Papers › Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks

Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks

27 Aug 2019IJCNLP 2019 11arXiv:1908.10084archive 2025-07-28

Nils Reimers, Iryna Gurevych

BERT (Devlin et al., 2018) and RoBERTa (Liu et al., 2019) has set a new state-of-the-art performance on sentence-pair regression tasks like semantic textual similarity (STS). However, it requires that both sentences are fed into the network, which causes a massive computational overhead: Finding the most similar pair in a collection of 10,000 sentences requires about 50 million inference computations (~65 hours) with BERT. The construction of BERT makes it unsuitable for semantic similarity search as well as for unsupervised tasks like clustering. In this publication, we present Sentence-BERT (SBERT), a modification of the pretrained BERT network that use siamese and triplet network structures to derive semantically meaningful sentence embeddings that can be compared using cosine-similarity. This reduces the effort for finding the most similar pair from 65 hours with BERT / RoBERTa to about 5 seconds with SBERT, while maintaining the accuracy from BERT. We evaluate SBERT and SRoBERTa on common STS tasks and transfer learning tasks, where it outperforms other state-of-the-art sentence embeddings methods.

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 (UKPLab/sentence-transformers) is linked to this paper; the 58 samples below come from 17 community repositories. Syntology harvested code from UKPLab/sentence-transformers for another paper.

UKPLab/sentence-transformers: Syntology's graph links these samples to COCO-Counterfactuals: Automatically Constructed Counterfactual Examples for Image-Text Pairs (arXiv:2309.14356; 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) · 3 unverified); nothing checks that they implement this paper's method.

Syntology 58 code samples harvested from 17 repositories linked to this paper: 33 ran (of which 9 constructed an object rather than computing a result; 30 with no instrument failure: 1 honoured, 0 violated, 29 with no contract checked; 3 where Syntology's instrument failed) · 25 unverified. Where Syntology's instrument failed: 3 where our contract draft was wrong; failures of Syntology's instrument, not of the code.

By repository: community (archive-listed): 58 samples from 17 repositories, 33 ran (30 with no instrument failure; 3 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 2026-09-24 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.

