One model many scores: Using multiverse analysis to prevent fairness hacking and evaluate the influence of model design decisions

DOI:	https://doi.org/10.1145/3630106.3658974
URL:	https://dl.acm.org/doi/10.1145/3630106.3658974
Document Type:	Conference or workshop publication
Year of publication:	2024
Book title:	FAccT '24, The 2024 ACM Conference on Fairness, Accountability, and Transparency, Rio de Janeiro Brazil, June 3-6, 2024
Page range:	1305-1320
Conference title:	The 2024 ACM Conference on Fairness, Accountability, and Transparency (FAccT '24)
Location of the conference venue:	Rio de Janeireo, Brazil
Date of the conference:	03.-06.06.2024
Place of publication:	New York, NY
Publishing house:	Association for Computing Machinery
ISBN:	979-8-4007-0450-5
Publication language:	English
Institution:	Außerfakultäre Einrichtungen > Mannheim Centre for European Social Research - Research Department A
Subject:	004 Computer science, internet