{"arxiv_id":"2305.16199","incoming":{"papers":0,"sentences":0,"groups":[],"unlabelled_sentences":0},"outgoing":{"papers":4,"sentences":5,"groups":[{"kind":"method_or_tool","label":"Uses the method or tool of","papers":1,"sentences":1,"quotes":[{"arxiv_id":"1412.6980","title":"Adam: A Method for Stochastic Optimization","url":"/paper/1412.6980","section":"Hyperparemeter Settings","sentence":"The models are optimized using the ADAM optimizer [ref] with the momentum set to 0.99 and a fixed learning rate of $0.002$.","intent_p":0.99,"contests_p":null}]},{"kind":"background","label":"Cites as background","papers":3,"sentences":4,"quotes":[{"arxiv_id":"1312.6114","title":"Auto-Encoding Variational Bayes","url":"/paper/1312.6114","section":"Background","sentence":"such posterior is employing the variational auto-encoder (VAE) [ref] .","intent_p":0.86,"contests_p":null},{"arxiv_id":"2204.02311","title":"PaLM: Scaling Language Modeling with Pathways","url":"/paper/2204.02311","section":"Introduction","sentence":"text generation [ref] , dialogue modeling [ref] , as well as analyzing the data used for pretraining large language models [ref] .","intent_p":0.95,"contests_p":null},{"arxiv_id":"2212.10819","title":"Attend to the Right Context: A Plug-and-Play Module for Content-Controllable Summarization","url":"/paper/2212.10819","section":"Introduction","sentence":"downstream applications, including summarization [ref] ,","intent_p":0.91,"contests_p":null}]}],"unlabelled_sentences":0},"claims":[],"thresholds":{"intent_p":0.8,"supports_p":0.95,"contests_p":0.7},"method":"Citing sentences come from each paper's LaTeX source; every \\cite marks the sentence and the works it cites. Pith's classifier typed each sentence. A label is shown at intent probability 0.8 or more (0.95 for support), a contest at 0.7 or more. Measured accuracy against two blind model families is at https://pith.science/accuracy. The quoted sentences are the citing authors' own.","held_up":null,"_links":{"html":"https://pith.science/paper/2305.16199"}}