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

UKPLab/sentence-transformers officialmentioned in papermentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to COCO-Counterfactuals: Automatically Constructed Counterfactual Examples for Image-Text Pairs (arXiv:2309.14356; 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) · 3 unverified); nothing checks that they implement this paper's method. report
Alexey-Borisov/3_course_diary mentioned on GitHubSyntology: not harvested report
AnzorGozalishvili/sentence_transformers_serving mentioned on GitHubSyntology: not harvested report
BM-K/KoSentenceBERT mentioned on GitHubpytorchSyntology: not harvested report
BM-K/KoSentenceBERT_ETRI mentioned on GitHubpytorchSyntology: not harvested report
BM-K/KoSentenceBERT_SKT mentioned on GitHubpytorchSyntology: not harvested report
BM-K/KoSentenceBERT_SKTBERT mentioned on GitHubpytorchSyntology: not harvested report
BinWang28/BERT_Sentence_Embedding mentioned on GitHubpytorchSyntology: 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
BinWang28/SBERT-WK-Sentence-Embedding mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
ClaudiuChelcea/2NHACK2021-CoverLetter-Generator-ML mentioned on GitHubtfSyntology: not harvested report
Danqi7/584-final mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
FreddeFrallan/Contrastive-Tension mentioned on GitHubtfSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
InsaneLife/dssm mentioned on GitHubtfSyntology: not harvested report
RaviTejaMaddhini/SBERT-Tensorflow-implementation mentioned on GitHubtfSyntology: not harvested report
Siamul/NLP-Project mentioned on GitHubpytorchSyntology: not harvested report
Susheel-1999/Sentence_Similarity mentioned on GitHubMITSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
TheNeuromancer/SentEmb mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
Walid-Rahman2/modified_sentence_transfomers mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
aneesha/SiameseBERT-Notebook mentioned on GitHubMITSyntology: not harvested report
asgaardlab/test-case-similarity-technique mentioned on GitHubtfSyntology: not harvested report
asreview/asreview-multilingual-feature-extractor mentioned on GitHubMITSyntology: not harvested report
autumn0409/Log-based-Anomaly-Detection-System mentioned on GitHubSyntology: not harvested report
bm-k/kosentencebert-skt mentioned on GitHubpytorchSyntology: not harvested report
brightjade/CS492E-CiteRec mentioned on GitHubpytorchSyntology: not harvested report
croitorualin/reverse-stable-diffusion mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Reverse Stable Diffusion: What prompt was used to generate this image? (arXiv:2308.01472; that paper's own run record: 7 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; 3 where Syntology's instrument failed) · 0 unverified); nothing checks that they implement this paper's method. report
datcancode/sentence-transformers mentioned on GitHubpytorchApache-2.0Syntology: not harvested report
dmmiller612/bert-extractive-summarizer mentioned on GitHubpytorchMITSyntology: not harvested report
eelenadelolmo/WordVectors mentioned on GitHubpytorchSyntology: not harvested report
eric11eca/NeuralLog mentioned on GitHubMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to NeuralLog: Natural Language Inference with Joint Neural and Logical Reasoning (arXiv:2105.14167; that paper's own run record: 3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
fangrouli/Document-embedding-generation-models mentioned on GitHubpytorchSyntology: 2 samples, 2 ran (0 instrument-failed) · 0 unverified report
gmcgoldr/theissues mentioned on GitHubpytorchMITSyntology: 9 samples, 7 ran (0 instrument-failed) · 2 unverified report
hhzrd/BEFAQ mentioned on GitHubApache-2.0Syntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
