Papers › Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting

Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting

14 Dec 2020arXiv:2012.07436archive 2025-07-28

Haoyi Zhou, Shanghang Zhang, Jieqi Peng, Shuai Zhang, JianXin Li, Hui Xiong, Wancai Zhang

Many real-world applications require the prediction of long sequence time-series, such as electricity consumption planning. Long sequence time-series forecasting (LSTF) demands a high prediction capacity of the model, which is the ability to capture precise long-range dependency coupling between output and input efficiently. Recent studies have shown the potential of Transformer to increase the prediction capacity. However, there are several severe issues with Transformer that prevent it from being directly applicable to LSTF, including quadratic time complexity, high memory usage, and inherent limitation of the encoder-decoder architecture. To address these issues, we design an efficient transformer-based model for LSTF, named Informer, with three distinctive characteristics: (i) a ProbSparse self-attention mechanism, which achieves O(L logL) in time complexity and memory usage, and has comparable performance on sequences' dependency alignment. (ii) the self-attention distilling highlights dominating attention by halving cascading layer input, and efficiently handles extreme long input sequences. (iii) the generative style decoder, while conceptually simple, predicts the long time-series sequences at one forward operation rather than a step-by-step way, which drastically improves the inference speed of long-sequence predictions. Extensive experiments on four large-scale datasets demonstrate that Informer significantly outperforms existing methods and provides a new solution to the LSTF problem.

PaperPDFCodeCode 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 76 code samples harvested from 6 repositories linked to this paper: 62 ran (of which 53 constructed an object rather than computing a result; 62 with no instrument failure: 0 honoured, 1 violated, 61 with no contract checked; 0 where Syntology's instrument failed) · 14 unverified. “Where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code; here there are none.

By repository: official repository: 3 samples from 1 repository, 0 ran (0 with no instrument failure; 0 where Syntology's instrument failed); named in the paper: 10 samples from 1 repository, 7 ran (7 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 63 samples from 4 repositories, 55 ran (55 with no instrument failure; 0 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 4 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.

14 repositories listed; official and paper-mentioned ones first.

WenjieDu/PyPOTS officialpytorchSyntology: 3 samples, 0 ran · 3 unverified report
zhouhaoyi/ETDataset mentioned in papermentioned on GitHubNOASSERTIONSyntology: not harvested report
zhouhaoyi/Informer2020 mentioned in papermentioned on GitHubpytorchSyntology: 10 samples, 7 ran (0 instrument-failed) · 3 unverified report
hubtru/LTBoost mentioned on GitHubpytorchMITSyntology: not harvested report
larsbentsen/fftransformer mentioned on GitHubpytorchSyntology: 13 samples, 11 ran (0 instrument-failed) · 2 unverified report
AndrzejMiskow/TradeAI pytorchSyntology: 16 samples, 14 ran (0 instrument-failed) · 2 unverified report
MindCode-4/code-10 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Fourier Contour Embedding for Arbitrary-Shaped Text Detection (arXiv:2104.10442; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
MindCode-4/code-10 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Fourier Contour Embedding for Arbitrary-Shaped Text Detection (arXiv:2104.10442; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 1 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
MindCode-4/code-14 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to IMMA: Immunizing text-to-image Models against Malicious Adaptation (arXiv:2311.18815; that paper's own run record: 11 ran (of which 0 constructed an object rather than computing a result; 10 with no instrument failure: 0 honoured, 0 violated, 10 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified); nothing checks that they implement this paper's method. report
MindSpore-scientific/code-12 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Block Diffusion: Interpolating Between Autoregressive and Diffusion Language Models (arXiv:2503.09573; that paper's own run record: 14 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 0 violated, 7 with no contract checked; 7 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
martinwhl/Informer-PyTorch-Lightning pytorchSyntology: 18 samples, 16 ran (0 instrument-failed) · 2 unverified report
pwc-1/Paper-9 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RandAugment: Practical automated data augmentation with a reduced search space (arXiv:1909.13719; that paper's own run record: 58 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 51 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
pwc-1/Paper-9 mindsporeSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to RandAugment: Practical automated data augmentation with a reduced search space (arXiv:1909.13719; that paper's own run record: 58 ran (of which 1 constructed an object rather than computing a result; 7 with no instrument failure: 0 honoured, 1 violated, 6 with no contract checked; 51 where Syntology's instrument failed) · 7 unverified); nothing checks that they implement this paper's method. report
tianhai123/Informer-Tensorflow tfSyntology: 16 samples, 14 ran (0 instrument-failed) · 2 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

76 samples harvested: 62 ran (of which 53 constructed an object rather than computing a result; 62 with no instrument failure: 0 honoured, 1 violated, 61 with no contract checked; 0 where Syntology's instrument failed) · 14 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.

