Work done while working at Allen Institute for AI.

As advocated by [39, 38, 18], procedurally generated environments are a promising direction for testing systematic generalization of RL agents.

This material may not be published, broadcast, rewritten, or redistributed. Quotes displayed in real-time or delayed by at least 15 minutes. Market data provided by Factset . Powered and implemented by FactSet Digital Solutions . Mutual Fund and ETF data provided by LSEG .

A growing collection of pocket-sized gadgets lets you record your meetings and extract value from them. Whether sitting in class, a meeting, or an interview, I've never been fond of taking notes, and I'm far from alone. Not only does the process of scribbling something down cause me to miss what was said immediately after, but I also suffer from awful handwriting, meaning that I can rarely read the notes anyway. Recording interviews has long been a solution, but transcribing interviews is another step (with extra cost) that can leave you with thousands of words of material to sift through, much of it irrelevant. AI notetakers--massively popular at CES 2026 --have emerged to offer a new way of making IRL notetaking easier and faster, putting the power of AI into (or at least adjacent to) a portable device that evokes the microcassette recorder of yesteryear.

Our technique greatly reduces the appearance of banding, without requiring any additional computation or post-processing at reconstructiontime.

In this supplementary material, we provide the proof of all theoretical results stated in the paper. We complete the proof in 8 steps by showing statements 1 - 8 above. Markov's inequality the first term on the RHS is also O This follows from Step 8 and the fact that by Chebyshev's inequality, The reasoning here is similar to Step 1. Since the number of splits K is bounded, we only need to verify for any k { 1, 2,...,K }, null null null null 1 n null Below we'll prove 1 n null Combining the above, we obtain (30). In the last inequality we utilize (32).