An Intelligent Class: The Development Of A Novel Context Capturing Method For The Functional Auto Classification Of Records
Bibliographic record
Abstract
The need to accurately classify records is a core problem in many domains. Historically, the classification of records was done manually, with those records "read" as they were received and categorized. Unfortunately, due to a significant growth in the volume of records, the need for robust auto-classification methods that can effectively "read" and classify records, is high. Today, significant challenges remain in the literature and practice relating to the development of effective, auto-classification processes. This is because the functional classification process is a challenge for both humans and machines, with little research on the steps needed to effectively functionally classify a record. In order to move research forward, this paper will address both challenges. Firstly, this paper, will seek to evaluate the efficacy of manual classifiers on a classification task, using knowledge from this process to articulate a process for functional classification that utilizes a record’s archival diplomatic context. Secondly, this paper will compare the efficacy of manual versus auto-classification using a record set with over 500,000 records, using a novel auto-classification approach that leverages a record’s archival diplomatic context, and not just its content, to improve classification accuracy. As this paper will discuss, there is significant variance between records managers during the manual classification process, with statistically significant differences in their ability to accurately classify both administrative and operational records. Moreover, this paper will demonstrate that an auto-classifier, when trained using key elements of archival diplomatic context, can statistically outperform a group of expert manual classifiers on a classification task.
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 | 0.001 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.002 | 0.003 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".