1ran · violated contract
61ran
14unverified

Licence: 13 of the 76 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 6 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. “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 12 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. A census tag appears when Syntology's census ran implementations with that name on one shared input per bucket: it gives how many were compared, from how many papers, and how many distinct outputs they produced, and names this sample's bucket when this sample was one of them.

WenjieDu/PyPOTS official repository 3 samples, 0 ran · 3 unverified
AttentionOperator pypots/nn/modules/informer/layers.py unverified BSD-3-Clause (permissive) · 6ff5ee23b6cba5dc · report
ProbAttention pypots/nn/modules/informer/layers.py unverified BSD-3-Clause (permissive) · ba17df251ef664ee · report
ProbMask pypots/nn/modules/informer/layers.py unverified BSD-3-Clause (permissive) · 3a5ab35b3f92f363 · report
zhouhaoyi/Informer2020 named in the paper 10 samples, 7 ran (0 instrument-failed) · 3 unverified
ConvLayer in 26 papers models/model.py ran · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · c26cdbaa0235c38e · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
DecoderLayer in 43 papers models/model.py ran · metamorphic tier: invariant Apache-2.0 (permissive) · 3c106372e0a83470 · report fixture: signature x:Tensor/3/float, cross:Tensor/3/float, x_mask:NoneType/0/?, cross_mask:NoneType/0/? · returned Tensor · level recorded 2026-09-22
Encoder in 278 papers models/model.py ran fingerprinted Apache-2.0 (permissive) · f832bb8dfa1e0d3d · report fixture: signature x:Tensor/3/float, attn_mask:NoneType/0/? · returned tuple · level recorded 2026-09-24
EncoderLayer in 73 papers models/model.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · 83c2325d104455ec · report fixture: signature x:Tensor/3/float, attn_mask:NoneType/0/? · returned tuple · level recorded 2026-09-22
ProbAttention models/model.py ran Apache-2.0 (permissive) · 9655ff6765e29f40 · report fixture: signature queries:Tensor/4/float, keys:Tensor/4/float, values:Tensor/4/float, attn_mask:NoneType/0/? · returned tuple · level recorded 2026-09-24
TimeFeatureEmbedding models/model.py ran fingerprinted Apache-2.0 (permissive) · af7ecc176fa05a0c · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-24
TokenEmbedding in 11 papers models/model.py ran · metamorphic tier: invariant fingerprinted Apache-2.0 (permissive) · 1f7e24f214af5f8f · report fixture: signature x:Tensor/3/float · returned Tensor · level recorded 2026-09-22
AttentionLayer in 30 papers models/model.py unverified Apache-2.0 (permissive) · c2ca1cd029bc98bf · report
DataEmbedding in 9 papers models/model.py unverified Apache-2.0 (permissive) · f9aee011366d797d · report
Informer models/model.py unverified Apache-2.0 (permissive) · 190b6802dfde5156 · report
larsbentsen/fftransformer community (archive-listed) 13 samples, 11 ran (0 instrument-failed) · 2 unverified
AttentionLayer in 30 papers models/Informer.py ran · metamorphic tier: deterministic no licence file found · pointer only · b3037a636b1488b2 · report fixture: returned AttentionLayer · level recorded 2026-09-22
ConvLayer in 26 papers models/Informer.py ran · metamorphic tier: deterministic no licence file found · pointer only · ece191004f71a0a6 · report fixture: returned ConvLayer · level recorded 2026-09-22
DataEmbedding in 9 papers models/Informer.py ran · metamorphic tier: deterministic no licence file found · pointer only · 3103f383ce197db7 · report fixture: returned DataEmbedding · level recorded 2026-09-22
Decoder in 210 papers models/Informer.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 6633278fb36185f5 · report fixture: returned Decoder · level recorded 2026-09-22
DecoderLayer in 43 papers models/Informer.py ran · metamorphic tier: deterministic no licence file found · pointer only · 50c2f756e8a28edb · report fixture: returned DecoderLayer · level recorded 2026-09-22
Encoder in 278 papers models/Informer.py ran no licence file found · pointer only · 24cd22b81486e6cf · report fixture: returned Encoder · level recorded 2026-09-22
EncoderLayer in 73 papers models/Informer.py ran · metamorphic tier: deterministic no licence file found · pointer only · f6e4afd880144625 · report fixture: returned EncoderLayer · level recorded 2026-09-22
ProbAttention models/Informer.py ran · metamorphic tier: deterministic no licence file found · pointer only · dc08cea57a2ab8c2 · report fixture: returned ProbAttention · level recorded 2026-09-22
TemporalEmbedding in 7 papers models/Informer.py ran · metamorphic tier: deterministic no licence file found · pointer only · 691256d926053823 · report fixture: returned TemporalEmbedding · level recorded 2026-09-22
TimeFeatureEmbedding models/Informer.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · 4734d6da3f0addcd · report fixture: returned TimeFeatureEmbedding · level recorded 2026-09-22
