Papers › Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks
Chelsea Finn, Pieter Abbeel, Sergey Levine
We propose an algorithm for meta-learning that is model-agnostic, in the sense that it is compatible with any model trained with gradient descent and applicable to a variety of different learning problems, including classification, regression, and reinforcement learning. The goal of meta-learning is to train a model on a variety of learning tasks, such that it can solve new learning tasks using only a small number of training samples. In our approach, the parameters of the model are explicitly trained such that a small number of gradient steps with a small amount of training data from a new task will produce good generalization performance on that task. In effect, our method trains the model to be easy to fine-tune. We demonstrate that this approach leads to state-of-the-art performance on two few-shot image classification benchmarks, produces good results on few-shot regression, and accelerates fine-tuning for policy gradient reinforcement learning with neural network policies.
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="1703.03400")get_code(code_sha256="…")with a sample'scode_sha256from the list belowget_citation_path(paper_1="1703.03400", paper_2="…")with another paper's arXiv id or titleget_concepts_for_paper(arxiv_id="1703.03400")
Code
Syntology 154 code samples: 153 from 43 repositories linked to this paper, 1 identical to code harvested from another paper's repository. Across all 154: 103 ran (of which 35 constructed an object rather than computing a result; 72 with no instrument failure: 6 honoured, 1 violated, 65 with no contract checked; 31 where Syntology's instrument failed) · 51 unverified. Where Syntology's instrument failed: 30 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: official repository: 1 sample from 1 repository, 1 ran (1 with no instrument failure; 0 where Syntology's instrument failed); community (archive-listed): 152 samples from 42 repositories, 101 ran (71 with no instrument failure; 30 where Syntology's instrument failed); 1 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:
- ThomasGoerttler/similarity-analysis-of-maml, community (archive-listed): harvested for another paper, listed under the repository
- Tikquuss/meta_XLM, community (archive-listed): harvested for 2 other papers, listed under the repository
- aliengirlliv/teachable, community (archive-listed): harvested for another paper, listed under the repository
- andrewbo29/mtm-meta-learning-sa, community (archive-listed): harvested for another paper, listed under the repository
- ebadrian/metadl, community (archive-listed): harvested for another paper, listed under the repository
- jonasrothfuss/promp, community (archive-listed): harvested for 2 other papers, listed under the repository
- leopard-ai/betty, community (archive-listed): harvested for another paper, listed under the repository
- prajjwal1/fluence, community (archive-listed): harvested for another paper, listed under the repository
- shaohua0116/MultiDigitMNIST, community (archive-listed): harvested for another paper, listed under the repository
- sidney1505/arc_maml_transformer, community (archive-listed): harvested for another paper, listed under the repository
- tristandeleu/pytorch-maml-rl, community (archive-listed): harvested for another paper, listed under the repository
- PaddlePaddle/PaddleRec, community (archive-listed): harvested for another paper, 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. 1 of the 103 samples that ran has no recorded date.
85 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
154 samples harvested: 103 ran (of which 35 constructed an object rather than computing a result; 72 with no instrument failure: 6 honoured, 1 violated, 65 with no contract checked; 31 where Syntology's instrument failed) · 51 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: 57 of the 154 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 43 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. 1 sample is 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 7 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.
