A Method to Detect Anomalies in Complex Socio-Technical Operations Using Structural Similarity
Bibliographic record
Abstract
Traditional techniques for accident investigation have hindsight biases. Specifically, they isolate the process of the accident event and trace backward from the event to determine the factors leading to the accident. Nonetheless, the importance of the contributing factors towards a successful operation is not considered in conventional accident modeling. The Safety-II approach promotes an examination of successful operations as well as failures. The rationale is that there is an opportunity to learn from successful operations, in addition to failure, and there is an opportunity to further differentiate failure processes from successful operations. The functional resonance analysis method (FRAM) has the capacity to monitor the functionality and performance of a complex socio-technical system. The method can model many possible ways a system could function, then captures the specifics of the functionality of individual operational events in functional signatures. However, the method does not support quantitative analysis of the functional signatures, which may demonstrate similarities as well as differences among each other. This paper proposes a method to detect anomalies in operations using functional signatures. The present work proposes how FRAM data models can be converted to graphs and how such graphs can be used to estimate anomalies in the data. The proposed approach is applied to human performance data obtained from ice-management tasks performed by a cohort of cadets and experienced seafarers in a ship simulator. The results show that functional differences can be captured by the proposed approach even though the differences were undetected by usual statistical measures.
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 | 0.005 | 0.003 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 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".