Bibliographic record
Abstract
In t hi s paper we exam i ne Elm an's posi t i on (1999) on general i zat i on i n sim pl e recurrent net works.El m an's sim ul ati on i s a response t o M arcus et al .'s (1999) experi m ent wi t h i nfant s; specifi cal l y t hei r abi l i t y t o di fferenti ate bet ween novel sequences of syll ables of t he form ABA and ABB.El m an cont ends t hat SRN s can l earn t o general i ze t o novel sti m ul i , j ust as M arcus et al 's i nfants did.H owever, w e bel i eve that El m an's concl usi ons are overstat ed.Speci fi cal l y, we perform ed l arge bat ch experi m ent s invol vi ng si m pl e recurrent net works w i t h di fferi ng dat a sets.O ur resul t s show ed t hat SRN s are m uch l ess successful t han El m an assert ed, alt hough t here is a w eak tendency for networks t o respond m eani ngful l y, rather t han random l y, t o i nput sti m ul i .
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 | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.002 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.008 | 0.005 |
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; both teacher heads agree on what is shown here.
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".