TokenEmbedding in 11 papers models/Informer.py ran · metamorphic tier: deterministic no licence file found · pointer only · 5757cd5e31be6f96 · report fixture: returned TokenEmbedding · level recorded 2026-09-22
Model in 227 papers models/Informer.py unverified no licence file found · pointer only · cefa5df29ad91fe1 · report
ProbMask models/Informer.py unverified no licence file found · pointer only · aef58ca04cf84ff4 · report
AndrzejMiskow/TradeAI community (archive-listed) 16 samples, 14 ran (0 instrument-failed) · 2 unverified
AttentionLayer in 30 papers prediction_service/transformers/models.py ran · metamorphic tier: deterministic MIT (permissive) · 959c303f905ec82e · report fixture: returned AttentionLayer · level recorded 2026-09-22
ConvLayer in 26 papers prediction_service/transformers/models.py ran · metamorphic tier: deterministic MIT (permissive) · 90e6de76603c9ae2 · report fixture: returned ConvLayer · level recorded 2026-09-22
DataEmbedding in 9 papers prediction_service/transformers/models.py ran · metamorphic tier: deterministic MIT (permissive) · 3585c641aefa6f6a · report fixture: returned DataEmbedding · level recorded 2026-09-22
Decoder in 210 papers prediction_service/transformers/models.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 50812a6b5a3f764f · report fixture: returned Decoder · level recorded 2026-09-22
DecoderLayer in 43 papers prediction_service/transformers/models.py ran · metamorphic tier: deterministic MIT (permissive) · 80e44c571e571357 · report fixture: returned DecoderLayer · level recorded 2026-09-22
Encoder in 278 papers prediction_service/transformers/models.py ran · metamorphic tier: deterministic MIT (permissive) · adb27dc3b112b5b7 · report fixture: returned Encoder · level recorded 2026-09-22
EncoderLayer in 73 papers prediction_service/transformers/models.py ran · metamorphic tier: deterministic MIT (permissive) · d4eb251d3b9b8157 · report fixture: returned EncoderLayer · level recorded 2026-09-22
FixedEmbedding in 6 papers prediction_service/transformers/models.py ran · metamorphic tier: deterministic MIT (permissive) · d54ef7cb9071ad5d · report fixture: returned FixedEmbedding · level recorded 2026-09-22
FullAttention in 10 papers prediction_service/transformers/models.py ran · metamorphic tier: deterministic MIT (permissive) · 8846b42edea92ff6 · report fixture: returned FullAttention · level recorded 2026-09-22
PositionalEmbedding in 43 papers
census: 6 implementations from 6 papers, 4 distinct outputs across 3 buckets, one shared input per bucket
prediction_service/transformers/models.py ran · metamorphic tier: deterministic fingerprinted MIT (permissive) · 3ec0eb0ce028e761 · report fixture: returned PositionalEmbedding · level recorded 2026-09-22
ProbAttention prediction_service/transformers/models.py ran · metamorphic tier: deterministic MIT (permissive) · dbdb7d5a6c687629 · report fixture: returned ProbAttention · level recorded 2026-09-22
TemporalEmbedding in 7 papers prediction_service/transformers/models.py ran · metamorphic tier: deterministic MIT (permissive) · 563ef8125c8457b9 · report fixture: returned TemporalEmbedding · level recorded 2026-09-22
TokenEmbedding in 11 papers prediction_service/transformers/models.py ran · metamorphic tier: deterministic MIT (permissive) · ffff571f678f5301 · report fixture: returned TokenEmbedding · level recorded 2026-09-22
TriangularCausalMask prediction_service/transformers/models.py ran MIT (permissive) · fc6e01b035a3c754 · report fixture: returned TriangularCausalMask · level recorded 2026-09-22
Informer prediction_service/transformers/models.py unverified MIT (permissive) · 0dfd73c78bc03560 · report
ProbMask prediction_service/transformers/models.py unverified MIT (permissive) · aca4221951f4315b · report
martinwhl/Informer-PyTorch-Lightning community (archive-listed) 18 samples, 16 ran (0 instrument-failed) · 2 unverified
AttentionLayer in 30 papers models/informer/model.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · e75ce51f514cede4 · report fixture: returned AttentionLayer · level recorded 2026-09-22
DataEmbedding in 9 papers models/informer/model.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · cb33a7664fc29bcd · report fixture: returned DataEmbedding · level recorded 2026-09-22
Decoder in 210 papers models/informer/model.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · 9371d53b3cf8de99 · report fixture: returned Decoder · level recorded 2026-09-22
DecoderLayer in 43 papers models/informer/model.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · da4711602410c52c · report fixture: returned DecoderLayer · level recorded 2026-09-22
Encoder in 278 papers models/informer/model.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 0ba91cc00e21b335 · report fixture: returned Encoder · level recorded 2026-09-22
EncoderLayer in 73 papers models/informer/model.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · b133a666f2dfc30a · report fixture: returned EncoderLayer · level recorded 2026-09-22
