Add PR links to previous commits

contamination_report.csv

@@ -1,402 +1,402 @@
 Evaluation Dataset;Subset;Contaminated Source;Model or corpus;Train Split;Development Split;Test Split;Approach;Reference;PR
 
 
-UCLNLP/adversarial_qa;adversarialQA;allenai/c4;corpus;;;0.03;data-based;https://arxiv.org/abs/2310.20707;
-UCLNLP/adversarial_qa;adversarialQA;oscar-corpus/OSCAR-2301;corpus;;;0.03;data-based;https://arxiv.org/abs/2310.20707;
-UCLNLP/adversarial_qa;adversarialQA;EleutherAI/pile;corpus;;;0.03;data-based;https://arxiv.org/abs/2310.20707;
-UCLNLP/adversarial_qa;adversarialQA;togethercomputer/RedPajama-Data-V2;corpus;;;0.03;data-based;https://arxiv.org/abs/2310.20707;
-
-UCLNLP/adversarial_qa;dbert;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-UCLNLP/adversarial_qa;dbert;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-UCLNLP/adversarial_qa;dbert;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-UCLNLP/adversarial_qa;dbert;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-
-UCLNLP/adversarial_qa;dbidaf;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-UCLNLP/adversarial_qa;dbidaf;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-UCLNLP/adversarial_qa;dbidaf;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-UCLNLP/adversarial_qa;dbidaf;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-
-UCLNLP/adversarial_qa;droberta;allenai/c4;corpus;;;0.1;data-based;https://arxiv.org/abs/2310.20707;
-UCLNLP/adversarial_qa;droberta;oscar-corpus/OSCAR-2301;corpus;;;0.1;data-based;https://arxiv.org/abs/2310.20707;
-UCLNLP/adversarial_qa;droberta;EleutherAI/pile;corpus;;;0.1;data-based;https://arxiv.org/abs/2310.20707;
+UCLNLP/adversarial_qa;adversarialQA;allenai/c4;corpus;;;0.03;data-based;https://arxiv.org/abs/2310.20707;2
+UCLNLP/adversarial_qa;adversarialQA;oscar-corpus/OSCAR-2301;corpus;;;0.03;data-based;https://arxiv.org/abs/2310.20707;2
+UCLNLP/adversarial_qa;adversarialQA;EleutherAI/pile;corpus;;;0.03;data-based;https://arxiv.org/abs/2310.20707;2
+UCLNLP/adversarial_qa;adversarialQA;togethercomputer/RedPajama-Data-V2;corpus;;;0.03;data-based;https://arxiv.org/abs/2310.20707;2
+
+UCLNLP/adversarial_qa;dbert;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+UCLNLP/adversarial_qa;dbert;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+UCLNLP/adversarial_qa;dbert;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+UCLNLP/adversarial_qa;dbert;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+
+UCLNLP/adversarial_qa;dbidaf;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+UCLNLP/adversarial_qa;dbidaf;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+UCLNLP/adversarial_qa;dbidaf;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+UCLNLP/adversarial_qa;dbidaf;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+
+UCLNLP/adversarial_qa;droberta;allenai/c4;corpus;;;0.1;data-based;https://arxiv.org/abs/2310.20707;2
+UCLNLP/adversarial_qa;droberta;oscar-corpus/OSCAR-2301;corpus;;;0.1;data-based;https://arxiv.org/abs/2310.20707;2
+UCLNLP/adversarial_qa;droberta;EleutherAI/pile;corpus;;;0.1;data-based;https://arxiv.org/abs/2310.20707;2
 UCLNLP/adversarial_qa;droberta;togethercomputer/RedPajama-Data-V2;corpus;;;0.1;data-based;https://arxiv.org/abs/2310.20707
 
-aeslc;;allenai/c4;corpus;;;1.57;data-based;https://arxiv.org/abs/2310.20707;
-aeslc;;oscar-corpus/OSCAR-2301;corpus;;;0.31;data-based;https://arxiv.org/abs/2310.20707;
-aeslc;;EleutherAI/pile;corpus;;;45.49;data-based;https://arxiv.org/abs/2310.20707;
-aeslc;;togethercomputer/RedPajama-Data-V2;corpus;;;0.1;data-based;https://arxiv.org/abs/2310.20707;
-
-amazon_reviews_multi;;allenai/c4;corpus;;;2.28;data-based;https://arxiv.org/abs/2310.20707;
-amazon_reviews_multi;;oscar-corpus/OSCAR-2301;corpus;;;2.10;data-based;https://arxiv.org/abs/2310.20707;
-amazon_reviews_multi;;EleutherAI/pile;corpus;;;1.48;data-based;https://arxiv.org/abs/2310.20707;
-amazon_reviews_multi;;togethercomputer/RedPajama-Data-V2;corpus;;;2.06;data-based;https://arxiv.org/abs/2310.20707;
-
-billsum;;allenai/c4;corpus;;;0.06;data-based;https://arxiv.org/abs/2310.20707;
-billsum;;oscar-corpus/OSCAR-2301;corpus;;;0.06;data-based;https://arxiv.org/abs/2310.20707;
-billsum;;EleutherAI/pile;corpus;;;0.03;data-based;https://arxiv.org/abs/2310.20707;
-billsum;;togethercomputer/RedPajama-Data-V2;corpus;;;0.06;data-based;https://arxiv.org/abs/2310.20707;
-
-cosmos_qa;;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-cosmos_qa;;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-cosmos_qa;;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-cosmos_qa;;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-
-crows_pairs;;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-crows_pairs;;oscar-corpus/OSCAR-2301;corpus;;;0.2;data-based;https://arxiv.org/abs/2310.20707;
-crows_pairs;;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-crows_pairs;;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-
-ibm/duorc;ParaphraseRC;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-ibm/duorc;ParaphraseRC;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-ibm/duorc;ParaphraseRC;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-ibm/duorc;ParaphraseRC;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-
-ibm/duorc;SelfRC;allenai/c4;corpus;;;0.01;data-based;https://arxiv.org/abs/2310.20707;
-ibm/duorc;SelfRC;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-ibm/duorc;SelfRC;EleutherAI/pile;corpus;;;0.02;data-based;https://arxiv.org/abs/2310.20707;
-ibm/duorc;SelfRC;togethercomputer/RedPajama-Data-V2;corpus;;;0.02;data-based;https://arxiv.org/abs/2310.20707;
-
-esnli;;allenai/c4;corpus;;;0.04;data-based;https://arxiv.org/abs/2310.20707;
-esnli;;oscar-corpus/OSCAR-2301;corpus;;;0.08;data-based;https://arxiv.org/abs/2310.20707;
-esnli;;EleutherAI/pile;corpus;;;1.13;data-based;https://arxiv.org/abs/2310.20707;
-esnli;;togethercomputer/RedPajama-Data-V2;corpus;;;1.24;data-based;https://arxiv.org/abs/2310.20707;
-
-gigaword;;allenai/c4;corpus;;;0.15;data-based;https://arxiv.org/abs/2310.20707;
-gigaword;;oscar-corpus/OSCAR-2301;corpus;;;0.36;data-based;https://arxiv.org/abs/2310.20707;
-gigaword;;EleutherAI/pile;corpus;;;1.18;data-based;https://arxiv.org/abs/2310.20707;
-gigaword;;togethercomputer/RedPajama-Data-V2;corpus;;;2.82;data-based;https://arxiv.org/abs/2310.20707;
-
-glue;ax;allenai/c4;corpus;;;1.99;data-based;https://arxiv.org/abs/2310.20707;
-glue;ax;oscar-corpus/OSCAR-2301;corpus;;;1.45;data-based;https://arxiv.org/abs/2310.20707;
-glue;ax;EleutherAI/pile;corpus;;;5.07;data-based;https://arxiv.org/abs/2310.20707;
-glue;ax;togethercomputer/RedPajama-Data-V2;corpus;;;6.16;data-based;https://arxiv.org/abs/2310.20707;
-
-glue;mnli-matched;allenai/c4;corpus;;;1.65;data-based;https://arxiv.org/abs/2310.20707;
-glue;mnli-matched;oscar-corpus/OSCAR-2301;corpus;;;1.77;data-based;https://arxiv.org/abs/2310.20707;
-glue;mnli-matched;EleutherAI/pile;corpus;;;2.17;data-based;https://arxiv.org/abs/2310.20707;