980919fe451414a1 · report
fixture: signature paths:list/1/str, labels:list/1/int, nb_samples:int/0/int, shuffle:bool/0/bool · returned list · level recorded 2026-09-25 2831361f8df0f5f8 · report
fixture: returned LSLRGradientDescentLearningRule · level recorded 2026-09-22 87ad94fd897e556d · report
fixture: returned MetaBatchNormLayer · level recorded 2026-09-22 cdc8953f39812984 · report
fixture: returned MetaConv2dLayer · level recorded 2026-09-22 8edf11cc4b58def8 · report
fixture: returned MetaLayerNormLayer · level recorded 2026-09-22 89b9a544fd4f74db · report
fixture: returned MetaLinearLayer · level recorded 2026-09-22 bf4e67105c8629b1 · report
fixture: signature current_dict:dict/0/? · returned dict · level recorded 2026-09-22 4073393cd947277e · report
b1868b4b615a2205 · report
94001abc0a8125df · report
ec9b3be9c253bbb4 · report
9639920d1e2bc40a · report
fixture: returned MAML · level recorded 2026-09-22 census: 5 implementations from 5 papers, 4 distinct outputs across 3 buckets, one shared input per bucket maml_rl/metalearners/maml_trpo.py ran · our draft was wrong MIT (permissive) ·
f7eb271fa323b29e · report
fixture: signature tensor:Tensor/3/float, lengths:list/1/int · returned Tensor · level recorded 2026-09-22 e853be7e5751d09c · report
7d550f79f6439186 · report
fixture: returned MetaLearner · level recorded 2026-09-22 58ec79d486693632 · report
9d71c45dd9887865 · report
fixture: signature transform:Tensor/3/float · returned Tensor · level recorded 2026-09-24 82bdff06f37e069f · report
fixture: signature k:int/0/int, q:int/0/int · returned Tensor · level recorded 2026-09-22 375aad94c3dde98d · report
fixture: signature parameter_gradients:dict/0/?, parameter_name:str/0/str · returned function · level recorded 2026-09-22 db5610da74aa6eb4 · report
fixture: signature weights:list/1/Param · returned list · level recorded 2026-09-26 b9e24c3e3e0e88a7 · report
fixture: signature args:Namespace/0/?, cfg:dict/0/? · returned dict · level recorded 2026-09-22 c0de2922e383c9ed · report
fixture: signature parser:ArgumentParser/0/?, cfg:dict/0/?, helper:dict/0/?, choices:dict/0/?, cfg_path:str/0/str · returned Namespace · level recorded 2026-09-26 b0f7ef341475d3d7 · report
fixture: signature yaml_path:str/0/str · returned tuple · level recorded 2026-09-24 fa6e636313bab28d · report
fixture: signature f_Ax:callable/0/?, b:Tensor/1/float, cg_iters:int/0/int, callback:callable/0/?, verbose:bool/0/bool, residual_tol:float/0/float · returned ndarray · level recorded 2026-09-26 a9ccffea4b0a614b · report
fixture: signature Ax:callable/0/?, b:Tensor/1/float, cg_iters:int/0/int, EPS:float/0/float · returned ndarray · level recorded 2026-09-26 efcef47843a31b3b · report
fixture: signature Ax:callable/0/?, b:EagerTensor/1/float, cg_iters:int/0/int, residual_tol:float/0/float · returned EagerTensor · level recorded 2026-09-26 4246e3602f23a27a · report
fixture: signature env_name:str/0/str · returned function · level recorded 2026-09-25 d72142a564b3e983 · report
fixture: signature gradient_list:list/1/list · returned list · level recorded 2026-09-26 b81fd63dd0116e06 · report
fixture: signature config_settings:str/0/str · returned Metaworld · level recorded 2026-09-26 c66cf06af6b43781 · report
fixture: signature config_settings:str/0/str · returned Config_custom · level recorded 2026-09-26 e01d3118f70d5b05 · report
fixture: signature layer:callable/0/?, std:float/0/float, bias_const:float/0/float · returned Linear · level recorded 2026-09-22 7a70484a8c6ea863 · report
fixture: signature agent:callable/0/?, buffer:Buffer/0/?, params:dict/0/? · returned Tensor · level recorded 2026-09-26 c302086299d47cb7 · report
fixture: signature agent:callable/0/?, buffer:SimpleBuffer/0/? · returned Tensor · level recorded 2026-09-26 654f52e17f8d3cea · report
fixture: signature agent:callable/0/?, buffer:MinimalBuffer/0/?, old_distribution:NoneType/0/?, logs_dict:dict/0/? · returned tuple · level recorded 2026-09-26 6e6461e77bd12cc0 · report
fixture: signature model:callable/0/?, support_images:list/1/Tensor, support_labels:list/1/Tensor, query_images:list/1/Tensor, query_labels:list/1/Tensor, inner_step:int/0/int, args:Args/0/?, optimizer:SGD/0/?, is_train:bool/0/bool · returned tuple · level recorded 2026-09-22 58242025465b988c · report
fixture: signature logits:Tensor/2/float, targets:Tensor/1/int · returned float · level recorded 2026-09-25 e78673d4bdd6ad3c · report
fixture: signature tensors:Tensor/2/float, device:device/0/? · returned Tensor · level recorded 2026-09-25 0630f74816818382 · report
fixture: returned Policy · level recorded 2026-09-22 d5de2c8b41668dfe · report
fixture: returned Serializable · level recorded 2026-09-22 195f4090e1a4521d · report
1369a1bcd8fcf219 · report
72d04eb97254c420 · report
6b2336c5bf8ba995 · report
93275e38a44a53ec · report
fixture: returned Policy · level recorded 2026-09-22 f40ad64b1be5cb3d · report
a5f9d9ba1b5e2d0c · report
ef054b436c8098d9 · report
fixture: signature input:Tensor/4/float · returned Tensor · level recorded 2026-09-24 260ae4e7be8f8d1b · report
fixture: signature x:Tensor/4/float · returned Tensor · level recorded 2026-09-24 f8d3ba63fa4d3088 · report
fixture: returned ConvNet · level recorded 2026-09-22 census: 8 implementations from 8 papers, 6 distinct outputs across 2 buckets, one shared input per bucket meta_learner.py ran · metamorphic tier: deterministic fingerprinted no licence file found · pointer only ·
6e452cdc0fadf441 · report
fixture: returned ConvBlock · level recorded 2026-09-22 5d78dd8984d02527 · report
fixture: returned ConvNet · level recorded 2026-09-22 d53073ad75a7ff00 · report
fixture: signature x:Tensor/2/float · returned Tensor · level recorded 2026-09-24 3f8474018a3a2204 · report
fixture: returned MetaLearner · level recorded 2026-09-22 23f25fc3752e2b12 · report
fixture: returned Learner · level recorded 2026-09-22 6f410bc3b799fb12 · report
fixture: returned Learner · level recorded 2026-09-22 ea8b6ed6450139f9 · report
fixture: signature x:Tensor/4/float, num_step:int/0/int, params:NoneType/0/?, training:bool/0/bool, backup_running_statistics:bool/0/bool · returned Tensor · level recorded 2026-09-24 609db509762535cb · report
fixture: returned BottleneckLayer · level recorded 2026-09-22 census: 7 implementations from 7 papers, 6 distinct outputs on one shared input few_shot_learning_system.py ran fingerprinted MIT (permissive) ·
b0978ebdb0ce3ed2 · report
fixture: signature x:Tensor/4/float, num_step:int/0/int, params:NoneType/0/?, training:bool/0/bool, backup_running_statistics:bool/0/bool · returned Tensor · level recorded 2026-09-24 5011b08348e5492e · report
fixture: returned Critic · level recorded 2026-09-22 d84b7628e44a934d · report
fixture: returned DenseBlockUnit · level recorded 2026-09-22 51af2ebd778ea8d5 · report
fixture: returned MetaBatchNormLayer · level recorded 2026-09-22 5457b64a9cf91ad9 · report
fixture: signature x:Tensor/4/float, num_step:int/0/int, params:NoneType/0/?, training:bool/0/bool, backup_running_statistics:bool/0/bool · returned Tensor · level recorded 2026-09-24 54cb681500cf4722 · report
fixture: signature key:str/0/str, params_dict:dict/0/? · returned dict · level recorded 2026-09-22 437eaec2eb46d98e · report
5bfe2bb721bea138 · report
a687d54df08772c6 · report
e8f44cef97a4105d · report
d573fd8507d96088 · report
census: 5 implementations from 5 papers, 4 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 1 of 3, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32 maml_rl/metalearner.py ran · our draft was wrong fingerprinted MIT (permissive) ·
e1f576439c6726f0 · report
fixture: signature tensor:Tensor/2/float, dim:int/0/int, weights:Tensor/2/float · returned Tensor · level recorded 2026-09-22 a69240d5d84f2010 · report
fixture: signature tensor:Tensor/2/float, dim:NoneType/0/?, weights:Tensor/2/float, epsilon:float/0/float · returned Tensor · level recorded 2026-09-22 4d83438ea4c97aac · report
9815cdb73b01463a · report
fixture: returned MetaLearner · level recorded 2026-09-22 f735a270b8af92fc · report
8bdb2b9d394d85bf · report
fixture: returned BatchNorm2d · level recorded 2026-09-22 a1a99ec23db1357b · report
fixture: returned Module · level recorded 2026-09-22 a80e314d2c3c05c8 · report
fixture: signature params:dict/0/?, key:str/0/str · returned OrderedDict · level recorded 2026-09-22 0f3d548c0cb6818a · report