FixedEmbedding in 6 papers models/informer/model.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 11d00cdc1be5dc46 · report fixture: returned FixedEmbedding · level recorded 2026-09-22
FullAttention in 10 papers models/informer/model.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 8f1c5d305ce86430 · report fixture: returned FullAttention · level recorded 2026-09-22
Informer models/informer/model.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 1e94250aa40e5761 · report fixture: returned Informer · level recorded 2026-09-22
PositionalEmbedding in 43 papers
census: 6 implementations from 6 papers, 4 distinct outputs across 3 buckets, one shared input per bucket
models/informer/model.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · fe4e559b538b3ba0 · report fixture: returned PositionalEmbedding · level recorded 2026-09-22
ProbSparseAttention models/informer/model.py ran Apache-2.0 (permissive) · 927aac1e136e7bb9 · report fixture: signature queries:Tensor/4/float, keys:Tensor/4/float, values:Tensor/4/float, attention_mask:NoneType/0/? · returned tuple · level recorded 2026-09-24
SelfAttentionDistil models/informer/model.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · e591315794c8447c · report fixture: returned SelfAttentionDistil · level recorded 2026-09-22
TemporalEmbedding in 7 papers models/informer/model.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · f439ed4caab077e1 · report fixture: returned TemporalEmbedding · level recorded 2026-09-22
TimeFeatureEmbedding models/informer/model.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · 868faa6c4998dccc · report fixture: returned TimeFeatureEmbedding · level recorded 2026-09-22
TokenEmbedding in 11 papers models/informer/model.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · b27ba004293a09c9 · report fixture: returned TokenEmbedding · level recorded 2026-09-22
triangular_causal_mask models/informer/model.py ran · violated contract Apache-2.0 (permissive) · 8f29d78a5fd4b737 · report fixture: signature B:int/0/int, L:int/0/int, device:device/0/? · returned Tensor · level recorded 2026-09-22
BaseInformer models/informer/model.py unverified Apache-2.0 (permissive) · db99350a84cd9bef · report
prob_mask models/informer/model.py unverified Apache-2.0 (permissive) · ae2f9589f94253a9 · report
tianhai123/Informer-Tensorflow community (archive-listed) 16 samples, 14 ran (0 instrument-failed) · 2 unverified
AttentionLayer in 30 papers models/model.py ran Apache-2.0 (permissive) · 2fb65948fb331ab5 · report fixture: returned AttentionLayer · level recorded 2026-09-22
ConvLayer in 26 papers models/model.py ran Apache-2.0 (permissive) · 5523438213912ed4 · report fixture: returned ConvLayer · level recorded 2026-09-22
DataEmbedding in 9 papers models/model.py ran Apache-2.0 (permissive) · e430cc85d15ea52c · report fixture: returned DataEmbedding · level recorded 2026-09-22
Decoder in 210 papers models/model.py ran Apache-2.0 (permissive) · 93097c8261b019e4 · report fixture: returned Decoder · level recorded 2026-09-22
DecoderLayer in 43 papers models/model.py ran Apache-2.0 (permissive) · 373de80bb388a8f6 · report fixture: returned DecoderLayer · level recorded 2026-09-22
Encoder in 278 papers models/model.py ran Apache-2.0 (permissive) · 9cd2a01692c6a304 · report fixture: returned Encoder · level recorded 2026-09-22
EncoderLayer in 73 papers models/model.py ran Apache-2.0 (permissive) · f55313b7a30a6024 · report fixture: returned EncoderLayer · level recorded 2026-09-22
FixedEmbedding in 6 papers models/model.py ran Apache-2.0 (permissive) · 0545de0df17c8182 · report fixture: returned FixedEmbedding · level recorded 2026-09-22
FullAttention in 10 papers models/model.py ran Apache-2.0 (permissive) · 8842a439c7ec814d · report fixture: returned FullAttention · level recorded 2026-09-22
PositionalEmbedding in 43 papers
census: 6 implementations from 6 papers, 4 distinct outputs across 3 buckets, one shared input per bucket
models/model.py ran Apache-2.0 (permissive) · c9eed2b60149c2b6 · report fixture: returned PositionalEmbedding · level recorded 2026-09-22
ProbAttention models/model.py ran Apache-2.0 (permissive) · c438e9005b408fe1 · report fixture: returned ProbAttention · level recorded 2026-09-22
TemporalEmbedding in 7 papers models/model.py ran Apache-2.0 (permissive) · 546a049e0d4f1276 · report fixture: returned TemporalEmbedding · level recorded 2026-09-22
TokenEmbedding in 11 papers models/model.py ran Apache-2.0 (permissive) · db188ee2de158d14 · report fixture: returned TokenEmbedding · level recorded 2026-09-22
TriangularCausalMask models/model.py ran Apache-2.0 (permissive) · a1bb5de361dcc91c · report fixture: returned TriangularCausalMask · level recorded 2026-09-22
Informer models/model.py unverified Apache-2.0 (permissive) · e2a2f2031334067e · report
ProbMask models/model.py unverified Apache-2.0 (permissive) · 57860ae363ed0d8a · report

