Papers › Efficiently Modeling Long Sequences with Structured State Spaces

Efficiently Modeling Long Sequences with Structured State Spaces

31 Oct 2021ICLR 2022 4arXiv:2111.00396archive 2025-07-28

Albert Gu, Karan Goel, Christopher Ré

A central goal of sequence modeling is designing a single principled model that can address sequence data across a range of modalities and tasks, particularly on long-range dependencies. Although conventional models including RNNs, CNNs, and Transformers have specialized variants for capturing long dependencies, they still struggle to scale to very long sequences of 10000 or more steps. A promising recent approach proposed modeling sequences by simulating the fundamental state space model (SSM) x′(t) = Ax(t) + Bu(t), y(t) = Cx(t) + Du(t), and showed that for appropriate choices of the state matrix A, this system could handle long-range dependencies mathematically and empirically. However, this method has prohibitive computation and memory requirements, rendering it infeasible as a general sequence modeling solution. We propose the Structured State Space sequence model (S4) based on a new parameterization for the SSM, and show that it can be computed much more efficiently than prior approaches while preserving their theoretical strengths. Our technique involves conditioning A with a low-rank correction, allowing it to be diagonalized stably and reducing the SSM to the well-studied computation of a Cauchy kernel. S4 achieves strong empirical results across a diverse range of established benchmarks, including (i) 91% accuracy on sequential CIFAR-10 with no data augmentation or auxiliary losses, on par with a larger 2-D ResNet, (ii) substantially closing the gap to Transformers on image and language modeling tasks, while performing generation 60× faster (iii) SoTA on every task from the Long Range Arena benchmark, including solving the challenging Path-X task of length 16k that all prior work fails on, while being as efficient as all competitors.

PaperPDFConference PDFCodeCode Syntology ranMethod as code

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 55 code samples harvested from 9 repositories linked to this paper: 37 ran (of which 8 constructed an object rather than computing a result; 21 with no instrument failure: 2 honoured, 1 violated, 18 with no contract checked; 16 where Syntology's instrument failed) · 18 unverified. Where Syntology's instrument failed: 14 where our contract draft was wrong; 2 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 10 samples from 1 repository, 5 ran (2 with no instrument failure; 3 where Syntology's instrument failed); community (archive-listed): 43 samples from 7 repositories, 30 ran (19 with no instrument failure; 11 where Syntology's instrument failed); community: 2 samples from 1 repository, 2 ran (0 with no instrument failure; 2 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 between 2026-09-22 and 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 5 of the 37 samples that ran have no recorded date.

state-spaces/s4 officialmentioned on GitHubpytorchSyntology: 10 samples, 5 ran (3 instrument-failed) · 5 unverified report
ag1988/dss mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (1 instrument-failed) · 0 unverified report
elgazzarr/fmri-s4 mentioned on GitHubpytorchSyntology: 12 samples, 9 ran (4 instrument-failed) · 3 unverified report
forgi86/lru-reduction mentioned on GitHubjaxSyntology: 6 samples, 4 ran (4 instrument-failed) · 2 unverified report
leonty1/essm mentioned on GitHubpytorchSyntology: 7 samples, 4 ran (2 instrument-failed) · 3 unverified report
maxtimer97/ssm-inspired-lif mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
nicolaszucchet/minimal-lru mentioned on GitHubjaxSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
srush/annotated-s4 jaxMITSyntology: 14 samples, 9 ran (0 instrument-failed) · 5 unverified 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

55 samples harvested: 37 ran (of which 8 constructed an object rather than computing a result; 21 with no instrument failure: 2 honoured, 1 violated, 18 with no contract checked; 16 where Syntology's instrument failed) · 18 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Syntology's record for this page has not changed since , the first build that kept a record date for it; when this build read Syntology's graph is in the build record. That date is not when the samples ran.

2ran · honoured contract
1ran · violated contract
14ran · our draft was wrong
2ran; the contract check could not run
18ran
18unverified

Licence: 3 of the 55 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 9 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. 1 sample whose link to this paper records no repository is listed under one of this paper's own repositories, because identical code was harvested from it for another paper. “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”. For 4 samples that ran, the graph records a signature this page does not show: for a class the fixture built without calling, the harness called the object with inputs it made up itself, so the recorded signature is the harness's probe, not the fixture's arguments. “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.

state-spaces/s4 official repository 10 samples, 5 ran (3 instrument-failed) · 5 unverified
Kernel in 16 papers models/s4/s4.py ran Apache-2.0 (permissive) · 855fe49867900076 · report fixture: returned Kernel · level recorded 2026-09-22
SSMKernel models/s4/s4.py ran Apache-2.0 (permissive) · a0aad68e21728b6a · report fixture: returned SSMKernel · level recorded 2026-09-22
cauchy_naive in 7 papers models/s4/s4.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · b7d9d94554e93b1b · report fixture: signature v:Tensor/2/float, z:Tensor/2/float, w:Tensor/2/float · returned Tensor · level recorded, date not recorded
log_vandermonde_naive in 6 papers models/s4/s4.py ran · our draft was wrong Apache-2.0 (permissive) · e25911109ba29783 · report fixture: signature v:Tensor/2/float, x:Tensor/2/float, L:int/0/int, conj:bool/0/bool · returned Tensor · level recorded, date not recorded
nplr in 6 papers models/s4/s4.py ran · our draft was wrong Apache-2.0 (permissive) · d43b03a2d76a4e41 · report fixture: signature measure:str/0/str, N:int/0/int, rank:int/0/int, dtype:dtype/0/?, diagonalize_precision:bool/0/bool, B_clip:float/0/float · returned tuple · level recorded 2026-09-22
SSMKernelDPLR models/s4/s4.py unverified Apache-2.0 (permissive) · 2e1521f562fb37ea · report
SSMKernelDiag models/s4/s4.py unverified Apache-2.0 (permissive) · b2fe7789636402f0 · report
combination in 8 papers models/s4/s4.py unverified Apache-2.0 (permissive) · 7564850110a688c1 · report
dplr in 7 papers models/s4/s4.py unverified Apache-2.0 (permissive) · 9eb8abe7e31d874d · report
ssm in 8 papers models/s4/s4.py unverified Apache-2.0 (permissive) · 64dd93f539b06f8e · report
ag1988/dss community (archive-listed) 1 sample, 1 ran (1 instrument-failed) · 0 unverified
get_initializer in 32 papers src/models/sequence/ss/standalone/dss.py identical code Syntology harvested from this repository for another paper; this paper's link records no repository, path or licence of its own ran · our draft was wrong licence of this copy not recorded · f3449af8fae1d130 · report fixture: signature name:str/0/str, activation:str/0/str · returned partial · level recorded, date not recorded
elgazzarr/fmri-s4 community (archive-listed) 12 samples, 9 ran (4 instrument-failed) · 3 unverified
LinearActivation in 16 papers src/models/sequence/ss/standalone/s4.py ran · our draft was wrong MIT (permissive) · 522a1fc1276ec144 · report fixture: signature d_input:int/0/int, d_output:int/0/int, bias:bool/0/bool, zero_bias_init:bool/0/bool, transposed:bool/0/bool, initializer:str/0/str, activation:str/0/str, activate:bool/0/bool, weight_norm:bool/0/bool · returned Linear · level recorded 2026-09-22
SE_Block src/models/sequence/ss/standalone/s4.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · a19e25de29fbaae4 · report fixture: returned SE_Block · level recorded 2026-09-22
TransposedLinear src/models/sequence/ss/standalone/s4.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 5a5e28e0e6ccd2d2 · report fixture: returned TransposedLinear · level recorded 2026-09-22
