Comparing information extraction between \ninstance-based data models and relational data \nmodels
Bibliographic record
Abstract
Instance-based representation has been developed to overcome the limitations of class- \nbased models for storing data. A class-based data model organizes data into pre- \ndefined classes that represent specific entities within a domain. However, instance- \nbased model introduces two separated layers for representing instance and classes, \nfreeing instances from pre-defined, fixed schemas and enabling more dynamic and \n \nexible data representations. Despite the well-established theoretical foundations of \ninstance-based representation, there is little empirical research that investigates its \npractical usefulness. In this study, we conduct an experiment to compare the effec- \ntiveness of information extraction between instance-based data models and class-based \ndata models. Participants randomly received data represented using data structured \naccording to one of the models and answered information extraction/retrieval questions. The results show that, depending on the type of information extraction task, \none representation supported more effective retrieval than the other, suggesting that \nthe models can be complementary. In complex use cases including extracting infor- \nmation about relationships of instance/entities and retrieving information involving \ninstances from different classes, the instance-based model outperformed the class- \nbased model. On the other hand, for simpler use cases involving extracting infor- \nmation about cardinalities of relationships and retrieving information involving only \none entity (i.e., instances from a same class), the class-based model proved to be \nmore effective. The findings both provide empirical evidence for the effectiveness and \nusefulness of the instance-based model and demonstrate how it can complement the \nclass-based model in representing the domain.
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 | 0.002 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.002 | 0.003 |
| Science and technology studies | 0.002 | 0.000 |
| Scholarly communication | 0.001 | 0.014 |
| Open science | 0.007 | 0.003 |
| Research integrity | 0.001 | 0.002 |
| 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".