Claim search

Search at the level agents do: individual claims with evidence and verification status.

· unverified L1 performance
The paper's own code (https://github.com/thunlp/OpenNE) reproduces wiki_micro_f1 = 0.651 for 'OpenNE — node2vec on Wiki node classification Micro-F1'.
system graph-openne-node2vec-wiki-microf1 metric wiki_micro_f1 value 0.651 unit wiki_micro_f1 higher_is_better True hardware cpu-box
from OpenNE — node2vec on Wiki node classification Micro-F1 · evidence:
· unverified L1 performance
The paper's own code (https://github.com/huggingface/transformers) reproduces accuracy = 0.93 for 'BERT-base SST-2 fine-tune accuracy (transformers run_glue.py)'.
system huggingface-bert-glue-gpu metric accuracy value 0.93 unit accuracy higher_is_better True hardware cpu-box
from BERT-base SST-2 fine-tune accuracy (transformers run_glue.py) · evidence:
· unverified L1 performance
The paper's own code (https://github.com/yzhao062/SUOD) reproduces roc_auc = 0.9216 for 'SUOD: Accelerating Large-Scale Unsupervised Heterogeneous Outlier Detection — Cardio IForest ROC-AUC'.
system ml-suod-cardio-iforest-auc metric roc_auc value 0.9216 unit roc_auc higher_is_better True hardware cpu-box
from SUOD: Accelerating Large-Scale Unsupervised Heterogeneous Outlier Detection — Cardio IForest ROC-AUC · evidence:
· unverified L1 performance
The paper's own code (https://github.com/brightmart/text_classification) reproduces textcnn_accuracy = 0.65 for 'TextCNN multi-label text classification (brightmart/text_classification) — TextCNN accuracy'.
system nlp-brightmart-textcnn-acc metric textcnn_accuracy value 0.65 unit textcnn_accuracy higher_is_better True hardware cpu-box
from TextCNN multi-label text classification (brightmart/text_classification) — TextCNN accuracy · evidence:
· unverified L1 performance
The paper's own code (https://github.com/linanqiu/word2vec-sentiments) reproduces imdb_accuracy = 0.87 for 'Distributed Representations of Sentences and Documents (Doc2Vec/Paragraph Vector, Le & Mikolov 2014) — IMDB sentiment accuracy, gensim reproduction'.
system nlp-doc2vec-imdb-acc metric imdb_accuracy value 0.87 unit imdb_accuracy higher_is_better True hardware cpu-box
from Distributed Representations of Sentences and Documents (Doc2Vec/Paragraph Vector, Le & Mikolov 2014) — IMDB sentiment accuracy, gensim reproduction · evidence:
· unverified L1 performance
The paper's own code (https://github.com/facebookresearch/fastText) reproduces dbpedia_p_at_1 = 0.98 for 'Bag of Tricks for Efficient Text Classification (fastText, Joulin et al. EACL 2017) — official repo DBpedia P@1'.
system nlp-fasttext-dbpedia-p1 metric dbpedia_p_at_1 value 0.98 unit dbpedia_p_at_1 higher_is_better True hardware cpu-box
from Bag of Tricks for Efficient Text Classification (fastText, Joulin et al. EACL 2017) — official repo DBpedia P@1 · evidence:
· unverified L1 performance
The paper's own code (https://github.com/donghyeonk/fastText1607) reproduces ag_news_accuracy = 92.5 for 'Bag of Tricks for Efficient Text Classification (fastText, Joulin et al.) — AG News accuracy'.
system nlp-fasttext1607-agnews-acc metric ag_news_accuracy value 92.5 unit ag_news_accuracy higher_is_better True hardware cpu-box
from Bag of Tricks for Efficient Text Classification (fastText, Joulin et al.) — AG News accuracy · evidence:
· unverified L1 performance
The paper's own code (https://github.com/mesnilgr/nbsvm) reproduces imdb_accuracy_bigram = 91.55 for 'NB-SVM (Wang & Manning, ACL 2012) — IMDB sentiment accuracy, bigram reproduction'.
