Papers › ALBERT: A Lite BERT for Self-supervised Learning of Language Representations

ALBERT: A Lite BERT for Self-supervised Learning of Language Representations

26 Sep 2019ICLR 2020 1arXiv:1909.11942archive 2025-07-28

Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, Radu Soricut

Increasing model size when pretraining natural language representations often results in improved performance on downstream tasks. However, at some point further model increases become harder due to GPU/TPU memory limitations and longer training times. To address these problems, we present two parameter-reduction techniques to lower memory consumption and increase the training speed of BERT. Comprehensive empirical evidence shows that our proposed methods lead to models that scale much better compared to the original BERT. We also use a self-supervised loss that focuses on modeling inter-sentence coherence, and show it consistently helps downstream tasks with multi-sentence inputs. As a result, our best model establishes new state-of-the-art results on the GLUE, RACE, and \squad benchmarks while having fewer parameters compared to BERT-large. The code and the pretrained models are available at https://github.com/google-research/ALBERT.

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 126 code samples harvested from 18 repositories linked to this paper: 81 ran (of which 17 constructed an object rather than computing a result; 56 with no instrument failure: 4 honoured, 0 violated, 52 with no contract checked; 25 where Syntology's instrument failed) · 45 unverified. Where Syntology's instrument failed: 21 where our contract draft was wrong; 4 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 6 samples from 1 repository, 6 ran (4 with no instrument failure; 2 where Syntology's instrument failed); community (archive-listed): 120 samples from 17 repositories, 75 ran (52 with no instrument failure; 23 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 9 of its repositories that Syntology harvested for other papers:

Levels written between 2026-09-22 and 2026-09-27 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed. 1 of the 81 samples that ran has no recorded date.

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

google-research/ALBERT officialmentioned in papermentioned on GitHubtfApache-2.0Syntology: 6 samples, 6 ran (2 instrument-failed) · 0 unverified report
CLUEbenchmark/CLUE mentioned in papermentioned on GitHubtfSyntology: not harvested report
AdamStein97/Semi-Supervised-BERT-NER mentioned on GitHubtfSyntology: not harvested report
AhmedYounes94/Semi-supervised-BERT-NER mentioned on GitHubtfSyntology: not harvested report
DataScienceNigeria/ALBERT-for-Natural-Language-Processing mentioned on GitHubSyntology: not harvested report
KnightZhang625/BERT_TF mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (arXiv:1810.04805; that paper's own run record: 300 ran (of which 75 constructed an object rather than computing a result; 234 with no instrument failure: 18 honoured, 5 violated, 211 with no contract checked; 66 where Syntology's instrument failed) · 359 unverified); nothing checks that they implement this paper's method. report
Sanyuan-Chen/RecAdam mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
Soikonomou/albert_final mentioned on GitHubpytorchApache-2.0Syntology: 10 samples, 8 ran (1 instrument-failed) · 2 unverified report
Soikonomou/albert_final_infer12 mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Matching the Blanks: Distributional Similarity for Relation Learning (arXiv:1906.03158; that paper's own run record: 9 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; 2 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
Soikonomou/albert_final_infer8 mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
Soikonomou/bert_new mentioned on GitHubpytorchApache-2.0Syntology: 6 samples, 5 ran (2 instrument-failed) · 1 unverified report
Soikonomou/bert_new_new mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
Tencent/TurboTransformers mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
appcoreopc/berty mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Attention Is All You Need (arXiv:1706.03762; that paper's own run record: 610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified) and BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding (arXiv:1810.04805; that paper's own run record: 300 ran (of which 75 constructed an object rather than computing a result; 234 with no instrument failure: 18 honoured, 5 violated, 211 with no contract checked; 66 where Syntology's instrument failed) · 359 unverified); nothing checks that they implement this paper's method. report
benywon/Chinese-GPT-2 mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
benywon/ReCO mentioned on GitHubpytorchSyntology: not harvested report
brightmart/albert_zh mentioned on GitHubtfSyntology: 14 samples, 3 ran (2 instrument-failed) · 11 unverified report
codegram/calbert mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
common-english/bert-all mentioned on GitHubpytorchSyntology: not harvested report
cypressd1999/FYP_2021 mentioned on GitHubpytorchApache-2.0Syntology: 17 samples, 9 ran (1 instrument-failed) · 8 unverified report
epfml/collaborative-attention mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (1 instrument-failed) · 1 unverified report
facebookresearch/anli mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
graykode/ALBERT-Pytorch mentioned on GitHubpytorchSyntology: 7 samples, 7 ran (2 instrument-failed) · 0 unverified report
hieudepchai/BERT_IE mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
huggingface/transformers mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Attention Is All You Need (arXiv:1706.03762; that paper's own run record: 610 ran (of which 293 constructed an object rather than computing a result; 529 with no instrument failure: 45 honoured, 15 violated, 469 with no contract checked; 81 where Syntology's instrument failed) · 336 unverified), HuggingFace's Transformers: State-of-the-art Natural Language Processing (arXiv:1910.03771; that paper's own run record: 3 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; 3 where Syntology's instrument failed) · 0 unverified), DeBERTa: Decoding-enhanced BERT with Disentangled Attention (arXiv:2006.03654; that paper's own run record: 4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 1 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 9 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
jpablou/Matching-The-Blanks-Ths mentioned on GitHubpytorchApache-2.0Syntology: 5 samples, 3 ran (0 instrument-failed) · 2 unverified report
kpe/bert-for-tf2 mentioned on GitHubtfMITSyntology: 8 samples, 7 ran (2 instrument-failed) · 1 unverified report
lonePatient/albert_pytorch mentioned on GitHubpytorchApache-2.0Syntology: 6 samples, 4 ran (1 instrument-failed) · 2 unverified report
lucidrains/compressive-transformer-pytorch mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Compressive Transformers for Long-Range Sequence Modelling (arXiv:1911.05507; that paper's own run record: 6 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 2 violated, 3 with no contract checked; 1 where Syntology's instrument failed) · 5 unverified); nothing checks that they implement this paper's method. report
lucidrains/routing-transformer mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Efficient Content-Based Sparse Attention with Routing Transformers (arXiv:2003.05997; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 2 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
lucidrains/sinkhorn-transformer mentioned on GitHubpytorchSyntology: 14 samples, 11 ran (9 instrument-failed) · 3 unverified report
mandubian/codenets mentioned on GitHubpytorchNOASSERTIONSyntology: not harvested report
mtzcorporations/nlp_teamjodka mentioned on GitHubpytorchSyntology: not harvested report
plkmo/BERT-Relation-Extraction mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
rajatgermany/qa-nlp mentioned on GitHubpytorchSyntology: not harvested report
tensorflow/models mentioned on GitHubtfSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift (arXiv:1502.03167; that paper's own run record: 19 ran (of which 5 constructed an object rather than computing a result; 14 with no instrument failure: 0 honoured, 0 violated, 14 with no contract checked; 5 where Syntology's instrument failed) · 2 unverified), Deep Residual Learning for Image Recognition (arXiv:1512.03385; that paper's own run record: 254 ran (of which 108 constructed an object rather than computing a result; 163 with no instrument failure: 3 honoured, 1 violated, 159 with no contract checked; 91 where Syntology's instrument failed) · 123 unverified), Wide Residual Networks (arXiv:1605.07146; that paper's own run record: 66 ran (of which 31 constructed an object rather than computing a result; 47 with no instrument failure: 0 honoured, 0 violated, 47 with no contract checked; 19 where Syntology's instrument failed) · 30 unverified) and 1 more (every one in this page's JSON twin); nothing checks that they implement this paper's method. report
vvvm23/albert mentioned on GitHubpytorchSyntology: 7 samples, 4 ran (0 instrument-failed) · 3 unverified report
xinyooo/ALBERT4Rec mentioned on GitHubpytorchSyntology: 6 samples, 2 ran (0 instrument-failed) · 4 unverified report
yahah100/text_summarization mentioned on GitHubtfSyntology: not harvested report
2023-MindSpore-1/ms-code-219 mindsporeSyntology: not harvested report
Mind23-2/MindCode-131 mindsporeSyntology: not harvested report
MindSpore-paper-code-3/code9 mindsporeSyntology: not harvested report
PaddlePaddle/PaddleNLP paddleSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to ERNIE 3.0 Tiny: Frustratingly Simple Method to Improve Task-Agnostic Distillation... (arXiv:2301.03416; that paper's own run record: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified); nothing checks that they implement this paper's method. report
cui0523/Code6 mindsporeSyntology: not harvested report
kamalkraj/ALBERT-TF2.0 tfSyntology: 11 samples, 5 ran (1 instrument-failed) · 6 unverified report
lyqcom/albert mindsporeApache-2.0Syntology: 3 samples, 3 ran (1 instrument-failed) · 0 unverified report
mindspore-lab/mindnlp mindsporeApache-2.0Syntology: not harvested report
pwc-1/Paper-8 mindsporeApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to MathOdyssey: Benchmarking Mathematical Problem-Solving Skills in Large Language Models... (arXiv:2406.18321; 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, 0 violated, 4 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