embed_c2r src/models/sequence/ss/standalone/s4.py ran · honoured contract fingerprinted MIT (permissive) · ada726a93c0d5dfc · report fixture: signature A:ndarray/2/float · returned ndarray · level recorded 2026-09-22
linear in 88 papers src/models/sequence/ss/standalone/s4.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · f1cab21ec84db199 · report fixture: returned linear · level recorded 2026-09-22
nplr in 6 papers src/models/sequence/ss/standalone/s4.py ran · our draft was wrong MIT (permissive) · 63d9be34f73a43ef · report fixture: signature measure:str/0/str, N:int/0/int, rank:int/0/int, dtype:dtype/0/? · returned tuple · level recorded 2026-09-22
power in 16 papers src/models/sequence/ss/standalone/s4.py ran · our draft was wrong MIT (permissive) · 348275db42a37bee · report fixture: signature L:int/0/int, A:Tensor/2/float, v:Tensor/2/float · returned tuple · level recorded 2026-09-22
rank_correction in 7 papers src/models/sequence/ss/standalone/s4.py ran · honoured contract MIT (permissive) · b719a3ec912becb6 · report fixture: signature measure:str/0/str, N:int/0/int, rank:int/0/int, dtype:dtype/0/? · returned Tensor · level recorded 2026-09-22
transition in 16 papers src/models/sequence/ss/standalone/s4.py ran · our draft was wrong MIT (permissive) · 81a948ed6d1a963f · report fixture: signature measure:str/0/str, N:int/0/int · returned tuple · level recorded 2026-09-22
HippoSSKernel src/models/sequence/ss/standalone/s4.py unverified MIT (permissive) · 5c8e4f0e400a4956 · report
S4 src/models/sequence/ss/standalone/s4.py unverified MIT (permissive) · 7d9920a7ef12302c · report
SSKernelNPLR src/models/sequence/ss/standalone/s4.py unverified MIT (permissive) · 29e51ca431baa365 · report
forgi86/lru-reduction community (archive-listed) 6 samples, 4 ran (4 instrument-failed) · 2 unverified
_interleave lru/linear.py ran · our draft was wrong fingerprinted MIT (permissive) · 95f2fb2164162bdd · report fixture: signature a:Tensor/3/float, b:Tensor/3/float, axis:int/0/int · returned Tensor · level recorded 2026-09-22
associative_scan lru/linear.py ran · our draft was wrong MIT (permissive) · 22730030e03982a4 · report fixture: signature operator:callable/0/?, elems:list/1/Tensor, axis:int/0/int, reverse:bool/0/bool · returned list · level recorded 2026-09-22
binary_operator_diag in 6 papers lru/linear.py ran; the contract check could not run (RAISES) MIT (permissive) · a6aaaac22e971146 · report fixture: returned tuple · level recorded 2026-09-22
slice_along_axis lru/linear.py ran · our draft was wrong fingerprinted MIT (permissive) · 34b3f63a52000df0 · report fixture: signature start:int/0/int, end:int/0/int, stride:int/0/int, axis:int/0/int · returned tuple · level recorded 2026-09-22
LRU lru/linear.py unverified MIT (permissive) · 0d14eeb8e803d789 · report
dlyap_torch_direct_diagonal lru/linear.py unverified MIT (permissive) · fbd06741252dd8e2 · report
leonty1/essm community (archive-listed) 7 samples, 4 ran (2 instrument-failed) · 3 unverified
LinearActivation in 16 papers src/models/sequence/ss/standalone/dss.py ran · our draft was wrong Apache-2.0 (permissive) · 6c960a9598a04692 · report fixture: signature d_input:int/0/int, d_output:int/0/int, bias:bool/0/bool, zero_bias_init:bool/0/bool, transposed:bool/0/bool, initializer:str/0/str, activation:str/0/str, activate:bool/0/bool, weight_norm:bool/0/bool · returned Linear · level recorded 2026-09-22
TransposedLinear src/models/sequence/ss/standalone/dss.py ran · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · 7bbdbc08ffa75119 · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
hippo_skew_evals src/models/sequence/ss/standalone/dss.py ran · violated contract fingerprinted Apache-2.0 (permissive) · 818366932a065b68 · report fixture: signature N:int/0/int · returned Tensor · level recorded 2026-09-22
reciprocal src/models/sequence/ss/standalone/dss.py ran; the contract check could not run (RAISES) fingerprinted Apache-2.0 (permissive) · e6971caf5e1cc5c1 · report fixture: signature x:Tensor/2/complex, epsilon:float/0/float, clamp:bool/0/bool · returned Tensor · level recorded 2026-09-22
