Papers › Domain-Adversarial Training of Neural Networks
Domain-Adversarial Training of Neural Networks
Yaroslav Ganin, Evgeniya Ustinova, Hana Ajakan, Pascal Germain, Hugo Larochelle, François Laviolette, Mario Marchand, Victor Lempitsky
We introduce a new representation learning approach for domain adaptation, in which data at training and test time come from similar but different distributions. Our approach is directly inspired by the theory on domain adaptation suggesting that, for effective domain transfer to be achieved, predictions must be made based on features that cannot discriminate between the training (source) and test (target) domains. The approach implements this idea in the context of neural network architectures that are trained on labeled data from the source domain and unlabeled data from the target domain (no labeled target-domain data is necessary). As the training progresses, the approach promotes the emergence of features that are (i) discriminative for the main learning task on the source domain and (ii) indiscriminate with respect to the shift between the domains. We show that this adaptation behaviour can be achieved in almost any feed-forward model by augmenting it with few standard layers and a new gradient reversal layer. The resulting augmented architecture can be trained using standard backpropagation and stochastic gradient descent, and can thus be implemented with little effort using any of the deep learning packages. We demonstrate the success of our approach for two distinct classification problems (document sentiment analysis and image classification), where state-of-the-art domain adaptation performance on standard benchmarks is achieved. We also validate the approach for descriptor learning task in the context of person re-identification application.
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):
get_harvested_code_for_paper(arxiv_id="1505.07818")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="1505.07818", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="1505.07818")
Code
Syntology 52 code samples: 50 from 17 repositories linked to this paper, 2 identical to code harvested from another paper's repository. Across all 52: 35 ran (of which 11 constructed an object rather than computing a result; 18 with no instrument failure: 1 honoured, 0 violated, 17 with no contract checked; 17 where Syntology's instrument failed) · 17 unverified. Where Syntology's instrument failed: 16 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): 50 samples from 17 repositories, 34 ran (18 with no instrument failure; 16 where Syntology's instrument failed); 2 identical to code first harvested elsewhere. 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 12 of its repositories that Syntology harvested for other papers:
- JorisRoels/domain-adaptive-segmentation, community (archive-listed): harvested for another paper, listed under the repository
- ShichengChen/WaveNetSeparateAudio, community (archive-listed): harvested for another paper, listed under the repository
- asahi417/DeepDomainAdaptation, community (archive-listed): harvested for another paper, listed under the repository
- erlendd/ddan, community (archive-listed): harvested for another paper, listed under the repository
- gentlezhu/shift-robust-gnns, community (archive-listed): harvested for another paper, listed under the repository
- mashaan14/DANN-toy, community (archive-listed): harvested for another paper, listed under the repository
- tachitachi/GradientReversal, community (archive-listed): harvested for another paper, listed under the repository
- thuml/Transfer-Learning-Library, community (archive-listed): harvested for 7 other papers, listed under the repository
- vict0rsch/PaperMemory, community (archive-listed): harvested for another paper, listed under the repository
- vihari/crossgrad, community (archive-listed): harvested for another paper, listed under the repository
- PaddlePaddle/PaddleSpeech, community (archive-listed): harvested for another paper, listed under the repository
- kevinmusgrave/pytorch-adapt, community (archive-listed): harvested for 4 other papers, listed under the repository
Levels written between 2026-09-22 and 2026-09-26 (UTC): the dates Syntology's graph wrote each sample's verification level, not when the code executed.
37 repositories listed; official and paper-mentioned ones first.
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
52 samples harvested: 35 ran (of which 11 constructed an object rather than computing a result; 18 with no instrument failure: 1 honoured, 0 violated, 17 with no contract checked; 17 where Syntology's instrument failed) · 17 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.