hkust-nlp/syncse mentioned on GitHubpytorchSyntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
idiap/analogy_learning mentioned on GitHubpytorchSyntology: not harvested report
imperialite/BERT-Embeddings-For-ARA mentioned on GitHubMITSyntology: not harvested report
jcyk/mse-amr mentioned on GitHubpytorchMITSyntology: 11 samples, 7 ran (2 instrument-failed) · 4 unverified report
kihohan/NLP_Reference mentioned on GitHubpytorchSyntology: not harvested report
lambert-x/prolab mentioned on GitHubpytorchApache-2.0Syntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to id 05527 (not an arXiv id) (that paper's own run record: 4 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; 0 where Syntology's instrument failed) · 2 unverified); nothing checks that they implement this paper's method. report
law-ai/summarization mentioned on GitHubpytorchSyntology: not harvested report
martinomensio/spacy-sentence-bert mentioned on GitHubpytorchMITSyntology: 3 samples, 2 ran (0 instrument-failed) · 1 unverified report
max-planck-innovation-competition/sentence-transformers mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation (arXiv:2004.09813; that paper's own run record: 0 ran · 1 unverified); nothing checks that they implement this paper's method. report
nuochenpku/sscl mentioned on GitHubpytorchApache-2.0Syntology: 7 samples, 3 ran (0 instrument-failed) · 4 unverified report
oto-labs/librarian mentioned on GitHubMITSyntology: not harvested report
p208p2002/Sentence-BERT-mean-operation mentioned on GitHubSyntology: not harvested report
princeton-nlp/SimCSE mentioned 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
projeto-de-algoritmos/Grafos1_Joao_Lucas_Leonardo_Miranda mentioned on GitHubpytorchMITSyntology: not harvested report
puerrrr/focal-infonce mentioned on GitHubpytorchSyntology: 7 samples, 3 ran (1 instrument-failed) · 4 unverified report
rafaljanwojcik/SentenceBERT_vs_SiameseLSTM mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
reoneo97/wutr-buildon-2021 mentioned on GitHubpytorchSyntology: not harvested report
rmslick/SummarySearch mentioned on GitHubpytorchSyntology: not harvested report
saulhazelius/transformer-clustering mentioned on GitHubSyntology: not harvested report
sjtu-lit/syncse mentioned on GitHubpytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Contrastive Learning of Sentence Embeddings from Scratch (arXiv:2305.15077; that paper's own run record: 3 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; 2 where Syntology's instrument failed) · 3 unverified); nothing checks that they implement this paper's method. report
skojaku/Practical-Guide-to-Sentence-Transformers mentioned on GitHubApache-2.0Syntology: not harvested report
thisisclement/STS-Benchmark-SentEval mentioned on GitHubSyntology: not harvested report
valdecy/pybibx mentioned on GitHubtfNOASSERTIONSyntology: not harvested report
xiaoouwang/frenchnlp mentioned on GitHubpytorchSyntology: 1 sample, 1 ran (0 instrument-failed) · 0 unverified report
yjiangcm/dcpcse mentioned on GitHubpytorchSyntology: 5 samples, 1 ran (0 instrument-failed) · 4 unverified report
yjiangcm/promcse mentioned on GitHubpytorchSyntology: 1 sample, 0 ran · 1 unverified report
yur7nd/ptss mentioned on GitHubpytorchSyntology: not harvested report
zhihaillm/wisdominterrogatory mentioned on GitHubpytorchApache-2.0Syntology: 2 samples, 1 ran (0 instrument-failed) · 1 unverified report
OctopusMind/longBert pytorchSyntology: 1 sample, 0 ran · 1 unverified 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
abhilash1910/ClusterTransformer pytorchNOASSERTIONSyntology: not harvested report
varun-suresh/experiments-with-gpt2 pytorchMITSyntology: not harvested 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

58 samples harvested: 33 ran (of which 9 constructed an object rather than computing a result; 30 with no instrument failure: 1 honoured, 0 violated, 29 with no contract checked; 3 where Syntology's instrument failed) · 25 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
3ran · our draft was wrong
29ran
25unverified

Licence: 11 of the 58 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 17 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, each row saying why in its tooltip: for 4, 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; for 1, an argument's recorded type or element kind is a printout of an object in Syntology's harness (such as a mock object, a class or a pandas printout), not the type of an input, so it does not describe the call's shape. “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.

Danqi7/584-final community (archive-listed) 1 sample, 0 ran · 1 unverified
SentBert models.py unverified no licence file found · pointer only · 442b59853addd2de · report
FreddeFrallan/Contrastive-Tension community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
ContrastivTensionModel ContrastiveTension/ContrastiveTensionModel.py ran MIT (permissive) · 00b78ef545fe4550 · report fixture: returned ContrastivTensionModel · level recorded 2026-09-22
Susheel-1999/Sentence_Similarity community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
manhattan sentence_similarity/similarity_functions.py ran fingerprinted MIT (permissive) · 51432767e48e693e · report fixture: signature x:list/1/float, y:list/1/float · returned float · level recorded 2026-09-24
minkowski sentence_similarity/similarity_functions.py ran fingerprinted MIT (permissive) · b53bdc3c4189a65f · report fixture: signature x:list/1/float, y:list/1/float · returned float · level recorded 2026-09-24
euclidean in 6 papers sentence_similarity/similarity_functions.py unverified MIT (permissive) · f066e3a9c1823a5d · report
fangrouli/Document-embedding-generation-models community (archive-listed) 2 samples, 2 ran (0 instrument-failed) · 0 unverified
PositionalEncoding in 126 papers
census: 13 implementations from 9 papers, 9 distinct outputs across 5 buckets, one shared input per bucket
Transformer.py ran · metamorphic tier: deterministic no licence file found · pointer only · df850ec18857365a · report fixture: returned PositionalEncoding · level recorded 2026-09-22
TransformerModel in 26 papers Transformer.py ran no licence file found · pointer only · 265a0746f1edf50c · report fixture: returned TransformerModel · level recorded 2026-09-22
gmcgoldr/theissues community (archive-listed) 9 samples, 7 ran (0 instrument-failed) · 2 unverified
build_intra_topic_pairs src/theissues/clustering.py ran MIT (permissive) · 4f1eabf533121ffa · report fixture: signature groups:list/1/list, embeddings:ndarray/2/float, num_pairs:int/0/int, rng:Generator/0/? · returned ndarray · level recorded 2026-09-24
build_sequence_gather_indices src/theissues/training.py ran MIT (permissive) · 8369d387619c884e · report fixture: signature num_tokens:int/0/int, splits:Tensor/1/int, seq_len:int/0/int · returned Tensor · level recorded 2026-09-24
build_sequence_mask_after src/theissues/training.py ran fingerprinted MIT (permissive) · 9f093abe8a8633f3 · report fixture: signature sequences:Tensor/2/int, end_value:int/0/int · returned Tensor · level recorded 2026-09-24
build_sequences_splits src/theissues/training.py ran fingerprinted MIT (permissive) · 31bba20e3bd8bab6 · report fixture: signature sequences:Tensor/1/int, split_token_id:int/0/int · returned Tensor · level recorded 2026-09-24
build_topic_groups src/theissues/clustering.py ran MIT (permissive) · 5939fd392b84fb91 · report fixture: signature texts:list/1/str · returned dict · level recorded 2026-09-24
calculate_pca src/theissues/clustering.py ran fingerprinted MIT (permissive) · 89511893f786e611 · report fixture: signature x:ndarray/2/float, q:int/0/int · returned tuple · level recorded 2026-09-24
prepare_statement_encoding src/theissues/utils.py ran MIT (permissive) · fcc6795327e2fa96 · report fixture: signature statement:Statement/1/str · returned str · level recorded 2026-09-24
