VeriForge raises perceived creativity support and lowers workload relative to a same-retrieval baseline, with mixed survival after correction¶

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

Subclaims¶

q2 i3 CSI Total was higher under VeriForge (M=81.47 vs M=69.31; r=.804) and remained significant after FDR correction; Exploration and Expressiveness subscales also survived correction. → Ruqi Sun 2026 q2 i? NASA-TLX Weighted Total was lower under VeriForge (M=48.58 vs M=57.72; r=.611) but did not survive FDR correction (q=.060); Performance remained significant while Effort was equivalent (p=.691). → 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

Paired Wilcoxon signed-rank tests in the within-subjects study (N=12) with Benjamini–Hochberg FDR correction; CSI Total "remained significant after FDR correction" with printed effect size r=.804. Exploration (q=.022) and Expressiveness (q=.017) also survived; Value showed a positive trend that did not (q=.066).

"VeriForge was associated with higher creativity support (CSI Total: 𝑀= 81.47vs. 𝑀= 69.31;𝑊= 3.0, 𝑝=. 005,𝑞=. 017,𝑟=. 804)"

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

NASA-TLX weighted total from the same paired analysis showed a positive trend that did not survive correction (printed r=.611). The authors interpret equivalent Effort (p=.691) as "cognitive reallocation rather than reduction"; Immersion did not differ (p=.578).

"lower overall cognitive workload (NASA-TLX Weighted Total:𝑀= 48.58vs. 𝑀= 57.72;𝑊= 12.0, 𝑝=. 034,𝑞=. 060,𝑟=. 611)"

Discussion¶

Related Claims¶

• Proactive flow-aware highlighting helps fiction writers recognize latent knowledge gaps they would not search for on their own — related
• VeriForge's integrated workflow is associated with higher one-week delayed recall of domain terms and a higher retention rate (exploratory) — related
• Blind expert raters judged VeriForge passages as conveying stronger perceived authorial domain competence, with other quality dimensions showing uncorrected trends — related
• Source provenance labels functioned as a seal of authority: 11 of 12 participants failed to detect a planted source-card mismatch — related