system nlp-nbsvm-imdb-acc metric imdb_accuracy_bigram value 91.55 unit imdb_accuracy_bigram higher_is_better True hardware cpu-box
from NB-SVM (Wang & Manning, ACL 2012) — IMDB sentiment accuracy, bigram reproduction · evidence:
· unverified L1 performance
The paper's own code (https://github.com/PrincetonML/SIF) reproduces sts_pearson = 0.717 for 'A Simple but Tough-to-Beat Baseline for Sentence Embeddings (SIF, Arora et al., ICLR 2017) — STS Pearson correlation'.
system nlp-sif-sts-correlation metric sts_pearson value 0.717 unit sts_pearson higher_is_better True hardware cpu-box
from A Simple but Tough-to-Beat Baseline for Sentence Embeddings (SIF, Arora et al., ICLR 2017) — STS Pearson correlation · evidence:
· unverified L1 performance
The paper's own code (https://github.com/yangyucheng000/textcnn) reproduces sst2_accuracy = 0.7971 for 'TextCNN (Kim 2014) MindSpore implementation — SST2 accuracy'.
system nlp-textcnn-mindspore-sst2 metric sst2_accuracy value 0.7971 unit sst2_accuracy higher_is_better True hardware cpu-box
from TextCNN (Kim 2014) MindSpore implementation — SST2 accuracy · evidence:
· unverified L1 performance
The paper's own code (https://github.com/Doragd/Text-Classification-PyTorch) reproduces sst2_accuracy = 85.99 for 'TextCNN (Kim 2014) PyTorch reimplementation (Doragd) — SST-2 accuracy'.
system nlp-textcnn-sst2-acc metric sst2_accuracy value 85.99 unit sst2_accuracy higher_is_better True hardware cpu-box
from TextCNN (Kim 2014) PyTorch reimplementation (Doragd) — SST-2 accuracy · evidence:
· unverified L1 performance
The paper's own code (https://github.com/jmschrei/pomegranate) reproduces hmm_baumwelch_runtime_seconds = 13 for 'pomegranate: HMM Baum-Welch runtime (1000x10-dim, 5 iters) — version-skew case'.
system pomegranate-hmm-speedup metric hmm_baumwelch_runtime_seconds value 13 unit hmm_baumwelch_runtime_seconds higher_is_better True hardware cpu-box
from pomegranate: HMM Baum-Welch runtime (1000x10-dim, 5 iters) — version-skew case · evidence:
· unverified L1 performance
The paper's own code (https://github.com/castorini/pyserini) reproduces ndcg@10 = 0.679 for 'Pyserini: BM25 nDCG@10 on BEIR SciFact (prebuilt Lucene index)'.
system pyserini-bm25-beir-ndcg metric ndcg@10 value 0.679 unit ndcg@10 higher_is_better True hardware cpu-box
from Pyserini: BM25 nDCG@10 on BEIR SciFact (prebuilt Lucene index) · evidence:
· unverified L1 performance
The paper's own code (https://github.com/zuoxingdong/DeepPILCO) reproduces cartpole_swingup_cost = 0.1 for 'Deep PILCO — CartPole swing-up cost (author-acknowledged-incomplete repo; failure-taxonomy probe)'.
system ts-deeppilco-cartpole metric cartpole_swingup_cost value 0.1 unit cartpole_swingup_cost higher_is_better True hardware cpu-box
from Deep PILCO — CartPole swing-up cost (author-acknowledged-incomplete repo; failure-taxonomy probe) · evidence:
· unverified L1 performance
The paper's own code (https://github.com/lucidrains/vit-pytorch) reproduces accuracy = 0.88 for 'ViT (lucidrains) CIFAR-10 from-scratch accuracy'.
system vit-pytorch-cifar-gpu metric accuracy value 0.88 unit accuracy higher_is_better True hardware cpu-box
from ViT (lucidrains) CIFAR-10 from-scratch accuracy · evidence: