Users' Manual and Validation of the Automated Grading System (AGS): Improving the Quality of Intelligence Summaries Using Feedback from an Unsupervised Model of Semantics
Bibliographic record
Abstract
Abstract : The Automated Grading System (AGS) was developed jointly by Defence Research and Development Canada (DRDC) Toronto and the Canadian Forces School of Military Intelligence (CFSMI) to provide students at the school a tool to help in the composition of accurate and effective Intelligence Summaries (INTSUMs). The AGS is a web-browser based system that provides feedback to students about how well their summary matches that of a gold standard summary written by an instructor. The AGS allows students to iteratively correct and re-submit their summaries as they attempt to maximize the match between their summary and the gold standard. In this report, we provide both the instructor and student user's manual for the AGS. Importantly, we also provide the results of a small validation study wherein we asked participants to summarize news stories about sea piracy near Somalia. Participants used feedback from the AGS to improve their summaries until they were satisfied that they had done the best job they could do. The grades given to the first and final summaries by the AGS were then compared to the grades awarded by the lead instructor at CFSMI. The tool and the instructor's assessments of the summaries were in close agreement. The results confirm that the AGS can be used as an effective teaching tool to help students improve their summary-writing skills.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.037 | 0.191 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.006 | 0.004 |
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 source (direct Gemma or distilled Codex), 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".