Papers › Repeat After Me: Transformers are Better than State Space Models at Copying

Repeat After Me: Transformers are Better than State Space Models at Copying

1 Feb 2024arXiv:2402.01032archive 2025-07-28

Samy Jelassi, David Brandfonbrener, Sham M. Kakade, Eran Malach

Transformers are the dominant architecture for sequence modeling, but there is growing interest in models that use a fixed-size latent state that does not depend on the sequence length, which we refer to as "generalized state space models" (GSSMs). In this paper we show that while GSSMs are promising in terms of inference-time efficiency, they are limited compared to transformer models on tasks that require copying from the input context. We start with a theoretical analysis of the simple task of string copying and prove that a two layer transformer can copy strings of exponential length while GSSMs are fundamentally limited by their fixed-size latent state. Empirically, we find that transformers outperform GSSMs in terms of efficiency and generalization on synthetic tasks that require copying the context. Finally, we evaluate pretrained large language models and find that transformer models dramatically outperform state space models at copying and retrieving information from context. Taken together, these results suggest a fundamental gap between transformers and GSSMs on tasks of practical interest.

PaperPDFCodeCode Syntology ran

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 10 code samples harvested from 1 repository linked to this paper: 10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: official repository: 10 samples from 1 repository, 10 ran (6 with no instrument failure; 4 where Syntology's instrument failed). The run record, sample by sample. “Ran” means executed on a synthesized input, not that the code is correct or reproduces the paper.

No sample is linked to this paper from 1 of its repositories that Syntology harvested for other papers:

Levels written on 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

sjelassi/transformers_ssm_copy officialmentioned in papermentioned on GitHubpytorchMITSyntology: 10 samples, 10 ran (4 instrument-failed) · 0 unverified report
hazyresearch/based mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Zoology: Measuring and Improving Recall in Efficient Language Models (arXiv:2312.04927; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

10 samples harvested: 10 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 1 violated, 4 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page last changed ; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

1ran · honoured contract
1ran · violated contract
4ran · our draft was wrong
4ran

Licence: 0 of the 10 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from sjelassi/transformers_ssm_copy. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

Each sample ends with its code_sha256. A sample's code_sha256 is Syntology's identity for that exact code. It is printed in full (16 hexadecimal characters for every sample in this build), and get_code(code_sha256="…") takes it exactly as printed. An agent calls it on Syntology's MCP service (how to connect); click an identity to copy that call.

Repository labels, per sample. official repository: The archive marks this repository official for the paper. named in the paper: The archive records that the paper mentions this repository; it is not marked official. community (archive-listed): In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper. found in paper text by Syntology: Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted. community: Not in the archive's code links for this paper; a community repository Syntology harvested. Samples are grouped by repository: a repository marked official first, then by how directly the repository is tied to the paper, then in the archive's order; never by how many ran. Licence labels name the repository's licence as recorded at harvest. “Pointer only” means Syntology does not serve that copy's text, for one of six reasons: no licence file was found; the licence was not identified; the licence is recorded as permissive but that copy's record is not marked cleared; the licence is outside the permissive list Syntology serves text under (MIT, Apache-2.0, BSD and similar); this paper's copy was not located, so its licence is not recorded; or this paper's copy is cleared, but the stored copy of the same code that Syntology serves is not. Some licences outside that list permit redistribution, such as WTFPL, and GPL-3.0 under its conditions; they are simply not on the list. Hover a licence label for the reason. File links open the file on GitHub at the default branch, which may have changed since the harvest.

A function or class name links to its page when the name occurs in the harvested code of at least 5 papers; the name is a string, not an identity.

sjelassi/transformers_ssm_copy official repository 10 samples, 10 ran (4 instrument-failed) · 0 unverified
arr_to_str synthetic_exps/data_utils.py ran · our draft was wrong fingerprinted MIT (permissive) · 0d92dcc623352c2c · report fixture: signature x:list/1/int · returned str · level recorded 2026-09-24
build_mpt_alibi_tensor synthetic_exps/models/alibi_model.py ran MIT (permissive) · f25aff9e401bdd61 · report fixture: signature num_heads:int/0/int, sequence_length:int/0/int, alibi_bias_max:int/0/int, device:NoneType/0/? · returned Tensor · level recorded 2026-09-24
ce_loss in 34 papers synthetic_exps/train_utils.py ran MIT (permissive) · b9b929da44e45018 · report fixture: signature inputs:Tensor/2/int, logits:Tensor/3/float, mask:Tensor/2/float, TO_TOKEN:dict/0/? · returned Tensor · level recorded 2026-09-24
custom_get_scheduler synthetic_exps/train_utils.py ran MIT (permissive) · 72642a4d8a990cb5 · report fixture: signature optimizer:Adam/0/?, num_training_steps:int/0/int · returned LambdaLR · level recorded 2026-09-24
exact_match_score in 82 papers pretrained_exps/qa_evaluation_utils.py ran · violated contract fingerprinted MIT (permissive) · 67b1c1bbca4316ab · report fixture: signature prediction:str/0/str, ground_truth:str/0/str · returned bool · level recorded 2026-09-24
f1_score in 121 papers pretrained_exps/qa_evaluation_utils.py ran · honoured contract fingerprinted MIT (permissive) · 933e94e11554ccb1 · report fixture: signature prediction:str/0/str, ground_truth:str/0/str · returned float · level recorded 2026-09-24
generate_str_unique_ngram synthetic_exps/data_utils.py ran MIT (permissive) · 0314589d134038a1 · report fixture: signature len1:int/0/int, n_gram:int/0/int, length_answer:int/0/int, vocab_size:int/0/int · returned tuple · level recorded 2026-09-24
get_optimizer in 228 papers synthetic_exps/train_utils.py ran · our draft was wrong MIT (permissive) · 32a6a2b055feb482 · report fixture: signature model:callable/0/?, args:Args/0/? · returned AdamW · level recorded 2026-09-24
normalize_answer in 304 papers pretrained_exps/qa_evaluation_utils.py ran · our draft was wrong fingerprinted MIT (permissive) · c29fc928dae85749 · report fixture: signature s:str/0/str · returned str · level recorded 2026-09-24
rand_num synthetic_exps/data_utils.py ran · our draft was wrong MIT (permissive) · b80507bc684ce720 · report fixture: signature length:int/0/int, vocab_size:int/0/int · returned str · level recorded 2026-09-24

Tasks

State Space Models

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections