"The world needs automated fact checking, and the world is going to get it."
Today’s “always on” environment, together with social media, really does give us the ability to hear anything said by anyone, anywhere, anytime. Ironically, this flood of material makes it difficult to know what is actually true! Knowing the believability and accuracy of what we read, hear and see is important around the world -- and no less important for us here in the world’s leading democracy.
Fact checking is the process of verifying what someone has said, and then receiving a rating about the accuracy of the ‘fact.’ Fact checking enables us to sort through a tidal wave of massive information and communication.
Some fact checking services exist, but none are instant.
Fact checking today is done mostly by qualified humans. It’s a laborious, time-consuming process that is not easy, quick, cheap or comprehensive. There simply aren’t enough journalism researchers with the skills to verify all the claims made by our political candidates and public figures. It often takes a day or more to verify the accuracy of statements, especially in the context that they were made. And as time elapses, the truth moves further and further away from us.
The critical time to know if political claims and statements are accurate is now -- as we read or view it. Therefore, the breakthroughs sought in this prize are those that improve speed of results in fact checking.
Challenge Guidelines updated 3 October 2016.
The prize offers a total purse of US$50,000 in a competition to develop faster ways to check facts through automation-- whether instantaneous, or just faster than humans can check. This breakthrough will enable people to know if something they see or hear is accurate when it’s most relevant: ASAP.
We invite you or your team to create a solution to increase timeliness of fact checking. We encourage teams to leverage the power of computers, of search technologies, software algorithms, machine learning, natural language processing technologies, crowdsourced checking, data science, voice intonation or facial emotion analyses, chatbots, and even existing technologies such as Facebook’s anti-fake news tool.
TRUTH RATING - How true is a claim or statement? Your solution must assign a “truth rating” to each claim or statement tested and achieve at least 80% accuracy for the competition overall.
To be eligible for an award. The truth rating must use the following scale:
Creation of Truth Rating. Teams have 2 options to create the Truth Rating. Teams may choose only one option for answering all claims:
To push available technology ahead a quickly as possible, this allowance for a human-assigned Truth Rating will be accepted if teams choose option A. For option A, teams may still only input the claim into their software and must receive all results by automated means, however, they may use human input to analyze these results and assign a Truth Rating.
AUTOMATION- automated fact checking will revolutionize our society. Your solution must be automated to be eligible for an award. Only the following tasks can be completed by a person:
FAST AND FURIOUS - The fastest solution to assign accurate “truth ratings” via automation will win. It’s that simple.
The challenge has three parts:
The competition is your canvas! Teams will submit a description of their approach to increase the speed of fact checking. This can include the technologies and tools they will leverage, any original pieces of technology in process or fully created, the intent/vision for their solution, and a description of how these elements will be developed into their entry. Teams may cite prior work or work that team members have undertaken as part of their description.
Teams are encouraged to provide a clear picture of the method used to develop their submission, as well as the intended features and strengths of the solution. Entrants may submit written descriptions, technical descriptions, results of outcomes, as well as photos, drawings, video, comparative examples, and/or other media. A maximum of 1,500 words (approximately 3 pages) is allowed for the submission.
FACT CHECKING SPEED TEST
All registered innovators participate in a real time race to check the truth behind stated claims. Innovators will receive a series of quizzes (consisting of multiple claims) in which they must use their automated solution to determine the truth (and assign a “truth rating” if elected) to each claim in the quiz, and submit their answers in the fastest time possible while achieving at least 80% accuracy over the course of the competition. Winners will be selected based on the team that scores the highest RABBIT marks - awarded based on speed of accurate answers.
Quiz release dates and times are outlined below in "Quiz Schedule". Teams will check each claim in the quiz and determine if it is TRUE, Somewhat TRUE, Somewhat FALSE, or FALSE. Teams also have the option to copy and paste their automated justification into the submission form if they elect this option (Option A). Results may only be submitted to HeroX as a batch (answer all the claims in a quiz at the same time). Each quiz will be given an expiration, and after this time no further submissions for the quiz will be allowed. Teams can submit only once per batch.