fixture: returned OmniglotModel · level recorded 2026-09-22 e3ee206f6ec04d58 · report
fixture: returned MAMLmodel · level recorded 2026-09-22 6990e7e380ef497e · report
fixture: signature inp:SymbolicTensor/2/float, weights:list/1/SymbolicTensor, reuse:bool/0/bool · returned EagerTensor · level recorded 2026-09-22 census: 2 implementations from 6 papers, 2 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 2 of 2, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32 meta_mb/algos/sac.py ran · honoured contract fingerprinted MIT (permissive) ·
31deb9c7be58e00c · report
fixture: signature reward:Tensor/2/float, discount:float/0/float, next_value:Tensor/2/float · returned Tensor · level recorded, date not recorded a384fd2f6407795c · report
4a59b5aa3c2e6207 · report
21fa635295537d1c · report
34f35211dea92750 · report
fixture: returned Axes · level recorded 2026-09-22 c930e1b84447e6cb · report
fixture: returned MAML · level recorded 2026-09-22 08e27fecd8630d42 · report
fixture: signature x:ndarray/1/float, ax:Axes/0/?, q:ndarray/1/float, showmeans:bool/0/bool, means_args:dict/0/?, dots:bool/0/bool, color:str/0/str, linewidth:float/0/float, label:str/0/str · returned Axes · level recorded 2026-09-22 24418e88c369907e · report
fixture: signature est_name:str/0/str · returned tuple · level recorded 2026-09-22 b92731b55be235fa · report
fixture: signature input:Tensor/4/float, weight:Tensor/4/float, bias:Tensor/1/float, stride:int/0/int, padding:int/0/int, dilation:int/0/int, groups:int/0/int · returned Tensor · level recorded 2026-09-24 c5e794825d1e6ee1 · report
fixture: signature input:Tensor/2/float, weight:Tensor/2/float, bias:Tensor/1/float · returned Tensor · level recorded 2026-09-24 census: 8 implementations from 11 papers, 4 distinct outputs across 2 buckets, one shared input per bucket src/layers.py ran fingerprinted MIT (permissive) ·
8dd8a8e3eac0253a · report
fixture: signature input:Tensor/2/float · returned Tensor · level recorded 2026-09-24 c5becc80cbb51e3d · report
fixture: returned MAML · level recorded 2026-09-22 census: 5 implementations from 6 papers, 4 distinct outputs across 3 buckets, one shared input per bucket sinusoid/maml.py ran · our draft was wrong no licence file found · pointer only ·
44ef1cbe96c1a0d4 · report
fixture: signature pred:SymbolicTensor/2/float, label:SymbolicTensor/2/float · returned SymbolicTensor · level recorded 2026-09-22 cc6f21a12ec084fc · report
census: 70 implementations from 82 papers, 51 distinct outputs across 11 buckets, one shared input per bucket sinusoid/maml.py unverified no licence file found · pointer only ·
13460feadb3fa71f · report
6318e1b6fc749097 · report
census: 8 implementations from 7 papers, 7 distinct outputs across 6 buckets, one shared input per bucket this sample: bucket 4 of 6, arg 1: rank 1, kind int, dtype int64 · arg 2: rank 1, kind int, dtype int64 algorithms/maml.py ran · our draft was wrong fingerprinted MIT (permissive) ·
6169b24cbef2d3af · report
fixture: signature y_pred:Tensor/1/int, y:Tensor/1/int · returned float · level recorded 2026-09-22 dc1834f86f4b0e22 · report
fixture: signature criterion:callable/0/? · returned tuple · level recorded 2026-09-22 252b1f1cf01d5b28 · report
fixture: signature model:callable/0/?, train_x:Tensor/2/float, train_y:Tensor/2/float, flat:bool/0/bool, weights:NoneType/0/?, item_loss:bool/0/bool, create_graph:bool/0/bool, retain_graph:bool/0/bool · returned tuple · level recorded 2026-09-24 d6eb53b51abcd3ba · report
fixture: signature dev:str/0/str, tensors:list/1/Tensor · returned list · level recorded 2026-09-22 census: 6 implementations from 8 papers, 5 distinct outputs across 2 buckets, one shared input per bucket MAML/lib/networks.py ran · violated contract fingerprinted no licence file found · pointer only ·
826e48b56e489fae · report
fixture: signature pred:EagerTensor/2/float, label:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-22 94d6d525278d2bd5 · report
46ca33eedd6bd1cf · report
2a31274d3bff46a8 · report
fixture: returned MetaLearner · level recorded 2026-09-22 65320d46ade5b2da · report
fixture: returned GradientBasedMetaLearner · level recorded 2026-09-22 c4daaf04c83ccbd2 · report