DSS src/models/sequence/ss/standalone/dss.py unverified Apache-2.0 (permissive) · f3322f19b651f88b · report
DSSKernel src/models/sequence/ss/standalone/dss.py unverified Apache-2.0 (permissive) · e604fd0087c1b8f3 · report
OptimModule in 5 papers src/models/sequence/ss/standalone/dss.py unverified Apache-2.0 (permissive) · 67c82b9a05adebd0 · report
maxtimer97/ssm-inspired-lif community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
S4D models/snns.py ran no licence file found · pointer only · 9d310a2394e754b7 · report fixture: returned S4D · level recorded 2026-09-22
S4DKernel models/snns.py ran no licence file found · pointer only · 1f674b4ed2ecc8cd · report fixture: returned S4DKernel · level recorded 2026-09-22
nicolaszucchet/minimal-lru community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
LRU lru/model.py ran · metamorphic tier: deterministic MIT (permissive) · 6e1825a893399540 · report fixture: returned LRU · level recorded 2026-09-22
srush/annotated-s4 community (archive-listed) 14 samples, 9 ran (0 instrument-failed) · 5 unverified
cauchy s4/memory_bug.py ran fingerprinted MIT (permissive) · b294cd8cde986e7e · report fixture: signature omega:ArrayImpl/1/float, lambd:ArrayImpl/1/float · returned ArrayImpl · level recorded 2026-09-24
complex_softmax s4/dss.py ran MIT (permissive) · b895231ad0d7eb03 · report fixture: signature x:ArrayImpl/2/complex, eps:float/0/float · returned ArrayImpl · level recorded 2026-09-24
create_sin_ax_b_dataset s4/data.py ran MIT (permissive) · a9f0a96fb976b6ac · report fixture: signature n_examples:int/0/int, bsz:int/0/int · returned tuple · level recorded 2026-09-24
create_sin_x_dataset s4/data.py ran MIT (permissive) · d637a7237715e2ea · report fixture: signature n_examples:int/0/int, bsz:int/0/int · returned tuple · level recorded 2026-09-24
discretize in 13 papers s4/s4.py ran MIT (permissive) · 2fbdf4a5c125f869 · report fixture: signature A:ArrayImpl/2/float, B:ArrayImpl/2/float, C:ArrayImpl/2/float, step:float/0/float · returned tuple · level recorded 2026-09-24
dss_ssm s4/dss.py ran MIT (permissive) · 12ff0e50a74997cf · report fixture: signature W:ArrayImpl/1/float, Lambda:ArrayImpl/1/float, L:int/0/int, step:float/0/float · returned tuple · level recorded 2026-09-24
random_SSM s4/s4.py ran MIT (permissive) · 5b97d5371e044049 · report fixture: signature rng:ArrayImpl/1/int, N:int/0/int · returned tuple · level recorded 2026-09-24
s4d_kernel s4/s4d.py ran MIT (permissive) · 2cebc3a83a8c3bc5 · report fixture: signature C:ArrayImpl/1/float, A:ArrayImpl/1/float, L:int/0/int, step:float/0/float · returned ArrayImpl · level recorded 2026-09-24
scan_SSM s4/s4.py ran MIT (permissive) · f78db7b4e91ceafa · report fixture: signature Ab:ArrayImpl/2/float, Bb:ArrayImpl/2/float, Cb:ArrayImpl/2/float, u:ArrayImpl/2/float, x0:ArrayImpl/1/float · returned tuple · level recorded 2026-09-24
DefaultMNIST s4/sample.py unverified MIT (permissive) · e4f2a7408ee25578 · report
create_mnist_dataset s4/data.py unverified MIT (permissive) · 200d610a7e1bda69 · report
discretize in 13 papers s4/s4d.py unverified MIT (permissive) · c29c5241ff1d2f5a · report
dss_kernel s4/dss.py unverified MIT (permissive) · 48664b31b86bdb2f · report
vandermonde_product s4/s4d.py unverified MIT (permissive) · 002674cddd8530fd · report
raminmh/liquid-s4 community 2 samples, 2 ran (2 instrument-failed) · 0 unverified
Activation in 28 papers src/models/s4/s4.py ran · our draft was wrong Apache-2.0 (permissive) · 89b10a8b26bbb7ed · report fixture: signature activation:str/0/str, dim:int/0/int · returned ReLU · level recorded, date not recorded
LinearActivation in 16 papers src/models/s4/s4.py ran · our draft was wrong Apache-2.0 (permissive) · 898daef1784ec4bd · report fixture: signature d_input:int/0/int, d_output:int/0/int, bias:bool/0/bool, transposed:bool/0/bool, activation:str/0/str, activate:bool/0/bool · returned Sequential · level recorded, date not recorded