Scoring will be based on both accuracy and speed of results for each quiz.
The fastest submissions will be considered in this order:
Note that “second degree correct” answers will count toward the minimum accuracy achievement of 80%, regardless of whether RABBIT marks are awarded.
Optional Practice Runs will be held prior to the start of the Fact Checking Speed Test. This is solely for the purpose of enabling teams to test their software and submission posting process. None of these results will count toward the Speed Rating.
Once the Fact Checking Speed Tests are completed, the top placing teams must provide a write up detailing their solution and verify the use of automation to achieve their results. These teams must submit proof of automation to the Judges to confirm that results were achieved via automated (not manual) means. Upon request, teams will have three calendar days to submit their proof of automation. Teams must prove automation in order to be eligible for an award. Teams will be required to demonstrate automation using only the Truth Rating creation method chosen. Any team who cannot verify automation will be disqualified from the competition, regardless of their results.
An automated solution is one which the solution does not require human involvement, with the exception of the following tasks:
The burden for proof of automation will rest upon the teams. Each fact checking solution will be unique, thus teams must determine the best means to prove automation to the judges for their unique solution. The following examples may or may not be sufficient to substantiate your unique solution:
Judges may request additional information or additional testing to verify automation if your provided material is inconclusive or insufficient.
Prizes will be awarded to the teams with the fastest Speed Rating who achieve at least 80% accuracy (and receive a Pass for verifying automated results):
1st Place: $40,000 for fastest Speed Rating
2nd Place: $10,000 for second fastest Speed Rating
Tiebreakers for the prize award will be based on the speed of checking the most difficult claims. The Judging panel will pre-identify and designate a subset of the most “difficult” claims as tiebreakers. The tiebreaker status of the claims will not be disclosed unless a tie occurs. The team with the most RABBIT ratings for these claims will be the winner.
Claims to be tested will include, but are not limited to, information about/provided by either U.S. politicians or public figures. Fact checking will be tested for a variety of fact checking elements. Please see the list of Practise Claims for more information.
The results of the competition will be leveraged and promoted by a respected media figure. Diane Francis is an award-winning columnist, author, investigative journalist, television commentator, and screenplay writer. She is Editor-at-Large at Canada’s National Post and writes for the US Edition of the Huffington Post. Ms. Francis intends to pursue partnerships and collaborations with key media and journalism partners once the competition has concluded. These partnerships will spur the use and trust in fact checking.
Post-prize activities may include efforts to secure additional grants or funding for the technology and to commercialize the winning solution developed in the competition. Teams competing in this Challenge will retain control of their IP, but also agree to provide access to their technology in the form of a licensing agreement, or, receive a stake in a commercial enterprise in exchange for use of their technology (assuming they are the eventual 1st or 2nd place winner). Exact terms of any partnership will be mutually negotiated.
The Judging panel will determine the correct answer to each claim, and will determine the accuracy rating by which teams results are compared. Although some degree of interpretation in unavoidable, particularly between True and Somewhat True (or False and Somewhat False), the Judging panel’s determination of the correct answer will be used as the standard by which team submissions are judged.
Automated fact checking is defined as the use of non-human means to check, research, and/or provide context to the claim. However humans may input the claims on the quizzes manually into the software and initiate the checking. Humans may also take the results rendered and post/submit the results.
For validation of automation, Judges will use videoconference, in-person meetings, and/or technical reviews of the team’s entry to confirm achievement via automation (not human fact checking). If needed, the Judges will ask for the team to run test claims. The results of these test claims will not count toward the prize award, but will be used to verify eligibility for a prize award. For crowdsourcing, teams must show that the “crowd” is truly a large group of people without any special expertise in fact checking. Judges may call upon outside technical experts to assist with this validation.
November 6, 11:59 pm ET
November 7 - December 9
Fact Check Speed Testing
December 12, 11:59 pm ET
Validation Phase materials due from finalists
December 15 - January 28
January 29, 2017
The challenge is open to all individuals, private teams, public teams, and collegiate teams. Teams may originate from any country.