fixture: signature f_Ax:callable/0/?, b:Tensor/1/float, cg_iters:int/0/int, residual_tol:float/0/float · returned Tensor · level recorded 2026-09-22 2459a4e7bc46e742 · report
fixture: signature pi:Categorical/0/? · returned Categorical · level recorded 2026-09-22 census: 24 implementations from 29 papers, 2 distinct outputs across 2 buckets, one shared input per bucket this sample: bucket 1 of 2, arg 1: rank 2, kind float, dtype float32 maml_rl/metalearners/maml_trpo.py ran · honoured contract MIT (permissive) ·
e329883dde48a331 · report
fixture: signature tensor:Tensor/2/float · returned ndarray · level recorded 2026-09-22 census: 5 implementations from 5 papers, 4 distinct outputs across 3 buckets, one shared input per bucket maml_rl/metalearners/maml_trpo.py ran · our draft was wrong MIT (permissive) ·
9e2447675de7c741 · report
fixture: returned Tensor · level recorded 2026-09-22 220e4973c329aa66 · report
0b9aaae9c620514c · report
93c4edf2272400b5 · report
fixture: returned LearnerConv · level recorded 2026-09-22 a8f78f0cacf4d49a · report
fixture: signature x:Tensor/2/float, params:NoneType/0/? · returned Tensor · level recorded 2026-09-24 159ae31bd6bceefb · report
fixture: signature pi:Categorical/0/? · returned Categorical · level recorded 2026-09-22 census: 5 implementations from 5 papers, 4 distinct outputs across 3 buckets, one shared input per bucket this sample: bucket 1 of 3, arg 1: rank 2, kind float, dtype float32 · arg 2: rank 2, kind float, dtype float32 maml_rl/metalearner.py ran · our draft was wrong fingerprinted MIT (permissive) ·
84d8e466a8a42e55 · report
fixture: signature tensor:Tensor/2/float, dim:NoneType/0/?, weights:Tensor/2/float · returned Tensor · level recorded 2026-09-22 b5feb3c5fe651042 · report
fixture: signature tensor:Tensor/2/float, dim:NoneType/0/?, weights:Tensor/2/float, epsilon:float/0/float · returned Tensor · level recorded 2026-09-22 0c94d755db4b139e · report
b3c76271d8b0eb64 · report
fixture: returned MAMLClassifier · level recorded 2026-09-22 0119024a5f2c09b7 · report
fixture: signature in_channels:int/0/int, out_channels:int/0/int · returned Sequential · level recorded 2026-09-22 05555b0c97352c11 · report
fixture: signature x:Tensor/4/float, weights:Tensor/4/float, biases:Tensor/1/float, bn_weights:Tensor/1/float, bn_biases:Tensor/1/float · returned Tensor · level recorded 2026-09-22 428acd76dd218c3d · report
fixture: signature pred:EagerTensor/2/float, label:EagerTensor/2/float · returned EagerTensor · level recorded 2026-09-22 ec0fb012c0b639eb · report
fixture: returned Task · level recorded 2026-09-22 e0e936b85f1b650d · report
fixture: signature p_model:list/1/Tensor, meta_optimizer:SGD/0/?, inner_training_steps:int/0/int, nb_epochs:int/0/int, batch_size_K:int/0/int, alpha:float/0/float, nb_tasks:int/0/int, device:str/0/str · returned list · level recorded 2026-09-22 e78a9a3c93b39d53 · report
fixture: signature x:Tensor/2/float, params:list/1/Tensor · returned Tensor · level recorded 2026-09-22 617daca3f7cba9e0 · report
fixture: signature params:list/1/Tensor, task:SimpleTask/0/?, batch_size:int/0/int, inner_training_steps:int/0/int, alpha:float/0/float, device:str/0/str · returned list · level recorded 2026-09-22 187bc4818a35dd85 · report
fixture: returned Task · level recorded 2026-09-22 77bf690edcbd2974 · report
fixture: returned BaseLearner · level recorded 2026-09-22 bbe0a23f6db14d65 · report
fixture: signature module:callable/0/?, memo:NoneType/0/? · returned SimpleModule · level recorded 2026-09-22 59b665121c69f877 · report
fixture: signature model:callable/0/?, lr:float/0/float, grads:list/1/Tensor · returned SimpleModel · level recorded 2026-09-22 f9c02bacacf8dfc0 · report
fixture: signature module:callable/0/?, updates:list/1/Tensor, memo:NoneType/0/? · returned SimpleModel · level recorded 2026-09-22 ef83f512b95bdb2e · report
fixture: returned CNN_MAML · level recorded 2026-09-22 9eb20bff998008f7 · report
fixture: returned ResNet_MAML · level recorded 2026-09-22 d54ad2d81fd18390 · report
fixture: returned MockImageFolder · level recorded 2026-09-22 1 sample is 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.