Licence: 22 of the 52 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. 2 samples are listed last, in a group without a repository. “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 2 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.
d86e29f3ca97a8c2 · report
fixture: signature inputs:KerasTensor/0/float · returned KerasTensor · level recorded 2026-09-22 4a9bc68de4ae0c55 · report
fixture: signature data:list/1/ndarray, batch_size:int/0/int · returned generator · level recorded 2026-09-22 f9776e8c18b947b6 · report
fixture: signature model_name:str/0/str · returned tuple · level recorded 2026-09-22 851159feffea3b04 · report
fixture: signature inputs:KerasTensor/0/float · returned KerasTensor · level recorded 2026-09-22 1e5fb974a2b9088c · report
882f695d04b3d5b7 · report
917fb058e1f4bb05 · report
fixture: returned ReverseLayerF · level recorded 2026-09-22 3ce4eba45b4ca3fc · report
fixture: returned GRL · level recorded 2026-09-22 cd9167b485a751fd · report
fixture: signature input_size:int/0/int, output_size:int/0/int · returned Sequential · level recorded 2026-09-22 3e123903386d5131 · report
fixture: signature input_size:int/0/int, output_size:int/0/int · returned Sequential · level recorded 2026-09-22 cec816fd8905007d · report
fixture: signature input_size:int/0/int, output_size:int/0/int · returned Sequential · level recorded 2026-09-22 946555f6a21e149f · report
fixture: signature input_size:int/0/int, output_size:int/0/int · returned Sequential · level recorded 2026-09-22 f64f43c34c4542e9 · report
fixture: signature name:str/0/str, pretrained:bool/0/bool · returned tuple · level recorded 2026-09-22 8d9374ad6935ac3d · report
fixture: signature name:str/0/str, input_size:int/0/int, output_size:int/0/int · returned Sequential · level recorded 2026-09-22 4c1fc418e3779b2d · report
fixture: signature x:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-22 ff4ee6a4efd6ea00 · report
fixture: signature shape:int/0/int, activation:str/0/str, C:int/0/int, name:str/0/str · returned Functional · level recorded 2026-09-22 138b0d8c38a323bc · report
fixture: signature x:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-22 95838026a4f67e63 · report
e2db8a3a21c6bf4c · report
fixture: returned CellTypeCLF · level recorded 2026-09-22 1a6a7062274a346d · report
fixture: returned GradReverse · level recorded 2026-09-22 census: 6 implementations from 5 papers, 6 distinct outputs across 2 buckets, one shared input per bucket scnym/model.py ran Apache-2.0 (permissive) ·
1a8c0c365eb16cdc · report
fixture: returned ResBlock · level recorded 2026-09-22 0e5b0fea39063b16 · report
fixture: returned BaseAdaptTrainer · level recorded 2026-09-22 a9713d2fe23f5ada · report
fixture: returned ReverseLayerF · level recorded 2026-09-22 310d54a1dd86ec79 · report
fixture: signature linear_output:Tensor/2/float, label:Tensor/1/int, weights:Tensor/1/float · returned tuple · level recorded 2026-09-22 4113c2e807d432ee · report
fixture: signature metric_name_list:list/1/str, metric_outputs:list/1/dict · returned dict · level recorded 2026-09-22 61fd42a2e2a7cfcc · report
fixture: signature input_metric_dict:dict/0/? · returned dict · level recorded 2026-09-22 704df3b8019c2aa5 · report
fixture: signature parameter_dict:dict/0/?, device:str/0/str · returned dict · level recorded 2026-09-22 6ca780e6cedb8469 · report
b69e7e3bd38b5a79 · report
c0ae116e1108bfcf · report
59f8b8a3c0a6bdfe · report
fixture: signature inputs:Tensor/4/float, completion_lambda:float/0/float · returned tuple · level recorded 2026-09-22 a5f777ab36b3f81e · report
8a387c444dc4c6a4 · report
fixture: returned AbstractDANN · level recorded 2026-09-22 c601b6f644d029af · report
fixture: signature x:Tensor/4/float, alpha:float/0/float, dest:str/0/str · returned Tensor · level recorded 2026-09-22 f70dbf08bbfa9c34 · report
fixture: signature x:Tensor/4/float, y:Tensor/4/float, z:Tensor/4/float, action:str/0/str · returned tuple · level recorded 2026-09-24 f1707c22da402ad3 · report
fixture: returned AdversarialNetwork · level recorded 2026-09-22 87db2131110dfd0a · report
fixture: returned Discriminator · level recorded 2026-09-22 22d411c2795ced15 · report
fixture: returned GradReverse · level recorded 2026-09-22 fcde4e5aa7af7696 · report
48ebff402229f303 · report
census: 22 implementations from 25 papers, 16 distinct outputs across 4 buckets, one shared input per bucket this sample: bucket 1 of 4, arg 1: rank 2, kind float, dtype float32 support_alignment/core/algorithms.py ran · our draft was wrong fingerprinted MIT (permissive) ·
5b9be386bbb3d10e · report
fixture: signature logits:Tensor/2/float · returned Tensor · level recorded 2026-09-22 aa6ec272928f9093 · report
b140a1b50f334aa6 · report
3d0632c955417561 · report
2fb3457e6f433bd8 · report
fixture: signature imgs:list/1/ndarray, axis:int/0/int · returned tuple · level recorded 2026-09-26 census: 5 implementations from 5 papers, 4 distinct outputs across 4 buckets, one shared input per bucket extra/imgs/concat.py ran MIT (permissive) ·
2e5319a051a23ef3 · report
fixture: signature img:ndarray/3/int, min_h:int/0/int, min_w:NoneType/0/? · returned ndarray · level recorded 2026-09-26 2 samples are identical to code Syntology harvested from another paper's repository; this paper's own copy was not located, so no repository is named and no licence is recorded.