No specific qualifications or expertise in working with journalism, media, publishing, fact checking, political research, software, computers or other technology development is required. Challenge organizers encourage outside individuals and non-expert teams to compete and propose new solutions. To give new and innovative ideas due consideration, the judging panel may include individuals who are not subject matter experts in any of these fields.
To be eligible to compete, you must comply with all the terms of the challenge as defined in the Challenge-Specific Agreement.
Registration and Submissions:
Submissions must be made online (only), via upload to the HeroX.com website. Teams will be notified of the availability of quizzes for fact checking per a predefined schedule. Quizzes will be posted on or after these dates/times.
Submissions must be made in English. All prize-related communication will be in English.
Selection of Winners:
Based on the winning criteria, 2 prizes will be awarded per the Judging Criteria section above. A qualified Judging Panel will determine winners.
The determination of the winners will be made by a group of people including thought leaders, influencers, and people with unique insight for computational journalism and fact checking, as well as technology development in these areas. Judges will have expertise in journalism, media, publishing, fact checking, political research, software or other technology development areas.
As importantly, the Judging Panel may also include judges who have expertise in new forms of potential technology/innovation, the psychology in media, or crowd source development, but who have no background or experience related to fact checking. The intent of including these individuals is to proliferate approaches which are available but not necessarily adopted or leveraged by ordinary users -- both of which will move the field forward.
Challenge Guidelines are subject to change. Registered competitors will receive notification when changes are made, however, we highly encourage you to visit the challenge page often to review updates.
"The world needs automated fact checking, and the world is going to get it."
Fake news, misinformation, and journalistic integrity and credibility under attack -- all familiar themes from 2016. From the looks of it, the trend may continue for a while. Here's a Poynter article that makes some predictions for the next 365 days....
This is the announcement you've been waiting for.
I am pleased to introduce the three teams whose ground-breaking technology is pushing the field of automated fact checking forward. These teams will be competing in a real time Fact Checking race over the next four weeks to make automated, faster fact checking a reality.
I encourage you to comment on this post and say hello to the teams entering the race. You can also show your support for the cause by sharing on social media and with your network.
We propose to apply state-of-the-art question answering techniques that are able to generate the semantic parse of a claim. We focus on methods that can learn semantic parsers with limited training data so that our approach can be extended to different domains quickly. We plan on taking a novel step to adapt these to construct questions about the claim to be checked, and - using a knowledge base - assess its truthfulness.
Fact-checking is now a household terminology. The amount of information to be fact-checked is beyond the capability of fact-checkers. ClaimBuster will substantially improve their efficacy. Given a factual claim, it analyzes the claim, collects relevant evidence from multiple sources, and generates justifications to help fact-checkers produce a true/false rating for the claim. ClaimBuster is making strides toward our quest for the ”Holy Grail” – an automated, instant fact-checking machine.
Our solution leverages current AI technologies available for Natural Language Processing, Audio, Video and Image-Based Text Recognition An integrated web-based platform for fact-checking, leveraging latest AI & cloud computing technologies available.
There are TWO DAYS left to submit the written description of your solution in order to be eligible for the Fact Checking Speed Test! Be sure you enter before 11:59pm EST on November 6!
You CAN continue to iterate on and develop your soultion throughout the testing period.
Your fellow innovators have been asking lots of questions and we want to share the answers with you:
Anything not answered for you? Post your question in the forum!
Best of luck!
We’re Full Fact, the UK’s independent fact checking organization, and the authors of The State of Automated Factchecking. The following claims were used to test the software created by finalists in the Fast and Furious Fact Check Challenge. For more information on the types of claims used in the challenge and the Truth rating system, check out our introduction to the claims here.