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. 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. 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.

6 assemblies on this paper: 6 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

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

harvested Assembly for Informer (graph method: Informer). 18 bricks; individually on a fixture: 16 ran (of which 14 constructed an object rather than computing a result; 16 with no instrument failure: 0 honoured, 1 violated, 15 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 6 siblings

  1. Informer entry · level 1 · ran · 1e94250aa40e5761
  2. AttentionLayer model · level 1 · ran · e75ce51f514cede4
  3. BaseInformer helper · level 0 · unverified · db99350a84cd9bef
  4. Encoder model · level 1 · ran · 0ba91cc00e21b335
  5. EncoderLayer model · level 1 · ran · b133a666f2dfc30a
  6. FullAttention helper · level 1 · ran · 8f1c5d305ce86430
  7. ProbSparseAttention model · level 1 · ran · 927aac1e136e7bb9
  8. SelfAttentionDistil helper · level 1 · ran · e591315794c8447c
  9. DataEmbedding helper · level 1 · ran · cb33a7664fc29bcd
  10. Decoder model · level 1 · ran · 9371d53b3cf8de99
  11. DecoderLayer model · level 1 · ran · da4711602410c52c
  12. triangular_causal_mask helper · level 1 · ran · violated contract · 8f29d78a5fd4b737
  13. prob_mask helper · level 0 · unverified · ae2f9589f94253a9
  14. PositionalEmbedding helper · level 1 · ran · fe4e559b538b3ba0
  15. TemporalEmbedding helper · level 1 · ran · f439ed4caab077e1
  16. TimeFeatureEmbedding helper · level 1 · ran · 868faa6c4998dccc
  17. TokenEmbedding helper · level 1 · ran · b27ba004293a09c9
  18. FixedEmbedding helper · level 1 · ran · 11d00cdc1be5dc46

