Yun Sing Koh (born 1978) is a New Zealand computer science academic, and is a full professor at the University of Auckland, specialising in machine learning and artificial intelligence. She is a co-director of the Centre of Machine Learning for Social Good, and the Advanced Machine Learning and Data Analytics Research (MARS) Lab at Auckland. == Academic career == Koh earned a Bachelor of Science with Honours and a Master of Software Engineering at the University of Malaya. She then completed a PhD titled Generating sporadic association rules at the University of Otago in 2007. Koh joined the faculty of the University of Auckland in 2010, rising to full professor. As of 2024, she is director of the Centre of Machine Learning for Social Good at Auckland, alongside Gillian Dobbie and Daniel Wilson, and is director of the Master of AI course at the university. Koh also co-directs the Advanced Machine Learning and Data Analytics Research (MARS) Lab. Koh's research covers machine learning and artificial intelligence. She is especially interested in designing machine learning algorithms for data streams, and has led research using AI systems to identify individual stoats for pest population research. In 2018 she was awarded a Marsden grant for a research project "An Adaptive Predictive System for Life-long Learning on Data Streams", and has been part of three MBIE projects. In 2025 the stoat identification project Koh co-leads with Daniel Wilson was awarded $1 million per annum by the MBIE Smart Ideas fund. Koh was a finalist in the AI in Climate section of the Women in AI Australia and New Zealand Awards in 2022. She was a 2023 Fellow at the United States National Science Foundation-funded Convergence Research (CORE) Institute. Koh has chaired a number of sessions at international conferences on data mining. In March 2026 it was announced that Koh would be a member of the New Zealand Human Rights Commission's Expert Advisory Group on Artificial Intelligence, Emerging Digital Technologies and Human Rights. == Selected works == Philippe Fournier-Viger; Jerry Chun-Wei Lin; Rage Uday Kiran; Yun Sing Koh; Rincy Thomas (2017). "A Survey of Sequential Pattern Mining". Data Science and Pattern Recognition. 1 (1): 54–77. Wikidata Q138719481. Yun Sing Koh; Nathan Rountree; Richard O’Keefe (1 April 2006). "Finding Non-Coincidental Sporadic Rules Using Apriori-Inverse". International Journal of Data Warehousing and Mining (in Ndonga). 2 (2): 38–54. doi:10.4018/JDWM.2006040102. ISSN 1548-3924. Wikidata Q125185222. Russel Pears; Sripirakas Sakthithasan; Yun Sing Koh (11 January 2014). "Detecting concept change in dynamic data streams". Machine Learning. 97 (3): 259–293. doi:10.1007/S10994-013-5433-9. ISSN 1573-0565. Zbl 1319.68186. Wikidata Q125185156. David Tse Jung Huang; Yun Sing Koh; Gillian Dobbie; Russel Pears (December 2014), Detecting Volatility Shift in Data Streams, Institute of Electrical and Electronics Engineers, doi:10.1109/ICDM.2014.50, Wikidata Q125185151 Sidney Tsang; Yun Sing Koh; Gillian Dobbie (2011). "RP-Tree: Rare Pattern Tree Mining". Lecture Notes in Computer Science: 277–288. doi:10.1007/978-3-642-23544-3_21. ISSN 0302-9743. Wikidata Q125185206. Yun Sing Koh; Sri Devi Ravana (24 May 2016). "Unsupervised Rare Pattern Mining". ACM Transactions on Knowledge Discovery from Data. 10 (4): 1–29. doi:10.1145/2898359. ISSN 1556-4681. Wikidata Q125185136. Jack Julian; Yun Sing Koh; Albert Bifet (1 October 2025), Building adaptive knowledge bases for evolving continual learning models (PDF), vol. 1, doi:10.1038/S44387-025-00028-4, Wikidata Q138719496
SGT STAR
SGT STAR, also known as Sgt. Star or Sergeant Star, was a chatbot operated by the United States Army to answer questions about recruitment. == Background == After the September 11 attacks, traffic increased significantly to chatrooms on the U.S. Army's website, goarmy.com, increasing costs of staffing the live chatrooms. As a cost-cutting measure, the SGT STAR project was initiated as a partnership between the United States Army Accessions Command and Spectre AI, a wholly owned subsidiary of Next IT. Next IT, a Spokane, Washington-based company deploys "intelligent virtual assistants," using its software dubbed "ActiveAgent" which is a framework for functional presence engines. Testing began in 2003, and SGT STAR launched to the public in 2006. "STAR" is an acronym for "strong, trained and ready." SGT STAR was launched as a chat interface on goarmy.com, but has since been developed as a mobile application, as well as a life-size animated projection that has appeared live at public events. SGT STAR can also interact with users on Facebook. == FOIA request == In 2013, the Electronic Frontier Foundation filed a Freedom of Information Act request to learn more about SGT STAR, including input and output patterns (questions and answers), usage statistics, contracts, and privacy policies. They received these records in April 2014, after coverage from various media outlets and a tongue-in-cheek campaign to "Free Sgt. Star."
AlternativeTo
AlternativeTo is a website which lists alternatives to web-based software, desktop computer software, and mobile apps, and sorts the alternatives by various criteria, including the number of registered users who have "Liked" each of them on AlternativeTo. Users can search the site to find better alternatives to an application they are using or previously have used, including free alternatives such as free web applications (cloud computing) which don't require any installation and can be accessed from any browser. == Differences == Unlike a number of other software directory websites, the software is not arranged into categories, but each individual piece of software has its own list of alternatives. However, users can also search by tag to find software, which offers an alternative way of finding related software. Users can also narrow their search by focusing on particular platforms and license types (such as "free for non-commercial use"). AlternativeTo lists basic information such as platform and license type at the top of each entry, but does not have comparison tables listing software features side by side. AlternativeTo does not host software for download but it provides links to official websites to where you can download or buy them. AlternativeTo allows anyone to register and suggest new alternatives, or to update the information held about existing entries. Suggestions and alterations are reviewed before being made publicly visible. Users can register using either email and password or OpenID. Login with Facebook has been discontinued. As AlternativeTo is itself a web application, it even has a page for alternatives to itself. == Features == Tweets from anyone mentioning particular pieces of software are also pulled in dynamically from Twitter. Each application has an RSS feed for notifying users of newly listed alternatives to that application. After a user has clicked the Like button next to an application, they are offered the opportunity to tell their friends on Facebook or their followers on Twitter that they liked it. The site also has a forum. For software developers, a JSON API used to be available, but has been taken down indefinitely.
JDoodle
JDoodle is a cloud-based online integrated development environment and compiler platform that supports execution of source code in 70+ programming languages including Java, Python, C/C++, PHP, Ruby, Perl, HTML, and more. It provides zero‑setup code for compilation, execution, and sharing via a web browser interface. == Features == Provides real‑time collaboration and code embedding via shareable URLs and APIs Offers an integrated terminal interface supporting database engines such as MySQL and MongoDB. JDroid — AI‑assistant to generate code snippets, optimize code, and assist debugging. == Languages and frameworks supported ==
Misskey
Misskey (Japanese: ミスキー, romanized: Misukī) is an open source, federated, social networking service created in 2014 by Japanese software engineer Eiji "syuilo" Shinoda. Misskey uses the ActivityPub protocol for federation, allowing users to interact between independent Misskey instances, and other ActivityPub compatible platforms. Misskey is generally considered to be part of the Fediverse. Despite being a decentralized service, Misskey is not philosophically opposed to centralization. The name Misskey comes from the lyrics of Brain Diver, a song by the Japanese singer May'n. == History == Misskey was initially developed as a BBS-style internet forum by high school student Eiji Shinoda in 2014. After introducing a timeline feature, Misskey gained popularity as the microblogging platform it is today. In 2018, Misskey added support for ActivityPub, becoming a federated social media platform. The flagship Misskey server, Misskey.io, was started on April 15, 2019. Misskey, alongside Mastodon and Bluesky, has received attention as a potential replacement for Twitter following Twitter's acquisition by Elon Musk in 2022. On April 8, 2023, Misskey.io incorporated as MisskeyHQ K.K. As of February 2024, over 450,000 users were registered, making it the largest instance of Misskey. Misskey.io is crowdfunded. The administrator of Misskey.io is Japanese system administrator Yoshiki Eto, who operates under the alias Murakami-san. Eiji Shinoda serves as director. In July 2023, Twitter introduced extreme restrictions on their API in order to combat scraping from bots. Some users were critical of the changes, and as a result migrated to other social networks. The number of users registering on Misskey.io, Misskey's official instance and the largest one, increased rapidly, with other Misskey instances also receiving a spike in signups. In response to this trend, Skeb, a platform for sharing art, announced on July 14, 2023 that it would sponsor the Misskey development team. In early 2024, Misskey was targeted by a spam attack from