Papers › On First-Order Meta-Learning Algorithms

On First-Order Meta-Learning Algorithms

8 Mar 2018arXiv:1803.02999archive 2025-07-28

Alex Nichol, Joshua Achiam, John Schulman

This paper considers meta-learning problems, where there is a distribution of tasks, and we would like to obtain an agent that performs well (i.e., learns quickly) when presented with a previously unseen task sampled from this distribution. We analyze a family of algorithms for learning a parameter initialization that can be fine-tuned quickly on a new task, using only first-order derivatives for the meta-learning updates. This family includes and generalizes first-order MAML, an approximation to MAML obtained by ignoring second-order derivatives. It also includes Reptile, a new algorithm that we introduce here, which works by repeatedly sampling a task, training on it, and moving the initialization towards the trained weights on that task. We expand on the results from Finn et al. showing that first-order meta-learning algorithms perform well on some well-established benchmarks for few-shot classification, and we provide theoretical analysis aimed at understanding why these algorithms work.

PaperPDFCodeCode Syntology ranMethod as code

In Syntology View this paper on Syntology, its page in Syntology's graph. That page adds which of its functions are also present in other papers' code Syntology holds, with dates, and its dated run record as JSON and a README badge. It also lists the repositories linked to the paper, the abstract and the calls for agents.

Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

For agents, on Syntology's MCP service (how to connect):

Code

Syntology 42 code samples harvested from 8 repositories linked to this paper: 27 ran (of which 2 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 2 violated, 6 with no contract checked; 18 where Syntology's instrument failed) · 15 unverified. Where Syntology's instrument failed: 14 where our contract draft was wrong; 4 where the contract check could not run; failures of Syntology's instrument, not of the code.

By repository: official repository: 10 samples from 1 repository, 8 ran (2 with no instrument failure; 6 where Syntology's instrument failed); community (archive-listed): 32 samples from 7 repositories, 19 ran (7 with no instrument failure; 12 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 1 of its repositories that Syntology harvested for other papers:

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.

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

openai/supervised-reptile officialmentioned on GitHubtfSyntology: 10 samples, 8 ran (6 instrument-failed) · 2 unverified report
Yuzhe-CHEN/NerfSNN mentioned on GitHubpytorchMITSyntology: not harvested report
aravindMahadevan/metaLearningAlgos mentioned on GitHubpytorchSyntology: not harvested report
gabrielhuang/reptile-pytorch mentioned on GitHubpytorchBSD-2-ClauseSyntology: 3 samples, 3 ran (0 instrument-failed) · 0 unverified report
gebob19/REPTILE-Metalearning mentioned on GitHubpytorchSyntology: not harvested report
gebob19/cscd94-metalearning mentioned on GitHubpytorchSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks (arXiv:1703.03400; that paper's own run record: 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); nothing checks that they implement this paper's method. report
gebob19/cscd94_metalearning mentioned on GitHubpytorchSyntology: not harvested report
hfahrudin/reptile_implement_tf2 mentioned on GitHubtfSyntology: 7 samples, 3 ran (2 instrument-failed) · 4 unverified report
peisungtsai/Reptile-Pytorch-Implementation mentioned on GitHubpytorchSyntology: 10 samples, 8 ran (6 instrument-failed) · 2 unverified report
radrumond/Chameleon mentioned on GitHubtfSyntology: 3 samples, 1 ran (1 instrument-failed) · 2 unverified report
sanowar-raihan/nerf-meta mentioned on GitHubpytorchSyntology: 5 samples, 3 ran (3 instrument-failed) · 2 unverified report
MaximeVandegar/Papers-in-100-Lines-of-Code pytorchSyntology: 3 samples, 1 ran (0 instrument-failed) · 2 unverified report
learnables/learn2learn pytorchSyntology: 1 sample, 0 ran · 1 unverified 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

42 samples harvested: 27 ran (of which 2 constructed an object rather than computing a result; 9 with no instrument failure: 1 honoured, 2 violated, 6 with no contract checked; 18 where Syntology's instrument failed) · 15 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
2ran · violated contract
14ran · our draft was wrong
4ran; the contract check could not run
6ran
15unverified

Licence: 13 of the 42 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 8 repositories linked to this paper, official or community; the list below is grouped by repository, each group headed by its name and what it is to the paper. “Ran” means the sample executed on a synthesized input. It does not mean the output is correct, and nothing here reproduces the paper's results. A line beginning “fixture:” under a sample that ran gives the arguments Syntology's fixture called the sample with, each as name:type/rank/element kind (? where none was recorded), and the type of what the fixture's run returned, exactly as the harness recorded them; the arguments and the returned type were recorded by two separate runs of the same fixture. No output value is shown, and a returned type says nothing about whether the output was right. “Level recorded” gives the UTC date when Syntology's graph wrote the sample's verification level, not when the code executed; where the level was written before Syntology's graph kept that date, the row says “level recorded, date not recorded”. “Honoured” and “violated” refer to a contract Syntology drafted from the code itself. “Our draft was wrong” and “the contract check could not run” are failures of Syntology's instrument, not of the code: the sample ran on Syntology's synthesized input, and then the drafted contract did not describe it, or the check itself raised an error (RAISES), lacked a dependency (DEP_MISSING) or ran out of time (TIMEOUT); hover the label for which. A metamorphic tier, where shown, is evidence of the output's shape, not that the sample implements the method.