-glue;mnli-matched;togethercomputer/RedPajama-Data-V2;corpus;;;2.26;data-based;https://arxiv.org/abs/2310.20707;
-
-glue;mnli-mismatched;allenai/c4;corpus;;;1.73;data-based;https://arxiv.org/abs/2310.20707;
-glue;mnli-mismatched;oscar-corpus/OSCAR-2301;corpus;;;1.91;data-based;https://arxiv.org/abs/2310.20707;
-glue;mnli-mismatched;EleutherAI/pile;corpus;;;2.11;data-based;https://arxiv.org/abs/2310.20707;
-glue;mnli-mismatched;togethercomputer/RedPajama-Data-V2;corpus;;;2.17;data-based;https://arxiv.org/abs/2310.20707;
-
-glue;mrpc;allenai/c4;corpus;;;0.06;data-based;https://arxiv.org/abs/2310.20707;
-glue;mrpc;oscar-corpus/OSCAR-2301;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;
-glue;mrpc;EleutherAI/pile;corpus;;;0.64;data-based;https://arxiv.org/abs/2310.20707;
-glue;mrpc;togethercomputer/RedPajama-Data-V2;corpus;;;1.16;data-based;https://arxiv.org/abs/2310.20707;
-
-glue;qnli;allenai/c4;corpus;;;0.13;data-based;https://arxiv.org/abs/2310.20707;
-glue;qnli;oscar-corpus/OSCAR-2301;corpus;;;0.04;data-based;https://arxiv.org/abs/2310.20707;
-glue;qnli;EleutherAI/pile;corpus;;;1.48;data-based;https://arxiv.org/abs/2310.20707;
-glue;qnli;togethercomputer/RedPajama-Data-V2;corpus;;;1.21;data-based;https://arxiv.org/abs/2310.20707;
-
-glue;rte;allenai/c4;corpus;;;0.20;data-based;https://arxiv.org/abs/2310.20707;
-glue;rte;oscar-corpus/OSCAR-2301;corpus;;;0.17;data-based;https://arxiv.org/abs/2310.20707;
-glue;rte;EleutherAI/pile;corpus;;;0.13;data-based;https://arxiv.org/abs/2310.20707;
-glue;rte;togethercomputer/RedPajama-Data-V2;corpus;;;67.47;data-based;https://arxiv.org/abs/2310.20707;
-
-glue;stsb;allenai/c4;corpus;;;3.48;data-based;https://arxiv.org/abs/2310.20707;
-glue;stsb;oscar-corpus/OSCAR-2301;corpus;;;3.12;data-based;https://arxiv.org/abs/2310.20707;
-glue;stsb;EleutherAI/pile;corpus;;;11.09;data-based;https://arxiv.org/abs/2310.20707;
-glue;stsb;togethercomputer/RedPajama-Data-V2;corpus;;;9.86;data-based;https://arxiv.org/abs/2310.20707;
-
-glue;wnli;allenai/c4;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;
-glue;wnli;oscar-corpus/OSCAR-2301;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;
-glue;wnli;EleutherAI/pile;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;
-glue;wnli;togethercomputer/RedPajama-Data-V2;corpus;;;2.05;data-based;https://arxiv.org/abs/2310.20707;
-
-head_qa;en;allenai/c4;corpus;;;5.22;data-based;https://arxiv.org/abs/2310.20707;
-head_qa;en;oscar-corpus/OSCAR-2301;corpus;;;5.29;data-based;https://arxiv.org/abs/2310.20707;
-head_qa;en;EleutherAI/pile;corpus;;;5.11;data-based;https://arxiv.org/abs/2310.20707;
-head_qa;en;togethercomputer/RedPajama-Data-V2;corpus;;;5.94;data-based;https://arxiv.org/abs/2310.20707;
-
-health_fact;;allenai/c4;corpus;;;7.53;data-based;https://arxiv.org/abs/2310.20707;
-health_fact;;oscar-corpus/OSCAR-2301;corpus;;;3.40;data-based;https://arxiv.org/abs/2310.20707;
-health_fact;;EleutherAI/pile;corpus;;;1.94;data-based;https://arxiv.org/abs/2310.20707;
-health_fact;;togethercomputer/RedPajama-Data-V2;corpus;;;18.70;data-based;https://arxiv.org/abs/2310.20707;
-
-hlgd;;allenai/c4;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;
-hlgd;;oscar-corpus/OSCAR-2301;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;
-hlgd;;EleutherAI/pile;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;
-hlgd;;togethercomputer/RedPajama-Data-V2;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;
-
-liar;;allenai/c4;corpus;;;29.23;data-based;https://arxiv.org/abs/2310.20707;
-liar;;oscar-corpus/OSCAR-2301;corpus;;;13.95;data-based;https://arxiv.org/abs/2310.20707;
-liar;;EleutherAI/pile;corpus;;;10.91;data-based;https://arxiv.org/abs/2310.20707;
-liar;;togethercomputer/RedPajama-Data-V2;corpus;;;45.05;data-based;https://arxiv.org/abs/2310.20707;
-
-math_dataset;algebra__linear_1d;allenai/c4;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;
-math_dataset;algebra__linear_1d;oscar-corpus/OSCAR-2301;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;
-math_dataset;algebra__linear_1d;EleutherAI/pile;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;
-math_dataset;algebra__linear_1d;togethercomputer/RedPajama-Data-V2;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;
-
-math_dataset;algebra__linear_2d;allenai/c4;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;
-math_dataset;algebra__linear_2d;oscar-corpus/OSCAR-2301;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;
-math_dataset;algebra__linear_2d;EleutherAI/pile;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;
-math_dataset;algebra__linear_2d;togethercomputer/RedPajama-Data-V2;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;
-
-math_dataset;algebra__linear_2d_composed;allenai/c4;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;
-math_dataset;algebra__linear_2d_composed;oscar-corpus/OSCAR-2301;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;
-math_dataset;algebra__linear_2d_composed;EleutherAI/pile;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;
-math_dataset;algebra__linear_2d_composed;togethercomputer/RedPajama-Data-V2;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;
-
-math_qa;;allenai/c4;corpus;;;0.34;data-based;https://arxiv.org/abs/2310.20707;
-math_qa;;oscar-corpus/OSCAR-2301;corpus;;;0.03;data-based;https://arxiv.org/abs/2310.20707;
-math_qa;;EleutherAI/pile;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;
-math_qa;;togethercomputer/RedPajama-Data-V2;corpus;;;0.07;data-based;https://arxiv.org/abs/2310.20707;
-
-mc_taco;;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-mc_taco;;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-mc_taco;;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-mc_taco;;togethercomputer/RedPajama-Data-V2;corpus;;;0.14;data-based;https://arxiv.org/abs/2310.20707;
-
-mocha;;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-mocha;;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-mocha;;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-mocha;;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-
-openai_humaneval;;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-openai_humaneval;;oscar-corpus/OSCAR-2301;corpus;;;1.22;data-based;https://arxiv.org/abs/2310.20707;
-openai_humaneval;;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-openai_humaneval;;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-
-paws-x;en;allenai/c4;corpus;;;0.05;data-based;https://arxiv.org/abs/2310.20707;
-paws-x;en;oscar-corpus/OSCAR-2301;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;
-paws-x;en;EleutherAI/pile;corpus;;;0.15;data-based;https://arxiv.org/abs/2310.20707;
-paws-x;en;togethercomputer/RedPajama-Data-V2;corpus;;;0.2;data-based;https://arxiv.org/abs/2310.20707;
-
-paws;labeled_final;allenai/c4;corpus;;;0.05;data-based;https://arxiv.org/abs/2310.20707;
-paws;labeled_final;oscar-corpus/OSCAR-2301;corpus;;;0.04;data-based;https://arxiv.org/abs/2310.20707;
-paws;labeled_final;EleutherAI/pile;corpus;;;0.25;data-based;https://arxiv.org/abs/2310.20707;
-paws;labeled_final;togethercomputer/RedPajama-Data-V2;corpus;;;0.35;data-based;https://arxiv.org/abs/2310.20707;
-
-piqa;;allenai/c4;corpus;;;0.06;data-based;https://arxiv.org/abs/2310.20707;
-piqa;;oscar-corpus/OSCAR-2301;corpus;;;0.03;data-based;https://arxiv.org/abs/2310.20707;
-piqa;;EleutherAI/pile;corpus;;;0.06;data-based;https://arxiv.org/abs/2310.20707;
-piqa;;togethercomputer/RedPajama-Data-V2;corpus;;;0.13;data-based;https://arxiv.org/abs/2310.20707;
-
-race;all;allenai/c4;corpus;;;0.14;data-based;https://arxiv.org/abs/2310.20707;
-race;all;oscar-corpus/OSCAR-2301;corpus;;;0.06;data-based;https://arxiv.org/abs/2310.20707;
-race;all;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-race;all;togethercomputer/RedPajama-Data-V2;corpus;;;0.28;data-based;https://arxiv.org/abs/2310.20707;
-
-race;high;allenai/c4;corpus;;;0.11;data-based;https://arxiv.org/abs/2310.20707;
-race;high;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-race;high;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-race;high;togethercomputer/RedPajama-Data-V2;corpus;;;0.26;data-based;https://arxiv.org/abs/2310.20707;
-
-race;middle;allenai/c4;corpus;;;0.21;data-based;https://arxiv.org/abs/2310.20707;
-race;middle;oscar-corpus/OSCAR-2301;corpus;;;0.21;data-based;https://arxiv.org/abs/2310.20707;
-race;middle;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-race;middle;togethercomputer/RedPajama-Data-V2;corpus;;;0.35;data-based;https://arxiv.org/abs/2310.20707;
-
-allenai/ropes;;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-allenai/ropes;;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-allenai/ropes;;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-allenai/ropes;;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-
-samsum;;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-samsum;;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-samsum;;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-samsum;;togethercomputer/RedPajama-Data-V2;corpus;;;0.12;data-based;https://arxiv.org/abs/2310.20707;
-
-scan;addprim_jump;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-scan;addprim_jump;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-scan;addprim_jump;EleutherAI/pile;corpus;;;0.05;data-based;https://arxiv.org/abs/2310.20707;
-scan;addprim_jump;togethercomputer/RedPajama-Data-V2;corpus;;;0.16;data-based;https://arxiv.org/abs/2310.20707;
-
-scan;addprim_turn;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-scan;addprim_turn;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-scan;addprim_turn;EleutherAI/pile;corpus;;;0.08;data-based;https://arxiv.org/abs/2310.20707;
-scan;addprim_turn;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-
-scan;filler_num0;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-scan;filler_num0;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-scan;filler_num0;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-scan;filler_num0;togethercomputer/RedPajama-Data-V2;corpus;;;0.9;data-based;https://arxiv.org/abs/2310.20707;
-
-scan;length;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-scan;length;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-scan;length;EleutherAI/pile;corpus;;;0.03;data-based;https://arxiv.org/abs/2310.20707;
-scan;length;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-
-scan;simple;allenai/c4;corpus;;;0.02;data-based;https://arxiv.org/abs/2310.20707;
-scan;simple;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-scan;simple;EleutherAI/pile;corpus;;;0.1;data-based;https://arxiv.org/abs/2310.20707;
-scan;simple;togethercomputer/RedPajama-Data-V2;corpus;;;0.26;data-based;https://arxiv.org/abs/2310.20707;
-
-scan;template_around;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-scan;template_around;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-scan;template_around;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-scan;template_around;togethercomputer/RedPajama-Data-V2;corpus;;;0.18;data-based;https://arxiv.org/abs/2310.20707;
-
-scan;template_jump;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-scan;template_jump;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-scan;template_jump;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-scan;template_jump;togethercomputer/RedPajama-Data-V2;corpus;;;0.9;data-based;https://arxiv.org/abs/2310.20707;
-
-scan;template_opposite;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-scan;template_opposite;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-scan;template_opposite;EleutherAI/pile;corpus;;;0.04;data-based;https://arxiv.org/abs/2310.20707;
-scan;template_opposite;togethercomputer/RedPajama-Data-V2;corpus;;;0.16;data-based;https://arxiv.org/abs/2310.20707;
-
-scan;template_right;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-scan;template_right;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-scan;template_right;EleutherAI/pile;corpus;;;0.11;data-based;https://arxiv.org/abs/2310.20707;
-scan;template_right;togethercomputer/RedPajama-Data-V2;corpus;;;0.16;data-based;https://arxiv.org/abs/2310.20707;
-
-allenai/scicite;;allenai/c4;corpus;;;1.78;data-based;https://arxiv.org/abs/2310.20707;
-allenai/scicite;;oscar-corpus/OSCAR-2301;corpus;;;1.51;data-based;https://arxiv.org/abs/2310.20707;
-allenai/scicite;;EleutherAI/pile;corpus;;;0.86;data-based;https://arxiv.org/abs/2310.20707;
-allenai/scicite;;togethercomputer/RedPajama-Data-V2;corpus;;;1.72;data-based;https://arxiv.org/abs/2310.20707;
-
-scitail;snli_format;allenai/c4;corpus;;;0.09;data-based;https://arxiv.org/abs/2310.20707;
-scitail;snli_format;oscar-corpus/OSCAR-2301;corpus;;;0.38;data-based;https://arxiv.org/abs/2310.20707;
-scitail;snli_format;EleutherAI/pile;corpus;;;0.28;data-based;https://arxiv.org/abs/2310.20707;
-scitail;snli_format;togethercomputer/RedPajama-Data-V2;corpus;;;0.71;data-based;https://arxiv.org/abs/2310.20707;
-
-scitail;tsv_format;allenai/c4;corpus;;;0.09;data-based;https://arxiv.org/abs/2310.20707;
-scitail;tsv_format;oscar-corpus/OSCAR-2301;corpus;;;0.38;data-based;https://arxiv.org/abs/2310.20707;
-scitail;tsv_format;EleutherAI/pile;corpus;;;0.28;data-based;https://arxiv.org/abs/2310.20707;
-scitail;tsv_format;togethercomputer/RedPajama-Data-V2;corpus;;;0.71;data-based;https://arxiv.org/abs/2310.20707;
-
-sem_eval_2014_task_1;;allenai/c4;corpus;;;0.35;data-based;https://arxiv.org/abs/2310.20707;
-sem_eval_2014_task_1;;oscar-corpus/OSCAR-2301;corpus;;;0.18;data-based;https://arxiv.org/abs/2310.20707;
-sem_eval_2014_task_1;;EleutherAI/pile;corpus;;;4.89;data-based;https://arxiv.org/abs/2310.20707;
-sem_eval_2014_task_1;;togethercomputer/RedPajama-Data-V2;corpus;;;52.81;data-based;https://arxiv.org/abs/2310.20707;
-
-sick;;allenai/c4;corpus;;;0.31;data-based;https://arxiv.org/abs/2310.20707;
-sick;;oscar-corpus/OSCAR-2301;corpus;;;0.18;data-based;https://arxiv.org/abs/2310.20707;
-sick;;EleutherAI/pile;corpus;;;4.79;data-based;https://arxiv.org/abs/2310.20707;