126 samples harvested: 81 ran (of which 17 constructed an object rather than computing a result; 56 with no instrument failure: 4 honoured, 0 violated, 52 with no contract checked; 25 where Syntology's instrument failed) · 45 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.

4ran · honoured contract
21ran · our draft was wrong
4ran; the contract check could not run
52ran
45unverified

Licence: 28 of the 126 samples are pointer only, meaning Syntology does not serve that copy's text. For 6 of them, this paper's copy is under a permissive licence and cleared, but the stored copy of the same code that Syntology serves is not; the licence label's tooltip gives Syntology's recorded reason. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 18 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 5 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.

google-research/ALBERT official repository 6 samples, 6 ran (2 instrument-failed) · 0 unverified
create_float_feature in 11 papers create_pretraining_data.py ran Apache-2.0 (permissive) · 5b0793599d029a67 · report fixture: signature values:list/1/float · returned Feature · level recorded 2026-09-25
create_int_feature in 14 papers create_pretraining_data.py ran Apache-2.0 (permissive) · b03d45af664a39e3 · report fixture: signature values:list/1/int · returned Feature · level recorded 2026-09-26
file_based_input_fn_builder in 16 papers classifier_utils.py ran Apache-2.0 (permissive) · ff6bac8bf3944cbe · report fixture: signature input_file:list/1/str, seq_length:int/0/int, is_training:bool/0/bool, drop_remainder:bool/0/bool, task_name:str/0/str, use_tpu:bool/0/bool, bsz:int/0/int, multiple:int/0/int · returned function · level recorded 2026-09-25
gelu in 308 papers
census: 43 implementations from 74 papers, 6 distinct outputs on one shared input
modeling.py ran · our draft was wrong Apache-2.0 (permissive) · 51d3bc0cfa6415a3 · report fixture: signature x:SymbolicTensor/2/float · returned SymbolicTensor · level recorded 2026-09-26
get_activation in 218 papers modeling.py ran · our draft was wrong Apache-2.0 (permissive) · 217fe96a5945a42d · report fixture: signature activation_string:str/0/str · returned function · level recorded 2026-09-26
get_assignment_map_from_checkpoint in 32 papers modeling.py ran Apache-2.0 (permissive) · 6bf234f32ff01978 · report fixture: signature tvars:list/1/RefVariable, init_checkpoint:str/0/str, num_of_group:int/0/int · returned tuple · level recorded 2026-09-25
Sanyuan-Chen/RecAdam community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
RecAdam RecAdam.py ran Apache-2.0 (permissive) · 350a1a7ab2f301c8 · report fixture: returned RecAdam · level recorded 2026-09-22
anneal_function RecAdam.py ran · honoured contract fingerprinted Apache-2.0 (permissive) · b8301a2a061e30a2 · report fixture: signature function:str/0/str, step:int/0/int, k:float/0/float, t0:int/0/int, weight:float/0/float · returned float · level recorded 2026-09-22
Soikonomou/albert_final community (archive-listed) 10 samples, 8 ran (1 instrument-failed) · 2 unverified
gelu in 308 papers
census: 43 implementations from 74 papers, 6 distinct outputs on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
src/model/ALBERT/modeling_bert.py ran · honoured contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 211753ba29188d4e · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
gelu_new in 55 papers
census: 3 implementations from 7 papers, 1 distinct output on one shared input this sample: bucket 1 of 1, arg 1: rank 2, kind float, dtype float32
src/model/ALBERT/modeling_bert.py ran · honoured contract fingerprinted Apache-2.0 (permissive) here; the stored copy is pointer only · 77601724cad03f95 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
hf_bucket_url in 13 papers src/model/ALBERT/file_utils.py ran fingerprinted Apache-2.0 (permissive) · b2be6c932ce41084 · report fixture: signature identifier:str/0/str, postfix:str/0/str, cdn:bool/0/bool · returned str · level recorded 2026-09-25
is_remote_url in 23 papers src/model/ALBERT/file_utils.py ran Apache-2.0 (permissive) · 4381d1f588a7f42a · report fixture: signature url_or_filename:str/0/str · returned bool · level recorded 2026-09-26
prune_conv1d_layer in 20 papers src/model/ALBERT/modeling_utils.py ran Apache-2.0 (permissive) · 8cc492d40c50497b · report fixture: signature layer:callable/0/?, index:Tensor/1/int, dim:int/0/int · returned Conv1D · level recorded 2026-09-25
prune_linear_layer in 40 papers src/model/ALBERT/modeling_utils.py ran · our draft was wrong Apache-2.0 (permissive) · d30d6c3098df2c42 · report fixture: signature layer:callable/0/?, index:Tensor/1/int, dim:int/0/int · returned Linear · level recorded 2026-09-22
top_k_top_p_filtering in 96 papers
census: 8 implementations from 8 papers, 4 distinct outputs across 2 buckets, one shared input per bucket
src/model/ALBERT/modeling_utils.py ran Apache-2.0 (permissive) · 8e873fc150477bd1 · report fixture: returned Tensor · level recorded 2026-09-27
url_to_filename in 73 papers src/model/ALBERT/file_utils.py ran fingerprinted Apache-2.0 (permissive) · e827d94caab33f59 · report fixture: signature url:str/0/str, etag:str/0/str · returned str · level recorded 2026-09-24
