Board 128: An Automated Management Process for Digital Correction
Bibliographic record
Abstract
Abstract When students complete an assessment activity, the teacher's corrective work begins. It is done under the pressure of time. However, correcting in a relatively short time may affect the quantity and quality of feedback. It is therefore not surprising that the teacher is thinking of time-saving solutions to provide and further enrich their feedback while offering rapid correction. Traditionally, in mechanical engineering courses featuring multiple groups and a large population of students, the grading is organized so that each teacher corrects an open-ended engineering problem on an exam for all groups in the same course. Correcting this way is fairer and faster than each teacher correcting all problems for a subgroup of students. This method also blurs the Pygmalion effect. The downside is that the teacher must wait for a colleague's papers to return before they can correct their question. To recover this lost time, we developed an automated digital correction management tool (a Python script). The tool automatically splits scanned student copies by question into pdf format and then assembles, for each question, all student copies into a single file. A customized exam booklet, with known allotted number of pages for each question, was produced to ease the process. The assembled files are uploaded to a cloud storage platform, where each teacher can access their assigned file for handwritten correction on a tablet using a digital pencil. Thus, the teacher corrects at his own pace, avoiding conflicts with other correctors. The anonymity of copies is guaranteed since the identification page of the exam booklet is absent from the assembled files, and the equality of chances is reinforced. When the correction is complete, a digital mark recognition algorithm is used to extract the marks assigned to each question by the correctors. The copies are reassembled and the mark is reported automatically for each question on the main page of the exam booklet. The integration of the tool into the correction process has been seamless, since only the professor in charge has to interact with the tool and the correctors grade the copies in the same manner as usual – albeit on a tablet. Digital correction allows both the student and the teacher to benefit from the advantages of digital technology. It saves the teacher the need to carry a large number of copies and reduces the risk of loss of copies. Electronic delivery of copies to students also frees up the classroom time usually reserved for handing in copies. This time is now used more efficiently by the teacher to give feedback to the class.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".