-sick;;togethercomputer/RedPajama-Data-V2;corpus;;;52.61;data-based;https://arxiv.org/abs/2310.20707;
-
-snli;;allenai/c4;corpus;;;0.04;data-based;https://arxiv.org/abs/2310.20707;
-snli;;oscar-corpus/OSCAR-2301;corpus;;;0.08;data-based;https://arxiv.org/abs/2310.20707;
-snli;;EleutherAI/pile;corpus;;;1.11;data-based;https://arxiv.org/abs/2310.20707;
-snli;;togethercomputer/RedPajama-Data-V2;corpus;;;1.22;data-based;https://arxiv.org/abs/2310.20707;
-
-squadshifts;amazon;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-squadshifts;amazon;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-squadshifts;amazon;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-squadshifts;amazon;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-
-squadshifts;new_wiki;allenai/c4;corpus;;;0.01;data-based;https://arxiv.org/abs/2310.20707;
-squadshifts;new_wiki;oscar-corpus/OSCAR-2301;corpus;;;0.01;data-based;https://arxiv.org/abs/2310.20707;
-squadshifts;new_wiki;EleutherAI/pile;corpus;;;0.01;data-based;https://arxiv.org/abs/2310.20707;
-squadshifts;new_wiki;togethercomputer/RedPajama-Data-V2;corpus;;;0.03;data-based;https://arxiv.org/abs/2310.20707;
-
-squadshifts;nyt;allenai/c4;corpus;;;0.01;data-based;https://arxiv.org/abs/2310.20707;
-squadshifts;nyt;oscar-corpus/OSCAR-2301;corpus;;;0.03;data-based;https://arxiv.org/abs/2310.20707;
-squadshifts;nyt;EleutherAI/pile;corpus;;;0.02;data-based;https://arxiv.org/abs/2310.20707;
-squadshifts;nyt;togethercomputer/RedPajama-Data-V2;corpus;;;0.04;data-based;https://arxiv.org/abs/2310.20707;
-
-stsb_multi_mt;;allenai/c4;corpus;;;3.48;data-based;https://arxiv.org/abs/2310.20707;
-stsb_multi_mt;;oscar-corpus/OSCAR-2301;corpus;;;3.12;data-based;https://arxiv.org/abs/2310.20707;
-stsb_multi_mt;;EleutherAI/pile;corpus;;;11.09;data-based;https://arxiv.org/abs/2310.20707;
-stsb_multi_mt;;togethercomputer/RedPajama-Data-V2;corpus;;;9.86;data-based;https://arxiv.org/abs/2310.20707;
-
-subjqa;books;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-subjqa;books;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-subjqa;books;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-subjqa;books;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-
-subjqa;grocery;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-subjqa;grocery;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-subjqa;grocery;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-subjqa;grocery;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-
-subjqa;movies;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-subjqa;movies;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-subjqa;movies;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-subjqa;movies;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-
-subjqa;restaurants;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-subjqa;restaurants;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-subjqa;restaurants;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-subjqa;restaurants;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-
-super_glue;axb;allenai/c4;corpus;;;1.99;data-based;https://arxiv.org/abs/2310.20707;
-super_glue;axb;oscar-corpus/OSCAR-2301;corpus;;;1.45;data-based;https://arxiv.org/abs/2310.20707;
-super_glue;axb;EleutherAI/pile;corpus;;;5.07;data-based;https://arxiv.org/abs/2310.20707;
-super_glue;axb;togethercomputer/RedPajama-Data-V2;corpus;;;6.16;data-based;https://arxiv.org/abs/2310.20707;
-
-super_glue;axg;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-super_glue;axg;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-super_glue;axg;EleutherAI/pile;corpus;;;0.28;data-based;https://arxiv.org/abs/2310.20707;
-super_glue;axg;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-
-super_glue;boolq;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-super_glue;boolq;oscar-corpus/OSCAR-2301;corpus;;;3.05;data-based;https://arxiv.org/abs/2310.20707;
-super_glue;boolq;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-super_glue;boolq;togethercomputer/RedPajama-Data-V2;corpus;;;0.03;data-based;https://arxiv.org/abs/2310.20707;
-
-super_glue;cb;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-super_glue;cb;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-super_glue;cb;EleutherAI/pile;corpus;;;2.0;data-based;https://arxiv.org/abs/2310.20707;
-super_glue;cb;togethercomputer/RedPajama-Data-V2;corpus;;;1.6;data-based;https://arxiv.org/abs/2310.20707;
-
-super_glue;copa;allenai/c4;corpus;;;0.6;data-based;https://arxiv.org/abs/2310.20707;
-super_glue;copa;oscar-corpus/OSCAR-2301;corpus;;;1.0;data-based;https://arxiv.org/abs/2310.20707;
-super_glue;copa;EleutherAI/pile;corpus;;;1.2;data-based;https://arxiv.org/abs/2310.20707;
-super_glue;copa;togethercomputer/RedPajama-Data-V2;corpus;;;100.0;data-based;https://arxiv.org/abs/2310.20707;
-
-super_glue;multirc;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-super_glue;multirc;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-super_glue;multirc;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-super_glue;multirc;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-
-super_glue;record;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-super_glue;record;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-super_glue;record;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-super_glue;record;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-
-super_glue;rte;allenai/c4;corpus;;;0.2;data-based;https://arxiv.org/abs/2310.20707;
-super_glue;rte;oscar-corpus/OSCAR-2301;corpus;;;0.17;data-based;https://arxiv.org/abs/2310.20707;
-super_glue;rte;EleutherAI/pile;corpus;;;0.13;data-based;https://arxiv.org/abs/2310.20707;
-super_glue;rte;togethercomputer/RedPajama-Data-V2;corpus;;;67.47;data-based;https://arxiv.org/abs/2310.20707;
-
-super_glue;wic;allenai/c4;corpus;;;64.43;data-based;https://arxiv.org/abs/2310.20707;
-super_glue;wic;oscar-corpus/OSCAR-2301;corpus;;;49.43;data-based;https://arxiv.org/abs/2310.20707;
-super_glue;wic;EleutherAI/pile;corpus;;;18.57;data-based;https://arxiv.org/abs/2310.20707;
-super_glue;wic;togethercomputer/RedPajama-Data-V2;corpus;;;60.21;data-based;https://arxiv.org/abs/2310.20707;
-
-swag;regular;allenai/c4;corpus;;;2.48;data-based;https://arxiv.org/abs/2310.20707;
-swag;regular;oscar-corpus/OSCAR-2301;corpus;;;1.65;data-based;https://arxiv.org/abs/2310.20707;
-swag;regular;EleutherAI/pile;corpus;;;2.21;data-based;https://arxiv.org/abs/2310.20707;
-swag;regular;togethercomputer/RedPajama-Data-V2;corpus;;;2.79;data-based;https://arxiv.org/abs/2310.20707;
-
-tab_fact;tab_fact;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-tab_fact;tab_fact;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-tab_fact;tab_fact;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-tab_fact;tab_fact;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-
-wiki_qa;;allenai/c4;corpus;;;0.24;data-based;https://arxiv.org/abs/2310.20707;