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

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

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

openai/supervised-reptile official repository 10 samples, 8 ran (6 instrument-failed) · 2 unverified
_mini_batches supervised_reptile/reptile.py ran · our draft was wrong MIT (permissive) · a9fca842e7dce3dc · report fixture: signature samples:list/1/tuple, batch_size:int/0/int, num_batches:int/0/int, replacement:bool/0/bool · returned generator · level recorded 2026-09-22
_sample_mini_dataset supervised_reptile/reptile.py ran · our draft was wrong MIT (permissive) · 8a4d810f710c7156 · report fixture: signature dataset:list/1/MockClass, num_classes:int/0/int, num_shots:int/0/int · returned generator · level recorded 2026-09-22
_split_train_test supervised_reptile/reptile.py ran · our draft was wrong MIT (permissive) · d91fc29b93983a36 · report fixture: signature samples:list/1/tuple, test_shots:int/0/int · returned tuple · level recorded 2026-09-22
add_vars supervised_reptile/reptile.py ran · our draft was wrong fingerprinted MIT (permissive) · 4e38232a76ab2c21 · report fixture: signature var_seq_1:list/1/Tensor, var_seq_2:list/1/Tensor · returned list · level recorded 2026-09-22
average_vars supervised_reptile/reptile.py ran · violated contract MIT (permissive) · 59c0d53cfcbb2398 · report fixture: signature var_seqs:list/1/list · returned list · level recorded 2026-09-22
interpolate_vars supervised_reptile/reptile.py ran · our draft was wrong fingerprinted MIT (permissive) · b6a6811d1b4f3cb1 · report fixture: signature old_vars:list/1/Tensor, new_vars:list/1/Tensor, epsilon:float/0/float · returned list · level recorded 2026-09-22
scale_vars supervised_reptile/reptile.py ran · violated contract fingerprinted MIT (permissive) · 546a058c2eeefb61 · report fixture: signature var_seq:list/1/Tensor, scale:float/0/float · returned list · level recorded 2026-09-22
subtract_vars supervised_reptile/reptile.py ran · our draft was wrong fingerprinted MIT (permissive) · 3880e32be4fd7c7f · report fixture: signature var_seq_1:list/1/Tensor, var_seq_2:list/1/Tensor · returned list · level recorded 2026-09-22
Reptile supervised_reptile/reptile.py unverified MIT (permissive) · 12c044306a7432d7 · report
VariableState supervised_reptile/reptile.py unverified MIT (permissive) · fc567dbf68a97f9c · report
gabrielhuang/reptile-pytorch community (archive-listed) 3 samples, 3 ran (0 instrument-failed) · 0 unverified
find_latest_file utils.py ran BSD-2-Clause (permissive) · b63cb25f52bfa440 · report fixture: signature folder:str/0/str · returned str · level recorded 2026-09-26
list_dir in 22 papers utils.py ran BSD-2-Clause (permissive) · 9bc2cdc80cede326 · report fixture: signature root:str/0/str, prefix:bool/0/bool · returned list · level recorded 2026-09-26
list_files in 33 papers utils.py ran BSD-2-Clause (permissive) · fdee3ec4c52c3c4e · report fixture: signature root:str/0/str, suffix:str/0/str, prefix:bool/0/bool · returned list · level recorded 2026-09-26
hfahrudin/reptile_implement_tf2 community (archive-listed) 7 samples, 3 ran (2 instrument-failed) · 4 unverified
SineModel Reptile.py ran MIT (permissive) · 4c7e734776a0037f · report fixture: returned SineModel · level recorded 2026-09-22
copy_model Reptile.py ran · our draft was wrong MIT (permissive) · 5b32ff71531a63f4 · report fixture: signature model:callable/0/?, x:ndarray/2/float · returned SineModel · level recorded 2026-09-22
np_to_tensor Reptile.py ran · our draft was wrong MIT (permissive) · 6898b2b8e89e013c · report fixture: signature list_of_numpy_objs:list/1/ndarray · returned generator · level recorded 2026-09-22
train_batch in 14 papers Reptile.py unverified MIT (permissive) · 6ccf8109b819b534 · report
train_reptile Reptile.py unverified MIT (permissive) · 7ce7bf6a46593388 · report
peisungtsai/Reptile-Pytorch-Implementation community (archive-listed) 10 samples, 8 ran (6 instrument-failed) · 2 unverified
MiniimagenetModel reptile.py ran · metamorphic tier: deterministic no licence file found · pointer only · 8d746ce18ec482a7 · report fixture: returned MiniimagenetModel · level recorded 2026-09-22
Variable_ reptile.py ran; the contract check could not run (RAISES) · metamorphic tier: deterministic fingerprinted no licence file found · pointer only · e2090b8a7ed2f304 · report fixture: signature inputs:Tensor/2/float, labels:Tensor/1/int, cuda:bool/0/bool · returned tuple · level recorded 2026-09-22
