The IMDb Movie Reviews dataset is a binary sentiment analysis dataset consisting of 50,000 reviews from the Internet Movie Database (IMDb) labeled as positive or negative. The dataset contains an even number of positive and negative reviews. Only highly polarizing reviews are considered. A negative review has a score ≤ 4 out of 10, and a positive review has a score ≥ 7 out of 10. No more than 30 reviews are included per movie. The dataset contains additional unlabeled data.

990 PAPERS • 7 BENCHMARKS

The MovieLens datasets, first released in 1998, describe people’s expressed preferences for movies. These preferences take the form of tuples, each the result of a person expressing a preference (a 0-5 star rating) for a movie at a particular time. These preferences were entered by way of the MovieLens web site1 — a recommender system that asks its users to give movie ratings in order to receive personalized movie recommendations.

678 PAPERS • 10 BENCHMARKS

The Medical Information Mart for Intensive Care III (MIMIC-III) dataset is a large, de-identified and publicly-available collection of medical records. Each record in the dataset includes ICD-9 codes, which identify diagnoses and procedures performed. Each code is partitioned into sub-codes, which often include specific circumstantial details. The dataset consists of 112,000 clinical reports records (average length 709.3 tokens) and 1,159 top-level ICD-9 codes. Each report is assigned to 7.6 codes, on average. Data includes vital signs, medications, laboratory measurements, observations and notes charted by care providers, fluid balance, procedure codes, diagnostic codes, imaging reports, hospital length of stay, survival data, and more.

522 PAPERS • 7 BENCHMARKS

NAS-Bench-101 is the first public architecture dataset for NAS research. To build NASBench-101, the authors carefully constructed a compact, yet expressive, search space, exploiting graph isomorphisms to identify 423k unique convolutional architectures. The authors trained and evaluated all of these architectures multiple times on CIFAR-10 and compiled the results into a large dataset of over 5 million trained models. This allows researchers to evaluate the quality of a diverse range of models in milliseconds by querying the precomputed dataset.

86 PAPERS • 1 BENCHMARK

Netflix Prize consists of about 100,000,000 ratings for 17,770 movies given by 480,189 users. Each rating in the training dataset consists of four entries: user, movie, date of grade, grade. Users and movies are represented with integer IDs, while ratings range from 1 to 5.

85 PAPERS • NO BENCHMARKS YET

UNSW-NB15 is a network intrusion dataset. It contains nine different attacks, includes DoS, worms, Backdoors, and Fuzzers. The dataset contains raw network packets. The number of records in the training set is 175,341 records and the testing set is 82,332 records from the different types, attack and normal.

62 PAPERS • 2 BENCHMARKS

WikiTableQuestions is a question answering dataset over semi-structured tables. It is comprised of question-answer pairs on HTML tables, and was constructed by selecting data tables from Wikipedia that contained at least 8 rows and 5 columns. Amazon Mechanical Turk workers were then tasked with writing trivia questions about each table. WikiTableQuestions contains 22,033 questions. The questions were not designed by predefined templates but were hand crafted by users, demonstrating high linguistic variance. Compared to previous datasets on knowledge bases it covers nearly 4,000 unique column headers, containing far more relations than closed domain datasets and datasets for querying knowledge bases. Its questions cover a wide range of domains, requiring operations such as table lookup, aggregation, superlatives (argmax, argmin), arithmetic operations, joins and unions.

35 PAPERS • 1 BENCHMARK

The friedman1 data set is commonly used to test semi-supervised regression methods.

20 PAPERS • NO BENCHMARKS YET

The Yahoo! Learning to Rank Challenge dataset consists of 709,877 documents encoded in 700 features and sampled from query logs of the Yahoo! search engine, spanning 29,921 queries.

20 PAPERS • NO BENCHMARKS YET

CAL500 (Computer Audition Lab 500) is a dataset aimed for evaluation of music information retrieval systems. It consists of 502 songs picked from western popular music. The audio is represented as a time series of the first 13 Mel-frequency cepstral coefficients (and their first and second derivatives) extracted by sliding a 12 ms half-overlapping short-time window over the waveform of each song. Each song has been annotated by at least 3 people with 135 musically-relevant concepts spanning six semantic categories:

18 PAPERS • NO BENCHMARKS YET

Data Set Information: Extraction was done by Barry Becker from the 1994 Census database. A set of reasonably clean records was extracted using the following conditions: ((AAGE>16) && (AGI>100) && (AFNLWGT>1)&& (HRSWK>0))

11 PAPERS • 1 BENCHMARK

Two datasets are provided. the original dataset, in the form provided by Prof. Hofmann, contains categorical/symbolic attributes and is in the file "german.data".

