Rubric-item guidance table for delegating AI feedback by criterion

Design · All designs
Evidence · 1 claim (1 mixed) · 1 study (1 design), q2 · 0 of 1 report an effect size · 1 claim rests on one study

Description

Table 1 of the article provides per-criterion recommendations for instructors using AI feedback on laboratory reports, elaborated by the authors from the analyzed experience. Objectives may be accepted after general review as the safest item to delegate; theoretical framework feedback, especially formulas and mathematical notation, should be manually reviewed; comments on experimental setup referring to images or apparatus diagrams should be verified before acceptance; data analysis requires prioritized teacher review of calculations, units, graphs, and uncertainties; conclusions should be compared with the graphical evidence cited before validating the score; and the overall assessment should be used only as an orienting input.

Design Implications

Context

Requirements

• Instructors review AI feedback differentially by rubric item, with heavier verification for items depending on mathematical and visual evidence.

Constraints

• The table is based on the authors' own elaboration from one analyzed experience in experimental physics laboratory report assessment.

Target Learners

• higher education instructors assessing physics laboratory reports

Learning Goals

• calibrated use of AI feedback across rubric criteria

Claims

• Differences between AI-generated and teacher assessments of laboratory reports may stem from difficulties retrieving and interpreting equations, graphs, tables, and units, not only from model reasoning capabilities. [~M] — why items referring to images, diagrams and calculations need teacher review

Related Designs

• Three-stage hybrid AI assessment workflow — the workflow this per-criterion guidance plugs into
• Observable, verifiable rubric criteria with citable evidence
• Report submission practices that support AI evidence retrieval

Examples

-

Key Sources

• Marcos Abreu, Cecilia Stari, Arturo C. Martí. (2026). AI-Assisted Assessment of Experimental Physics Laboratory Reports: Potential, Limitations, and Support for Teaching Practice. arXiv. https://arxiv.org/abs/2609.22417

Page metadata

Field	Value
type	design
id	rubric-item-ai-feedback-guidance-table
title	Rubric-item guidance table for delegating AI feedback by criterion
description	Table 1 of the article provides per-criterion recommendations for instructors using AI feedback on laboratory reports, elaborated by the authors from the analyzed experience.
status	review
generated	by process:settle-candidates on 2026-10-10
trust	unverified — no one has confirmed this page's content
sources	1 — marcos-abreu-2026

Frontmatter is the page's machine-readable record — see the Schema & Guide.