Japan. The cause of the attack is believed to be a dispute between rival groups on a Japanese hacker forum and a DDoS attack on a Discord bot. Mastodon instances with open registration were used in the attack. In November 2025, Eto announced intentions to replace ActivityPub with Misskey's own low-overhead federation system in "a few years". Shinoda later said that this was "fake news". == Development == Misskey is open source software and is licensed under the AGPLv3. The Misskey API is publicly available and is documented using the OpenAPI Specification, which allows users to build automated accounts and use it on any Misskey instance. The service is translated using Crowdin. Misskey is developed using Node.js. TypeScript is used on both the frontend and backend. PostgreSQL is used as its database. Vue.js is used for the frontend. == Functionality == Posts on Misskey are called "notes". Notes are limited to a maximum of 3,000 characters (a limit which can be customized by instances), and can be accompanied by any file, including polls, images, videos, and audio. Notes can be reposted, either by themselves or with another "quote" note. Misskey comes with multiple timelines to sort through the notes that an instance has available, and are displayed in reverse chronological order. The Home timeline shows notes from users that you follow, the Local timeline shows all notes from the instance in use, the Social timeline shows both the Home and Local timeline, and the Global timeline shows every public note that the instance knows about. Notes have customizable privacy settings to control what users can see a note, similar to Mastodon's post visibility ranges. Public notes show up on all timelines, while Home notes only show on a user's Home timeline. Notes can also be set to be available only for followers. Direct messages using notes can be sent to users.
Language model benchmark
A language model benchmark is a standardized test designed to evaluate the performance of language models on various natural language processing tasks. These tests are intended for comparing different models' capabilities in areas such as language understanding, generation, and reasoning. Benchmarks generally consist of a dataset and corresponding evaluation metrics. The dataset provides text samples and annotations, while the metrics measure a model's performance on tasks like answering questions, text classification, and machine translation. These benchmarks are developed and maintained by academic institutions, research organizations, and industry players to track progress in the field. In addition to accuracy, the metrics can include throughput, energy efficiency, bias, trust, and sustainability. == Overview == === Types === Benchmarks may be described by the following adjectives, not mutually exclusive: Classical: These tasks are studied in natural language processing, even before the advent of deep learning. Examples include the Penn Treebank for testing syntactic and semantic parsing, as well as bilingual translation benchmarked by BLEU scores. Question answering: These tasks have a text question and a text answer, often multiple-choice. They can be open-book or closed-book. Open-book QA resembles reading comprehension questions, with relevant passages included as annotation in the question, in which the answer appears. Closed-book QA includes no relevant passages. Closed-book QA is also called open-domain question-answering. Before the era of large language models, open-book QA was more common, and understood as testing information retrieval methods. Closed-book QA became common since GPT-2 as a method to measure knowledge stored within model parameters. Omnibus: An omnibus benchmark combines many benchmarks, often previously published. It is intended as an all-in-one benchmarking solution. Reasoning: These tasks are usually in the question-answering format, but are intended to be more difficult than standard question answering. Multimodal: These tasks require processing not only text, but also other modalities, such as images and sound. Examples include OCR and transcription. Agency: These tasks are for a language-model–based software agent that operates a computer for a user, such as editing images, browsing the web, etc. Adversarial: A benchmark is "adversarial" if the items in the benchmark are picked specifically so that certain models do badly on them. Adversarial benchmarks are often constructed after state of the art (SOTA) models have saturated (achieved 100% performance) a benchmark, to renew the benchmark. A benchmark is "adversarial" only at a certain moment in time, since what is adversarial may cease to be adversarial as newer SOTA models appear. Public/Private: A benchmark might be partly or entirely private, meaning that some or all of the questions are not publicly available. The idea is that if a question is publicly