9 PAPERS • NO BENCHMARKS YET

The Abt-Buy dataset for entity resolution derives from the online retailers Abt.com and Buy.com. The dataset contains 1081 entities from abt.com and 1092 entities from buy.com as well as a gold standard (perfect mapping) with 1097 matching record pairs between the two data sources. The common attributes between the two data sources are: product name, product description and product price.

5 PAPERS • 1 BENCHMARK

The Amazon-Google dataset for entity resolution derives from the online retailers Amazon.com and the product search service of Google accessible through the Google Base Data API. The dataset contains 1363 entities from amazon.com and 3226 google products as well as a gold standard (perfect mapping) with 1300 matching record pairs between the two data sources. The common attributes between the two data sources are: product name, product description, manufacturer and price.

5 PAPERS • 1 BENCHMARK

Many e-shops have started to mark-up product data within their HTML pages using the schema.org vocabulary. The Web Data Commons project regularly extracts such data from the Common Crawl, a large public web crawl. The Web Data Commons Training and Test Sets for Large-Scale Product Matching contain product offers from different e-shops in the form of binary product pairs (with corresponding label "match" or "no match") for four product categories, computers, cameras, watches and shoes.

5 PAPERS • 4 BENCHMARKS

ACS PUMS stands for American Community Survey (ACS) Public Use Microdata Sample (PUMS) and has been used to construct several tabular datasets for studying fairness in machine learning:

3 PAPERS • NO BENCHMARKS YET

CI-MNIST (Correlated and Imbalanced MNIST) is a variant of MNIST dataset with introduced different types of correlations between attributes, dataset features, and an artificial eligibility criterion. For an input image $x$, the label $y \in \{1, 0\}$ indicates eligibility or ineligibility, respectively, given that $x$ is even or odd. The dataset defines the background colors as the protected or sensitive attribute $s \in \{0, 1\}$, where blue denotes the unprivileged group and red denotes the privileged group. The dataset was designed in order to evaluate bias-mitigation approaches in challenging setups and be capable of controlling different dataset configurations.

3 PAPERS • NO BENCHMARKS YET

Open Dataset: Mobility Scenario FIMU

3 PAPERS • NO BENCHMARKS YET

The Papers with Code Leaderboards dataset is a collection of over 5,000 results capturing performance of machine learning models. Each result is a tuple of form (task, dataset, metric name, metric value). The data was collected using the Papers with Code review interface.

3 PAPERS • 1 BENCHMARK

A coronavirus dataset with 98 countries constructed from different reliable sources, where each row represents a country, and the columns represent geographic, climate, healthcare, economic, and demographic factors that may contribute to accelerate/slow the spread of the COVID-19. The assumptions for the different factors are as follows:

2 PAPERS • NO BENCHMARKS YET

This resource, our Concepticon, links concept labels from different conceptlists to concept sets. Each concept set is given a unique identifier, a unique label, and a human-readable definition. Concept sets are further structured by defining different relations between the concepts, as you can see in the graphic to the right, which displays the relations between concept sets linked to the concept set SIBLING. The resource can be used for various purposes. Serving as a rich reference for new and existing databases in diachronic and synchronic linguistics, it allows researchers a quick access to studies on semantic change, cross-linguistic polysemies, and semantic associations.

2 PAPERS • NO BENCHMARKS YET

This experiment was performed in order to empirically measure the energy use of small, electric Unmanned Aerial Vehicles (UAVs). We autonomously direct a DJI ® Matrice 100 (M100) drone to take off, carry a range of payload weights on a triangular flight pattern, and land. Between flights, we varied specified parameters through a set of discrete options, payload of 0 , 250 g and 500 g; altitude during cruise of 25 m, 50 m, 75 m and 100 m; and speed during cruise of 4 m/s, 6 m/s, 8 m/s, 10 m/s and 12 m/s.

2 PAPERS • 1 BENCHMARK

The dataset contains transactions made by credit cards in September 2013 by European cardholders. This dataset presents transactions that occurred in two days, where we have 492 frauds out of 284,807 transactions. The dataset is highly unbalanced, the positive class (frauds) account for 0.172% of all transactions.

