Updates

contamination_report.csv

@@ -244,43 +244,19 @@ natural_questions;;FLAN;;model;;3.2;;data-based;https://arxiv.org/abs/2109.01652
 natural_questions;;GLaM;;model;;3.9;;data-based;https://arxiv.org/abs/2112.06905;13
 natural_questions;;GPT-3;;model;;;1.0;data-based;https://arxiv.org/abs/2005.14165;13
 
-nyu-mll/glue;BoolQ;allenai/c4;;corpus;;;2.4;data-based;https://arxiv.org/abs/2104.08758;6
-
-nyu-mll/glue;CoLA;allenai/c4;;corpus;;;14.4;data-based;https://arxiv.org/abs/2104.08758;6
-
-nyu-mll/glue;MNLI-hypothesis;allenai/c4;;corpus;;;14.2;data-based;https://arxiv.org/abs/2104.08758;6
-
-nyu-mll/glue;MNLI-premise;allenai/c4;;corpus;;;15.2;data-based;https://arxiv.org/abs/2104.08758;6
-
-nyu-mll/glue;MRPC-sentence-1;allenai/c4;;corpus;;;2.7;data-based;https://arxiv.org/abs/2104.08758;6
-
-nyu-mll/glue;MRPC-sentence-2;allenai/c4;;corpus;;;2.7;data-based;https://arxiv.org/abs/2104.08758;6
-
-nyu-mll/glue;QNLI-question;allenai/c4;;corpus;;;1.8;data-based;https://arxiv.org/abs/2104.08758;6
-
-nyu-mll/glue;QNLI-sentence;allenai/c4;;corpus;;;53.6;data-based;https://arxiv.org/abs/2104.08758;6
-
-nyu-mll/glue;RTE-sentence-1;allenai/c4;;corpus;;;6;data-based;https://arxiv.org/abs/2104.08758;6
-
-nyu-mll/glue;RTE-sentence-2;allenai/c4;;corpus;;;10.8;data-based;https://arxiv.org/abs/2104.08758;6
-
-nyu-mll/glue;SST-2;allenai/c4;;corpus;;;11;data-based;https://arxiv.org/abs/2104.08758;6
-
-nyu-mll/glue;STS-B-sentence-1;allenai/c4;;corpus;;;18.3;data-based;https://arxiv.org/abs/2104.08758;6
-
-nyu-mll/glue;STS-B-sentence-2;allenai/c4;;corpus;;;18.6;data-based;https://arxiv.org/abs/2104.08758;6
-
-nyu-mll/glue;WNLI-sentence-1;allenai/c4;;corpus;;;4.8;data-based;https://arxiv.org/abs/2104.08758;6
-
-nyu-mll/glue;WNLI-sentence-2;allenai/c4;;corpus;;;2.1;data-based;https://arxiv.org/abs/2104.08758;6
-
 nyu-mll/glue;ax;EleutherAI/pile;;corpus;;;5.07;data-based;https://arxiv.org/abs/2310.20707;2
 nyu-mll/glue;ax;allenai/c4;;corpus;;;1.99;data-based;https://arxiv.org/abs/2310.20707;2
 nyu-mll/glue;ax;oscar-corpus/OSCAR-2301;;corpus;;;1.45;data-based;https://arxiv.org/abs/2310.20707;2
 nyu-mll/glue;ax;togethercomputer/RedPajama-Data-V2;;corpus;;;6.16;data-based;https://arxiv.org/abs/2310.20707;2
 
+nyu-mll/glue;boolq;allenai/c4;;corpus;;;2.4;data-based;https://arxiv.org/abs/2104.08758;6
+
+nyu-mll/glue;cola;allenai/c4;;corpus;;;14.4;data-based;https://arxiv.org/abs/2104.08758;6
+
 nyu-mll/glue;mnli;GPT-3.5;;model;100.0;100.0;;model-based;https://hitz-zentroa.github.io/lm-contamination/blog/;7
 
+nyu-mll/glue;mnli-hypothesis;allenai/c4;;corpus;;;14.2;data-based;https://arxiv.org/abs/2104.08758;6
+
 nyu-mll/glue;mnli-matched;EleutherAI/pile;;corpus;;;2.17;data-based;https://arxiv.org/abs/2310.20707;2
 nyu-mll/glue;mnli-matched;allenai/c4;;corpus;;;1.65;data-based;https://arxiv.org/abs/2310.20707;2
 nyu-mll/glue;mnli-matched;oscar-corpus/OSCAR-2301;;corpus;;;1.77;data-based;https://arxiv.org/abs/2310.20707;2
@@ -291,16 +267,26 @@ nyu-mll/glue;mnli-mismatched;allenai/c4;;corpus;;;1.73;data-based;https://arxiv.
 nyu-mll/glue;mnli-mismatched;oscar-corpus/OSCAR-2301;;corpus;;;1.91;data-based;https://arxiv.org/abs/2310.20707;2
 nyu-mll/glue;mnli-mismatched;togethercomputer/RedPajama-Data-V2;;corpus;;;2.17;data-based;https://arxiv.org/abs/2310.20707;2
 
+nyu-mll/glue;mnli-premise;allenai/c4;;corpus;;;15.2;data-based;https://arxiv.org/abs/2104.08758;6
+
 nyu-mll/glue;mrpc;EleutherAI/pile;;corpus;;;0.64;data-based;https://arxiv.org/abs/2310.20707;2
 nyu-mll/glue;mrpc;allenai/c4;;corpus;;;0.06;data-based;https://arxiv.org/abs/2310.20707;2
 nyu-mll/glue;mrpc;oscar-corpus/OSCAR-2301;;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
 nyu-mll/glue;mrpc;togethercomputer/RedPajama-Data-V2;;corpus;;;1.16;data-based;https://arxiv.org/abs/2310.20707;2
 
+nyu-mll/glue;mrpc-sentence-1;allenai/c4;;corpus;;;2.7;data-based;https://arxiv.org/abs/2104.08758;6
+
+nyu-mll/glue;mrpc-sentence-2;allenai/c4;;corpus;;;2.7;data-based;https://arxiv.org/abs/2104.08758;6
+
 nyu-mll/glue;qnli;EleutherAI/pile;;corpus;;;1.48;data-based;https://arxiv.org/abs/2310.20707;2
 nyu-mll/glue;qnli;allenai/c4;;corpus;;;0.13;data-based;https://arxiv.org/abs/2310.20707;2
 nyu-mll/glue;qnli;oscar-corpus/OSCAR-2301;;corpus;;;0.04;data-based;https://arxiv.org/abs/2310.20707;2
 nyu-mll/glue;qnli;togethercomputer/RedPajama-Data-V2;;corpus;;;1.21;data-based;https://arxiv.org/abs/2310.20707;2
 
+nyu-mll/glue;qnli-question;allenai/c4;;corpus;;;1.8;data-based;https://arxiv.org/abs/2104.08758;6
+
+nyu-mll/glue;qnli-sentence;allenai/c4;;corpus;;;53.6;data-based;https://arxiv.org/abs/2104.08758;6
+
 nyu-mll/glue;rte;EleutherAI/pile;;corpus;;;0.13;data-based;https://arxiv.org/abs/2310.20707;2
 nyu-mll/glue;rte;GPT-3.5;;model;0.0;;0.0;model-based;https://arxiv.org/abs/2308.08493;3
 nyu-mll/glue;rte;GPT-3.5;;model;;71.00;;model-based;https://arxiv.org/abs/2311.06233;8
@@ -310,11 +296,21 @@ nyu-mll/glue;rte;allenai/c4;;corpus;;;0.2;data-based;https://arxiv.org/abs/2310.
 nyu-mll/glue;rte;oscar-corpus/OSCAR-2301;;corpus;;;0.17;data-based;https://arxiv.org/abs/2310.20707;2
 nyu-mll/glue;rte;togethercomputer/RedPajama-Data-V2;;corpus;;;67.47;data-based;https://arxiv.org/abs/2310.20707;2
 
+nyu-mll/glue;rte-sentence-1;allenai/c4;;corpus;;;6;data-based;https://arxiv.org/abs/2104.08758;6
+
+nyu-mll/glue;rte-sentence-2;allenai/c4;;corpus;;;10.8;data-based;https://arxiv.org/abs/2104.08758;6
+
+nyu-mll/glue;sst2;allenai/c4;;corpus;;;11;data-based;https://arxiv.org/abs/2104.08758;6
+
 nyu-mll/glue;stsb;EleutherAI/pile;;corpus;;;11.09;data-based;https://arxiv.org/abs/2310.20707;2
 nyu-mll/glue;stsb;allenai/c4;;corpus;;;3.48;data-based;https://arxiv.org/abs/2310.20707;2
 nyu-mll/glue;stsb;oscar-corpus/OSCAR-2301;;corpus;;;3.12;data-based;https://arxiv.org/abs/2310.20707;2
 nyu-mll/glue;stsb;togethercomputer/RedPajama-Data-V2;;corpus;;;9.86;data-based;https://arxiv.org/abs/2310.20707;2
 
+nyu-mll/glue;stsb-sentence-1;allenai/c4;;corpus;;;18.3;data-based;https://arxiv.org/abs/2104.08758;6
+
+nyu-mll/glue;stsb-sentence-2;allenai/c4;;corpus;;;18.6;data-based;https://arxiv.org/abs/2104.08758;6
+
 nyu-mll/glue;wnli;EleutherAI/pile;;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
 nyu-mll/glue;wnli;GPT-3.5;;model;0.0;;0.0;model-based;https://arxiv.org/abs/2308.08493;3
 nyu-mll/glue;wnli;GPT-3.5;;model;;12.68;;model-based;https://arxiv.org/abs/2311.06233;8
@@ -324,6 +320,10 @@ nyu-mll/glue;wnli;allenai/c4;;corpus;;;0.0;data-based;https://arxiv.org/abs/2310
 nyu-mll/glue;wnli;oscar-corpus/OSCAR-2301;;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
 nyu-mll/glue;wnli;togethercomputer/RedPajama-Data-V2;;corpus;;;2.05;data-based;https://arxiv.org/abs/2310.20707;2
 
+nyu-mll/glue;wnli-sentence-1;allenai/c4;;corpus;;;4.8;data-based;https://arxiv.org/abs/2104.08758;6
+
+nyu-mll/glue;wnli-sentence-2;allenai/c4;;corpus;;;2.1;data-based;https://arxiv.org/abs/2104.08758;6
+
 openai_humaneval;;EleutherAI/pile;;corpus;;;12.2;data-based;https://arxiv.org/abs/2403.04811;12
 openai_humaneval;;EleutherAI/pile;;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
 openai_humaneval;;GPT-3.5-turbo;0613;model;;;23.79;model-based;https://arxiv.org/abs/2402.15938;16

postprocessing.py

@@ -35,7 +35,7 @@ def main():
             if key != past_key:
                 f.write("\n")
                 past_key = key
-            line = line[:3] + [""] + line[3:]
+            line = line[:3] + line[3:]
             f.write(";".join(line) + "\n")