{
  "annotation_id": "7cf48888-840d-4cfa-83cd-53b4f53fbb91",
  "date_created": "2026-02-17T05:53:24.219000Z",
  "date_modified": "2026-02-17T05:53:24.219000Z",
  "file_hash": "61e1d311f388ba52f61a3aa3f3579f2a873b78c5fe86e653d98d190a8f8a516e",
  "private": false,
  "record": {
    "abstract": "Large programming courses struggle to provide timely, detailed feedback on student code. We developed Mark My Works, a local autograding system that combines traditional unit testing with LLM-generated explanations. The system uses role-based prompts to analyze submissions, critique code quality, and generate pedagogical feedback while maintaining transparency in its reasoning process.\n  We piloted the system in a 191-student engineering course, comparing AI-generated assessments with human grading on 79 submissions. While AI scores showed no linear correlation with human scores (r = -0.177, p = 0.124), both systems exhibited similar left-skewed distributions, suggesting they recognize comparable quality hierarchies despite different scoring philosophies. The AI system demonstrated more conservative scoring (mean: 59.95 vs 80.53 human) but generated significantly more detailed technical feedback.",
    "arxiv_id": "2601.10093",
    "authors": [
      "Yiding Qiu",
      "Seyed Mahdi Azimi",
      "Artem Lensky"
    ],
    "categories": [
      "cs.SE"
    ],
    "license": "http://creativecommons.org/licenses/by/4.0/",
    "title": "Mark My Works Autograder for Programming Courses",
    "url": "https://arxiv.org/abs/2601.10093",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "d141eb6f-85c4-4ecf-967c-6e232bbde0e3",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}