5c44538154dad8a7 · report
fixture: signature seed:int/0/int · returned RandomState · 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.
36 assemblies on this paper: 36 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).
36 sibling assemblies for Model-Agnostic Meta-Learning (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 36 sibling assemblies; the other 24 are listed with their counts; every brick is in this page's JSON twin.
harvested Assembly for Model-Agnostic Meta-Learning (graph method: Model-Agnostic Meta-Learning). 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 36 siblings
- OmniglotModel entry · level 1 · ran ·
0f3d548c0cb6818a
harvested Assembly for Model-Agnostic Meta-Learning (graph method: Model-Agnostic Meta-Learning). 5 bricks; individually on a fixture: 4 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; 3 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.
one of 36 siblings
- MAML entry · level 0 · unverified ·
686262f4f165565a - BaseLearner model · level 1 · ran ·
77bf690edcbd2974 - clone_module helper · level 1 · ran · our draft was wrong ·
bbe0a23f6db14d65 - maml_update update_rule · level 1 · ran · our draft was wrong ·
59b665121c69f877 - update_module helper · level 1 · ran · our draft was wrong ·
f9c02bacacf8dfc0
harvested Assembly for Model-Agnostic Meta-Learning (graph method: Model-Agnostic Meta-Learning). 4 bricks; individually on a fixture: 3 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; 0 where Syntology's instrument failed) · 1 unverified. The assembly has not been run end-to-end.
one of 36 siblings
- CNN_MAML entry · level 1 · ran ·
ef83f512b95bdb2e - ResNet_MAML helper · level 1 · ran ·
9eb20bff998008f7 - Config helper · level 0 · unverified ·
312e877e19776da5 - get_imageset helper · level 1 · ran ·
d54ad2d81fd18390
harvested Assembly for Model-Agnostic Meta-Learning (graph method: Model-Agnostic Meta-Learning). 5 bricks; individually on a fixture: 5 ran (of which 1 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 36 siblings
- maml entry · level 1 · ran · honoured contract ·
e0e936b85f1b650d - mlp model · level 1 · ran · our draft was wrong ·
e78a9a3c93b39d53 - perform_k_training_steps update_rule · level 1 · ran · our draft was wrong ·
617daca3f7cba9e0 - sample_task sampler · level 1 · ran ·
187bc4818a35dd85 - Task helper · level 1 · ran ·
ec0fb012c0b639eb
harvested Assembly for Model-Agnostic Meta-Learning (graph method: Model-Agnostic Meta-Learning). 4 bricks; individually on a fixture: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.
