Low comment rewriting does not imply a smooth process: students describe the main effort as verifying generated code rather than revising prompts¶

Claim · All claims
Evidence · 1 study · qualitative r2 · q2
Currency · no dated study recorded · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? The low rate of explicit comment rewriting does not imply a smooth process; many students described the main effort as checking generated code, interpreting test results, and deciding whether output matched intended behavior. → verify-burden

Evidence¶

verify-burden¶

Nasser Giacaman, Valerio Terragni, Paul Denny, and Viraj Kumar. 2026. Commenting with Copilot: A Taxonomy and Multi-Year Analysis of Student Code-Generation Specifications. Proceedings of the 2nd ACM Virtual Global Computing Education Conference (SIGCSE Virtual 2026). https://doi.org/10.1145/3795867.3830978

q2 · i? · qualitative · r2

Authors' interpretation in the Discussion connecting the RQ2 modification results to the Verification burden theme from the reflection analysis; the article states "work shifted from rewriting prompts to reviewing generated code". No effect size is printed.

"The reflections suggest that this does not mean the process was easy. Instead, many students described the main effort as checking generated code, interpreting test results, and deciding whether output matched intended behavior."

Discussion¶

Related Claims¶

• Students used visualizations to verify their own reasoning rather than as primary explanation tools, valuing control over their cognitive effort (agency) — related
• Students shift toward How comments for procedural constructs: 94.3% of Multi-Step-Block and 57.3% of Loop-Iteration comments were How comments — related
• Students rarely rewrite specification comments: within the first 10 attempts, Unchanged (48.4%) and New (41.3%) dominate while substantial revisions total only 4.4% — related
• Student reflections identify speed and scaffolding as the dominant theme, with verification burden, overreliance worries, and prompt precision also prevalent — related
• Comment revision effort concentrates on Multi-Step-Block and other procedural constructs, with the widest flows ending in Heavy Modification — related
• GenAI use involves substantial hidden labor of prompting, verification, and correction that remains invisible in productivity evaluation — a broader claim this one bears on
• Within a single LLM session, students' help-seeking shifts toward answer- and verification-seeking while explicit self-regulation modestly increases — related
• Design students report low trust in GenAI outputs and systematically modify and verify them, with inaccuracy the main deterrent — related
• LLMs redistributed educational labor while family and institutional rules left parents and professionals responsible for interpreting outputs and deciding how they entered practice — related
• Trained students more often identify and remediate GenAI deficiencies such as visual errors and reasoning flaws — related
• Active engagement with AI outputs (cross-verifying, refining prompts, revising) supports productive learning and depends on learners' prior knowledge — related
• Student narratives complicated the educator assumption that copied AI answers imply no learning, revealing invisible post-AI learning activities — related
• Chat-driven vibe-coding builders converge on a single generate-and-check script whose dominant time cost is dead waiting for the tool — related
• Coded prompt logs show different prompting strategies foreground different pedagogical themes, with technical prompts the largest strategy total (398 instances) — related
• Physical Strain, reported by 120 participants, comprises visual fatigue and session exhaustion from reading and verifying AI outputs — related
• Instructors engage LLM-generated suggestions as a controllable refinement process — related
• Students use self-initiated strategies of verification, skill improvement, post-editing, pre-editing and reliance management to cope with GenAI challenges — related
• Classroom verification norm is predicted to show threshold behavior and hysteresis rather than a smooth response to teacher-set requirements — related