Blind expert raters judged VeriForge passages as conveying stronger perceived authorial domain competence, with other quality dimensions showing uncorrected trends¶

Claim · All claims
Evidence · 1 study (2 entries) · causal r1–r2 · q2 · i3 large
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person · recheck by 2029: tool and model accuracy changes quickly

Subclaims¶

q2 i3 Perceived authorial domain competence was rated higher for VeriForge (M=4.58 vs M=3.58; r=.818) and remained significant after FDR correction. → Ruqi Sun 2026 q2 i? Natural integration (M=4.92 vs M=4.25; q=.065) and specificity (M=4.17 vs M=3.54; q=.065) showed positive trends that did not survive correction; the uncorrected composite favored VeriForge in 10 of 12 pairs. → Ruqi Sun 2026 (2)

Evidence¶

Ruqi Sun 2026¶

Ruqi Sun, Jiaping Li, Wenhui Tao, Ximing Zheng, Yuefeng Tan, Jiahao Wei, and Yuxin Ma. (2026). VeriForge: Mitigating Latent Knowledge Gaps in Narrative Drafting via Mixed-Initiative Scaffolding. https://arxiv.org/abs/2608.09698 doi:10.48550/arxiv.2608.09698

q2 · i3 · causal · r2

Blind expert rating by two published authors of anonymized story snippets on 7-point scales across three verisimilitude-informed dimensions; printed effect size r=.818; single-rater absolute-agreement ICCs were moderate (ICC(A,1)=0.53–0.59).

"Only perceived authorial domain competence remained significant after correction ( 𝑀= 4.58vs. 𝑀= 3.58; 𝑊= 2.5, 𝑝=. 005,𝑞=. 015,𝑟=. 818)."

Ruqi Sun 2026 (2)¶

Ruqi Sun, Jiaping Li, Wenhui Tao, Ximing Zheng, Yuefeng Tan, Jiahao Wei, and Yuxin Ma. (2026). VeriForge: Mitigating Latent Knowledge Gaps in Narrative Drafting via Mixed-Initiative Scaffolding. https://arxiv.org/abs/2608.09698

q2 · i? · causal · r1

Composite expert rating from the same blind evaluation (printed r=.770); both raters independently assigned higher scores to VeriForge snippets in the same 10 pairs despite moderate scoring variance. Word count did not differ (p=.532).

"The composite score was higher for VeriForge (𝑀= 4.56vs. 𝑀= 3.79; 𝑝=. 005,𝑟=. 770), with 10 of 12 pairs favoring the system; this composite test was uncorrected."

Discussion¶

Related Claims¶

• VeriForge raises perceived creativity support and lowers workload relative to a same-retrieval baseline, with mixed survival after correction — related
• Proactive flow-aware highlighting helps fiction writers recognize latent knowledge gaps they would not search for on their own — related