collection curated by joecohen https://academictorrents.com/collection/networking-datasets @article{, title= {Microsoft Academic Graph - 2016/02/05}, keywords= {}, author= {Arnab Sinha and Zhihong Shen and Yang Song and Hao Ma and Darrin Eide and Bo-June (Paul) Hsu and Kuansan Wang}, abstract= {The Microsoft Academic Graph is a heterogeneous graph containing scientific publication records, citation relationships between those publications, as well as authors, institutions, journals, conferences, and fields of study. This graph is used to power experiences in Bing, Cortana, and in Microsoft Academic. }, terms= {We kindly request that any published research that makes use of this data cites our data paper listed below. Arnab Sinha, Zhihong Shen, Yang Song, Hao Ma, Darrin Eide, Bo-June (Paul) Hsu, and Kuansan Wang. 2015. An Overview of Microsoft Academic Service (MAS) and Applications. In Proceedings of the 24th International Conference on World Wide Web (WWW ’15 Companion). ACM, New York, NY, USA, 243-246. DOI=http://dx.doi.org/10.1145/2740908.2742839}, url= {https://academicgraph.blob.core.windows.net/graph-2016-02-05/index.html} } https://academictorrents.com/download/1e0a00b9c606cf87c03e676f75929463c7756fb5 @article{, title = {LBL-CONN-7 Network Traces}, journal = {}, author = {Vern Paxson}, year = {1993}, url = {http://ita.ee.lbl.gov/html/contrib/LBL-CONN-7.html}, abstract = {Description This trace contains thirty days' worth of all wide-area TCP connections between the Lawrence Berkeley Laboratory (LBL) and the rest of the world. Format The reduced trace was generated by tcp-reduce, and has the format explained in that script's documentation . Briefly, the trace is an ASCII file with one line per connection, with the following columns: timestamp duration protocol bytes sent by originator of the connection, or ? if not available bytes sent by responder to the connection, or ? if not available local host - the (renumbered) LBL host that participated in the connection remote host - the remote (non-LBL) host that participated in the connection. Remote hosts have not been renumbered, to allow for geographic analysis of the data. Please do not attempt any further traffic analysis regarding the remote hosts. state that the connection ended in. The two most important states are SF, indicating normal SYN/FIN completion, and REJ, indicating a rejected connection (initial SYN elicited a RST in reply). Other states are discussed in the tcp_reduce documentation . flags zero or more flags: L indicates the connection was initiated locally (i.e., the LBL host is the one that began the connection) N indicates the connection was with nearby U.C. Berkeley. When this dataset was captured, a filter was used so that only nntp traffic with UCB was included, so this flag is only ever set for nntp connections. Measurement The trace ran from midnight, Thursday, September 16 1993 through midnight, Friday, October 15 1993 (times are Pacific Standard Time), capturing 606,497 wide-area connections. The tracing was done on the Ethernet DMZ network over which flows all traffic into or out of the Lawrence Berkeley Laboratory, located in Berkeley, California. The raw trace was made using tcpdump on a Sun Sparcstation using the BPF kernel packet filter. Fewer than 15 SYN/FIN/RST packets in a million were dropped. Timestamps have microsecond precision. As noted above, the traffic was filtered to exclude connections with nearby UCB except for nntp. Privacy The LBL hosts in the trace have been renumbered. The remote hosts remain as full IP addresses, to allow for geographic analysis of the data. Please do not attempt any further traffic analysis regarding the remote hosts. Acknowledgements The trace was made by Vern Paxson (vern@ee.lbl.gov). In publications, please include one or more citations to the papers mentioned below, as appropriate. Publications The SF connections in this trace correspond to LBL-7 in the papers Empirically-Derived Analytic Models of Wide-Area TCP Connections, V. Paxson, IEEE/ACM Transactions on Networking, 2(4), pp. 316-336, August 1994; Growth Trends in Wide-Area TCP Connections, V. Paxson, IEEE Network, 8(4), pp. 8-17, July 1994; and Wide-Area Traffic: The Failure of Poisson Modeling, V. Paxson and S. Floyd, IEEE/ACM Transactions on Networking, 3(3), pp. 226-244, June 1995. Restrictions The trace may be freely redistributed.} } https://academictorrents.com/download/2060d7faa61dd774f9279be7f3f79cece12ed0ed @article{, title = {BU-Web-Client Network Traces}, journal = {}, author = {Oceans research group at Boston University}, year = {1994}, url = {http://ita.ee.lbl.gov/html/contrib/BU-Web-Client.html}, license = {The traces may be freely redistributed.}, abstract = {Description These traces contain records of the HTTP requests and user behavior of a set of Mosaic clients running in the Boston University Computer Science Department, spanning the timeframe of 21 November 1994 through 8 May 1995. During the data collection period a total of 9,633 Mosaic sessions were traced, representing a population of 762 different users, and resulting in 1,143,839 requests for data transfer. Format Trace logfiles contain the sequence of WWW object requests (whether the object was served from the local cache or from the network). Each log file name contains a user id number, converted from Unix UIDs via a one-way function that allows user IDs to be compared for equality but not to be easily traced back to particular users. The file name also gives the machine on which the session took place, and the Unix timestamp when the session started. Boston University is located in the United States Eastern Time Zone. For example, a file named con1.cs20.785526125 is a log of a session from user 1, on machine cs20, starting at time 785526125 (12:42:05 EST, Tuesday, November 22, 1994). Each line in a log corresponds to a single URL requested by the user; it contains the machine name, the timestamp when the request was made, the user id number, the URL, the size of the document (including the overhead of the protocol) and the object retrieval time in seconds (reflecting only actual communication time, and not including the intermediate processing performed by Mosaic in a multi-connection transfer). An example of a line from a condensed log is: cs20 785526142 920156 "http://cs-www.bu.edu/lib/pics/bu-logo.gif" 1804 0.484092 Lines with the number of bytes equal to 0 and retrieval delay equal to 0.0 mean that the request was satisfied by Mosaic's internal cache. Measurement To collect this data we installed an instrumented version of Mosaic in the general computing environment at Boston University's Computer Science Department. This environment consists principally of 37 SparcStation 2 workstations connected in a local network, which is divided in 2 subnets. Each workstation has its own local disk; logs were written to the local disk and subsequently transferred to a central repository. We began by collecting data on a subset of the workstations only, while testing our data collection process. This period lasted from 21 November 1994 until 17 January 1995. When we were statisfied that data collection was occurring correctly, we extended the data collection process to include all workstations; data collection then took place until 8 May 1995. Since Mosaic ceased to be the dominant browser in use by early March 1995, the most representative portion of the traces are those covering the period 21 November 1995 through 28 February 1995. Privacy The user IDs in these logs have been renumbered to protect privacy. Acknowledgements These logs were collected by the members of the Oceans research group at Boston University. Mosaic was instrumented by Carlos Cunha (carro@cs.bu.edu). When referring to the use of these traces in published work, please cite Characteristics of WWW Client Traces, Carlos A. Cunha, Azer Bestavros and Mark E. Crovella, Boston University Department of Computer Science, Technical Report TR-95-010, April 1995. } } https://academictorrents.com/download/f305fe91840e1e117bdf27bd6c3970a69d90b92f