available, then it might be used for training, which would be "training on the test set" and invalidate the result of the benchmark. Usually, only the guardians of the benchmark have access to the private subsets, and to score a model on such a benchmark, one must send the model weights, or provide API access, to the guardians. The boundary between a benchmark and a dataset is not sharp. Generally, a dataset contains three "splits": training, test, and validation. Both the test and validation splits are essentially benchmarks. In general, a benchmark is distinguished from a test/validation dataset in that a benchmark is typically intended to be used to measure the performance of many different models that are not trained specifically for doing well on the benchmark, while a test/validation set is intended to be used to measure the performance of models trained specifically on the corresponding training set. In other words, a benchmark may be thought of as a test/validation set without a corresponding training set. Conversely, certain benchmarks may be used as a training set, such as the English Gigaword or the One Billion Word Benchmark, which in modern language is just the negative log-likelihood loss on a pretraining set with 1 billion words. Indeed, the distinction between benchmark and dataset in language models became sharper after the rise of the pretraining paradigm, whereby a model is first trained on massive, unlabeled datasets to learn general language patterns, syntax, and knowledge (pretraining), and the base model is then adapted to specific, downstream tasks using smaller, labeled datasets (fine-tuning). === Lifecycle === Generally, the life cycle of a benchmark consists of the following steps: Inception: A benchmark is published. It can be simply given as a demonstration of the power of a new model (implicitly) that others then picked up as a benchmark, or as a benchmark that others are encouraged to use (explicitly). Growth: More papers and models use the benchmark, and the performance on the benchmark grows. Maturity, degeneration or deprecation: A benchmark may be saturated, after which researchers move on to other benchmarks. Progress on the benchmark may also be neglected as the field moves to focus on other benchmarks. Renewal: A saturated benchmark can be upgraded to make it no longer saturated, allowing further progress. === Construction === Like datasets, benchmarks are typically constructed by several methods, individually or in combination: Web scraping: Ready-made question-answer pairs may be scraped online, such as from websites that teach mathematics and programming. Conversion: Items may be constructed programmatically from scraped web content, such as by blanking out named entities from sentences, and asking the model to fill in the blank. This was used for making the CNN/Daily Mail Reading Comprehension Task. Crowd sourcing: Items may be constructed by paying people to write them, such as on Amazon Mechanical Turk. This was used for making the MCTest. === Evaluation === Generally, benchmarks are fully automated. This limits the questions that can be asked. For example, with mathematical questions, "proving a claim" would be difficult to automatically check, while "calculate an answer with a unique integer answer" would be automatically checkable. With programming tasks, the answer can generally be checked by running unit tests, with an upper limit on runtime. The benchmark scores are of the following kinds: For multiple choice or cloze questions, common scores are accuracy (frequency of correct answer), precision, recall, F1 score, etc. pass@n: The model is given n {\displaystyle n} attempts to solve each problem. If any attempt is correct, the model earns a point. The pass@n score is the model's average score over all problems. k@n: The model makes n {\displaystyle n} attempts to solve each problem, but only k {\displaystyle k} attempts out of them are selected for submission. If any submission is correct, the model earns a point. The k@n score is the model's average score over all problems. cons@n: The model is given n {\displaystyle n} attempts to solve each problem. If the most common answer is correct, the model earns a point. The cons@n score is the model's average score over all problems. Here "cons" stands for "consensus" or "majority voting". The pass@n score can be estimated more accurately by making N > n {\displaystyle N>n} attempts, and use the unbiased estimator 1 − ( N − c n ) ( N n ) {\displaystyle 1-{\frac {\binom {N-c}{n}}{\binom {N}{n}}}} , where c {\displaystyle c} is the number of correct attempts. For less well-formed tasks, where the output can be any sentence, there are the following commonly used scores including BLEU ROUGE, METEOR, NIST, word error rate, LEPOR, CIDEr, and SPICE. === Issues === error: Some benchmark answers may be wrong. ambiguity: Some