OpenAlex Author Name Disambiguation V3 Data - Disambiguation Model
Why is this work in the frame?
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Full frame distilled prediction
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.
- Candidate categories
- Metaresearch, Meta-epidemiology (narrow), Science and technology studies, Scholarly communication, Open science, Insufficient payload (model declined to judge)
- Consensus categories
- Open science, Insufficient payload (model declined to judge)
- Domain
- Candidate signal: noneConsensus signal: none
- Study design
- Candidate signal: Not applicableConsensus signal: Not applicable
- Genre
- Candidate signal: DatasetConsensus signal: Dataset
- Teacher disagreement score
- 0.207
- Threshold uncertainty score
- 1.000
- Validation status
machine_predicted_unvalidated·codex-gemma-dda1882f352a
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.013 | 0.019 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.002 |
| Science and technology studies | 0.003 | 0.000 |
| Scholarly communication | 0.006 | 0.002 |
| Open science | 0.012 | 0.018 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.009 | 0.217 |
Machine scores (provisional)
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
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.
- Teacher spread
- 0.037 · how far apart the two teachers sit on this one work
- Validation status
score_only:v0-immature-baseline· verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it
Abstract
5 Separate files used in the OpenAlex (https://openalex.org) V3 Author Name Disambiguation Model Creation: ORCID_hard_negative_pairs: Pairs of ORCIDs where either the full name, family name, or given name are a match and would therefore be more difficult to disambiguate. Disambiguator_all_possible_training_data: Dataset created which contains all possible features for modeling and all possible samples of data. Eventually, this was split into train/val/test and also processed more to create a better balance of positive to negative samples for our purposes. Disambiguator_final_train_data: Final data which the disambiguator was trained on. Disambiguator_final_val_data: Data which was used to test the model during training to optimize the features/hyperparameters chosen. Disambiguator_final_test_data: Final dataset which gave model performance indication after all hyperparameters were tuned and features were chosen. More details can be found at https://github.com/ourresearch/openalex-name-disambiguation
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.
The record
- Venue
- Zenodo (CERN European Organization for Nuclear Research)
- Topic
- Data Quality and Management
- Field
- Decision Sciences
- Canadian institutions
- OpenAlex
- Funders
- not available
- Keywords
- Computer scienceNatural language processingArtificial intelligenceInformation retrieval
- Has abstract in OpenAlex
- yes