Bibliographic record
Abstract
Over half a century ago, Alan Turing proposed "the Imitation Game" as a test of whether machines such as digital computers can be said to think.Subsequent discussion of Turing tests -human-machine interactions that are importantly similar to Turing's original Imitation Game -has been limited in its understanding of what they are good for, viewing them as good either for prompting philosophical reflection on the limits of our concept of the mental or for addressing empirical questions about the machines involved in human-machine interactions.This project is an attempt to expand our understanding of what Turing tests are good for: my novel proposal is that they are good for addressing empirical questions about the humans involved in human-machine interactions.More simply put, I argue Turing tests are useful not merely as conceptual prompts or nonreflexive experimental apparatus, but as reflexive experimental apparatus.I begin with an examination of Turing's own work and of the subsequent discussion's limited understanding of the usefulness of Turing tests as either conceptual prompts or nonreflexive experimental apparatus.I then lay out the key elements of my novel proposal that they are useful as reflexive experimental apparatus.Finally, I offer a "proof of concept" for this novel proposal by describing and discussing the results of one preliminary attempt to use Turing tests as reflexive experimental apparatus.to making our experiment even more comprehensive than it would have been had I designed it alone.Each of them has my sincerest thanks.I also wish to thank Cassandra Ommerli for her early contributions to the project.Cassandra did not work with us for long, but her early contributions to the team are much
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 | 0.024 | 0.097 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.002 | 0.028 |
| Scholarly communication | 0.005 | 0.016 |
| Open science | 0.003 | 0.006 |
| Research integrity | 0.003 | 0.008 |
| Insufficient payload (model declined to judge) | 0.008 | 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".