-wiki_qa;;oscar-corpus/OSCAR-2301;corpus;;;0.18;data-based;https://arxiv.org/abs/2310.20707;
-wiki_qa;;EleutherAI/pile;corpus;;;0.19;data-based;https://arxiv.org/abs/2310.20707;
-wiki_qa;;togethercomputer/RedPajama-Data-V2;corpus;;;0.91;data-based;https://arxiv.org/abs/2310.20707;
-
-winograd_wsc;wsc273;allenai/c4;corpus;;;29.30;data-based;https://arxiv.org/abs/2310.20707;
-winograd_wsc;wsc273;oscar-corpus/OSCAR-2301;corpus;;;30.40;data-based;https://arxiv.org/abs/2310.20707;
-winograd_wsc;wsc273;EleutherAI/pile;corpus;;;32.23;data-based;https://arxiv.org/abs/2310.20707;
-winograd_wsc;wsc273;togethercomputer/RedPajama-Data-V2;corpus;;;58.24;data-based;https://arxiv.org/abs/2310.20707;
-
-winogrande;winogrande_xl;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-winogrande;winogrande_xl;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-winogrande;winogrande_xl;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-winogrande;winogrande_xl;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-
-xnli;en;allenai/c4;corpus;;;0.12;data-based;https://arxiv.org/abs/2310.20707;
-xnli;en;oscar-corpus/OSCAR-2301;corpus;;;0.24;data-based;https://arxiv.org/abs/2310.20707;
-xnli;en;EleutherAI/pile;corpus;;;0.36;data-based;https://arxiv.org/abs/2310.20707;
-xnli;en;togethercomputer/RedPajama-Data-V2;corpus;;;0.44;data-based;https://arxiv.org/abs/2310.20707;
-
-xsum;;allenai/c4;corpus;;;2.13;data-based;https://arxiv.org/abs/2310.20707;
-xsum;;oscar-corpus/OSCAR-2301;corpus;;;0.13;data-based;https://arxiv.org/abs/2310.20707;
-xsum;;EleutherAI/pile;corpus;;;3.30;data-based;https://arxiv.org/abs/2310.20707;
-xsum;;togethercomputer/RedPajama-Data-V2;corpus;;;4.28;data-based;https://arxiv.org/abs/2310.20707;
-
-zest;;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-zest;;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-zest;;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
-zest;;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;
+aeslc;;allenai/c4;corpus;;;1.57;data-based;https://arxiv.org/abs/2310.20707;2
+aeslc;;oscar-corpus/OSCAR-2301;corpus;;;0.31;data-based;https://arxiv.org/abs/2310.20707;2
+aeslc;;EleutherAI/pile;corpus;;;45.49;data-based;https://arxiv.org/abs/2310.20707;2
+aeslc;;togethercomputer/RedPajama-Data-V2;corpus;;;0.1;data-based;https://arxiv.org/abs/2310.20707;2
+
+amazon_reviews_multi;;allenai/c4;corpus;;;2.28;data-based;https://arxiv.org/abs/2310.20707;2
+amazon_reviews_multi;;oscar-corpus/OSCAR-2301;corpus;;;2.10;data-based;https://arxiv.org/abs/2310.20707;2
+amazon_reviews_multi;;EleutherAI/pile;corpus;;;1.48;data-based;https://arxiv.org/abs/2310.20707;2
+amazon_reviews_multi;;togethercomputer/RedPajama-Data-V2;corpus;;;2.06;data-based;https://arxiv.org/abs/2310.20707;2
+
+billsum;;allenai/c4;corpus;;;0.06;data-based;https://arxiv.org/abs/2310.20707;2
+billsum;;oscar-corpus/OSCAR-2301;corpus;;;0.06;data-based;https://arxiv.org/abs/2310.20707;2
+billsum;;EleutherAI/pile;corpus;;;0.03;data-based;https://arxiv.org/abs/2310.20707;2
+billsum;;togethercomputer/RedPajama-Data-V2;corpus;;;0.06;data-based;https://arxiv.org/abs/2310.20707;2
+
+cosmos_qa;;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+cosmos_qa;;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+cosmos_qa;;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+cosmos_qa;;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+
+crows_pairs;;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+crows_pairs;;oscar-corpus/OSCAR-2301;corpus;;;0.2;data-based;https://arxiv.org/abs/2310.20707;2
+crows_pairs;;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+crows_pairs;;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+
+ibm/duorc;ParaphraseRC;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+ibm/duorc;ParaphraseRC;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+ibm/duorc;ParaphraseRC;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+ibm/duorc;ParaphraseRC;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+
+ibm/duorc;SelfRC;allenai/c4;corpus;;;0.01;data-based;https://arxiv.org/abs/2310.20707;2
+ibm/duorc;SelfRC;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+ibm/duorc;SelfRC;EleutherAI/pile;corpus;;;0.02;data-based;https://arxiv.org/abs/2310.20707;2
+ibm/duorc;SelfRC;togethercomputer/RedPajama-Data-V2;corpus;;;0.02;data-based;https://arxiv.org/abs/2310.20707;2
+
+esnli;;allenai/c4;corpus;;;0.04;data-based;https://arxiv.org/abs/2310.20707;2
+esnli;;oscar-corpus/OSCAR-2301;corpus;;;0.08;data-based;https://arxiv.org/abs/2310.20707;2
+esnli;;EleutherAI/pile;corpus;;;1.13;data-based;https://arxiv.org/abs/2310.20707;2
+esnli;;togethercomputer/RedPajama-Data-V2;corpus;;;1.24;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
+gigaword;;EleutherAI/pile;corpus;;;1.18;data-based;https://arxiv.org/abs/2310.20707;2
+gigaword;;togethercomputer/RedPajama-Data-V2;corpus;;;2.82;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;EleutherAI/pile;corpus;;;5.07;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;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
+nyu-mll/glue;mnli-matched;EleutherAI/pile;corpus;;;2.17;data-based;https://arxiv.org/abs/2310.20707;2
+nyu-mll/glue;mnli-matched;togethercomputer/RedPajama-Data-V2;corpus;;;2.26;data-based;https://arxiv.org/abs/2310.20707;2
+
+nyu-mll/glue;mnli-mismatched;allenai/c4;corpus;;;1.73;data-based;https://arxiv.org/abs/2310.20707;2
+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;EleutherAI/pile;corpus;;;2.11;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;mrpc;allenai/c4;corpus;;;0.06;data-based;https://arxiv.org/abs/2310.20707;2
+nyu-mll/glue;mrpc;oscar-corpus/OSCAR-2301;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;2
+nyu-mll/glue;mrpc;EleutherAI/pile;corpus;;;0.64;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;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;EleutherAI/pile;corpus;;;1.48;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;rte;allenai/c4;corpus;;;0.20;data-based;https://arxiv.org/abs/2310.20707;2
+nyu-mll/glue;rte;oscar-corpus/OSCAR-2301;corpus;;;0.17;data-based;https://arxiv.org/abs/2310.20707;2
+nyu-mll/glue;rte;EleutherAI/pile;corpus;;;0.13;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;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;EleutherAI/pile;corpus;;;11.09;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;wnli;allenai/c4;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;2
+nyu-mll/glue;wnli;oscar-corpus/OSCAR-2301;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;2
+nyu-mll/glue;wnli;EleutherAI/pile;corpus;;;0.00;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
+
+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
+head_qa;en;EleutherAI/pile;corpus;;;5.11;data-based;https://arxiv.org/abs/2310.20707;2
+head_qa;en;togethercomputer/RedPajama-Data-V2;corpus;;;5.94;data-based;https://arxiv.org/abs/2310.20707;2
+
+health_fact;;allenai/c4;corpus;;;7.53;data-based;https://arxiv.org/abs/2310.20707;2
+health_fact;;oscar-corpus/OSCAR-2301;corpus;;;3.40;data-based;https://arxiv.org/abs/2310.20707;2