9768efb52f591b55 · report
fixture: signature coeff:float/0/float · returned function · level recorded 2026-09-22 e352afa5762c5a6b · 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.
17 assemblies on this paper: 17 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).
17 sibling assemblies for Domain-Adversarial Training of Neural Networks (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 17 sibling assemblies; the other 5 are listed with their counts; every brick is in this page's JSON twin.
harvested Assembly for Domain-Adversarial Training of Neural Networks (graph method: Domain-Adversarial Training of Neural Networks). 4 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) · 2 unverified. The assembly has not been run end-to-end.
one of 17 siblings
- AdversarialNetwork entry · level 1 · ran ·
f1707c22da402ad3 - calc_coeff helper · level 0 · unverified ·
e352afa5762c5a6b - grl_hook update_rule · level 1 · ran · our draft was wrong ·
9768efb52f591b55 - init_weights helper · level 0 · unverified ·
7babf7ea472eba97
harvested Assembly for Domain-Adversarial Training of Neural Networks (graph method: Domain-Adversarial Training of Neural Networks). 8 bricks; individually on a fixture: 7 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; 6 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.
one of 17 siblings
- MADA entry · level 0 · unverified ·
e61d73732bf10468 - GRL helper · level 1 · ran ·
3ce4eba45b4ca3fc - load_backbone helper · level 1 · ran · our draft was wrong ·
f64f43c34c4542e9 - load_classifier helper · level 1 · ran · our draft was wrong ·
8d9374ad6935ac3d - linear2_bn helper · level 1 · ran · our draft was wrong ·
cd9167b485a751fd - linear2_dr2_bn helper · level 1 · ran · our draft was wrong ·
3e123903386d5131 - linear3_bn2_v1 helper · level 1 · ran · our draft was wrong ·
cec816fd8905007d - linear3_bn2_v2 helper · level 1 · ran · our draft was wrong ·
946555f6a21e149f
harvested Assembly for Domain-Adversarial Training of Neural Networks (graph method: Domain-Adversarial Training of Neural Networks). 9 bricks; individually on a fixture: 6 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; 4 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.
one of 17 siblings
- DANNtrainer entry · level 0 · unverified ·
b69e7e3bd38b5a79 - BaseDANNLike model · level 0 · unverified ·
6ca780e6cedb8469 - Method helper · level 0 · unverified ·
c0ae116e1108bfcf - ReverseLayerF helper · level 1 · ran ·
a9713d2fe23f5ada - BaseAdaptTrainer helper · level 1 · ran ·
0e5b0fea39063b16 - cross_entropy_logits loss · level 1 · ran; the contract check could not run (RAISES) ·
310d54a1dd86ec79 - get_aggregated_metrics helper · level 1 · ran · our draft was wrong ·
4113c2e807d432ee - get_aggregated_metrics_from_dict helper · level 1 · ran · our draft was wrong ·
61fd42a2e2a7cfcc - get_metrics_from_parameter_dict helper · level 1 · ran · our draft was wrong ·
704df3b8019c2aa5
harvested Assembly for Domain-Adversarial Training of Neural Networks (graph method: Domain-Adversarial Training of Neural Networks). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.