load_tf_weights_in_albert in 9 papers src/model/ALBERT/modeling_albert.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · 4f56c9a37e92815f · report
load_tf_weights_in_bert in 135 papers src/model/ALBERT/modeling_bert.py unverified Apache-2.0 (permissive) here; the stored copy is pointer only · ca4a7d28d683cd33 · report
Soikonomou/bert_new community (archive-listed) 6 samples, 5 ran (2 instrument-failed) · 1 unverified
whitespace_tokenize in 49 papers src/model/BERT/tokenization_bert.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · cf9ffa02a42184af · report fixture: signature text:str/0/str · returned list · level recorded, date not recorded
load_tf_weights_in_bert in 135 papers src/model/BERT/modeling_bert.py ran · our draft was wrong Apache-2.0 (permissive) here; the stored copy is pointer only · 0c145728a35789fa · report fixture: signature model:callable/0/?, config:Config/0/?, tf_checkpoint_path:str/0/str · returned BertModel · level recorded 2026-09-22
load_vocab in 107 papers src/model/BERT/tokenization_bert.py ran Apache-2.0 (permissive) · 659f3761c1dc81fa · report fixture: signature vocab_file:str/0/str · returned OrderedDict · level recorded 2026-09-24
prune_conv1d_layer in 20 papers src/model/BERT/modeling_utils.py ran Apache-2.0 (permissive) · 7183a17dd79327a8 · report fixture: signature layer:callable/0/?, index:Tensor/1/int, dim:int/0/int · returned Conv1D · level recorded 2026-09-25
url_to_filename in 73 papers src/model/BERT/file_utils.py ran fingerprinted Apache-2.0 (permissive) · 07a2e3e996a6dc8e · report fixture: signature url:str/0/str, etag:str/0/str · returned str · level recorded 2026-09-24
prune_layer in 8 papers src/model/BERT/modeling_utils.py unverified Apache-2.0 (permissive) · e31093ffc8275cff · report
benywon/Chinese-GPT-2 community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
MultiHeadBlockSelf modules.py ran · metamorphic tier: deterministic no licence file found · pointer only · 0afbeb40a45a72b6 · report fixture: returned MultiHeadBlockSelf · level recorded 2026-09-22
brightmart/albert_zh community (archive-listed) 14 samples, 3 ran (2 instrument-failed) · 11 unverified
dropout in 34 papers modeling_google.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 2bf900d0da165894 · report fixture: signature input_tensor:EagerTensor/2/float, dropout_prob:float/0/float · returned EagerTensor · level recorded 2026-09-22
gelu in 308 papers
census: 43 implementations from 74 papers, 6 distinct outputs on one shared input
modeling_google.py ran · honoured contract fingerprinted no licence file found · pointer only · cb61421413d30b87 · report fixture: signature x:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-22
get_activation in 218 papers modeling_google.py ran · our draft was wrong no licence file found · pointer only · ae9ebb2661d2ddd4 · report fixture: signature activation_string:str/0/str · returned function · level recorded 2026-09-22
AlbertModel modeling_google.py unverified no licence file found · pointer only · 91c075af55caeadc · report
attention_ffn_block modeling_google.py unverified no licence file found · pointer only · 94f549fd1bf6a555 · report
attention_layer in 9 papers modeling_google.py unverified no licence file found · pointer only · 154407ccae03925e · report
dense_layer_2d modeling_google.py unverified no licence file found · pointer only · f9aab49e4bfb299f · report
dense_layer_3d modeling_google.py unverified no licence file found · pointer only · babf39a9a9bf5587 · report
dense_layer_3d_proj modeling_google.py unverified no licence file found · pointer only · b0e3d2a74b1bb3e4 · report
dot_product_attention in 15 papers modeling_google.py unverified no licence file found · pointer only · 847351b08a6a93c6 · report
embedding_lookup in 9 papers modeling_google.py unverified no licence file found · pointer only · 058d2e8f50dd0987 · report
embedding_postprocessor in 7 papers modeling_google.py unverified no licence file found · pointer only · 8efebf3cb9b8ca4d · report
layer_norm_and_dropout in 6 papers modeling_google.py unverified no licence file found · pointer only · 4e61fb4457fa4a37 · report
transformer_model in 7 papers modeling_google.py unverified no licence file found · pointer only · e447e4b29a5d024b · report
codegram/calbert community (archive-listed) 1 sample, 0 ran · 1 unverified
CalbertForMaskedLM calbert/model.py unverified no licence file found · pointer only · ff36be852a0ce11b · report
cypressd1999/FYP_2021 community (archive-listed) 17 samples, 9 ran (1 instrument-failed) · 8 unverified
evaluate_ src/train_funcs.py ran Apache-2.0 (permissive) · e1935088b1c311cc · report fixture: signature lm_logits:Tensor/2/float, blanks_logits:Tensor/2/float, masked_for_pred:Tensor/1/int, blank_labels:Tensor/2/float, tokenizer:SimpleTokenizer/0/?, print_:bool/0/bool · returned tuple · level recorded 2026-09-24
evaluate_ src/tasks/train_funcs.py ran Apache-2.0 (permissive) · ee14d5932438dd30 · report fixture: signature output:Tensor/2/float, labels:Tensor/2/int, ignore_idx:int/0/int · returned tuple · level recorded 2026-09-24
get_e1e2_start src/tasks/preprocessing_funcs.py ran Apache-2.0 (permissive) · a1a367cc1b634bfd · report fixture: signature x:list/1/int, e1_id:int/0/int, e2_id:int/0/int · returned tuple · level recorded 2026-09-24
get_subject_objects src/misc.py ran Apache-2.0 (permissive) · 540b1fdc61fb8b88 · report fixture: signature sent_:MockSentence/0/? · returned list · level recorded 2026-09-24
load_pickle in 115 papers src/tasks/infer.py ran · our draft was wrong Apache-2.0 (permissive) · bb4b4b5ebab73228 · report fixture: signature filename:str/0/str · returned dict · level recorded 2026-09-22
load_pickle in 115 papers src/misc.py ran Apache-2.0 (permissive) · 67bc2e6f6f0fb28d · report fixture: signature filename:str/0/str · returned dict · level recorded 2026-09-24
load_state in 19 papers src/train_funcs.py ran Apache-2.0 (permissive) · 203cc08d9f87f46e · report fixture: returned tuple · level recorded 2026-09-24
load_state in 19 papers src/tasks/train_funcs.py ran Apache-2.0 (permissive) · 87f6efb51cc0c000 · report fixture: returned tuple · level recorded 2026-09-24
process_text in 21 papers src/tasks/preprocessing_funcs.py ran fingerprinted Apache-2.0 (permissive) · 7b81e295d0e6fff5 · report fixture: signature text:list/1/str, mode:str/0/str · returned tuple · level recorded 2026-09-24
create_pretraining_corpus src/preprocessing_funcs.py unverified Apache-2.0 (permissive) · abe15205f0893ad7 · report
load_results in 82 papers src/train_funcs.py unverified Apache-2.0 (permissive) · a8f8b3ec011da390 · report
load_results in 82 papers src/tasks/train_funcs.py unverified Apache-2.0 (permissive) · e60b8c4379569b89 · report
preprocess_semeval2010_8 src/tasks/preprocessing_funcs.py unverified Apache-2.0 (permissive) · 6fbd1282310c47ff · report
process_sent src/preprocessing_funcs.py unverified Apache-2.0 (permissive) · 0556e020c58f45e5 · report
process_textlines src/preprocessing_funcs.py unverified Apache-2.0 (permissive) · 4d87999c53e2b001 · report
train_and_fit src/trainer.py unverified Apache-2.0 (permissive) · 9d1c4a6cfaa4ed85 · report
train_and_fit src/tasks/trainer.py unverified Apache-2.0 (permissive) · 4aa3e688bf3ebaeb · report
epfml/collaborative-attention community (archive-listed) 2 samples, 1 ran (1 instrument-failed) · 1 unverified
albert_layers src/collaborative_attention/adapter_albert.py ran · our draft was wrong Apache-2.0 (permissive) · b2116e6e872a2a35 · report fixture: signature model:callable/0/? · returned ModuleList · level recorded 2026-09-22
ALBERTCollaborativeAdapter src/collaborative_attention/adapter_albert.py unverified Apache-2.0 (permissive) · b6a5b207adc026a6 · report
graykode/ALBERT-Pytorch community (archive-listed) 7 samples, 7 ran (2 instrument-failed) · 0 unverified
Embeddings in 15 papers models.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 00437373da100756 · report fixture: returned Embeddings · level recorded 2026-09-22
LayerNorm in 121 papers
census: 5 implementations from 5 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
models.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · 31b6e6cb2bf23d35 · report fixture: returned LayerNorm · level recorded 2026-09-22
MultiHeadedSelfAttention in 5 papers models.py ran · metamorphic tier: deterministic Apache-2.0 (permissive) · 8734ddba5f76437a · report fixture: returned MultiHeadedSelfAttention · level recorded 2026-09-22
PositionWiseFeedForward in 7 papers models.py ran · metamorphic tier: deterministic fingerprinted Apache-2.0 (permissive) · e952b1d84bed0af6 · report fixture: returned PositionWiseFeedForward · level recorded 2026-09-22
Transformer in 173 papers models.py ran Apache-2.0 (permissive) · b11322b4f500cef1 · report fixture: signature x:Tensor/2/int, seg:Tensor/2/int, mask:Tensor/2/float · returned Tensor · level recorded 2026-09-24
merge_last models.py ran; the contract check could not run (RAISES) fingerprinted Apache-2.0 (permissive) · d5e69fc7b0ee7c8c · report fixture: signature x:Tensor/4/float, n_dims:int/0/int · returned Tensor · level recorded 2026-09-22
split_last models.py ran; the contract check could not run (RAISES) Apache-2.0 (permissive) · a4a5354a3138c8ef · report fixture: signature x:Tensor/3/float, shape:tuple/1/int · returned Tensor · level recorded 2026-09-22
jpablou/Matching-The-Blanks-Ths community (archive-listed) 5 samples, 3 ran (0 instrument-failed) · 2 unverified
evaluate_ src/tasks/train_funcs.py ran Apache-2.0 (permissive) · f92f017fe0d849f2 · report fixture: signature output:Tensor/2/float, labels:Tensor/2/int, ignore_idx:int/0/int · returned tuple · level recorded 2026-09-24
get_e1e2_start src/tasks/preprocessing_funcs.py ran Apache-2.0 (permissive) · ee0c581972df0258 · report fixture: signature x:list/1/int, e1_id:int/0/int, e2_id:int/0/int · returned tuple · level recorded 2026-09-24
process_text in 21 papers src/tasks/preprocessing_funcs.py ran fingerprinted Apache-2.0 (permissive) · 6bf6a61197367217 · report fixture: signature text:list/1/str, mode:str/0/str · returned tuple · level recorded 2026-09-24
preprocess_semeval2010_8 src/tasks/preprocessing_funcs.py unverified Apache-2.0 (permissive) · 27b5913d3a803ad4 · report
train_and_fit src/tasks/trainer.py unverified Apache-2.0 (permissive) · 86862f4dd3b7cc86 · report
kpe/bert-for-tf2 community (archive-listed) 8 samples, 7 ran (2 instrument-failed) · 1 unverified
convert_to_unicode in 40 papers bert/tokenization/bert_tokenization.py ran · our draft was wrong fingerprinted MIT (permissive) here; the stored copy is pointer only · 1923fc05163d207d · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-22
encode_pieces bert/tokenization/albert_tokenization.py ran MIT (permissive) · 6e2a0964af8411ad · report fixture: signature sp_model:MockSentencePiece/0/?, text:str/0/str, return_unicode:bool/0/bool, sample:bool/0/bool · returned list · level recorded 2026-09-24
load_vocab in 107 papers bert/tokenization/bert_tokenization.py ran MIT (permissive) · 30b05f2a415dd132 · report fixture: signature vocab_file:str/0/str · returned OrderedDict · level recorded 2026-09-25
map_from_stock_variale_name bert/loader.py ran MIT (permissive) · 8a6e1a7c602e8104 · report fixture: signature name:str/0/str, prefix:str/0/str · returned str · level recorded 2026-09-24
map_to_stock_variable_name bert/loader.py ran fingerprinted MIT (permissive) · d05c370def845f01 · report fixture: signature name:str/0/str, prefix:str/0/str · returned str · level recorded 2026-09-24
preprocess_text in 26 papers bert/tokenization/albert_tokenization.py ran MIT (permissive) · 20e27f52f8beba5e · report fixture: signature inputs:str/0/str, remove_space:bool/0/bool, lower:bool/0/bool · returned str · level recorded 2026-09-24
printable_text in 36 papers bert/tokenization/bert_tokenization.py ran · our draft was wrong MIT (permissive) · 0e5615f8994003cf · report fixture: signature text:str/0/str · returned str · level recorded 2026-09-26
encode_ids bert/tokenization/albert_tokenization.py unverified MIT (permissive) · 73a4c1c1621ab1fc · report
lonePatient/albert_pytorch community (archive-listed) 6 samples, 4 ran (1 instrument-failed) · 2 unverified
encode_ids model/tokenization_albert.py ran Apache-2.0 (permissive) · 9c4914e087369deb · report fixture: signature sp_model:MockSentencePieceModel/0/?, text:str/0/str, sample:bool/0/bool · returned list · level recorded 2026-09-24
encode_pieces model/tokenization_albert.py ran Apache-2.0 (permissive) · 306ef06ed54230e4 · report fixture: signature sp_model:MockSentencePieceModel/0/?, text:str/0/str, return_unicode:bool/0/bool, sample:bool/0/bool · returned list · level recorded 2026-09-24
preprocess_text in 26 papers model/tokenization_albert.py ran Apache-2.0 (permissive) · 53ab86e6b6c686ae · report fixture: signature inputs:str/0/str, remove_space:bool/0/bool, do_lower_case:bool/0/bool · returned str · level recorded 2026-09-24
url_to_filename in 73 papers model/file_utils.py ran · our draft was wrong fingerprinted Apache-2.0 (permissive) · 5eff22fa0a651276 · report fixture: signature url:str/0/str, etag:str/0/str · returned str · level recorded 2026-09-22
load_tf_weights_in_albert in 9 papers model/modeling_albert.py unverified Apache-2.0 (permissive) · c7c4917ba776e16d · report
load_tf_weights_in_albert in 9 papers model/modeling_albert_bright.py unverified Apache-2.0 (permissive) · c405dd24b1c4e3bc · report
lucidrains/sinkhorn-transformer community (archive-listed) 14 samples, 11 ran (9 instrument-failed) · 3 unverified
AttentionSortNet sinkhorn_transformer/sinkhorn_transformer.py ran fingerprinted MIT (permissive) · d143b86f7eb37e1d · report fixture: returned AttentionSortNet · level recorded 2026-09-22
SimpleSortNet sinkhorn_transformer/sinkhorn_transformer.py ran MIT (permissive) · 04cc0c0e9fb1cf4c · report fixture: returned SimpleSortNet · level recorded 2026-09-22
batched_index_select in 44 papers sinkhorn_transformer/sinkhorn_transformer.py ran · our draft was wrong MIT (permissive) · 8429e6520e353d4d · report fixture: signature values:Tensor/3/float, indices:Tensor/2/int · returned Tensor · level recorded 2026-09-22
bucket sinkhorn_transformer/sinkhorn_transformer.py ran · our draft was wrong fingerprinted MIT (permissive) · 048663070f64ac68 · report fixture: signature buckets:int/0/int, t:Tensor/2/float, dim:int/0/int · returned Tensor · level recorded 2026-09-22
differentiable_topk sinkhorn_transformer/sinkhorn_transformer.py ran · our draft was wrong fingerprinted MIT (permissive) · 9477e59f3a606128 · report fixture: signature x:Tensor/3/float, k:int/0/int, temperature:float/0/float · returned Tensor · level recorded 2026-09-22
expand_batch_and_merge_head sinkhorn_transformer/sinkhorn_transformer.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · e5d5e9b3569db056 · report fixture: signature b:int/0/int, t:Tensor/3/float · returned Tensor · level recorded 2026-09-22
gumbel_sinkhorn in 5 papers sinkhorn_transformer/sinkhorn_transformer.py ran · our draft was wrong fingerprinted MIT (permissive) · 75494c9e9243dc8c · report fixture: signature r:Tensor/3/float, n_iters:int/0/int, temperature:float/0/float · returned Tensor · level recorded 2026-09-22
merge_dims sinkhorn_transformer/sinkhorn_transformer.py ran · our draft was wrong fingerprinted MIT (permissive) · 9e2c5a79e9d85bc3 · report fixture: signature ind_from:int/0/int, ind_to:int/0/int, tensor:Tensor/4/float · returned Tensor · level recorded 2026-09-22
reorder_buckets sinkhorn_transformer/sinkhorn_transformer.py ran · our draft was wrong MIT (permissive) · 1ef7a31f789d0d5a · report fixture: signature t:Tensor/4/float, r:Tensor/3/float · returned Tensor · level recorded 2026-09-22
sinkhorn_sorting_operator sinkhorn_transformer/sinkhorn_transformer.py ran · our draft was wrong fingerprinted MIT (permissive) · 0cbc5bf5174a2a25 · report fixture: signature r:Tensor/3/float, n_iters:int/0/int · returned Tensor · level recorded 2026-09-22
unbucket sinkhorn_transformer/sinkhorn_transformer.py ran · our draft was wrong fingerprinted MIT (permissive) · caf39b2dd49a315b · report fixture: signature t:Tensor/4/float, dim:int/0/int · returned Tensor · level recorded 2026-09-22
SinkhornAttention sinkhorn_transformer/sinkhorn_transformer.py unverified MIT (permissive) · 15d94e7dd53dd4b7 · report
all_none sinkhorn_transformer/sinkhorn_transformer.py unverified MIT (permissive) · 30f0276ce4caf77f · report
vvvm23/albert community (archive-listed) 7 samples, 4 ran (0 instrument-failed) · 3 unverified
FactorizedEmbedding albert/model.py ran MIT (permissive) · 9850e836a8bb97ce · report fixture: returned FactorizedEmbedding · level recorded 2026-09-22
NystromAttention in 7 papers albert/model.py ran MIT (permissive) · a0dff78471b54854 · report fixture: returned NystromAttention · 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
albert/model.py ran fingerprinted MIT (permissive) · d6e09a6ed82fe99e · report fixture: returned PositionalEmbedding · level recorded 2026-09-22
SoftmaxAttention albert/model.py ran MIT (permissive) · 979c42dd40b4b6bb · report fixture: returned SoftmaxAttention · level recorded 2026-09-22
ALBERT albert/model.py unverified MIT (permissive) · fea0515d9942074e · report
TransformerLayer in 34 papers albert/model.py unverified MIT (permissive) · 3fbbc185d6497778 · report
moore_penrose_iter_pinv in 10 papers albert/model.py unverified MIT (permissive) · 8434ec6cb6412213 · report
xinyooo/ALBERT4Rec community (archive-listed) 6 samples, 2 ran (0 instrument-failed) · 4 unverified
LayerNorm in 121 papers
census: 5 implementations from 5 papers, 5 distinct outputs across 3 buckets, one shared input per bucket
models/albert_modules/albert.py ran · metamorphic tier: invariant fingerprinted no licence file found · pointer only · 3f504ebe7af3ba40 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
TokenEmbedding in 11 papers models/albert_modules/albert.py ran · metamorphic tier: deterministic no licence file found · pointer only · 80bf93fd89246988 · report fixture: returned TokenEmbedding · level recorded 2026-09-22
ALBERT models/albert_modules/albert.py unverified no licence file found · pointer only · fa81a9ae49ac9b0d · report
ALBERTEmbedding models/albert_modules/albert.py unverified no licence file found · pointer only · 2bd58eb578fc4911 · report
PositionwiseFeedForward in 36 papers models/albert_modules/albert.py unverified no licence file found · pointer only · b0a2ed9c8469e733 · report
TransformerLayer in 34 papers models/albert_modules/albert.py unverified no licence file found · pointer only · d36a9fea67ab62a3 · report
kamalkraj/ALBERT-TF2.0 community (archive-listed) 11 samples, 5 ran (1 instrument-failed) · 6 unverified
AlbertConfig albert.py ran Apache-2.0 (permissive) · 35df638989183cf3 · report fixture: returned AlbertConfig · level recorded 2026-09-22
Dense3D albert.py ran Apache-2.0 (permissive) · 215c14713864147c · report fixture: returned Dense3D · level recorded 2026-09-22
EmbeddingLookup albert.py ran Apache-2.0 (permissive) · 6cbf6bc0afb44768 · report fixture: returned EmbeddingLookup · level recorded 2026-09-22
EmbeddingPostprocessor albert.py ran Apache-2.0 (permissive) · bc41b5cdd27882da · report fixture: returned EmbeddingPostprocessor · level recorded 2026-09-22
get_initializer in 32 papers albert.py ran · our draft was wrong Apache-2.0 (permissive) · 591598c6e9e9294a · report fixture: signature initializer_range:float/0/float · returned TruncatedNormal · level recorded 2026-09-22
AlbertModel albert.py unverified Apache-2.0 (permissive) · 252e953d83e45726 · report
Dense2DProjection albert.py unverified Apache-2.0 (permissive) · aa9a005ff917d7df · report
Transformer in 173 papers albert.py unverified Apache-2.0 (permissive) · fe12e4019156a236 · report
TransformerBlock in 73 papers albert.py unverified Apache-2.0 (permissive) · 64da3191abb9f8c9 · report
create_attention_mask_from_input_mask in 8 papers albert.py unverified Apache-2.0 (permissive) · 37b7e327abf6ebe3 · report
lyqcom/albert community (archive-listed) 3 samples, 3 ran (1 instrument-failed) · 0 unverified
merge in 85 papers model_utils/config.py ran · our draft was wrong Apache-2.0 (permissive) · b9e24c3e3e0e88a7 · report fixture: signature args:Namespace/0/?, cfg:dict/0/? · returned dict · level recorded 2026-09-22
parse_cli_to_yaml in 29 papers model_utils/config.py ran Apache-2.0 (permissive) · 37834d67b70e1be4 · report fixture: signature parser:ArgumentParser/0/?, cfg:dict/0/?, helper:dict/0/?, choices:dict/0/?, cfg_path:str/0/str · returned Namespace · level recorded 2026-09-24
parse_yaml in 32 papers model_utils/config.py ran Apache-2.0 (permissive) · b0f7ef341475d3d7 · report fixture: signature yaml_path:str/0/str · returned tuple · level recorded 2026-09-24

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.

9 assemblies on this paper: 9 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

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

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

one of 9 siblings

  1. MultiHeadBlockSelf entry · level 1 · ran · 0afbeb40a45a72b6

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

one of 9 siblings

  1. ALBERT entry · level 0 · unverified · fa81a9ae49ac9b0d
  2. ALBERTEmbedding model · level 0 · unverified · 2bd58eb578fc4911
  3. TransformerLayer model · level 0 · unverified · d36a9fea67ab62a3
  4. LayerNorm helper · level 1 · ran · 3f504ebe7af3ba40
  5. TokenEmbedding helper · level 1 · ran · 80bf93fd89246988
  6. PositionwiseFeedForward helper · level 0 · unverified · b0a2ed9c8469e733

harvested Assembly for ALBERT (graph method: ALBERT). 8 bricks; individually on a fixture: 8 ran (of which 4 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. Transformer entry · level 1 · ran · b11322b4f500cef1
  2. Embeddings model · level 1 · ran · 00437373da100756
  3. LayerNorm model · level 1 · ran · 31b6e6cb2bf23d35
  4. MultiHeadedSelfAttention model · level 1 · ran · 8734ddba5f76437a
  5. PositionWiseFeedForward model · level 1 · ran · e952b1d84bed0af6
  6. merge_last helper · level 1 · ran; the contract check could not run (RAISES) · d5e69fc7b0ee7c8c
  7. split_last helper · level 1 · ran; the contract check could not run (RAISES) · a4a5354a3138c8ef
  8. gelu helper · level 1 · ran · honoured contract · 62e7409a816626ac

harvested Assembly for ALBERT (graph method: ALBERT). 11 bricks; individually on a fixture: 5 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 1 where Syntology's instrument failed) · 6 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. AlbertModel entry · level 0 · unverified · 252e953d83e45726
  2. AlbertConfig helper · level 1 · ran · 35df638989183cf3
  3. EmbeddingLookup model · level 1 · ran · 6cbf6bc0afb44768
  4. EmbeddingPostprocessor model · level 1 · ran · bc41b5cdd27882da
  5. Transformer model · level 0 · unverified · fe12e4019156a236
  6. create_attention_mask_from_input_mask helper · level 0 · unverified · 37b7e327abf6ebe3
  7. get_initializer helper · level 1 · ran · our draft was wrong · 591598c6e9e9294a
  8. Dense2DProjection model · level 0 · unverified · aa9a005ff917d7df
  9. TransformerBlock model · level 0 · unverified · 64da3191abb9f8c9
  10. Attention model · level 0 · unverified · a8a24272ed7b74f4
  11. Dense3D model · level 1 · ran · 215c14713864147c

harvested Assembly for ALBERT (graph method: ALBERT). 9 bricks; individually on a fixture: 5 ran (of which 4 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 1 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. ALBERT entry · level 0 · unverified · fea0515d9942074e
  2. FactorizedEmbedding model · level 1 · ran · 9850e836a8bb97ce
  3. HelperModule helper · level 0 · unverified · 394400bd8d814f2c
  4. PositionalEmbedding model · level 1 · ran · d6e09a6ed82fe99e
  5. TransformerLayer model · level 0 · unverified · 3fbbc185d6497778
  6. NystromAttention helper · level 1 · ran · a0dff78471b54854
  7. SoftmaxAttention model · level 1 · ran · 979c42dd40b4b6bb
  8. exists helper · level 1 · ran · violated contract · aa5486a3650902d8
  9. moore_penrose_iter_pinv helper · level 0 · unverified · 8434ec6cb6412213

harvested Assembly for ALBERT (graph method: ALBERT). 18 bricks; individually on a fixture: 4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 14 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. AlbertModel entry · level 0 · unverified · 91c075af55caeadc
  2. create_initializer helper · level 0 · unverified · e3981aa2fadfb2eb
  3. embedding_lookup helper · level 0 · unverified · 058d2e8f50dd0987
  4. embedding_postprocessor helper · level 0 · unverified · 8efebf3cb9b8ca4d
  5. get_activation helper · level 1 · ran · our draft was wrong · ae9ebb2661d2ddd4
  6. get_shape_list helper · level 1 · ran · our draft was wrong · 4c33136de32333c9
  7. transformer_model model · level 0 · unverified · e447e4b29a5d024b
  8. layer_norm_and_dropout helper · level 0 · unverified · 4e61fb4457fa4a37
  9. gelu helper · level 1 · ran · honoured contract · cb61421413d30b87
  10. assert_rank helper · level 0 · unverified · 01e4a365b28cda00
  11. attention_ffn_block helper · level 0 · unverified · 94f549fd1bf6a555
  12. dense_layer_2d helper · level 0 · unverified · f9aab49e4bfb299f
  13. dropout helper · level 1 · ran; the contract check could not run (RAISES) · 2bf900d0da165894
  14. layer_norm helper · level 0 · unverified · fedeb6766bad1fad
  15. attention_layer model · level 0 · unverified · 154407ccae03925e
  16. dense_layer_3d_proj helper · level 0 · unverified · b0e3d2a74b1bb3e4
  17. dense_layer_3d helper · level 0 · unverified · babf39a9a9bf5587
  18. dot_product_attention helper · level 0 · unverified · 847351b08a6a93c6

harvested Assembly for ALBERT (graph method: ALBERT). 2 bricks; individually on a fixture: 2 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; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. RecAdam entry · level 1 · ran · 350a1a7ab2f301c8
  2. anneal_function helper · level 1 · ran · honoured contract · b8301a2a061e30a2

harvested Assembly for ALBERT (graph method: ALBERT). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.

one of 9 siblings

  1. CalbertForMaskedLM entry · level 0 · unverified · ff36be852a0ce11b

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

one of 9 siblings

  1. ALBERTCollaborativeAdapter entry · level 0 · unverified · b6a5b207adc026a6
  2. CollaborativeLayerAdapter helper · level 1 · ran · e6c28dfaa7ebc812
  3. albert_layers helper · level 1 · ran · our draft was wrong · b2116e6e872a2a35

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="1909.11942") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Common Sense ReasoningLinguistic AcceptabilityMulti-task Language UnderstandingMultimodal Intent RecognitionNatural Language InferenceQuestion AnsweringSelf-Supervised LearningSemantic Textual SimilaritySentence

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Common Sense Reasoning CommonsenseQA Albert Lan et al. (2020) (ensemble) Accuracy 76.5 #11 of 38 Archive leaderboard report
Linguistic Acceptability CoLA ALBERT Accuracy 69.1% #14 of 43 Archive leaderboard report
Multimodal Intent Recognition PhotoChat ALBERT-base F1 52.2 #6 of 6 Archive leaderboard report
Multimodal Intent Recognition PhotoChat ALBERT-base Precision 44.8 #6 of 6 Archive leaderboard report
Multimodal Intent Recognition PhotoChat ALBERT-base Recall 62.7 #6 of 6 Archive leaderboard report
Natural Language Inference MultiNLI ALBERT Matched 91.3 #6 of 67 Archive leaderboard report
Natural Language Inference QNLI ALBERT Accuracy 99.2% #1 of 43 Archive leaderboard report
Natural Language Inference RTE ALBERT Accuracy 89.2% #16 of 90 Archive leaderboard report
Natural Language Inference WNLI ALBERT Accuracy 91.8 #5 of 23 Archive leaderboard report
Question Answering MultiTQ ALBERT Hits@1 10.8 #8 of 11 Archive leaderboard report
Question Answering MultiTQ ALBERT Hits@10 45.9 #8 of 11 Archive leaderboard report
Question Answering Quora Question Pairs ALBERT Accuracy 90.5% #3 of 19 Archive leaderboard report
Question Answering SQuAD2.0 ALBERT (ensemble model) EM 89.731 #27 of 286 Archive leaderboard report
Question Answering SQuAD2.0 ALBERT (ensemble model) F1 92.215 #27 of 286 Archive leaderboard report
Question Answering SQuAD2.0 ALBERT (single model) EM 88.107 #67 of 286 Archive leaderboard report
Question Answering SQuAD2.0 ALBERT (single model) F1 90.902 #67 of 286 Archive leaderboard report
Question Answering SQuAD2.0 dev ALBERT xxlarge EM 85.1 #4 of 13 Archive leaderboard report
Question Answering SQuAD2.0 dev ALBERT xxlarge F1 88.1 #4 of 13 Archive leaderboard report
Question Answering SQuAD2.0 dev ALBERT xlarge EM 83.1 #7 of 13 Archive leaderboard report
Question Answering SQuAD2.0 dev ALBERT xlarge F1 85.9 #7 of 13 Archive leaderboard report
Question Answering SQuAD2.0 dev ALBERT large EM 79.0 #9 of 13 Archive leaderboard report
Question Answering SQuAD2.0 dev ALBERT large F1 82.1 #9 of 13 Archive leaderboard report
Question Answering SQuAD2.0 dev ALBERT base EM 76.1 #10 of 13 Archive leaderboard report
Question Answering SQuAD2.0 dev ALBERT base F1 79.1 #10 of 13 Archive leaderboard report
Semantic Textual Similarity MRPC ALBERT Accuracy 93.4% #2 of 45 Archive leaderboard report
Semantic Textual Similarity STS Benchmark ALBERT Pearson Correlation 0.925 #5 of 66 Archive leaderboard report
Sentiment Analysis SST-2 Binary classification ALBERT Accuracy 97.1 #5 of 87 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

ALBERTAdamAttentionAttention DropoutBERTDense ConnectionsDropoutLAMBLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionResidual ConnectionSPEEDSoftmaxWeight DecayWordPiece

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