+health_fact;;EleutherAI/pile;corpus;;;1.94;data-based;https://arxiv.org/abs/2310.20707;2
+health_fact;;togethercomputer/RedPajama-Data-V2;corpus;;;18.70;data-based;https://arxiv.org/abs/2310.20707;2
+
+hlgd;;allenai/c4;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;2
+hlgd;;oscar-corpus/OSCAR-2301;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;2
+hlgd;;EleutherAI/pile;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;2
+hlgd;;togethercomputer/RedPajama-Data-V2;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;2
+
+liar;;allenai/c4;corpus;;;29.23;data-based;https://arxiv.org/abs/2310.20707;2
+liar;;oscar-corpus/OSCAR-2301;corpus;;;13.95;data-based;https://arxiv.org/abs/2310.20707;2
+liar;;EleutherAI/pile;corpus;;;10.91;data-based;https://arxiv.org/abs/2310.20707;2
+liar;;togethercomputer/RedPajama-Data-V2;corpus;;;45.05;data-based;https://arxiv.org/abs/2310.20707;2
+
+math_dataset;algebra__linear_1d;allenai/c4;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;2
+math_dataset;algebra__linear_1d;oscar-corpus/OSCAR-2301;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;2
+math_dataset;algebra__linear_1d;EleutherAI/pile;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;2
+math_dataset;algebra__linear_1d;togethercomputer/RedPajama-Data-V2;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;2
+
+math_dataset;algebra__linear_2d;allenai/c4;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;2
+math_dataset;algebra__linear_2d;oscar-corpus/OSCAR-2301;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;2
+math_dataset;algebra__linear_2d;EleutherAI/pile;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;2
+math_dataset;algebra__linear_2d;togethercomputer/RedPajama-Data-V2;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;2
+
+math_dataset;algebra__linear_2d_composed;allenai/c4;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;2
+math_dataset;algebra__linear_2d_composed;oscar-corpus/OSCAR-2301;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;2
+math_dataset;algebra__linear_2d_composed;EleutherAI/pile;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;2
+math_dataset;algebra__linear_2d_composed;togethercomputer/RedPajama-Data-V2;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;2
+
+math_qa;;allenai/c4;corpus;;;0.34;data-based;https://arxiv.org/abs/2310.20707;2
+math_qa;;oscar-corpus/OSCAR-2301;corpus;;;0.03;data-based;https://arxiv.org/abs/2310.20707;2
+math_qa;;EleutherAI/pile;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;2
+math_qa;;togethercomputer/RedPajama-Data-V2;corpus;;;0.07;data-based;https://arxiv.org/abs/2310.20707;2
+
+mc_taco;;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+mc_taco;;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+mc_taco;;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+mc_taco;;togethercomputer/RedPajama-Data-V2;corpus;;;0.14;data-based;https://arxiv.org/abs/2310.20707;2
+
+mocha;;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+mocha;;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+mocha;;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+mocha;;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+
+openai_humaneval;;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+openai_humaneval;;oscar-corpus/OSCAR-2301;corpus;;;1.22;data-based;https://arxiv.org/abs/2310.20707;2
+openai_humaneval;;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+openai_humaneval;;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+
+paws-x;en;allenai/c4;corpus;;;0.05;data-based;https://arxiv.org/abs/2310.20707;2
+paws-x;en;oscar-corpus/OSCAR-2301;corpus;;;0.00;data-based;https://arxiv.org/abs/2310.20707;2
+paws-x;en;EleutherAI/pile;corpus;;;0.15;data-based;https://arxiv.org/abs/2310.20707;2
+paws-x;en;togethercomputer/RedPajama-Data-V2;corpus;;;0.2;data-based;https://arxiv.org/abs/2310.20707;2
+
+paws;labeled_final;allenai/c4;corpus;;;0.05;data-based;https://arxiv.org/abs/2310.20707;2
+paws;labeled_final;oscar-corpus/OSCAR-2301;corpus;;;0.04;data-based;https://arxiv.org/abs/2310.20707;2
+paws;labeled_final;EleutherAI/pile;corpus;;;0.25;data-based;https://arxiv.org/abs/2310.20707;2
+paws;labeled_final;togethercomputer/RedPajama-Data-V2;corpus;;;0.35;data-based;https://arxiv.org/abs/2310.20707;2
+
+piqa;;allenai/c4;corpus;;;0.06;data-based;https://arxiv.org/abs/2310.20707;2
+piqa;;oscar-corpus/OSCAR-2301;corpus;;;0.03;data-based;https://arxiv.org/abs/2310.20707;2
+piqa;;EleutherAI/pile;corpus;;;0.06;data-based;https://arxiv.org/abs/2310.20707;2
+piqa;;togethercomputer/RedPajama-Data-V2;corpus;;;0.13;data-based;https://arxiv.org/abs/2310.20707;2
+
+race;all;allenai/c4;corpus;;;0.14;data-based;https://arxiv.org/abs/2310.20707;2
+race;all;oscar-corpus/OSCAR-2301;corpus;;;0.06;data-based;https://arxiv.org/abs/2310.20707;2
+race;all;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+race;all;togethercomputer/RedPajama-Data-V2;corpus;;;0.28;data-based;https://arxiv.org/abs/2310.20707;2
+
+race;high;allenai/c4;corpus;;;0.11;data-based;https://arxiv.org/abs/2310.20707;2
+race;high;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+race;high;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+race;high;togethercomputer/RedPajama-Data-V2;corpus;;;0.26;data-based;https://arxiv.org/abs/2310.20707;2
+
+race;middle;allenai/c4;corpus;;;0.21;data-based;https://arxiv.org/abs/2310.20707;2
+race;middle;oscar-corpus/OSCAR-2301;corpus;;;0.21;data-based;https://arxiv.org/abs/2310.20707;2
+race;middle;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+race;middle;togethercomputer/RedPajama-Data-V2;corpus;;;0.35;data-based;https://arxiv.org/abs/2310.20707;2
+
+allenai/ropes;;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+allenai/ropes;;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+allenai/ropes;;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+allenai/ropes;;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+
+samsum;;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+samsum;;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+samsum;;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+samsum;;togethercomputer/RedPajama-Data-V2;corpus;;;0.12;data-based;https://arxiv.org/abs/2310.20707;2
+
+scan;addprim_jump;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+scan;addprim_jump;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+scan;addprim_jump;EleutherAI/pile;corpus;;;0.05;data-based;https://arxiv.org/abs/2310.20707;2
+scan;addprim_jump;togethercomputer/RedPajama-Data-V2;corpus;;;0.16;data-based;https://arxiv.org/abs/2310.20707;2
+
+scan;addprim_turn;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+scan;addprim_turn;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+scan;addprim_turn;EleutherAI/pile;corpus;;;0.08;data-based;https://arxiv.org/abs/2310.20707;2
+scan;addprim_turn;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+