one of 17 siblings
- domain_confusion entry · level 0 · unverified ·
48ebff402229f303
harvested Assembly for Domain-Adversarial Training of Neural Networks (graph method: Domain-Adversarial Training of Neural Networks). 6 bricks; individually on a fixture: 4 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.
one of 17 siblings
- train entry · level 0 · unverified ·
1e5fb974a2b9088c - batch_generator sampler · level 1 · ran · our draft was wrong ·
4a9bc68de4ae0c55 - build_models model · level 1 · ran · our draft was wrong ·
f9776e8c18b947b6 - write_log helper · level 0 · unverified ·
882f695d04b3d5b7 - alexnet helper · level 1 · ran · our draft was wrong ·
d86e29f3ca97a8c2 - vgg_16 helper · level 1 · ran · our draft was wrong ·
851159feffea3b04
harvested Assembly for Domain-Adversarial Training of Neural Networks (graph method: Domain-Adversarial Training of Neural Networks). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.
one of 17 siblings
- FeatureExtractor entry · level 0 · unverified ·
3d0632c955417561
harvested Assembly for Domain-Adversarial Training of Neural Networks (graph method: Domain-Adversarial Training of Neural Networks). 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 17 siblings
- Discriminator entry · level 1 · ran ·
87db2131110dfd0a - GradReverse helper · level 1 · ran ·
22d411c2795ced15
harvested Assembly for Domain-Adversarial Training of Neural Networks (graph method: Domain-Adversarial Training of Neural Networks). 2 bricks; 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) · 1 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 17 siblings
- DANNModel entry · level 0 · unverified ·
9e554f3838a1af56 - ReverseLayerF helper · level 1 · ran ·
917fb058e1f4bb05
harvested Assembly for Domain-Adversarial Training of Neural Networks (graph method: Domain-Adversarial Training of Neural Networks). 4 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) · 1 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 17 siblings
- DANN entry · level 0 · unverified ·
cd0abd234c0eba6b - CellTypeCLF model · level 1 · ran ·
e2db8a3a21c6bf4c - GradReverse model · level 1 · ran ·
1a6a7062274a346d - ResBlock helper · level 1 · ran ·
1a8c0c365eb16cdc
harvested Assembly for Domain-Adversarial Training of Neural Networks (graph method: Domain-Adversarial Training of Neural Networks). 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 17 siblings
- AbstractDANN entry · level 1 · ran ·
8a387c444dc4c6a4 - Algorithm helper · level 1 · ran ·
f4f62760b15a2f01
harvested Assembly for Domain-Adversarial Training of Neural Networks (graph method: Domain-Adversarial Training of Neural Networks). 2 bricks; 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) · 1 unverified. The assembly has not been run end-to-end.
one of 17 siblings
- DANN entry · level 1 · ran ·
59f8b8a3c0a6bdfe - GradientReversalLayer helper · level 0 · unverified ·
a5f777ab36b3f81e
harvested Assembly for Domain-Adversarial Training of Neural Networks (graph method: Domain-Adversarial Training of Neural Networks). 1 brick; individually on a fixture: 0 ran · 1 unverified. The assembly has not been run end-to-end.
one of 17 siblings
- DANN entry · level 0 · unverified ·
fcde4e5aa7af7696
- ClassifierBase · e8e9b56027129a67 · 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 · assemblies[12] in the JSON twin
- AlexNetDANN · f06496e357b07abb · 2 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) · 0 unverified · The assembly has not been run end-to-end · assemblies[13] in the JSON twin
- WANN · f2db1ef7274004c7 · 4 bricks; individually on a fixture: 3 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 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 · assemblies[14] in the JSON twin
- DANN · f679a4707e16e77e · 8 bricks; individually on a fixture: 5 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; 4 where Syntology's instrument failed) · 3 unverified · The assembly has not been run end-to-end · assemblies[15] in the JSON twin
- FlipGradientBuilder · f9923162a6acd1b6 · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[16] 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="1505.07818") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
Datasets
Introduced by this paper, per the archive.
Results from the paper archive 2025-07-28
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.
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