harvested Assembly for Informer (graph method: Informer). 3 bricks; individually on a fixture: 0 ran · 3 unverified. The assembly has not been run end-to-end.

one of 6 siblings

  1. ProbAttention entry · level 0 · unverified · ba17df251ef664ee
  2. AttentionOperator helper · level 0 · unverified · 6ff5ee23b6cba5dc
  3. ProbMask helper · level 0 · unverified · 3a5ab35b3f92f363

harvested Assembly for Informer (graph method: Informer). 15 bricks; individually on a fixture: 13 ran (of which 12 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 6 siblings

  1. Model entry · level 0 · unverified · cefa5df29ad91fe1
  2. AttentionLayer model · level 1 · ran · b3037a636b1488b2
  3. ConvLayer helper · level 1 · ran · ece191004f71a0a6
  4. DataEmbedding helper · level 1 · ran · 3103f383ce197db7
  5. Decoder model · level 1 · ran · 6633278fb36185f5
  6. DecoderLayer model · level 1 · ran · 50c2f756e8a28edb
  7. Encoder model · level 1 · ran · 24cd22b81486e6cf
  8. EncoderLayer model · level 1 · ran · f6e4afd880144625
  9. ProbAttention model · level 1 · ran · dc08cea57a2ab8c2
  10. PositionalEmbedding helper · level 1 · ran · 5da1d16a64cf53ce
  11. TemporalEmbedding helper · level 1 · ran · 691256d926053823
  12. TimeFeatureEmbedding helper · level 1 · ran · 4734d6da3f0addcd
  13. TokenEmbedding helper · level 1 · ran · 5757cd5e31be6f96
  14. ProbMask helper · level 0 · unverified · aef58ca04cf84ff4
  15. FixedEmbedding helper · level 1 · ran · 921d4aae41f22f16

harvested Assembly for Informer (graph method: Informer). 16 bricks; individually on a fixture: 14 ran (of which 14 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 14 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. Informer entry · level 0 · unverified · 0dfd73c78bc03560
  2. AttentionLayer helper · level 1 · ran · 959c303f905ec82e
  3. ConvLayer model · level 1 · ran · 90e6de76603c9ae2
  4. DataEmbedding helper · level 1 · ran · 3585c641aefa6f6a
  5. Decoder model · level 1 · ran · 50812a6b5a3f764f
  6. DecoderLayer model · level 1 · ran · 80e44c571e571357
  7. Encoder model · level 1 · ran · adb27dc3b112b5b7
  8. EncoderLayer model · level 1 · ran · d4eb251d3b9b8157
  9. FullAttention helper · level 1 · ran · 8846b42edea92ff6
  10. ProbAttention model · level 1 · ran · dbdb7d5a6c687629
  11. PositionalEmbedding helper · level 1 · ran · 3ec0eb0ce028e761
  12. TemporalEmbedding helper · level 1 · ran · 563ef8125c8457b9
  13. TokenEmbedding helper · level 1 · ran · ffff571f678f5301
  14. TriangularCausalMask helper · level 1 · ran · fc6e01b035a3c754
  15. ProbMask helper · level 0 · unverified · aca4221951f4315b
  16. FixedEmbedding helper · level 1 · ran · d54ef7cb9071ad5d

harvested Assembly for Informer (graph method: Informer). 16 bricks; individually on a fixture: 14 ran (of which 14 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified; every one of the 14 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. Informer entry · level 0 · unverified · e2a2f2031334067e
  2. AttentionLayer model · level 1 · ran · 2fb65948fb331ab5
  3. ConvLayer model · level 1 · ran · 5523438213912ed4
  4. DataEmbedding helper · level 1 · ran · e430cc85d15ea52c
  5. Decoder model · level 1 · ran · 93097c8261b019e4
  6. DecoderLayer model · level 1 · ran · 373de80bb388a8f6
  7. Encoder model · level 1 · ran · 9cd2a01692c6a304
  8. EncoderLayer model · level 1 · ran · f55313b7a30a6024
  9. FullAttention helper · level 1 · ran · 8842a439c7ec814d
  10. ProbAttention model · level 1 · ran · c438e9005b408fe1
  11. PositionalEmbedding helper · level 1 · ran · c9eed2b60149c2b6
  12. TemporalEmbedding helper · level 1 · ran · 546a049e0d4f1276
  13. TokenEmbedding helper · level 1 · ran · db188ee2de158d14
  14. TriangularCausalMask helper · level 1 · ran · a1bb5de361dcc91c
  15. ProbMask helper · level 0 · unverified · 57860ae363ed0d8a
  16. FixedEmbedding helper · level 1 · ran · 0545de0df17c8182

harvested Assembly for Informer (graph method: Informer). 17 bricks; individually on a fixture: 13 ran (of which 5 constructed an object rather than computing a result; 13 with no instrument failure: 0 honoured, 0 violated, 13 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

one of 6 siblings

  1. Informer entry · level 0 · unverified · 190b6802dfde5156
  2. AttentionLayer model · level 0 · unverified · c2ca1cd029bc98bf
  3. ConvLayer model · level 1 · ran · c26cdbaa0235c38e
  4. DataEmbedding helper · level 0 · unverified · f9aee011366d797d
  5. Decoder model · level 1 · ran · 9371d53b3cf8de99
  6. DecoderLayer helper · level 1 · ran · 3c106372e0a83470
  7. Encoder model · level 1 · ran · f832bb8dfa1e0d3d
  8. EncoderLayer helper · level 1 · ran · 83c2325d104455ec
  9. FullAttention helper · level 1 · ran · 144accee1fab81ad
  10. ProbAttention model · level 1 · ran · 9655ff6765e29f40
  11. PositionalEmbedding helper · level 1 · ran · 5da1d16a64cf53ce
  12. TemporalEmbedding helper · level 1 · ran · f42ba6fda711db0d
  13. TimeFeatureEmbedding helper · level 1 · ran · af7ecc176fa05a0c
  14. TokenEmbedding helper · level 1 · ran · 1f7e24f214af5f8f
  15. TriangularCausalMask helper · level 1 · ran · a297b58f69588d02
  16. ProbMask helper · level 0 · unverified · 3a5ab35b3f92f363
  17. FixedEmbedding helper · level 1 · ran · 921d4aae41f22f16

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="2012.07436") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

DecoderMultivariate Time Series ForecastingTime SeriesTime Series AnalysisTime Series ForecastingUnivariate Time Series Forecasting

Datasets

Introduced by this paper, per the archive.

ETTETTh1 (192)ETTh1 (96)