Method as code Syntology

What Syntology's graph records as this paper's claimed method, lifted into code: each assembly names its bricks (functions and classes), each with its own role and its own verification level. An assembly is not a check that the code implements the method correctly or reproduces the paper's results. Levels are each brick's own verification level in Syntology's graph (level 0: no recorded run), listed brick by brick and never combined into one level; “ran” means the brick executed on a synthesized input, not that its output is correct, and the instrument figure counts failures of Syntology's instrument, not of the code. For a generated assembly, an independent peer is a second implementation generated separately from the same paper text; neither implementation read the authors' code. At level 2 the two agreed numerically on the fixture's inputs; level 3 is recorded when property tests derived from the paper also passed on both, and each level 3 card prints how many its report lists. Where a model read the code against the paper's claim, each assembly's label verdict is one model's judgement, kept in this page's JSON twin; it is not calibrated, so no card prints it. A generated assembly's label was set when its code was generated for the method, and no model judged it; its card prints it as "by construction" or "not judged by a model". Siblings are assemblies lifted from this paper in the same batch for the same method: alternative readings kept side by side; none replaces or supersedes another.

7 assemblies on this paper: 6 harvested, 1 generated, listed in 2 groups (siblings lifted in one batch form one group).

generated Assembly whose link to a graph method was removed in Syntology's graph, so no method name is shown; generated from the paper text, not the repository's code. 1 brick; individually on a fixture: 0 ran · 1 unverified. Its end-to-end level was lowered from level 3 to level 0 on 2026-09-10 (level 0: no end-to-end run is now recorded); Syntology's graph records why: “lowered to the entry brick level: a single-routine assembly IS its brick”.

label: not the method (not judged by a model)

  1. dense_ssm_convolution_kernel entry · level 0 · unverified · 4cc043644be64be69be676eaff926ccd4d844cdecb198aec7722b2517ab93d82

6 sibling assemblies for S4 (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another.

harvested Assembly for S4 (graph method: S4). 15 bricks; individually on a fixture: 12 ran (of which 3 constructed an object rather than computing a result; 5 with no instrument failure: 2 honoured, 0 violated, 3 with no contract checked; 7 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 6 siblings

  1. S4 entry · level 0 · unverified · 7d9920a7ef12302c
  2. Activation helper · level 1 · ran · our draft was wrong · 89b10a8b26bbb7ed
  3. HippoSSKernel model · level 0 · unverified · 5c8e4f0e400a4956
  4. LinearActivation helper · level 1 · ran · our draft was wrong · 522a1fc1276ec144
  5. SE_Block helper · level 1 · ran · a19e25de29fbaae4
  6. SSKernelNPLR model · level 0 · unverified · 29e51ca431baa365
  7. nplr helper · level 1 · ran · our draft was wrong · 63d9be34f73a43ef
  8. TransposedLinear helper · level 1 · ran · 5a5e28e0e6ccd2d2
  9. get_initializer helper · level 1 · ran · our draft was wrong · f3449af8fae1d130
  10. linear helper · level 1 · ran · f1cab21ec84db199
  11. power helper · level 1 · ran · our draft was wrong · 348275db42a37bee
  12. rank_correction helper · level 1 · ran · honoured contract · b719a3ec912becb6
  13. transition helper · level 1 · ran · our draft was wrong · 81a948ed6d1a963f
  14. embed_c2r helper · level 1 · ran · honoured contract · ada726a93c0d5dfc
  15. get_logger helper · level 1 · ran · our draft was wrong · 61139ec62260b411

harvested Assembly for S4 (graph method: S4). 6 bricks; individually on a fixture: 6 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 6 siblings

  1. LRU entry · level 1 · ran · 6e1825a893399540
  2. binary_operator_diag helper · level 1 · ran · honoured contract · 0212f0ba3cfe6d69
  3. gamma_log_init helper · level 1 · ran; the contract check could not run · f1d67707c6650049
  4. matrix_init helper · level 1 · ran · our draft was wrong · 702f95276a6ff829
  5. nu_init helper · level 1 · ran · our draft was wrong · f832dda1d4b9b1d8
  6. theta_init helper · level 1 · ran · our draft was wrong · 5eb92a40d3fbcc07

harvested Assembly for S4 (graph method: S4). 3 bricks; individually on a fixture: 3 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified; every one of the 3 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 6 siblings

  1. S4D entry · level 1 · ran · 9d310a2394e754b7
  2. DropoutNd helper · level 1 · ran · 7b57689a78611e37
  3. S4DKernel helper · level 1 · ran · 1f674b4ed2ecc8cd

harvested Assembly for S4 (graph method: S4). 17 bricks; individually on a fixture: 11 ran (of which 2 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 8 where Syntology's instrument failed) · 6 unverified. The assembly has not been run end-to-end.

