SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.22244 · NeurIPS · 2024

Abrupt Learning in Transformers: A Case Study on Matrix Completion

Wei Hu, Pulkit Gopalani, Ekdeep Singh Lubana

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 2 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 failures of our instrument; 0 no recorded run), measured 2026-11-22; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2410.22244.json · badge: /api/ran/2410.22244.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
pulkitgopalani/tf-matcomp canonical (classifier label)
classifier basis: census
4 ran · 0 no recorded run
FunctionStatusWhere it lives
nuc_norm_alt Ran
ran, honoured the contract we drafted
pulkitgopalani/tf-matcomp/src/cvx_nuc_norm.py
pointer only (licence: NONE) · get_code("d1ff93c599a81f10")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, pulkitgopalani/tf-matcomp when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

nuc_norm_solver Ran
ran, honoured the contract we drafted
pulkitgopalani/tf-matcomp/src/cvx_nuc_norm.py
pointer only (licence: NONE) · get_code("5f8df68b6eb2411c")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, pulkitgopalani/tf-matcomp when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

rank_approx Ran
ran; our contract draft was wrong, not the code
pulkitgopalani/tf-matcomp/src/copy_check.py
pointer only (licence: NONE) · get_code("87164d0476074ab4")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, pulkitgopalani/tf-matcomp when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

reg_mse_solver Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
pulkitgopalani/tf-matcomp/src/cvx_nuc_norm.py
pointer only (licence: NONE) · get_code("594821afeae903a9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, pulkitgopalani/tf-matcomp when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 4 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Recent analysis on the training dynamics of Transformers has unveiled an interesting characteristic: the training loss plateaus for a significant number of training steps, and then suddenly (and sharply) drops to near-optimal values. To understand this phenomenon in depth, we formulate the low-rank matrix completion problem as a masked language modeling (MLM) task, and show that it is possible to train a BERT model to solve this task to low error. Furthermore, the loss curve shows a plateau early in training followed by a sudden drop to near-optimal values, despite no changes in the training procedure or hyper-parameters. To gain interpretability insights into this sudden drop, we examine the model's predictions, attention heads, and hidden states before and after this transition. Concretely, we observe that (a) the model transitions from simply copying the masked input to accurately predicting the masked entries; (b) the attention heads transition to interpretable patterns relevant to the task; and (c) the embeddings and hidden states encode information relevant to the problem. We also analyze the training dynamics of individual model components to understand the sudden drop in loss.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2410.22244")
get_code_for_paper("2410.22244")
have("2410.22244")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2410.22244.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2410.22244.svg)](https://syntology.ai/paper/2410.22244)

Connect an agent — have() is free.