Bibliographic record
Abstract
This thesis discusses the implementation of a set of logical forms to enrich the way meaning is modeled in a vector-based system of conceptual memory.Vector-space models can account for a variety of psycho-linguistic phenomena by representing relationships between concepts as distance in a high-dimensional space.But they lack logical organizational structure without which inferential operations are impossible.Augmenting cognitive architectures with innate, logical structures might be the key to resolving this issue.But proposing such structures risks over-attributing the complexity of behavior to complexity in the architecture.I propose using Kant's critical work for a strong theory to select a minimal set of logical forms.The Kantian logical forms are implemented onto vector space architecture in a system (Kantian-HDM) created in R programming language and has been published on GitHub.The results of the simulations run in the system are presented along with a description of the inferential behavior exhibited.First and foremost, I would like to thank my co-supervisors Andrew Brook and Robert West.Without Andrew's brilliant course on Kant, I would never have been able to give this work the philosophical direction vital to it.The many discussions I had with Rob were crucially important to stay motivated as I navigated the highly intersectional domain of this work.Their support in preparation and writing of this thesis was critical for its success.Second, I am grateful to Raj Singh for introducing me to the domain of computational linguistics and providing key feedback for this work.Thirdly, I want to extend my gratitude to Mathew Kelly who made himself available to help me through the often obscure literature and models on the topic of this thesis.I must also take a moment to thank my parents and sister who never faltered in their support for my pursuits.Finally, I would like to thank Garima Arora
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 | 0.002 | 0.005 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.006 |
| Scholarly communication | 0.003 | 0.008 |
| Open science | 0.001 | 0.003 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.005 | 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".