{"arxiv_id":"2206.12533","incoming":{"papers":1,"sentences":1,"groups":[],"unlabelled_sentences":1},"outgoing":{"papers":2,"sentences":9,"groups":[{"kind":"method_or_tool","label":"Uses the method or tool of","papers":1,"sentences":1,"quotes":[{"arxiv_id":"1908.02962","title":"CRIC: A VQA Dataset for Compositional Reasoning on Vision and Commonsense","url":"/paper/1908.02962","section":"Graph Representations","sentence":"We select 10 types of relations to reduce the computation cost following [ref] .","intent_p":0.93,"contests_p":null}]},{"kind":"data_used","label":"Uses data or values from","papers":1,"sentences":1,"quotes":[{"arxiv_id":"1908.02962","title":"CRIC: A VQA Dataset for Compositional Reasoning on Vision and Commonsense","url":"/paper/1908.02962","section":"Experimental Settings","sentence":"We evaluated our model on the CRIC [ref] , a large VQA dataset contains 1,303,271 deeper questions than other common datasets, which are randomly split into train (60%), validation (20%) and test (20%).","intent_p":0.97,"contests_p":null}]},{"kind":"comparison","label":"Compares with","papers":1,"sentences":1,"quotes":[{"arxiv_id":"1908.02962","title":"CRIC: A VQA Dataset for Compositional Reasoning on Vision and Commonsense","url":"/paper/1908.02962","section":"Experimental Results","sentence":"(3) RVC [ref] builds upon neural module networks with supervision of expert layout.","intent_p":0.91,"contests_p":null}]},{"kind":"background","label":"Cites as background","papers":1,"sentences":1,"quotes":[{"arxiv_id":"1910.03230","title":"Meta Module Network for Compositional Visual Reasoning","url":"/paper/1910.03230","section":"Introduction","sentence":"Most of existing VQA models [ref] that exhibit reasoning capabilities can be divided into three categories.","intent_p":0.93,"contests_p":null}]}],"unlabelled_sentences":5},"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/2206.12533"}}