benchmark questions may be ambiguously worded. subjective: Some benchmark questions may not have an objective answer at all. This problem generally prevents creative writing benchmarks. Similarly, this prevents benchmarking writing proofs in natural language, though benchmarking proofs in a formal language is possible. open-ended: Some benchmark questions may not have a single answer of a fixed size. This problem generally prevents programming benchmarks from using more natural tasks such as "write a program for X", and instead uses tasks such as "write a function that implements specification X". inter-annotator agreement: Some benchmark questions may be not fully objective, such that even people would not agree with 100% on what the answer should be. This is common in natural language processing tasks, such as syntactic annotation. shortcut: Some benchmark questions may be easily solved by an "unintended" shortcut. For example, in the SNLI benchmark, having a negative word like "not" in the second sentence is a strong signal for the "Contradiction" category, regardless of what the se
Cloud-based design and manufacturing
Cloud-based design and manufacturing (CBDM) refers to a service-oriented networked product development model in which service consumers are able to configure products or services and reconfigure manufacturing systems through Infrastructure-as-a-Service (IaaS), Platform-as-a-Service (PaaS), Hardware-as-a-Service (HaaS), and Software-as-a-Service (SaaS). Adapted from the original cloud computing paradigm and introduced into the realm of computer-aided product development, Cloud-Based Design and Manufacturing is gaining significant momentum and attention from both academia and industry. Cloud-based design and manufacturing includes two aspects: cloud-based design and cloud-based manufacturing. Another related concept is cloud manufacturing that is more general and popular. Cloud-Based Design (CBD) refers to a networked design model that leverages cloud computing, service-oriented architecture (SOA), Web 2.0 (e.g., social network sites), and semantic web technologies to support cloud-based engineering design services in distributed and collaborative environments. Cloud-Based Manufacturing (CBM) refers to a networked manufacturing model that exploits on-demand access to a shared collection of diversified and distributed manufacturing resources to form temporary, reconfigurable production lines which enhance efficiency, reduce product lifecycle costs, and allow for optimal resource allocation in response to variable-demand customer generated tasking. The enabling technologies for Cloud-Based Design and Manufacturing include cloud computing, Web 2.0, Internet of Things (IoT), and service-oriented architecture (SOA). == History == The term cloud-based design and manufacturing (CBDM) was initially coined by Dazhong Wu, David Rosen, and Dirk Schaefer at Georgia Tech in 2012 for the purpose of articulating a new paradigm for digital manufacturing and design innovation in distributed and collaborative settings. The main objective of CBDM is to further reduce time and cost associated with maintaining information and communication technology (ICT) infrastructures for design and manufacturing, enhancing digital manufacturing and design innovation in distributed and collaborative environments, and adapting to rapidly changing market demands. In 2014, the same research group also published the worldwide first two books on the subjects of Cloud-Based Design and Manufacturing (CBDM) and Social Product Development (SPD) with Springer, edited by Dirk Schaefer. == Characteristics == CBDM exhibits the following key characteristics: Cloud-based distributed file system High performance computing Cloud-based social collaboration Ubiquitous access to distributed big data Rapid manufacturing scalability Agility On-demand self-service Semantic Web Real-time request for quotation Pay-per-use pricing model Multi-tenancy CBDM differs from traditional collaborative and distributed design and manufacturing systems such as web-based systems and agent-based systems from a number of perspectives, including (1) computing architecture, (2) data storage, (3) sourcing process, (4) information and communication technology infrastructure, (5) business model, (6) programming model, and (7) communication. == Service models == Infrastructure as a service (IaaS) Platform as a service (PaaS) Hardware as a service (HaaS) Software as a service (SaaS) Similar to cloud computing, CBDM services can be categorized into four major deployment models: the public cloud, private cloud, hybrid cloud, and community cloud. == Research progress in Academia == The Defense Advanced Research Projects Agency (DARPA) MENTOR program Engineering and Physical Sciences Research Council cloud manufacturing program European Commission's Seventh Framework Program (EC FP7)