Add PR number + Postprocessing

contamination_report.csv

@@ -163,16 +163,12 @@ 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_7b;;model;;;0.15;data-based;https://openreview.net/pdf?id=4WnqRR915j;
-gsm8k;;EleutherAI/llemma_34b;;model;;;0.15;data-based;https://openreview.net/pdf?id=4WnqRR915j;
-gsm8k;;EleutherAI/proof-pile-2;;corpus;;;0.15;data-based;https://openreview.net/pdf?id=4WnqRR915j;
+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
 
-hendrycks/competition_math;;EleutherAI/llemma_7b;;model;;;7.72;data-based;https://openreview.net/pdf?id=4WnqRR915j;
-hendrycks/competition_math;;EleutherAI/llemma_34b;;model;;;7.72;data-based;https://openreview.net/pdf?id=4WnqRR915j;
-hendrycks/competition_math;;EleutherAI/proof-pile-2;;corpus;;;7.72;data-based;https://openreview.net/pdf?id=4WnqRR915j;
-
 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
 head_qa;en;oscar-corpus/OSCAR-2301;;corpus;;;5.29;data-based;https://arxiv.org/abs/2310.20707;2
@@ -183,6 +179,10 @@ 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;;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
+
 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

@@ -17,6 +17,9 @@ 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]))
 
@@ -25,6 +28,7 @@ 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: