The spin-glass phase-transition in the Hopfield model with p-spin\n interactions
Bibliographic record
Abstract
We study the Hopfield model with pure $p$-spin interactions with even $p\\geq\n4$, and a number of patterns, M(N) growing with the system size, $N$, as $M(N)\n= \\a N^{p-1}$. We prove the existence of a critical temperature $\\b_p$\ncharacterized as the first time quenched and annealed free energy differ. We\nprove that as $p\\uparrow\\infty$, $\\b_p\\to\\sqrt {\\a 2\\ln 2}$. Moreover, we show\nthat for any $\\a>0$ and for all inverse temperatures $\\b$, the free energy\nconverges to that of the REM at inverse temperature $\\b/\\sqrt\\a$. Moreover,\nabove the critical temperature the distribution of the replica overlap is\nconcentrated at zero. We show that for large enough $\\a$, there exists a\nnon-empty interval of in the low temperature regime where the distribution has\nmass both near zero and near $\\pm 1$. As was first shown by M. Talagrand in the\ncase of the $p$-spin SK model, this implies the the Gibbs measure at low\ntemperatures is concentrated, asymptotically for large $N$, on a countable\nunion of disjoint sets, no finite subset of which has full mass. Finally, we\nshow that there is $\\a_p\\sim 1/p!$ such that for $\\a>\\a_p$ the set carrying\nalmost all mass does not contain the original patterns. In this sense we\ndescribe a genuine spin glass transition.\n Our approach follows that of Talagrand's analysis of the $p$-spin SK-model.\nThe more complex structure of the random interactions necessitates, however,\nconsiderable technical modifications. In particular, various results that\nfollow easily in the Gaussian case from integration by parts fromulas have to\nbe derived by expansion techniques.\n
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 | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.001 |
| 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".