America has a surface area of 9,830,000 sq km. (TRUE)
There are 103 road accidents per 1,000,000 people in America. (FALSE)
Three quarters of the US population is obese. (SOMEWHAT TRUE)
14 percent of non US citizens are registered to vote. (FALSE)
13.3% of America is Black or African American. (TRUE)
America has 13,100,950 sq km of forest area. (FALSE)
40% of the Bolivian population lives in slums. (SOMEWHAT TRUE)
In 2014, in Sub-Saharan Africa there were an estimated 1,300,000 pregnant women living with HIV. (TRUE)
Ciprofloxacin can prevent infection from Anthrax. (TRUE)
On November 4th 2015 Bernie Sanders introduced a bill to legalize drugs. (SOMEWHAT FALSE)
The United States is estimated to consume almost 20,000,000 tonnes of chicken meat in 2025. (SOMEWHAT FALSE)
In Modesto, California, 102,000 people are unemployed. (FALSE)
Kang and Kodos were candidates in the 2016 US presidential race. (FALSE)
Obama kept his promise to double federal funding for cancer research. (FALSE)
2.7% of the USA's wealth is spent on R&D. (SOMEWHAT TRUE)
Around 90,000 unaccompanied children claimed asylum in the EU in 2015. (TRUE)
Rosa Parks said "The driver wanted us to stand up, the four of us. We didn't move at the beginning, but he says, 'Let me have these seats.' And the other three people moved, but I didn't.' (TRUE)
Eating meat causes cancer. (SOMEWHAT TRUE)
Exxon-Mobil reached a total value of $772 million in 2007. (FALSE)
Canada’s immigration minister met his target to resettle 30,000 Syrian refugees four months after he intended. (SOMEWHAT FALSE)
Hamas was founded in 1995. (FALSE)
In America, in June 1901, the average temperature was 16.6C. (TRUE)
Prince Harry said "Mr. President, thank you very, very much for hosting us today, and letting us steal the paralympics from you." (FALSE)
The world life expectancy was 52 in 1960, and rose sharply to 80 in 2014. (SOMEWHAT FALSE)
Smoking is the largest single preventable cause of cancer each year in the UK. (TRUE)
Prime Minister Justin Trudeau promised an immediate commitment to inject $3 billion over four years into nuclear weapons. (FALSE)
Syrian refugees are not properly vetted or tracked by the FBI once in the US. (SOMEWHAT FALSE)
Obama restored the Great Lakes. (SOMEWHAT TRUE)
In 2014 81.6% of American teenagers were enrolled in some sort of education. (SOMEWHAT TRUE)
The U.S. has a record number of abortions year after year. (FALSE)
There are more wireless mobile broadband subscriptions than there are people in the USA. (TRUE)
More ISDS cases have been launched by companies from the United States than any other country in the world. (SOMEWHAT TRUE)
Rep. Eliot Engel is the ranking member for the House Committee on Foreign Affairs. (TRUE)
Sen. Benjamin Sasse voted against the Comprehensive Addiction and Recovery Act of 2016. (TRUE)
In 2012 there were 3,282,570 bee colonies in America. (TRUE)
According to the IMF, since 1980 China has always exported more as a proportion of GDP than Japan. (SOMEWHAT TRUE)
Hurricane Katrina was the costliest natural disaster in the history of the world. (FALSE)
In 2016, the USA contributed $550bn to the financial intermediary funds. (FALSE)
Obama broke his promise to extend child credits and marriage-penalty fixes. (FALSE)
People from Syria are almost always successful in applying for asylum in the EU. (TRUE)
The USA worked more hours than the average of the OECD countries in 2014. (SOMEWHAT TRUE)
The IMF says that the USA will be the fastest growing advanced economy in the world this year. (FALSE)
Just over 5% of pupils in the UK were educated at grammar schools in 2016. (SOMEWHAT TRUE)
In the USA in 2010, the number of homicides by firearm was almost 10,000. (SOMEWHAT FALSE)
12.9% of the total population of the USA were daily smokers in 2014. (TRUE)
97% of children in America were vaccinated against measles in 2014. (FALSE)
In the USA there were 2.4 practicing doctors for every 1000 people in 2010. (TRUE)
Mark Zuckerberg is the richest man in tech. (FALSE)
Income tax revenue is higher as a share of the total economy in Iceland than it is in the USA. (TRUE)