decode_token_ids src/theissues/utils.py unverified MIT (permissive) · b6ee269d40006587 · report
get_id_to_token src/theissues/utils.py unverified MIT (permissive) · eb26fd491b20e527 · report
hhzrd/BEFAQ community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
kill_port common/kill_program.py ran fingerprinted Apache-2.0 (permissive) · 3e688147017e6353 · report fixture: signature port:int/0/int · returned str · level recorded 2026-09-24
hkust-nlp/syncse community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
BertForCL in 5 papers simcse/models.py ran MIT (permissive) · c15599049fd15b4a · report fixture: signature input_ids:Tensor/3/int, attention_mask:Tensor/3/float, token_type_ids:Tensor/3/int, position_ids:NoneType/0/?, head_mask:NoneType/0/?, inputs_embeds:NoneType/0/?, labels:NoneType/0/?, output_attentions:NoneType/0/?, output_hidden_states:NoneType/0/?, return_dict:bool/0/bool, mlm_input_ids:NoneType/0/?, mlm_labels:NoneType/0/? · returned SequenceClassifierOutput · level recorded 2026-09-24
cl_init in 8 papers simcse/models.py unverified MIT (permissive) · ecf7ae695fd278cd · report
jcyk/mse-amr community (archive-listed) 11 samples, 7 ran (2 instrument-failed) · 4 unverified
azhang_MLP simcse/models.py ran · metamorphic tier: invariant MIT (permissive) · fcf235d048bd02d9 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
bzhang_MLP simcse/models.py ran MIT (permissive) · 4e4cd886852d45da · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24
cl_forward in 23 papers simcse/models.py ran · our draft was wrong MIT (permissive) · 07787be6ded0e351 · report fixture: signature cls:callable/0/?, encoder:callable/0/?, input_ids:Tensor/3/int, attention_mask:Tensor/3/float, token_type_ids:NoneType/0/?, position_ids:NoneType/0/?, 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, mlm_input_ids:NoneType/0/?, mlm_labels:NoneType/0/? · returned SequenceClassifierOutput · level recorded 2026-09-24
czhang_MLP simcse/models.py ran · metamorphic tier: invariant MIT (permissive) · e1f8c403a1e96d8e · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
dzhang_MLP simcse/models.py ran · metamorphic tier: invariant MIT (permissive) · 932453f299fb7654 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
ozhang_MLP simcse/models.py ran · metamorphic tier: invariant MIT (permissive) · 39b082869b286751 · report fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-22
sentemb_forward in 21 papers simcse/models.py ran · our draft was wrong MIT (permissive) · 32d955e246903e89 · report fixture: signature cls:callable/0/?, encoder:callable/0/?, input_ids:Tensor/2/int, attention_mask:Tensor/2/int, 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 2026-09-24
BertForCL in 5 papers simcse/models.py unverified MIT (permissive) · cfcdc208c6f85bf3 · report
Pooler in 8 papers simcse/models.py unverified MIT (permissive) · 14d8220d0ad290ce · report
build_mlp in 74 papers simcse/models.py unverified MIT (permissive) · d7723134bf6e3bd2 · report
cl_init in 8 papers simcse/models.py unverified MIT (permissive) · 31852ff2075805f1 · report
martinomensio/spacy-sentence-bert community (archive-listed) 3 samples, 2 ran (0 instrument-failed) · 1 unverified
name_spacy_to_sentencebert spacy_sentence_bert/util.py ran fingerprinted MIT (permissive) · c38df05247b84a49 · report fixture: signature spacy_name:str/0/str · returned str · level recorded 2026-09-24
set_hooks spacy_sentence_bert/language.py ran MIT (permissive) · 4e8b30d8d981126f · report fixture: returned Mock · level recorded 2026-09-24
create_lang spacy_sentence_bert/util.py unverified MIT (permissive) · df6ff0395b06ea36 · report
nuochenpku/sscl community (archive-listed) 7 samples, 3 ran (0 instrument-failed) · 4 unverified
DropoutLayer sscl/models.py ran fingerprinted Apache-2.0 (permissive) · cbdb205ae8fa5618 · report fixture: returned DropoutLayer · level recorded 2026-09-22
Pooler in 8 papers sscl/models.py ran Apache-2.0 (permissive) · 084cdb52bc764df4 · report fixture: returned Pooler · level recorded 2026-09-22
ProjectionMLP sscl/models.py ran fingerprinted Apache-2.0 (permissive) · 872b7f900bfbde62 · report fixture: returned ProjectionMLP · level recorded 2026-09-22
BertForCL in 5 papers sscl/models.py unverified Apache-2.0 (permissive) · 67b848a28b094d8e · report
cl_forward in 23 papers sscl/models.py unverified Apache-2.0 (permissive) · 6240552f92bf148f · report
cl_init in 8 papers sscl/models.py unverified Apache-2.0 (permissive) · 6309d0697eb157fc · report
construct_negtives sscl/models.py unverified Apache-2.0 (permissive) · 941deecc46bb006c · report
puerrrr/focal-infonce community (archive-listed) 7 samples, 3 ran (1 instrument-failed) · 4 unverified
MLPLayer in 15 papers focalNCE/models.py ran fingerprinted MIT (permissive) · 9ac67fa1b927fc99 · report fixture: signature features:Tensor/2/float · returned Tensor · level recorded 2026-09-24
Similarity in 5 papers focalNCE/models.py ran fingerprinted MIT (permissive) · 302aa6c6e2e758b8 · report fixture: returned Similarity · level recorded 2026-09-22
cl_forward in 23 papers focalNCE/models.py ran · our draft was wrong MIT (permissive) · 7129023fed66db75 · report fixture: signature cls:callable/0/?, encoder:callable/0/?, input_ids:Tensor/3/int, attention_mask:Tensor/3/float, token_type_ids:Tensor/3/int, position_ids:NoneType/0/?, head_mask:NoneType/0/?, inputs_embeds:NoneType/0/?, labels:Tensor/1/int, output_attentions:bool/0/bool, output_hidden_states:bool/0/bool, return_dict:bool/0/bool, mlm_input_ids:Tensor/3/int, mlm_labels:Tensor/3/int · returned SequenceClassifierOutput · level recorded 2026-09-22
BertForCL in 5 papers focalNCE/models.py unverified MIT (permissive) · b248e7b923a2c743 · report
cl_init in 8 papers focalNCE/models.py unverified MIT (permissive) · 86a386d0f82442dc · report
gather_embeddings focalNCE/models.py unverified MIT (permissive) · b834174c62e09dbd · report
sp_logits focalNCE/models.py unverified MIT (permissive) · 0fe6a0e42f7b4354 · report
rafaljanwojcik/SentenceBERT_vs_SiameseLSTM community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
SiameseBERT modules/models.py ran no licence file found · pointer only · 858aaa4a9df561a0 · report fixture: returned SiameseBERT · level recorded 2026-09-22
xiaoouwang/frenchnlp community (archive-listed) 1 sample, 1 ran (0 instrument-failed) · 0 unverified
compare_sent_transformer frenchnlp/sentence.py ran · honoured contract licence not identified · pointer only · c571e67515e0ff95 · report fixture: signature model:MockSentenceTransformer/0/?, sent1:str/0/str, sent2:str/0/str · returned float32 · level recorded 2026-09-22
yjiangcm/dcpcse community (archive-listed) 5 samples, 1 ran (0 instrument-failed) · 4 unverified
PrefixEncoder promcse/models.py ran · metamorphic tier: deterministic no licence file found · pointer only · 9472f0fd91c6ce99 · report fixture: returned PrefixEncoder · level recorded 2026-09-22
BertForCL in 5 papers promcse/models.py unverified no licence file found · pointer only · 686396546abff873 · report
cl_forward in 23 papers promcse/models.py unverified no licence file found · pointer only · 11633811e04f78a3 · report
cl_init in 8 papers promcse/models.py unverified no licence file found · pointer only · 9b2126395aa31fff · report
sentemb_forward in 21 papers promcse/models.py unverified no licence file found · pointer only · 20ddfaeb2cd9188c · report
yjiangcm/promcse community (archive-listed) 1 sample, 0 ran · 1 unverified
RobertaForCL promcse/models.py unverified no licence file found · pointer only · ee25e6e27384a5bb · report
zhihaillm/wisdominterrogatory community (archive-listed) 2 samples, 1 ran (0 instrument-failed) · 1 unverified
key_words_match_intention app/langchain_demo/code/clc/matching.py ran Apache-2.0 (permissive) · c511c8001abbd371 · report fixture: signature input:str/0/str · returned set · level recorded 2026-09-24
upload_image_to_imgur pics/upload_fig.py unverified Apache-2.0 (permissive) · e49609a7ba74163b · report
OctopusMind/longBert community (archive-listed) 1 sample, 0 ran · 1 unverified
LongBertPredictor train/longbert_utils.py unverified Apache-2.0 (permissive) · 0cbdfd56794bd3b4 · 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.

13 assemblies on this paper: 13 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

13 sibling assemblies for Sentence-BERT (harvested), lifted in the same batch on 2026-09-09: alternative readings kept side by side; none replaces or supersedes another. Bricks printed for 12 of 13 sibling assemblies; the other 1 are listed with their counts; every brick is in this page's JSON twin.

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

one of 13 siblings

  1. BertForCL entry · level 0 · unverified · 686396546abff873
  2. PrefixEncoder helper · level 1 · ran · 9472f0fd91c6ce99
  3. cl_forward model · level 0 · unverified · 11633811e04f78a3
  4. cl_init helper · level 0 · unverified · 9b2126395aa31fff
  5. sentemb_forward model · level 0 · unverified · 20ddfaeb2cd9188c
  6. MLPLayer model · level 0 · unverified · 7d7789da5378c84b
  7. Pooler model · level 1 · ran · 31695b3bea2d46ee
  8. Similarity helper · level 1 · ran · 4d41003f996241f8

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

one of 13 siblings

  1. RobertaForCL entry · level 0 · unverified · ee25e6e27384a5bb
  2. PrefixEncoder helper · level 1 · ran · 9472f0fd91c6ce99
  3. cl_forward model · level 0 · unverified · 11633811e04f78a3
  4. cl_init helper · level 0 · unverified · 9b2126395aa31fff
  5. sentemb_forward model · level 0 · unverified · 20ddfaeb2cd9188c
  6. MLPLayer model · level 0 · unverified · 7d7789da5378c84b
  7. Pooler model · level 1 · ran · 31695b3bea2d46ee
  8. Similarity helper · level 1 · ran · 4d41003f996241f8

harvested Assembly for Sentence-BERT (graph method: Sentence-BERT). 2 bricks; individually on a fixture: 2 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; 0 where Syntology's instrument failed) · 0 unverified; every one of the 2 samples that ran constructed an object rather than computing a result. The assembly has not been run end-to-end.

one of 13 siblings

  1. TransformerModel entry · level 1 · ran · 265a0746f1edf50c
  2. PositionalEncoding helper · level 1 · ran · df850ec18857365a

harvested Assembly for Sentence-BERT (graph method: Sentence-BERT). 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 13 siblings

  1. compare_sent_transformer entry · level 1 · ran · honoured contract · c571e67515e0ff95

harvested Assembly for Sentence-BERT (graph method: Sentence-BERT). 10 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) · 5 unverified. The assembly has not been run end-to-end.

one of 13 siblings

  1. BertForCL entry · level 0 · unverified · 67b848a28b094d8e
  2. cl_forward model · level 0 · unverified · 6240552f92bf148f
  3. cl_init helper · level 0 · unverified · 6309d0697eb157fc
  4. sentemb_forward model · level 1 · ran · our draft was wrong · cb67cd5ac977480d
  5. construct_negtives helper · level 0 · unverified · 941deecc46bb006c
  6. DropoutLayer model · level 1 · ran · cbdb205ae8fa5618
  7. MLPLayer model · level 0 · unverified · 7d7789da5378c84b
  8. Pooler model · level 1 · ran · 084cdb52bc764df4
  9. ProjectionMLP model · level 1 · ran · 872b7f900bfbde62
  10. Similarity model · level 1 · ran · 4d41003f996241f8

harvested Assembly for Sentence-BERT (graph method: Sentence-BERT). 9 bricks; individually on a fixture: 5 ran (of which 2 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) · 4 unverified. The assembly has not been run end-to-end.

one of 13 siblings

  1. BertForCL entry · level 0 · unverified · b248e7b923a2c743
  2. cl_forward model · level 1 · ran · our draft was wrong · 7129023fed66db75
  3. cl_init helper · level 0 · unverified · 86a386d0f82442dc
  4. sentemb_forward model · level 1 · ran · our draft was wrong · cb67cd5ac977480d
  5. gather_embeddings helper · level 0 · unverified · b834174c62e09dbd
  6. sp_logits helper · level 0 · unverified · 0fe6a0e42f7b4354
  7. MLPLayer model · level 1 · ran · 9ac67fa1b927fc99
  8. Pooler model · level 1 · ran · dba0b61c9d62f82f
  9. Similarity helper · level 1 · ran · 302aa6c6e2e758b8

harvested Assembly for Sentence-BERT (graph method: Sentence-BERT). 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 13 siblings

  1. ContrastivTensionModel entry · level 1 · ran · 00b78ef545fe4550

harvested Assembly for Sentence-BERT (graph method: Sentence-BERT). 7 bricks; individually on a fixture: 5 ran (of which 2 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) · 2 unverified. The assembly has not been run end-to-end.

