Papers › SimCSE: Simple Contrastive Learning of Sentence Embeddings

SimCSE: Simple Contrastive Learning of Sentence Embeddings

18 Apr 2021EMNLP 2021 11arXiv:2104.08821archive 2025-07-28

Tianyu Gao, Xingcheng Yao, Danqi Chen

This paper presents SimCSE, a simple contrastive learning framework that greatly advances state-of-the-art sentence embeddings. We first describe an unsupervised approach, which takes an input sentence and predicts itself in a contrastive objective, with only standard dropout used as noise. This simple method works surprisingly well, performing on par with previous supervised counterparts. We find that dropout acts as minimal data augmentation, and removing it leads to a representation collapse. Then, we propose a supervised approach, which incorporates annotated pairs from natural language inference datasets into our contrastive learning framework by using "entailment" pairs as positives and "contradiction" pairs as hard negatives. We evaluate SimCSE on standard semantic textual similarity (STS) tasks, and our unsupervised and supervised models using BERT base achieve an average of 76.3% and 81.6% Spearman's correlation respectively, a 4.2% and 2.2% improvement compared to the previous best results. We also show -- both theoretically and empirically -- that the contrastive learning objective regularizes pre-trained embeddings' anisotropic space to be more uniform, and it better aligns positive pairs when supervised signals are available.

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

No sample from the archive's official repository (princeton-nlp/SimCSE) is linked to this paper; the 30 samples below come from 9 community repositories. Syntology harvested code from princeton-nlp/SimCSE for another paper.

princeton-nlp/SimCSE: Syntology's graph links these samples to Parametric Knowledge is Not All You Need: Toward Honest Large Language Models via... (arXiv:2601.21218; that paper's own run record: 2 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; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method.

Syntology 30 code samples harvested from 9 repositories linked to this paper: 17 ran (of which 9 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 5 where Syntology's instrument failed) · 13 unverified. Where Syntology's instrument failed: 4 where our contract draft was wrong; 1 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 30 samples from 9 repositories, 17 ran (12 with no instrument failure; 5 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 6 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.

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

princeton-nlp/SimCSE officialmentioned in papermentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Parametric Knowledge is Not All You Need: Toward Honest Large Language Models via... (arXiv:2601.21218; that paper's own run record: 2 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; 2 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
BM-K/KoSimCSE mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
BM-K/KoSimCSE_SKT mentioned on GitHubpytorchSyntology: not harvested report
bhuvanakundumani/SimCSE_unsupervised mentioned on GitHubpytorchSyntology: 6 samples, 4 ran (2 instrument-failed) · 2 unverified report
bm-k/kosimcse-skt mentioned on GitHubpytorchSyntology: not harvested report
cluebenchmark/simclue mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to mGTE: Generalized Long-Context Text Representation and Reranking Models for... (arXiv:2407.19669; that paper's own run record: 1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
dll-wu/is-cse mentioned on GitHubpytorchSyntology: 4 samples, 1 ran (1 instrument-failed) · 3 unverified report
dltmddbs100/SimCSE mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
exploration-lab/iitk-semeval-2024-task-1 mentioned on GitHubpytorchMITSyntology: not harvested report
hooman650/supcl-seq mentioned on GitHubpytorchMITSyntology: not harvested report
jeongukjae/KR-BERT-SimCSE mentioned on GitHubtfSyntology: 8 samples, 5 ran (1 instrument-failed) · 3 unverified report
liangyuxin42/SimCSE-reproduce mentioned on GitHubpytorchSyntology: not harvested report
mcgill-nlp/llm2vec mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Improving Text Embeddings with Large Language Models (arXiv:2401.00368; that paper's own run record: 5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 1 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
nlpods/layerattpooler mentioned on GitHubpytorchSyntology: 7 samples, 4 ran (1 instrument-failed) · 3 unverified report
oneflow-inc/libai mentioned on GitHubApache-2.0Syntology: not harvested report
shuhewang1998/sim-gpt mentioned on GitHubpytorchSyntology: not harvested report
shuxinyin/SimCSE-Pytorch mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
sulcantonin/text_icalepcs23 mentioned on GitHubpytorchSyntology: not harvested report
vdogmcgee/SimCSE-Chinese-Pytorch mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
voidism/diffcse mentioned on GitHubjaxMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to DiffCSE: Difference-based Contrastive Learning for Sentence Embeddings (arXiv:2204.10298; that paper's own run record: 2 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; 2 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
wakafengfan/simcse-pytorch mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
yaushian/msimcse mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to English Contrastive Learning Can Learn Universal Cross-lingual Sentence Embeddings (arXiv:2211.06127; that paper's own run record: 8 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 0 honoured, 1 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. 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

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

30 samples harvested: 17 ran (of which 9 constructed an object rather than computing a result; 12 with no instrument failure: 1 honoured, 0 violated, 11 with no contract checked; 5 where Syntology's instrument failed) · 13 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 · honoured contract
4ran · our draft was wrong
1ran; the contract check could not run
11ran
13unverified

Licence: 19 of the 30 samples are pointer only, meaning Syntology does not serve that copy's text. This page shows no code text for any sample; each one links to its file in the repository.

Harvested from 9 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

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

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

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

BM-K/KoSimCSE community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
BERT model/simcse/bert.py ran no licence file found · pointer only · 448b46ec4054641f · report fixture: signature inputs:dict/0/?, mode:str/0/str · returned tuple · level recorded 2026-09-24
bhuvanakundumani/SimCSE_unsupervised community (archive-listed) 6 samples, 4 ran (2 instrument-failed) · 2 unverified
BertForCL in 5 papers model.py ran · metamorphic tier: deterministic no licence file found · pointer only · 5a73e8e6db46e11d · report fixture: returned BertForCL · level recorded 2026-09-22
Pooler in 8 papers model.py ran · metamorphic tier: deterministic no licence file found · pointer only · cf28308ecfc2c9fd · report fixture: returned Pooler · level recorded 2026-09-22
cl_forward in 23 papers model.py ran · our draft was wrong no licence file found · pointer only · 565954449b2193d5 · report fixture: signature cls:callable/0/?, encoder:callable/0/?, input_ids:Tensor/2/int, attention_mask:Tensor/2/float, token_type_ids:Tensor/2/int, position_ids:Tensor/2/int, head_mask:NoneType/0/?, inputs_embeds:NoneType/0/?, labels:NoneType/0/?, output_attentions:bool/0/bool, output_hidden_states:bool/0/bool, return_dict:bool/0/bool · returned SequenceClassifierOutput · level recorded 2026-09-22
sentemb_forward in 21 papers model.py ran · our draft was wrong no licence file found · pointer only · 2f2997d4395b9e2d · report fixture: signature cls:callable/0/?, encoder:callable/0/?, input_ids:Tensor/2/int, attention_mask:Tensor/2/float, token_type_ids:Tensor/2/int, position_ids:Tensor/2/int, head_mask:NoneType/0/?, inputs_embeds:NoneType/0/?, labels:NoneType/0/?, output_attentions:bool/0/bool, output_hidden_states:bool/0/bool, return_dict:bool/0/bool · returned BaseModelOutputWithPoolingAndCrossAttentions · level recorded 2026-09-22
Arguments model.py unverified no licence file found · pointer only · b1116f6967379d83 · report
cl_init in 8 papers model.py unverified no licence file found · pointer only · 161f85267e41c87c · report
dll-wu/is-cse community (archive-listed) 4 samples, 1 ran (1 instrument-failed) · 3 unverified
find_neighbors_and_aggregation simcse/models.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only · 428008c6d9efb161 · report fixture: signature cls:callable/0/?, anchors:Tensor/2/float, mode:str/0/str, aggr:str/0/str · returned Tensor · level recorded 2026-09-22
BertForCL in 5 papers simcse/models.py unverified no licence file found · pointer only · 3233884fc81ed5ae · report
cl_forward in 23 papers simcse/models.py unverified no licence file found · pointer only · 77b8fc1348dbafc4 · report
cl_init in 8 papers simcse/models.py unverified no licence file found · pointer only · b697b04f307205e1 · report
dltmddbs100/SimCSE community (archive-listed) 1 sample, 0 ran · 1 unverified
SimCSE model/model.py unverified no licence file found · pointer only · 2617146828164292 · report
jeongukjae/KR-BERT-SimCSE community (archive-listed) 8 samples, 5 ran (1 instrument-failed) · 3 unverified
BertConfig in 14 papers model.py ran MIT (permissive) · d286e6c33947de1a · report fixture: returned BertConfig · level recorded 2026-09-22
BertEmbedding model.py ran MIT (permissive) · 6dd2aadc3b6d84c6 · report fixture: returned BertEmbedding · level recorded 2026-09-22
MultiheadAttention in 44 papers model.py ran MIT (permissive) · 0903880703193f2a · report fixture: returned MultiheadAttention · level recorded 2026-09-22
TransformerEncoder in 96 papers model.py ran MIT (permissive) · 9686cc4f31888062 · report fixture: returned TransformerEncoder · level recorded 2026-09-22
get_activation_fn in 67 papers model.py ran · our draft was wrong MIT (permissive) · f16e63fb25fd4d54 · report fixture: signature activation:str/0/str · returned function · level recorded 2026-09-22
BertModel in 16 papers model.py unverified MIT (permissive) · 1d4fef90a4837857 · report
BertModelForSimCSE model.py unverified MIT (permissive) · dfc8437383229830 · report
CosineSimilarity model.py unverified MIT (permissive) · d96e7952e9412323 · report
nlpods/layerattpooler community (archive-listed) 7 samples, 4 ran (1 instrument-failed) · 3 unverified
AttentionLayer in 30 papers cl/models.py ran no licence file found · pointer only · b949b4980657d9b2 · report fixture: returned AttentionLayer · level recorded 2026-09-22
MLPLayer in 15 papers cl/models.py ran no licence file found · pointer only · 8e0d3e09d28f3b02 · report fixture: signature features:Tensor/2/float · returned Tensor · level recorded 2026-09-24
Pooler in 8 papers cl/models.py ran no licence file found · pointer only · ccd86b57fd87c336 · report fixture: returned Pooler · level recorded 2026-09-22
sentemb_forward in 21 papers cl/models.py ran · our draft was wrong no licence file found · pointer only · 74c64a7d40a58644 · report fixture: signature cls:callable/0/?, encoder:callable/0/?, input_ids:Tensor/2/int, attention_mask:Tensor/2/float, token_type_ids:Tensor/2/int, position_ids:Tensor/2/int, head_mask:NoneType/0/?, inputs_embeds:NoneType/0/?, labels:NoneType/0/?, output_attentions:bool/0/bool, output_hidden_states:bool/0/bool, return_dict:bool/0/bool · returned BaseModelOutputWithPoolingAndCrossAttentions · level recorded 2026-09-22
BertForCL in 5 papers cl/models.py unverified no licence file found · pointer only · 2ffa456107908807 · report
cl_forward in 23 papers cl/models.py unverified no licence file found · pointer only · 279795ea7a63bfcd · report
cl_init in 8 papers cl/models.py unverified no licence file found · pointer only · d12475050e3e007b · report
shuxinyin/SimCSE-Pytorch community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
SimcseModel SimCSE/model.py ran · metamorphic tier: deterministic MIT (permissive) · d3e6dac55359895d · report fixture: returned SimcseModel · level recorded 2026-09-22
vdogmcgee/SimCSE-Chinese-Pytorch community (archive-listed) 1 sample, 0 ran · 1 unverified
SimcseModel simcse_unsup.py unverified MIT (permissive) · e8a2dd458c8798db · report
wakafengfan/simcse-pytorch community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
simcse_loss train_and_eval.py ran · honoured contract fingerprinted MIT (permissive) · 4702324b53d391dc · report fixture: signature y_pred:Tensor/2/float · returned Tensor · level recorded 2026-09-22

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.

11 assemblies on this paper: 11 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

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

harvested Assembly for SimCSE (graph method: SimCSE). 1 brick; individually on a fixture: 1 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; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.

one of 11 siblings

  1. simcse_loss entry · level 1 · ran · honoured contract · 4702324b53d391dc

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

one of 11 siblings

  1. BertForCL entry · level 0 · unverified · 3233884fc81ed5ae
  2. cl_forward model · level 0 · unverified · 77b8fc1348dbafc4
  3. cl_init helper · level 0 · unverified · b697b04f307205e1
  4. sentemb_forward helper · level 1 · ran · our draft was wrong · cb67cd5ac977480d
  5. find_neighbors_and_aggregation helper · level 1 · ran; the contract check could not run (RAISES) · 428008c6d9efb161
  6. MLPLayer helper · level 0 · unverified · 7d7789da5378c84b
  7. Pooler model · level 1 · ran · 31695b3bea2d46ee
  8. Similarity helper · level 1 · ran · 4d41003f996241f8

harvested Assembly for SimCSE (graph method: SimCSE). 8 bricks; individually on a fixture: 5 ran (of which 3 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 11 siblings

  1. BertForCL entry · level 1 · ran · 5a73e8e6db46e11d
  2. cl_forward loss · level 1 · ran · our draft was wrong · 565954449b2193d5
  3. cl_init helper · level 0 · unverified · 161f85267e41c87c
  4. sentemb_forward model · level 1 · ran · our draft was wrong · 2f2997d4395b9e2d
  5. MLPLayer helper · level 0 · unverified · 7d7789da5378c84b
  6. Pooler model · level 1 · ran · cf28308ecfc2c9fd
  7. Similarity helper · level 1 · ran · 4d41003f996241f8
  8. Arguments helper · level 0 · unverified · b1116f6967379d83

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

one of 11 siblings

  1. SimCSE entry · level 0 · unverified · 2617146828164292

harvested Assembly for SimCSE (graph method: SimCSE). 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 11 siblings

  1. SimcseModel entry · level 1 · ran · d3e6dac55359895d

harvested Assembly for SimCSE (graph method: SimCSE). 8 bricks; individually on a fixture: 5 ran (of which 3 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) · 3 unverified. The assembly has not been run end-to-end.

one of 11 siblings

  1. BertForCL entry · level 0 · unverified · 2ffa456107908807
  2. cl_forward model · level 0 · unverified · 279795ea7a63bfcd
  3. cl_init helper · level 0 · unverified · d12475050e3e007b
  4. sentemb_forward helper · level 1 · ran · our draft was wrong · 74c64a7d40a58644
  5. AttentionLayer helper · level 1 · ran · b949b4980657d9b2
  6. MLPLayer helper · level 1 · ran · 8e0d3e09d28f3b02
  7. Pooler model · level 1 · ran · ccd86b57fd87c336
  8. Similarity helper · level 1 · ran · 4d41003f996241f8

harvested Assembly for SimCSE (graph method: SimCSE). 8 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) · 3 unverified. The assembly has not been run end-to-end.

one of 11 siblings

  1. BertModelForSimCSE entry · level 0 · unverified · dfc8437383229830
  2. BertModel model · level 0 · unverified · 1d4fef90a4837857
  3. CosineSimilarity metric · level 0 · unverified · d96e7952e9412323
  4. BertConfig helper · level 1 · ran · d286e6c33947de1a
  5. BertEmbedding helper · level 1 · ran · 6dd2aadc3b6d84c6
  6. TransformerEncoder helper · level 1 · ran · 9686cc4f31888062
  7. get_activation_fn helper · level 1 · ran · our draft was wrong · f16e63fb25fd4d54
  8. MultiheadAttention helper · level 1 · ran · 0903880703193f2a

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

one of 11 siblings

  1. cl_forward entry · level 1 · ran · our draft was wrong · 4e0ff9c4d9a318ff

harvested Assembly for SimCSE (graph method: SimCSE). 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 11 siblings

  1. SupConLoss entry · level 1 · ran · 299961c9af1dd5a2

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

one of 11 siblings

  1. SimcseModel entry · level 0 · unverified · e8a2dd458c8798db

harvested Assembly for SimCSE (graph method: SimCSE). 1 brick; individually on a fixture: 1 ran (of which 0 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 assembly has not been run end-to-end.

one of 11 siblings

  1. BERT entry · level 1 · ran · 448b46ec4054641f

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="2104.08821") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Contrastive LearningData AugmentationLinear-Probe ClassificationNatural Language InferenceSTSSemantic Textual SimilaritySentenceSentence Embeddings

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic Textual Similarity SICK SimCSE-RoBERTalarge Spearman Correlation 0.8195 #4 of 22 Archive leaderboard report
Semantic Textual Similarity STS Benchmark SimCSE-RoBERTalarge Spearman Correlation 0.867 #40 of 66 Archive leaderboard report
Semantic Textual Similarity STS12 SimCSE-RoBERTa-large Spearman Correlation 0.7746 #9 of 20 Archive leaderboard report
Semantic Textual Similarity STS12 SimCSE-RoBERTa-base Spearman Correlation 0.7016 #15 of 20 Archive leaderboard report
Semantic Textual Similarity STS13 SimCSE-RoBERTa-large Spearman Correlation 0.8727 #10 of 22 Archive leaderboard report
Semantic Textual Similarity STS13 SimCSE-BERT-base Spearman Correlation 0.8241 #15 of 22 Archive leaderboard report
Semantic Textual Similarity STS13 SimCSE-RoBERTa-base Spearman Correlation 0.8136 #17 of 22 Archive leaderboard report
Semantic Textual Similarity STS14 SimCSE-RoBERTalarge Spearman Correlation 0.8236 #8 of 21 Archive leaderboard report
Semantic Textual Similarity STS15 SimCSE-RoBERTalarge Spearman Correlation 0.8666 #9 of 20 Archive leaderboard report
Semantic Textual Similarity STS16 SimCSE-RoBERTalarge Spearman Correlation 0.8393 #10 of 20 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

Introduced by this paper: SimCSE

AdamAttentionAttention DropoutBERTContrastive LearningDense ConnectionsDropoutLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionResidual ConnectionSimCSESoftmaxWeight 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