id	author	title	date	pages	extension	mime	words	sentence	flesch	summary	cache	txt
gm80ht2731s	Alec Pawling	Data Stream Summarization for Machine Learning	2011		.txt	text/plain	143	7	25	Our results indicate that while summarization based on equalwidth binning performs very well on data streams with a stationarydistribution,performance degrades on certain non-stationary distributions. Data stream summaries capture the essential characteristics of thestream in a managable amount of space.	cache/gm80ht2731s.txt	txt/gm80ht2731s.txt