7b;;model;;;7.72;data-based;https://openreview.net/forum?id=4WnqRR915j;23
-hendrycks/competition_math;;EleutherAI/proof-pile-2;;corpus;;;7.72;data-based;https://openreview.net/forum?id=4WnqRR915j;23
-hendrycks/competition_math;;Qwen/Qwen-14B;;model;1.766;;1.6;model-based;https://arxiv.org/abs/2404.18824;27
-hendrycks/competition_math;;Qwen/Qwen-1_8B;;model;4.533;;1.70;model-based;https://arxiv.org/abs/2404.18824;27
-hendrycks/competition_math;;Qwen/Qwen-7B;;model;1.266;;0.766;model-based;https://arxiv.org/abs/2404.18824;27
-hendrycks/competition_math;;THUDM/chatglm3-6b;;model;0.70;;0.4;model-based;https://arxiv.org/abs/2404.18824;27
-hendrycks/competition_math;;internlm/internlm2-20b;;model;4.733;;0.666;model-based;https://arxiv.org/abs/2404.18824;27
-hendrycks/competition_math;;internlm/internlm2-7b;;model;3.033;;0.433;model-based;https://arxiv.org/abs/2404.18824;27
-
 hlgd;;EleutherAI/pile;;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
 hlgd;;allenai/c4;;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
 hlgd;;oscar-corpus/OSCAR-2301;;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2

postprocessing.py

@@ -17,9 +17,6 @@ def remove_duplicates(data):
 def fix_arxiv_links(data):
     return [[*item[:-2], item[-2].replace("arxiv.org/pdf", "arxiv.org/abs"), item[-1]] for item in data]
 
-def fix_openreview_links(data):
-    return [[*item[:-2], item[-2].replace("openreview.net/pdf", "openreview.net/forum"), item[-1]] for item in data]
-
 def sort_data(data):
     return sorted(data, key=lambda x: (x[0], x[1], x[2], x[3], x[-1]))
 
@@ -28,7 +25,6 @@ def main():
     data = sort_data(data)
     data = remove_duplicates(data)
     data = fix_arxiv_links(data)
-    data = fix_openreview_links(data)
     print("Total datapoints:", len(data))
 
     with open("contamination_report.csv", 'w') as f: