The DARPA SocialSim Challenge: Massive Multi-Agent Simulations of the Github Ecosystem

J Blythe; E Ferrara; D Huang; K Lerman; G Muric; Anna SAPIENZA; A Tregubov; D Pacheco; J Bollenbacher; A Flammini; P Hui; F Menczer

doi:10.5555/3306127.3331935

The DARPA SocialSim Challenge: Massive Multi-Agent Simulations of the Github Ecosystem

J Blythe, E Ferrara, D Huang, K Lerman, G Muric, Anna SAPIENZA, A Tregubov, D Pacheco, J Bollenbacher, A Flammini, P Hui, F Menczer

Dipartimento di Scienze e Innovazione Tecnologica

Risultato della ricerca: Contributo alla conferenza › Abstract › peer review

Abstract

We model the evolution of GitHub, a large collaborative softwaredevelopment ecosystem, using massive multi-agent simulations as a part of DARPA’s SocialSim program. Our best performing models and our agent-based simulation framework are described here. Six different agent models were tested based on a variety of machine learning and statistical methods. The most successful models are based on sampling from a stationary probability distribution of actions and repositories for each agent.

Lingua originale	Inglese
DOI	https://doi.org/10.5555/3306127.3331935
Stato di pubblicazione	Pubblicato - 2019
Evento	International Conference on Autonomous Agents and Multiagent Systems - Montreal QC Canada Durata: 1 gen 2019 → …

???event.eventtypes.event.conference???

???event.eventtypes.event.conference???	International Conference on Autonomous Agents and Multiagent Systems
Città	Montreal QC Canada
Periodo	1/01/19 → …

Accesso al documento

10.5555/3306127.3331935

https://hdl.handle.net/11579/181348

Altri file e collegamenti

handle

Cita questo

Blythe, J., Ferrara, E., Huang, D., Lerman, K., Muric, G., SAPIENZA, A., Tregubov, A., Pacheco, D., Bollenbacher, J., Flammini, A., Hui, P., & Menczer, F. (2019). The DARPA SocialSim Challenge: Massive Multi-Agent Simulations of the Github Ecosystem. Abstract da International Conference on Autonomous Agents and Multiagent Systems, Montreal QC Canada. https://doi.org/10.5555/3306127.3331935

@conference{c3b51e5ab856474d9c4c1ba6cc619564,

title = "The DARPA SocialSim Challenge: Massive Multi-Agent Simulations of the Github Ecosystem",

abstract = "We model the evolution of GitHub, a large collaborative softwaredevelopment ecosystem, using massive multi-agent simulations as a part of DARPA{\textquoteright}s SocialSim program. Our best performing models and our agent-based simulation framework are described here. Six different agent models were tested based on a variety of machine learning and statistical methods. The most successful models are based on sampling from a stationary probability distribution of actions and repositories for each agent.",

author = "J Blythe and E Ferrara and D Huang and K Lerman and G Muric and Anna SAPIENZA and A Tregubov and D Pacheco and J Bollenbacher and A Flammini and P Hui and F Menczer",

year = "2019",

doi = "10.5555/3306127.3331935",

language = "English",

note = "International Conference on Autonomous Agents and Multiagent Systems ; Conference date: 01-01-2019",

}

Blythe, J, Ferrara, E, Huang, D, Lerman, K, Muric, G, SAPIENZA, A, Tregubov, A, Pacheco, D, Bollenbacher, J, Flammini, A, Hui, P & Menczer, F 2019, 'The DARPA SocialSim Challenge: Massive Multi-Agent Simulations of the Github Ecosystem', International Conference on Autonomous Agents and Multiagent Systems, Montreal QC Canada, 1/01/19. https://doi.org/10.5555/3306127.3331935

TY - CONF

T1 - The DARPA SocialSim Challenge: Massive Multi-Agent Simulations of the Github Ecosystem

AU - Blythe, J

AU - Ferrara, E

AU - Huang, D

AU - Lerman, K

AU - Muric, G

AU - SAPIENZA, Anna

AU - Tregubov, A

AU - Pacheco, D

AU - Bollenbacher, J

AU - Flammini, A

AU - Hui, P

AU - Menczer, F

PY - 2019

Y1 - 2019

N2 - We model the evolution of GitHub, a large collaborative softwaredevelopment ecosystem, using massive multi-agent simulations as a part of DARPA’s SocialSim program. Our best performing models and our agent-based simulation framework are described here. Six different agent models were tested based on a variety of machine learning and statistical methods. The most successful models are based on sampling from a stationary probability distribution of actions and repositories for each agent.

AB - We model the evolution of GitHub, a large collaborative softwaredevelopment ecosystem, using massive multi-agent simulations as a part of DARPA’s SocialSim program. Our best performing models and our agent-based simulation framework are described here. Six different agent models were tested based on a variety of machine learning and statistical methods. The most successful models are based on sampling from a stationary probability distribution of actions and repositories for each agent.

UR - https://iris.uniupo.it/handle/11579/181348

U2 - 10.5555/3306127.3331935

DO - 10.5555/3306127.3331935

M3 - Abstract

T2 - International Conference on Autonomous Agents and Multiagent Systems

Y2 - 1 January 2019

ER -

The DARPA SocialSim Challenge: Massive Multi-Agent Simulations of the Github Ecosystem

Abstract

???event.eventtypes.event.conference???

Accesso al documento

Altri file e collegamenti

Fingerprint

Cita questo