one of 36 siblings
- MAMLNet entry · level 0 · unverified ·
94d6d525278d2bd5 - Network helper · level 0 · unverified ·
46ca33eedd6bd1cf - cross_entropy loss · level 1 · ran · violated contract ·
826e48b56e489fae - tf_acc metric · level 1 · ran · honoured contract ·
d76ff0bd573853cd
harvested Assembly for Model-Agnostic Meta-Learning (graph method: Model-Agnostic Meta-Learning). 2 bricks; individually on a fixture: 2 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 36 siblings
- MAMLmodel entry · level 1 · ran ·
e3ee206f6ec04d58 - forward_func model · level 1 · ran · honoured contract ·
6990e7e380ef497e
harvested Assembly for Model-Agnostic Meta-Learning (graph method: Model-Agnostic Meta-Learning). 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 36 siblings
- MetaLearner entry · level 1 · ran ·
9815cdb73b01463a - Learner model · level 0 · unverified ·
f735a270b8af92fc
harvested Assembly for Model-Agnostic Meta-Learning (graph method: Model-Agnostic Meta-Learning). 4 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) · 2 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 36 siblings
- MAMLAlgo entry · level 0 · unverified ·
195f4090e1a4521d - MetaAlgo helper · level 0 · unverified ·
1369a1bcd8fcf219 - Policy helper · level 1 · ran ·
0630f74816818382 - Serializable helper · level 1 · ran ·
d5de2c8b41668dfe
harvested Assembly for Model-Agnostic Meta-Learning (graph method: Model-Agnostic Meta-Learning). 10 bricks; individually on a fixture: 7 ran (of which 5 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 2 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.
one of 36 siblings
- MAMLFewShotClassifier entry · level 0 · unverified ·
4073393cd947277e - LSLRGradientDescentLearningRule update_rule · level 1 · ran ·
2831361f8df0f5f8 - VGGReLUNormNetwork model · level 0 · unverified ·
94001abc0a8125df - set_torch_seed helper · level 1 · ran · our draft was wrong ·
5c44538154dad8a7 - MetaConvNormLayerReLU model · level 0 · unverified ·
b1868b4b615a2205 - MetaLinearLayer model · level 1 · ran ·
89b9a544fd4f74db - extract_top_level_dict helper · level 1 · ran · our draft was wrong ·
bf4e67105c8629b1 - MetaBatchNormLayer model · level 1 · ran ·
87ad94fd897e556d - MetaConv2dLayer model · level 1 · ran ·
cdc8953f39812984 - MetaLayerNormLayer model · level 1 · ran ·
8edf11cc4b58def8
harvested Assembly for Model-Agnostic Meta-Learning (graph method: Model-Agnostic Meta-Learning). 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.
one of 36 siblings
- meta_gradient_step entry · level 0 · unverified ·
1469e165f5adf02e - create_nshot_task_label helper · level 1 · ran · honoured contract ·
82bdff06f37e069f - replace_grad helper · level 1 · ran · our draft was wrong ·
375aad94c3dde98d - IdentityTransformLoss helper · level 1 · ran ·
9d71c45dd9887865
harvested Assembly for Model-Agnostic Meta-Learning (graph method: Model-Agnostic Meta-Learning). 8 bricks; individually on a fixture: 8 ran (of which 4 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified. The assembly has not been run end-to-end.
one of 36 siblings
- MetaLearner entry · level 1 · ran ·
3f8474018a3a2204 - Conv4 helper · level 1 · ran ·
f8d3ba63fa4d3088 - Linear_fw model · level 1 · ran ·
d53073ad75a7ff00 - ConvNet model · level 1 · ran ·
5d78dd8984d02527 - ConvBlock helper · level 1 · ran ·
6e452cdc0fadf441 - Flatten helper · level 1 · ran ·
e1419c05ef8cd25e - BatchNorm2d_fw model · level 1 · ran ·
ef054b436c8098d9 - Conv2d_fw model · level 1 · ran ·
260ae4e7be8f8d1b
harvested Assembly for Model-Agnostic Meta-Learning (graph method: Model-Agnostic Meta-Learning). 9 bricks; individually on a fixture: 5 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; 3 where Syntology's instrument failed) · 4 unverified. The assembly has not been run end-to-end.