one of 13 siblings

  1. BertForCL entry · level 1 · ran · c15599049fd15b4a
  2. cl_forward model · level 1 · ran · our draft was wrong · 4e0ff9c4d9a318ff
  3. cl_init helper · level 0 · unverified · ecf7ae695fd278cd
  4. sentemb_forward model · level 1 · ran · our draft was wrong · cb67cd5ac977480d
  5. MLPLayer model · level 0 · unverified · 7d7789da5378c84b
  6. Pooler model · level 1 · ran · dba0b61c9d62f82f
  7. Similarity model · level 1 · ran · 4d41003f996241f8

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

one of 13 siblings

  1. SentBert entry · level 0 · unverified · 442b59853addd2de

harvested Assembly for Sentence-BERT (graph method: Sentence-BERT). 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 13 siblings

  1. SiameseBERT entry · level 1 · ran · 858aaa4a9df561a0

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

one of 13 siblings

  1. LongBertPredictor entry · level 0 · unverified · 0cbdfd56794bd3b4

harvested Assembly for Sentence-BERT (graph method: Sentence-BERT). 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 13 siblings

  1. generate_embedding entry · level 1 · ran · 37763f7651473aeb
  1. BertForCL · e9166bd4fb3f8aa8 · 13 bricks; individually on a fixture: 8 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified · The assembly has not been run end-to-end · assemblies[12] in the JSON twin

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="1908.10084") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

ClusteringLinear-Probe ClassificationSTSSemantic SimilaritySemantic Textual SimilaritySentenceSentence EmbeddingSentence EmbeddingsTransfer Learning

1 archive task tag without a task page not shown.

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Semantic Textual Similarity SICK SentenceBERT Spearman Correlation 0.7462 #6 of 22 Archive leaderboard report
Semantic Textual Similarity SICK SRoBERTa-NLI-base Spearman Correlation 0.7446 #7 of 22 Archive leaderboard report
Semantic Textual Similarity SICK SRoBERTa-NLI-large Spearman Correlation 0.7429 #8 of 22 Archive leaderboard report
Semantic Textual Similarity SICK SBERT-NLI-large Spearman Correlation 0.7375 #10 of 22 Archive leaderboard report
Semantic Textual Similarity SICK SBERT-NLI-base Spearman Correlation 0.7291 #11 of 22 Archive leaderboard report
Semantic Textual Similarity STS Benchmark SRoBERTa-NLI-STSb-large Spearman Correlation 0.8615 #46 of 66 Archive leaderboard report
Semantic Textual Similarity STS Benchmark SBERT-STSb-base Spearman Correlation 0.8479 #47 of 66 Archive leaderboard report
Semantic Textual Similarity STS Benchmark SBERT-STSb-large Spearman Correlation 0.8445 #49 of 66 Archive leaderboard report
Semantic Textual Similarity STS Benchmark SBERT-NLI-large Spearman Correlation 0.79 #53 of 66 Archive leaderboard report
Semantic Textual Similarity STS Benchmark SRoBERTa-NLI-base Spearman Correlation 0.7777 #56 of 66 Archive leaderboard report
Semantic Textual Similarity STS Benchmark SBERT-NLI-base Spearman Correlation 0.7703 #57 of 66 Archive leaderboard report
Semantic Textual Similarity STS12 SRoBERTa-NLI-large Spearman Correlation 0.7453 #12 of 20 Archive leaderboard report
Semantic Textual Similarity STS13 SBERT-NLI-large Spearman Correlation 0.7846 #20 of 22 Archive leaderboard report
Semantic Textual Similarity STS14 SBERT-NLI-large Spearman Correlation 0.7490000000000001 #16 of 21 Archive leaderboard report
Semantic Textual Similarity STS15 SRoBERTa-NLI-large Spearman Correlation 0.8185 #15 of 20 Archive leaderboard report
Semantic Textual Similarity STS16 SRoBERTa-NLI-large Spearman Correlation 0.7682 #18 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: SBERT

AdamAttentionAttention DropoutBERTDense ConnectionsDropoutLayer NormalizationLinear LayerLinear Warmup With Linear DecayMulti-Head AttentionResidual ConnectionRoBERTaSBERTSoftmaxWeight 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