A Ukrainian soldier has described the moment a passenger train was targeted by Russian drones, killing five people. When a carriage on the train was hit in northeastern Ukraine, passengers threw themselves on the floor in panic and the military officer told them to get out immediately. Without his instruction, issued moments before the carriage burst into flames, many more passengers could have died. The officer, whose army call-sign is Omar, is part of Ukraine's 93rd brigade. He was among the passengers travelling on a route from Chop, on the border with Slovakia, to Barvinkove, the last stop before the front line in eastern Ukraine.

With demonstrations ramping up against the Trump administration, this week was all about protests. With President Donald Trump taking the historic step to deploy US Marines and the National Guard to Los Angeles, we dove into the "long-term dangers" of sending troops to LA, as well as what those troops are permitted to do while they're there. Of course, it's not just the military getting involved in the LA protests against the heavy crackdowns by Immigration and Customs Enforcement (ICE). There's also Customs and Border Protection (CBP), which further escalated federal involvement by flying Predator drones over LA. And there are local and state authorities, who've used "nonlethal" weapons and chemical agents like tear gas against protesters.

I don't know what Werner Herzog is up to these days, but if he's between projects, I humbly suggest that he make a documentary about Luna Luna, the Hamburg amusement park that took more than ten years to put together, included attractions designed by Dalí and Basquiat and Haring and Hockney, and spent thirty-five years in shipping containers. It's now been partly reassembled at the Shed, for the exhibition "Luna Luna, Forgotten Fantasy," through Jan. 5. The park's Fitzcarraldo, a poet-songwriter-pop star named André Heller, was born in Vienna in 1947 and spent much of his thirties persuading artists to decorate rides. Haring slathered a merry-go-round in melty cartoons; Basquiat dressed a Ferris wheel in his customary graffiti. The park opened to the public in 1987, largely funded by a gossip rag, and stayed that way for a summer.

As the underlying ranking policies constantly evolve, recommendation providers need to experiment offline with new approaches for ranking content before actually deploying and exposing them to the users [5, 6]. This serves the purpose of deploying only policies that have a large chance of improving the user experience. Deployed ranking policies provide a plethora of interaction logs that can be repurposed to learn and evaluate potentially better policies offline. These logs come in the form of implicit feedback, i.e., records of past interaction behavior, linked to information about the user, the context and the items to recommend. Off-policy evaluation of new policies on historic data requires adequate strategies to deal with biases coming from (i) the nature of user interaction and (ii) the logging policy. A prominent example of these biases is position bias [7] (content that is not ranked in the most visible positions is less likely to be seen). We focus on two popular classes of estimators that take different approaches to correcting for presentation bias. The first class, in the case of full visibility of all items, does not rely on explicit randomization, but models the randomness in user behavior. The most common model is the position-based model (PBM), which assumes that observed clicks on content factorize into relevance (depending on the item only) and the visibility of the content (depending on the position only).

On June 30, US Secretary of State Mike Pompeo's address to the UN Security Council calling for an arms embargo on Iran to be extended was expected to dominate the international news agenda. However, Iran's judiciary stole the morning's headlines by issuing an arrest warrant for Donald Trump the day before. Tehran prosecutor Ali Alqasimehr said on Monday that Trump, along with more than 30 others accused of involvement in the January 3 drone attack that killed Iran's top general, Qassem Soleimani, face "murder and terrorism charges". The prosecutor added that Tehran asked Interpol for help in detaining the US president. The same day, the US special envoy for Iran, Brian Hook, denounced the warrant as a "propaganda stunt" at a press conference in the Saudi capital, Riyadh.

The FBI may have scored a big win with operation Playpen, which helped dismantle a ring of TOR-based pedophiles and prosecute its members (thanks, Rule 41), but that was just one battle in the ongoing war against the sexual exploitation of children. That fight is now a bit easier for European law enforcement, which as debuted a new machine learning AI system that hunts for child porn on P2P networks. The system, known as iCOP (Identifying and Catching Originators in P2P Networks), works similarly to Microsoft's Photo DNA, wherein images of child porn are tagged with a digital signature after being collected in the course of an investigation. These signatures are then shared as a global database for law enforcement. This saves law enforcement the stomach-turning drudgery of manually checking the images against the database.