one of 36 siblings
- MAML entry · level 1 · ran ·
c930e1b84447e6cb - Axes helper · level 1 · ran ·
34f35211dea92750 - clip_ylim helper · level 0 · unverified ·
1aa223f468983762 - plot_quantiles helper · level 1 · ran; the contract check could not run (RAISES) ·
08e27fecd8630d42 - process_estimator helper · level 1 · ran · our draft was wrong ·
24418e88c369907e - quantile helper · level 1 · ran; the contract check could not run ·
39c3d160a2608b68 - set_all_seeds helper · level 0 · unverified ·
a7029a07ec1395db - fontsize helper · level 0 · unverified ·
41f8b0762a4201b5 - labels helper · level 0 · unverified ·
aba9590bba6ff8a8
- Meta · 3792933cf92d0fad · 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 · assemblies[12] in the JSON twin
- MetaLearner · 4102cbb477061ebe · 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 · assemblies[13] in the JSON twin
- MAML · 47a1f9cd886aa06a · 4 bricks; individually on a fixture: 3 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; 1 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[14] in the JSON twin
- MAMLNet · 4f360ab844ada472 · 4 bricks; individually on a fixture: 2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified · The assembly has not been run end-to-end · assemblies[15] in the JSON twin
- single_task_grad_and_losses · 5dfa0c81585107ce · 3 bricks; individually on a fixture: 0 ran · 3 unverified · The assembly has not been run end-to-end · assemblies[16] in the JSON twin
- MAML · 6c3e44b778c73946 · 5 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) · 3 unverified · The assembly has not been run end-to-end · assemblies[17] in the JSON twin
- Meta · 703d21ace93f8d36 · 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 · assemblies[18] in the JSON twin
- MAMLFewShotClassifier · 720cf5454cb6e01d · 19 bricks; individually on a fixture: 14 ran (of which 8 constructed an object rather than computing a result; 11 with no instrument failure: 0 honoured, 0 violated, 11 with no contract checked; 3 where Syntology's instrument failed) · 5 unverified · The assembly has not been run end-to-end · assemblies[19] in the JSON twin
- MAML · 7217635101985985 · 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 · assemblies[20] in the JSON twin
- meta_gradient_step · 8b32c93f79775357 · 3 bricks; individually on a fixture: 2 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; 1 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[21] in the JSON twin
- MAMLTRPO · 8eabe7795ab02bc4 · 8 bricks; individually on a fixture: 5 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified · The assembly has not been run end-to-end · assemblies[22] in the JSON twin
- MAMLClassifier · 92b64b176248df3b · 3 bricks; individually on a fixture: 3 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; 2 where Syntology's instrument failed) · 0 unverified · The assembly has not been run end-to-end · assemblies[23] in the JSON twin
- Regressor · 9e08ab670c1cbd06 · 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[24] in the JSON twin
- LearnerConv · b4c5196647a3c697 · 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 · assemblies[25] in the JSON twin
- MAMLAlgo · b5a315644989f0e0 · 4 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) · 2 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 · assemblies[26] in the JSON twin
- MetaLearner · b8b6ebcf3b9831fc · 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 · assemblies[27] in the JSON twin
- maml · c03e5911ef4fec13 · 1 brick; individually on a fixture: 0 ran · 1 unverified · The assembly has not been run end-to-end · assemblies[28] in the JSON twin
- MAMLTRPO · c136332a0251d93c · 8 bricks; individually on a fixture: 5 ran (of which 1 constructed an object rather than computing a result; 2 with no instrument failure: 1 honoured, 0 violated, 1 with no contract checked; 3 where Syntology's instrument failed) · 3 unverified · The assembly has not been run end-to-end · assemblies[29] in the JSON twin
- MetaLearner · c2495f0177573454 · 5 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) · 1 unverified · The assembly has not been run end-to-end · assemblies[30] in the JSON twin
- Meta · c375f1a6111447eb · 2 bricks; individually on a fixture: 0 ran · 2 unverified · The assembly has not been run end-to-end · assemblies[31] in the JSON twin
- maml_train · d02ca48f6f24fb17 · 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 · assemblies[32] in the JSON twin
- MetaLearner · d867dff44e1c9d4f · 4 bricks; individually on a fixture: 3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified · The assembly has not been run end-to-end · assemblies[33] in the JSON twin
- MetaLearner · f3c5129c0fd1cd5d · 5 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) · 1 unverified · The assembly has not been run end-to-end · assemblies[34] in the JSON twin
- MAML · f8d9c3a2f26460a5 · 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 · assemblies[35] 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="1703.03400") returns these assemblies with each brick's role and wiring (how to connect).
Tasks
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.
Methods
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