one of 6 siblings

  1. SSMKernelDPLR entry · level 0 · unverified · 2e1521f562fb37ea
  2. SSMKernel helper · level 1 · ran · a0aad68e21728b6a
  3. SSMKernelDiag helper · level 0 · unverified · b2fe7789636402f0
  4. cauchy_naive helper · level 1 · ran · our draft was wrong · b7d9d94554e93b1b
  5. power helper · level 1 · ran · our draft was wrong · 8e0326e9fa719a59
  6. Kernel helper · level 1 · ran · 855fe49867900076
  7. combination helper · level 0 · unverified · 7564850110a688c1
  8. inv_transform helper · level 1 · ran; the contract check could not run · 26b8695dba83b816
  9. transition helper · level 1 · ran · our draft was wrong · fe900ba398d10d9d
  10. log_vandermonde_naive helper · level 1 · ran · our draft was wrong · e25911109ba29783
  11. log_vandermonde_transpose_naive helper · level 0 · unverified · 7cfca855faa8e8dc
  12. param_transform helper · level 1 · ran; the contract check could not run · 6f7ad7d857dc0d1e
  13. ssm helper · level 0 · unverified · 64dd93f539b06f8e
  14. dplr helper · level 0 · unverified · 9eb8abe7e31d874d
  15. nplr helper · level 1 · ran · our draft was wrong · d43b03a2d76a4e41
  16. rank_correction helper · level 1 · ran · honoured contract · 3eab4e035dc5c1f0
  17. get_logger helper · level 1 · ran · our draft was wrong · 61139ec62260b411

harvested Assembly for S4 (graph method: S4). 7 bricks; individually on a fixture: 4 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; 4 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 6 siblings

  1. LRU entry · level 0 · unverified · 0d14eeb8e803d789
  2. associative_scan helper · level 1 · ran · our draft was wrong · 22730030e03982a4
  3. binary_operator_diag helper · level 1 · ran; the contract check could not run (RAISES) · a6aaaac22e971146
  4. dlyap_torch_direct_diagonal helper · level 0 · unverified · fbd06741252dd8e2
  5. _interleave helper · level 1 · ran · our draft was wrong · 95f2fb2164162bdd
  6. safe_map helper · level 0 · unverified · 10544dd48f3329c9
  7. slice_along_axis helper · level 1 · ran · our draft was wrong · 34b3f63a52000df0

harvested Assembly for S4 (graph method: S4). 10 bricks; individually on a fixture: 7 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 5 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 6 siblings

  1. DSS entry · level 0 · unverified · f3322f19b651f88b
  2. Activation helper · level 1 · ran · our draft was wrong · 89b10a8b26bbb7ed
  3. DSSKernel helper · level 0 · unverified · e604fd0087c1b8f3
  4. LinearActivation helper · level 1 · ran · our draft was wrong · 6c960a9598a04692
  5. OptimModule helper · level 0 · unverified · 67c82b9a05adebd0
  6. hippo_skew_evals helper · level 1 · ran · violated contract · 818366932a065b68
  7. reciprocal helper · level 1 · ran; the contract check could not run (RAISES) · e6971caf5e1cc5c1
  8. TransposedLinear helper · level 1 · ran · 7bbdbc08ffa75119
  9. get_initializer helper · level 1 · ran · our draft was wrong · f3449af8fae1d130
  10. get_logger helper · level 1 · ran · our draft was wrong · 61139ec62260b411

Each brick ends with its code_sha256, Syntology's identity for that exact code; click one to copy the get_code call that returns it. For agents, on Syntology's MCP service: assembly(arxiv_id="2111.00396") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Data AugmentationLanguage ModelingLanguage ModellingListOpsLong-range modelingSequential Image ClassificationSpeech Recognition

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Language Modelling WikiText-103 S4 Number of params 249M #45 of 89 Archive leaderboard report
Language Modelling WikiText-103 S4 Test perplexity 21.28 #45 of 89 Archive leaderboard report
Sequential Image Classification Sequential CIFAR-10 S4 Unpermuted Accuracy 91.80% #2 of 13 Archive leaderboard report
Sequential Image Classification Sequential MNIST S4 Permuted Accuracy 98.70% #4 of 30 Archive leaderboard report
Sequential Image Classification Sequential MNIST S4 Unpermuted Accuracy 99.63% #4 of 30 Archive leaderboard report
Speech Recognition Speech Commands S4 Accuracy (%) 98.32 #3 of 3 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Methods

1x1 ConvolutionAverage PoolingBatch NormalizationBottleneck Residual BlockConvolutionGlobal Average PoolingKaiming InitializationMax PoolingReLUResidual BlockResidual Connection

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