+scan;filler_num0;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+scan;filler_num0;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+scan;filler_num0;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+scan;filler_num0;togethercomputer/RedPajama-Data-V2;corpus;;;0.9;data-based;https://arxiv.org/abs/2310.20707;2
+
+scan;length;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+scan;length;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+scan;length;EleutherAI/pile;corpus;;;0.03;data-based;https://arxiv.org/abs/2310.20707;2
+scan;length;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+
+scan;simple;allenai/c4;corpus;;;0.02;data-based;https://arxiv.org/abs/2310.20707;2
+scan;simple;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+scan;simple;EleutherAI/pile;corpus;;;0.1;data-based;https://arxiv.org/abs/2310.20707;2
+scan;simple;togethercomputer/RedPajama-Data-V2;corpus;;;0.26;data-based;https://arxiv.org/abs/2310.20707;2
+
+scan;template_around;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+scan;template_around;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+scan;template_around;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+scan;template_around;togethercomputer/RedPajama-Data-V2;corpus;;;0.18;data-based;https://arxiv.org/abs/2310.20707;2
+
+scan;template_jump;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+scan;template_jump;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+scan;template_jump;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+scan;template_jump;togethercomputer/RedPajama-Data-V2;corpus;;;0.9;data-based;https://arxiv.org/abs/2310.20707;2
+
+scan;template_opposite;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+scan;template_opposite;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+scan;template_opposite;EleutherAI/pile;corpus;;;0.04;data-based;https://arxiv.org/abs/2310.20707;2
+scan;template_opposite;togethercomputer/RedPajama-Data-V2;corpus;;;0.16;data-based;https://arxiv.org/abs/2310.20707;2
+
+scan;template_right;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+scan;template_right;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+scan;template_right;EleutherAI/pile;corpus;;;0.11;data-based;https://arxiv.org/abs/2310.20707;2
+scan;template_right;togethercomputer/RedPajama-Data-V2;corpus;;;0.16;data-based;https://arxiv.org/abs/2310.20707;2
+
+allenai/scicite;;allenai/c4;corpus;;;1.78;data-based;https://arxiv.org/abs/2310.20707;2
+allenai/scicite;;oscar-corpus/OSCAR-2301;corpus;;;1.51;data-based;https://arxiv.org/abs/2310.20707;2
+allenai/scicite;;EleutherAI/pile;corpus;;;0.86;data-based;https://arxiv.org/abs/2310.20707;2
+allenai/scicite;;togethercomputer/RedPajama-Data-V2;corpus;;;1.72;data-based;https://arxiv.org/abs/2310.20707;2
+
+scitail;snli_format;allenai/c4;corpus;;;0.09;data-based;https://arxiv.org/abs/2310.20707;2
+scitail;snli_format;oscar-corpus/OSCAR-2301;corpus;;;0.38;data-based;https://arxiv.org/abs/2310.20707;2
+scitail;snli_format;EleutherAI/pile;corpus;;;0.28;data-based;https://arxiv.org/abs/2310.20707;2
+scitail;snli_format;togethercomputer/RedPajama-Data-V2;corpus;;;0.71;data-based;https://arxiv.org/abs/2310.20707;2
+
+scitail;tsv_format;allenai/c4;corpus;;;0.09;data-based;https://arxiv.org/abs/2310.20707;2
+scitail;tsv_format;oscar-corpus/OSCAR-2301;corpus;;;0.38;data-based;https://arxiv.org/abs/2310.20707;2
+scitail;tsv_format;EleutherAI/pile;corpus;;;0.28;data-based;https://arxiv.org/abs/2310.20707;2
+scitail;tsv_format;togethercomputer/RedPajama-Data-V2;corpus;;;0.71;data-based;https://arxiv.org/abs/2310.20707;2
+
+sem_eval_2014_task_1;;allenai/c4;corpus;;;0.35;data-based;https://arxiv.org/abs/2310.20707;2
+sem_eval_2014_task_1;;oscar-corpus/OSCAR-2301;corpus;;;0.18;data-based;https://arxiv.org/abs/2310.20707;2
+sem_eval_2014_task_1;;EleutherAI/pile;corpus;;;4.89;data-based;https://arxiv.org/abs/2310.20707;2
+sem_eval_2014_task_1;;togethercomputer/RedPajama-Data-V2;corpus;;;52.81;data-based;https://arxiv.org/abs/2310.20707;2
+
+sick;;allenai/c4;corpus;;;0.31;data-based;https://arxiv.org/abs/2310.20707;2
+sick;;oscar-corpus/OSCAR-2301;corpus;;;0.18;data-based;https://arxiv.org/abs/2310.20707;2
+sick;;EleutherAI/pile;corpus;;;4.79;data-based;https://arxiv.org/abs/2310.20707;2
+sick;;togethercomputer/RedPajama-Data-V2;corpus;;;52.61;data-based;https://arxiv.org/abs/2310.20707;2
+
+snli;;allenai/c4;corpus;;;0.04;data-based;https://arxiv.org/abs/2310.20707;2
+snli;;oscar-corpus/OSCAR-2301;corpus;;;0.08;data-based;https://arxiv.org/abs/2310.20707;2
+snli;;EleutherAI/pile;corpus;;;1.11;data-based;https://arxiv.org/abs/2310.20707;2
+snli;;togethercomputer/RedPajama-Data-V2;corpus;;;1.22;data-based;https://arxiv.org/abs/2310.20707;2
+
+squadshifts;amazon;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+squadshifts;amazon;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+squadshifts;amazon;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+squadshifts;amazon;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+
+squadshifts;new_wiki;allenai/c4;corpus;;;0.01;data-based;https://arxiv.org/abs/2310.20707;2
+squadshifts;new_wiki;oscar-corpus/OSCAR-2301;corpus;;;0.01;data-based;https://arxiv.org/abs/2310.20707;2
+squadshifts;new_wiki;EleutherAI/pile;corpus;;;0.01;data-based;https://arxiv.org/abs/2310.20707;2
+squadshifts;new_wiki;togethercomputer/RedPajama-Data-V2;corpus;;;0.03;data-based;https://arxiv.org/abs/2310.20707;2
+
+squadshifts;nyt;allenai/c4;corpus;;;0.01;data-based;https://arxiv.org/abs/2310.20707;2
+squadshifts;nyt;oscar-corpus/OSCAR-2301;corpus;;;0.03;data-based;https://arxiv.org/abs/2310.20707;2
+squadshifts;nyt;EleutherAI/pile;corpus;;;0.02;data-based;https://arxiv.org/abs/2310.20707;2
+squadshifts;nyt;togethercomputer/RedPajama-Data-V2;corpus;;;0.04;data-based;https://arxiv.org/abs/2310.20707;2
+
+stsb_multi_mt;;allenai/c4;corpus;;;3.48;data-based;https://arxiv.org/abs/2310.20707;2
+stsb_multi_mt;;oscar-corpus/OSCAR-2301;corpus;;;3.12;data-based;https://arxiv.org/abs/2310.20707;2
+stsb_multi_mt;;EleutherAI/pile;corpus;;;11.09;data-based;https://arxiv.org/abs/2310.20707;2
+stsb_multi_mt;;togethercomputer/RedPajama-Data-V2;corpus;;;9.86;data-based;https://arxiv.org/abs/2310.20707;2
+
+subjqa;books;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+subjqa;books;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+subjqa;books;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+subjqa;books;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+
+subjqa;grocery;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+subjqa;grocery;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+subjqa;grocery;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+subjqa;grocery;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+
+subjqa;movies;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+subjqa;movies;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+subjqa;movies;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+subjqa;movies;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+