2 PAPERS • 1 BENCHMARK

The original dataset was provided by Orange telecom in France, which contains anonymized and aggregated human mobility data. The Multivariate-Mobility-Paris dataset comprises information from 2020-08-24 to 2020-11-04 (72 days during the COVID-19 pandemic), with time granularity of 30 minutes and spatial granularity of 6 coarse regions in Paris, France. In other words, it represents a multivariate time series dataset.

2 PAPERS • NO BENCHMARKS YET

Context This large dataset with users interactions logs (page views) from a news portal was kindly provided by Globo.com, the most popular news portal in Brazil, for reproducibility of the experiments with CHAMELEON - a meta-architecture for contextual hybrid session-based news recommender systems. The source code was made available at GitHub.

2 PAPERS • NO BENCHMARKS YET

The softwarised network data zoo (SNDZoo) is an open collection of software networking data sets aiming to streamline and ease machine learning research in the software networking domain. Most of the published data sets focus on, but are not limited to, the performance of virtualised network functions (VNFs). The data is collected using fully automated NFV benchmarking frameworks, such as tng-bench, developed by us or third party solutions like Gym. The collection of the presented data sets follows the general VNF benchmarking methodology described in.

2 PAPERS • NO BENCHMARKS YET

This resource is designed to allow for research into Natural Language Generation. In particular, with neural data-to-text approaches although it is not limited to these.

2 PAPERS • NO BENCHMARKS YET

The eSports Sensors dataset contains sensor data collected from 10 players in 22 matches in League of Legends. The sensor data collected includes:

2 PAPERS • 2 BENCHMARKS

These are larger MATLAB .mat files required for reproducing plots from the sgbaird-5DOF/interp repository for grain boundary property interpolation. gitID-0055bee_uuID-475a2dfd_paper-data6.mat contains multiple trials of five degree-of-freedom interpolation model runs for various interpolation schemes. gpr46883_gitID-b473165_puuID-50ffdcf6_kim-rng11.mat contains a Gaussian Process Regression model trained on 46883 Fe simulation GBs. See Five degree-of-freedom property interpolation of arbitrary grain boundaries via Voronoi fundamental zone framework DOI: 10.1016/j.commatsci.2021.110756 for the peer-reviewed, published version of the paper.

1 PAPER • NO BENCHMARKS YET

Multimodal object recognition is still an emerging field. Thus, publicly available datasets are still rare and of small size. This dataset was developed to help fill this void and presents multimodal data for 63 objects with some visual and haptic ambiguity. The dataset contains visual, kinesthetic and tactile (audio/vibrations) data. To completely solve sensory ambiguity, sensory integration/fusion would be required. This report describes the creation and structure of the dataset. The first section explains the underlying approach used to capture the visual and haptic properties of the objects. The second section describes the technical aspects (experimental setup) needed for the collection of the data. The third section introduces the objects, while the final section describes the structure and content of the dataset.

1 PAPER • NO BENCHMARKS YET

The CANDOR corpus is a large, novel, multimodal corpus of 1,656 recorded conversations in spoken English. This 7+ million word, 850 hour corpus totals over 1TB of audio, video, and transcripts, with moment-to-moment measures of vocal, facial, and semantic expression, along with an extensive survey of speaker post conversation reflections.

1 PAPER • NO BENCHMARKS YET

This data set includes votes for each of the U.S. House of Representatives Congressmen on the 16 key votes identified by the CQA. The CQA lists nine different types of votes: voted for, paired for, and announced for (these three simplified to yea), voted against, paired against, and announced against (these three simplified to nay), voted present, voted present to avoid conflict of interest, and did not vote or otherwise make a position known (these three simplified to an unknown disposition).

1 PAPER • 1 BENCHMARK

Co/FeMn bilayers measured.

1 PAPER • NO BENCHMARKS YET

This dataset includes Direct Borohydride Fuel Cell (DBFC) impedance and polarization test in anode with Pd/C, Pt/C and Pd decorated Ni–Co/rGO catalysts. In fact, different concentration of Sodium Borohydride (SBH), applied voltages and various anode catalysts loading with explanation of experimental details of electrochemical analysis are considered in data. Voltage, power density and resistance of DBFC change as a function of weight percent of SBH (%), applied voltage and amount of anode catalyst loading that are evaluated by polarization and impedance curves with using appropriate equivalent circuit of fuel cell. Can be stated that interpretation of electrochemical behavior changes by the data of related cell is inevitable, which can be useful in simulation, power source investigation and depth analysis in DB fuel cell researches.