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Time Series Forecasting ETTh1 (168) Multivariate Informer MAE 0.722 #4 of 4 Archive leaderboard report
Time Series Forecasting ETTh1 (168) Multivariate Informer MSE 0.878 #4 of 4 Archive leaderboard report
Time Series Forecasting ETTh1 (168) Univariate Informer MAE 0.337 #4 of 4 Archive leaderboard report
Time Series Forecasting ETTh1 (168) Univariate Informer MSE 0.183 #4 of 4 Archive leaderboard report
Time Series Forecasting ETTh1 (24) Multivariate Informer MAE 0.523 #5 of 5 Archive leaderboard report
Time Series Forecasting ETTh1 (24) Multivariate Informer MSE 0.509 #5 of 5 Archive leaderboard report
Time Series Forecasting ETTh1 (24) Univariate Informer MAE 0.152 #3 of 5 Archive leaderboard report
Time Series Forecasting ETTh1 (24) Univariate Informer MSE 0.046 #3 of 5 Archive leaderboard report
Time Series Forecasting ETTh1 (336) Multivariate Informer MAE 0.753 #69 of 72 Archive leaderboard report
Time Series Forecasting ETTh1 (336) Multivariate Informer MSE 0.884 #69 of 72 Archive leaderboard report
Time Series Forecasting ETTh1 (336) Univariate Informer MAE 0.346 #10 of 10 Archive leaderboard report
Time Series Forecasting ETTh1 (336) Univariate Informer MSE 0.189 #10 of 10 Archive leaderboard report
Time Series Forecasting ETTh1 (48) Multivariate Informer MAE 0.563 #4 of 4 Archive leaderboard report
Time Series Forecasting ETTh1 (48) Multivariate Informer MSE 0.551 #4 of 4 Archive leaderboard report
Time Series Forecasting ETTh1 (48) Univariate Informer MAE 0.274 #4 of 4 Archive leaderboard report
Time Series Forecasting ETTh1 (48) Univariate Informer MSE 0.129 #4 of 4 Archive leaderboard report
Time Series Forecasting ETTh1 (720) Multivariate Informer MAE 0.768 #20 of 22 Archive leaderboard report
Time Series Forecasting ETTh1 (720) Multivariate Informer MSE 0.941 #20 of 22 Archive leaderboard report
Time Series Forecasting ETTh1 (720) Univariate Informer MAE 0.357 #10 of 12 Archive leaderboard report
Time Series Forecasting ETTh1 (720) Univariate Informer MSE 0.201 #10 of 12 Archive leaderboard report
Time Series Forecasting ETTh2 (168) Multivariate Informer MAE 0.996 #2 of 4 Archive leaderboard report
Time Series Forecasting ETTh2 (168) Multivariate Informer MSE 1.512 #2 of 4 Archive leaderboard report
Time Series Forecasting ETTh2 (168) Univariate Informer MAE 0.306 #1 of 4 Archive leaderboard report
Time Series Forecasting ETTh2 (168) Univariate Informer MSE 0.154 #1 of 4 Archive leaderboard report
Time Series Forecasting ETTh2 (24) Multivariate Informer MAE 0.523 #4 of 4 Archive leaderboard report
Time Series Forecasting ETTh2 (24) Multivariate Informer MSE 0.446 #4 of 4 Archive leaderboard report
Time Series Forecasting ETTh2 (24) Univariate Informer MAE 0.213 #2 of 5 Archive leaderboard report
Time Series Forecasting ETTh2 (24) Univariate Informer MSE 0.083 #2 of 5 Archive leaderboard report
Time Series Forecasting ETTh2 (336) Multivariate Informer MAE 1.035 #18 of 20 Archive leaderboard report
Time Series Forecasting ETTh2 (336) Multivariate Informer MSE 1.665 #18 of 20 Archive leaderboard report
Time Series Forecasting ETTh2 (336) Univariate Informer MAE 0.323 #3 of 10 Archive leaderboard report
Time Series Forecasting ETTh2 (336) Univariate Informer MSE 0.166 #3 of 10 Archive leaderboard report
Time Series Forecasting ETTh2 (48) Multivariate Informer MAE 0.733 #2 of 4 Archive leaderboard report
Time Series Forecasting ETTh2 (48) Multivariate Informer MSE 0.934 #2 of 4 Archive leaderboard report
Time Series Forecasting ETTh2 (48) Univariate Informer MAE 0.249 #2 of 4 Archive leaderboard report
Time Series Forecasting ETTh2 (48) Univariate Informer MSE 0.111 #2 of 4 Archive leaderboard report
Time Series Forecasting ETTh2 (720) Multivariate Informer MAE 1.209 #18 of 20 Archive leaderboard report
Time Series Forecasting ETTh2 (720) Multivariate Informer MSE 2.34 #18 of 20 Archive leaderboard report
Time Series Forecasting ETTh2 (720) Univariate Informer MAE 0.338 #2 of 11 Archive leaderboard report
Time Series Forecasting ETTh2 (720) Univariate Informer MSE 0.181 #2 of 11 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

Absolute Position EncodingsAdamAttentionBPEDense ConnectionsDropoutLabel SmoothingLayer NormalizationLinear LayerMulti-Head AttentionPosition-Wise Feed-Forward LayerResidual ConnectionSoftmaxTransformer

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