+subjqa;restaurants;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+subjqa;restaurants;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+subjqa;restaurants;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+subjqa;restaurants;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+
+super_nyu-mll/glue;axb;allenai/c4;corpus;;;1.99;data-based;https://arxiv.org/abs/2310.20707;2
+super_nyu-mll/glue;axb;oscar-corpus/OSCAR-2301;corpus;;;1.45;data-based;https://arxiv.org/abs/2310.20707;2
+super_nyu-mll/glue;axb;EleutherAI/pile;corpus;;;5.07;data-based;https://arxiv.org/abs/2310.20707;2
+super_nyu-mll/glue;axb;togethercomputer/RedPajama-Data-V2;corpus;;;6.16;data-based;https://arxiv.org/abs/2310.20707;2
+
+super_nyu-mll/glue;axg;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+super_nyu-mll/glue;axg;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+super_nyu-mll/glue;axg;EleutherAI/pile;corpus;;;0.28;data-based;https://arxiv.org/abs/2310.20707;2
+super_nyu-mll/glue;axg;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+
+super_nyu-mll/glue;boolq;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+super_nyu-mll/glue;boolq;oscar-corpus/OSCAR-2301;corpus;;;3.05;data-based;https://arxiv.org/abs/2310.20707;2
+super_nyu-mll/glue;boolq;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+super_nyu-mll/glue;boolq;togethercomputer/RedPajama-Data-V2;corpus;;;0.03;data-based;https://arxiv.org/abs/2310.20707;2
+
+super_nyu-mll/glue;cb;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+super_nyu-mll/glue;cb;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+super_nyu-mll/glue;cb;EleutherAI/pile;corpus;;;2.0;data-based;https://arxiv.org/abs/2310.20707;2
+super_nyu-mll/glue;cb;togethercomputer/RedPajama-Data-V2;corpus;;;1.6;data-based;https://arxiv.org/abs/2310.20707;2
+
+super_nyu-mll/glue;copa;allenai/c4;corpus;;;0.6;data-based;https://arxiv.org/abs/2310.20707;2
+super_nyu-mll/glue;copa;oscar-corpus/OSCAR-2301;corpus;;;1.0;data-based;https://arxiv.org/abs/2310.20707;2
+super_nyu-mll/glue;copa;EleutherAI/pile;corpus;;;1.2;data-based;https://arxiv.org/abs/2310.20707;2
+super_nyu-mll/glue;copa;togethercomputer/RedPajama-Data-V2;corpus;;;100.0;data-based;https://arxiv.org/abs/2310.20707;2
+
+super_nyu-mll/glue;multirc;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+super_nyu-mll/glue;multirc;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+super_nyu-mll/glue;multirc;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+super_nyu-mll/glue;multirc;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+
+super_nyu-mll/glue;record;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+super_nyu-mll/glue;record;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+super_nyu-mll/glue;record;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+super_nyu-mll/glue;record;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+
+super_nyu-mll/glue;rte;allenai/c4;corpus;;;0.2;data-based;https://arxiv.org/abs/2310.20707;2
+super_nyu-mll/glue;rte;oscar-corpus/OSCAR-2301;corpus;;;0.17;data-based;https://arxiv.org/abs/2310.20707;2
+super_nyu-mll/glue;rte;EleutherAI/pile;corpus;;;0.13;data-based;https://arxiv.org/abs/2310.20707;2
+super_nyu-mll/glue;rte;togethercomputer/RedPajama-Data-V2;corpus;;;67.47;data-based;https://arxiv.org/abs/2310.20707;2
+
+super_nyu-mll/glue;wic;allenai/c4;corpus;;;64.43;data-based;https://arxiv.org/abs/2310.20707;2
+super_nyu-mll/glue;wic;oscar-corpus/OSCAR-2301;corpus;;;49.43;data-based;https://arxiv.org/abs/2310.20707;2
+super_nyu-mll/glue;wic;EleutherAI/pile;corpus;;;18.57;data-based;https://arxiv.org/abs/2310.20707;2
+super_nyu-mll/glue;wic;togethercomputer/RedPajama-Data-V2;corpus;;;60.21;data-based;https://arxiv.org/abs/2310.20707;2
+
+swag;regular;allenai/c4;corpus;;;2.48;data-based;https://arxiv.org/abs/2310.20707;2
+swag;regular;oscar-corpus/OSCAR-2301;corpus;;;1.65;data-based;https://arxiv.org/abs/2310.20707;2
+swag;regular;EleutherAI/pile;corpus;;;2.21;data-based;https://arxiv.org/abs/2310.20707;2
+swag;regular;togethercomputer/RedPajama-Data-V2;corpus;;;2.79;data-based;https://arxiv.org/abs/2310.20707;2
+
+tab_fact;tab_fact;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+tab_fact;tab_fact;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+tab_fact;tab_fact;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+tab_fact;tab_fact;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+
+wiki_qa;;allenai/c4;corpus;;;0.24;data-based;https://arxiv.org/abs/2310.20707;2
+wiki_qa;;oscar-corpus/OSCAR-2301;corpus;;;0.18;data-based;https://arxiv.org/abs/2310.20707;2
+wiki_qa;;EleutherAI/pile;corpus;;;0.19;data-based;https://arxiv.org/abs/2310.20707;2
+wiki_qa;;togethercomputer/RedPajama-Data-V2;corpus;;;0.91;data-based;https://arxiv.org/abs/2310.20707;2
+
+winograd_wsc;wsc273;allenai/c4;corpus;;;29.30;data-based;https://arxiv.org/abs/2310.20707;2
+winograd_wsc;wsc273;oscar-corpus/OSCAR-2301;corpus;;;30.40;data-based;https://arxiv.org/abs/2310.20707;2
+winograd_wsc;wsc273;EleutherAI/pile;corpus;;;32.23;data-based;https://arxiv.org/abs/2310.20707;2
+winograd_wsc;wsc273;togethercomputer/RedPajama-Data-V2;corpus;;;58.24;data-based;https://arxiv.org/abs/2310.20707;2
+
+winogrande;winogrande_xl;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+winogrande;winogrande_xl;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+winogrande;winogrande_xl;EleutherAI/pile;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+winogrande;winogrande_xl;togethercomputer/RedPajama-Data-V2;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+
+xnli;en;allenai/c4;corpus;;;0.12;data-based;https://arxiv.org/abs/2310.20707;2
+xnli;en;oscar-corpus/OSCAR-2301;corpus;;;0.24;data-based;https://arxiv.org/abs/2310.20707;2
+xnli;en;EleutherAI/pile;corpus;;;0.36;data-based;https://arxiv.org/abs/2310.20707;2
+xnli;en;togethercomputer/RedPajama-Data-V2;corpus;;;0.44;data-based;https://arxiv.org/abs/2310.20707;2
+
+xsum;;allenai/c4;corpus;;;2.13;data-based;https://arxiv.org/abs/2310.20707;2
+xsum;;oscar-corpus/OSCAR-2301;corpus;;;0.13;data-based;https://arxiv.org/abs/2310.20707;2
+xsum;;EleutherAI/pile;corpus;;;3.30;data-based;https://arxiv.org/abs/2310.20707;2
+xsum;;togethercomputer/RedPajama-Data-V2;corpus;;;4.28;data-based;https://arxiv.org/abs/2310.20707;2
+
+zest;;allenai/c4;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+zest;;oscar-corpus/OSCAR-2301;corpus;;;0.0;data-based;https://arxiv.org/abs/2310.20707;2
+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

dataset.py

@@ -229,10 +229,11 @@ def get_dataframe():
         )
     )
 
+    PR_URL_FORMAT = "https://huggingface.co/spaces/CONDA-Workshop/Data-Contamination-Report/discussions/{}"
     data["PR"] = data["PR"].apply(
         lambda x: build_text_icon(
             text="",
-            url=x if x == x else "no link",
+            url=PR_URL_FORMAT.format(int(x)) if not pd.isna(x) else "no link",
             icon_url=HF_ICON if x == x else CROSS_ICON,
         )
     )