1 PAPER • NO BENCHMARKS YET

This dataset consisting 500 set of caption, table and coresponding paper page, processed from DocBank.

1 PAPER • NO BENCHMARKS YET

The data used for all results in this paper can be found here. This directory contains:

1 PAPER • NO BENCHMARKS YET

EUCA dataset description Associated Paper: EUCA: the End-User-Centered Explainable AI Framework

1 PAPER • NO BENCHMARKS YET

EUEN17037 Daylight and View Standard Test Dataset.

1 PAPER • NO BENCHMARKS YET

Each HDF5 file has the following structure:

1 PAPER • NO BENCHMARKS YET

Provide:

1 PAPER • NO BENCHMARKS YET

Optical images of printed circuit boards as well as detailed annotations of any text, logos, and surface-mount devices (SMDs). There are several hundred samples spanning a wide variety of manufacturing locations, sizes, node technology, applications, and more.

1 PAPER • NO BENCHMARKS YET

A MIDI dataset of 500 4-part chorales generated by the KS_Chorus algorithm, annotated with results from hundreds of listening test participants, with 150 further unannotated chorales.

1 PAPER • NO BENCHMARKS YET

The LinkedResults dataset contains around 1,600 results capturing performance of machine learning models from tables of 239 papers. All tables come from a subset of SegmentedTables dataset. Each result is a tuple of form (task, dataset, metric name, metric value) and is linked to a particular table, row and cell it originates from.

1 PAPER • NO BENCHMARKS YET

Nowadays, new branches of research are proposing the use of non-traditional data sources for the study of migration trends in order to find an original methodology to answer open questions about cross-border human mobility. The Multi-aspect Integrated Migration Indicators (MIMI) dataset is a new dataset to be exploited in migration studies as a concrete example of this new approach. It includes both official data about bidirectional human migration (traditional flow and stock data) with multidisciplinary variables and original indicators, including economic, demographic, cultural and geographic indicators, together with the Facebook Social Connectedness Index (SCI). It results from the process of gathering, embedding and integrating traditional and novel variables, resulting in this new multidisciplinary dataset that could significantly contribute to nowcast/forecast bilateral migration trends and migration drivers.

1 PAPER • NO BENCHMARKS YET

Retrospectively collected medical data has the opportunity to improve patient care through knowledge discovery and algorithm development. Broad reuse of medical data is desirable for the greatest public good, but data sharing must be done in a manner which protects patient privacy. The Medical Information Mart for Intensive Care (MIMIC)-III database provided critical care data for over 40,000 patients admitted to intensive care units at the Beth Israel Deaconess Medical Center (BIDMC). Importantly, MIMIC-III was deidentified, and patient identifiers were removed according to the Health Insurance Portability and Accountability Act (HIPAA) Safe Harbor provision. MIMIC-III has been integral in driving large amounts of research in clinical informatics, epidemiology, and machine learning. Here we present MIMIC-IV, an update to MIMIC-III, which incorporates contemporary data and improves on numerous aspects of MIMIC-III. MIMIC-IV adopts a modular approach to data organization, highlighting d

1 PAPER • NO BENCHMARKS YET

MIMIC-IV-ED is a large, freely available database of emergency department (ED) admissions at the Beth Israel Deaconess Medical Center between 2011 and 2019. As of MIMIC-ED v1.0, the database contains 448,972 ED stays. Vital signs, triage information, medication reconciliation, medication administration, and discharge diagnoses are available. All data are deidentified to comply with the Health Information Portability and Accountability Act (HIPAA) Safe Harbor provision. MIMIC-ED is intended to support a diverse range of education initiatives and research studies.

1 PAPER • NO BENCHMARKS YET

MPOSE2021, a dataset for real-time short-time HAR, suitable for both pose-based and RGB-based methodologies. It includes 15,429 sequences from 100 actors and different scenarios, with limited frames per scene (between 20 and 30). In contrast to other publicly available datasets, the peculiarity of having a constrained number of time steps stimulates the development of real-time methodologies that perform HAR with low latency and high throughput.

1 PAPER • NO BENCHMARKS YET

The Musk dataset describes a set of molecules, and the objective is to detect musks from non-musks. This dataset describes a set of 92 molecules of which 47 are judged by human experts to be musks and the remaining 45 molecules are judged to be non-musks. There are 166 features available that describe the molecules based on the shape of the molecule.

1 PAPER • NO BENCHMARKS YET