R0051/2026-03-31/Q001/SRC04

Research	R0051 — Fact-Checking Gap
Run	2026-03-31
Query	Q001
Search	S02
Result	S02-R03
Source	SRC04

Warren, Shklovski & Augenstein (2025) — Fact-checkers' evidence evaluation requirements

Source

Field	Value
Title	Show Me the Work: Fact-Checkers' Requirements for Explainable Automated Fact-Checking
Publisher	ACM / CHI Conference on Human Factors in Computing Systems
Author(s)	Greta Warren, Irina Shklovski, Isabelle Augenstein
Date	2025
URL	https://arxiv.org/html/2502.09083v1
Type	Research paper

Summary

Dimension	Rating
Reliability	High
Relevance	High
Bias: Missing data	Low risk
Bias: Measurement	Low risk
Bias: Selective reporting	Low risk
Bias: Randomization	N/A — not an RCT
Bias: Protocol deviation	N/A — not an RCT
Bias: COI/Funding	Low risk

Rationale

Dimension	Rationale
Reliability	Published at CHI 2025 — premier venue for human-computer interaction research. Multi-method qualitative study.
Relevance	Directly documents how fact-checkers evaluate evidence in practice and identifies gaps in structured confidence methodology — highly relevant to the query.
Bias flags	Interview-based study — participants self-report practices. No apparent conflicts of interest.

Evidence Extracts

Evidence ID	Summary
SRC04-E01	Fact-checkers lack structured confidence expression methodology
SRC04-E02	Primary source preference and evidence quality hierarchy in practice