VeriForge's integrated workflow is associated with higher one-week delayed recall of domain terms and a higher retention rate (exploratory)¶

Claim · All claims
Evidence · 1 study (2 entries) · causal r1 · q2 · i3 large
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i3 Participants recalled more domain-specific terms from the VeriForge condition (M=8.04 vs M=5.75; p=.008, r=.891). → Ruqi Sun 2026 q2 i3 The retention rate — proportion of original-snippet domain terms reappearing in recall — was also higher under VeriForge (M=.465 vs M=.321; p=.002, r=.883). → 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 · r1

Exploratory delayed recall task one week after the main session, with two researchers independently coding domain-specific terms; inter-rater reliability ICC(A,1)=.880 baseline, .790 VeriForge. The printed effect size is r=.891. These tests were not FDR-corrected.

"Participants recalled more domain-specific terms from the VeriForge condition ( 𝑀= 8.04vs. 𝑀= 5.75; 𝑝=. 008,𝑟=. 891)."

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 · i3 · causal · r1

Retention-rate analysis from the same delayed recall task, printed effect size r=.883; the authors note the larger denominator under VeriForge makes this comparison more conservative, consistent with deeper encoding rather than mere increased exposure.

"the retention rate, measured as the proportion of domain terms from the original story that reappeared in the recall paragraph, was also higher under VeriForge (𝑀=. 465vs. 𝑀=. 321;𝑝=. 002,𝑟=. 883)."

Discussion¶

Learner Variables¶

• Long-Term Memory — outcome: instruction changes it

Related Claims¶

• VeriForge raises perceived creativity support and lowers workload relative to a same-retrieval baseline, with mixed survival after correction — related
• Retention trajectories diverged by centre: Centre 1 retained gains at 30 days while Centre 2 showed significant post-to-delayed decay — related
• Vocabulary retention declines between immediate and first delayed recall, then rises slightly between the first and second delayed tests — related
• In Mnemosyne flashcard log data, adding a delay term improves the recall-prediction performance of exponential forgetting curve memory models. — related
• Retrieval practice improves long-term retention — a broader claim this one bears on
• Retrieval practice instructions improved final recall of translations in Experiment 1 — related
• Proactive flow-aware highlighting helps fiction writers recognize latent knowledge gaps they would not search for on their own — related
• Skilled comprehenders show superior one-week retention of a taught knowledge base despite comparable immediate recall — related
• Targeted retrieval via specific short-answer tasks improves retention of directly targeted information more than holistic retrieval via free-recall tasks — related