average_vars reptile.py ran · our draft was wrong no licence file found · pointer only · 634c4ae3d42d183d · report fixture: signature dict_list:list/1/dict · returned dict · level recorded 2026-09-22
clone_model reptile.py ran · our draft was wrong no licence file found · pointer only · 5756a43251ee78a0 · report fixture: signature num_classes:int/0/int, model_state:dict/0/? · returned MiniimagenetModel · level recorded 2026-09-22
get_loss in 107 papers
census: 5 implementations from 5 papers, 5 distinct outputs across 4 buckets, one shared input per bucket
reptile.py ran; the contract check could not run (RAISES) · metamorphic tier: invariant no licence file found · pointer only · 1aec86f12ed5bdbf · report fixture: signature prediction:Tensor/2/float, labels:Tensor/1/int · returned Tensor · level recorded 2026-09-22
get_optimizer in 228 papers reptile.py ran · our draft was wrong no licence file found · pointer only · 4119f639d71237d9 · report fixture: signature model:callable/0/?, state:dict/0/? · returned Adam · level recorded 2026-09-22
interpolate_vars reptile.py ran · our draft was wrong no licence file found · pointer only · e1d757cc1d97469e · report fixture: signature old_vars:dict/0/?, new_vars:dict/0/?, epsilon:float/0/float · returned dict · level recorded 2026-09-22
predict_label reptile.py ran · honoured contract fingerprinted no licence file found · pointer only · 1e9509d17fafd962 · report fixture: signature prob:Tensor/2/float · returned Tensor · level recorded 2026-09-22
Reptile reptile.py unverified no licence file found · pointer only · d215ca39171d7e6a · report
argument_parser reptile.py unverified no licence file found · pointer only · e5b4fcff02414010 · report
radrumond/Chameleon community (archive-listed) 3 samples, 1 ran (1 instrument-failed) · 2 unverified
padCols code/reptile.py ran; the contract check could not run (RAISES) fingerprinted no licence file found · pointer only · 663789fdc8b48fc7 · report fixture: signature vec:ndarray/2/float, size:int/0/int · returned ndarray · level recorded 2026-09-22
Reptile code/reptile.py unverified no licence file found · pointer only · 862a81450c933234 · report
savePlot code/reptile.py unverified no licence file found · pointer only · a2a852379817fd88 · report
sanowar-raihan/nerf-meta community (archive-listed) 5 samples, 3 ran (3 instrument-failed) · 2 unverified
get_rays_shapenet shapenet_train.py ran · our draft was wrong MIT (permissive) · 874a035aef959ab0 · report fixture: signature hwf:tuple/1/Tensor, poses:Tensor/3/float · returned tuple · level recorded 2026-09-22
sample_points shapenet_train.py ran · our draft was wrong fingerprinted MIT (permissive) · ee6a21f2e9ccd76e · report fixture: signature rays_o:Tensor/2/float, rays_d:Tensor/2/float, near:float/0/float, far:float/0/float, num_samples:int/0/int, perturb:bool/0/bool · returned tuple · level recorded 2026-09-22
volume_render shapenet_train.py ran; the contract check could not run (RAISES) fingerprinted MIT (permissive) · ea9eecfceada7f03 · report fixture: signature rgbs:Tensor/3/float, sigmas:Tensor/2/float, t_vals:Tensor/2/float, white_bkgd:bool/0/bool · returned Tensor · level recorded 2026-09-22
inner_loop in 5 papers shapenet_train.py unverified MIT (permissive) · 649f40959e38546d · report
train_meta shapenet_train.py unverified MIT (permissive) · 9ad33249189e3716 · report
MaximeVandegar/Papers-in-100-Lines-of-Code community (archive-listed) 3 samples, 1 ran (0 instrument-failed) · 2 unverified
sample_task On_First_Order_Meta_Learning_Algorithms/reptile.py ran MIT (permissive) · 38ba8a7c486030e7 · report fixture: returned tuple · level recorded 2026-09-22
perform_k_training_steps On_First_Order_Meta_Learning_Algorithms/reptile.py unverified MIT (permissive) · 7c5446461cabc053 · report
reptile On_First_Order_Meta_Learning_Algorithms/reptile.py unverified MIT (permissive) · a7a5b0bb081fdc90 · report
learnables/learn2learn community (archive-listed) 1 sample, 0 ran · 1 unverified
GBML learn2learn/algorithms/gbml.py unverified MIT (permissive) · c2a3170df7df4870 · 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.

8 assemblies on this paper: 8 harvested, 0 generated, listed in 1 groups (siblings lifted in one batch form one group).

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

harvested Assembly for Reptile (graph method: Reptile). 10 bricks; individually on a fixture: 8 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 6 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. Reptile entry · level 0 · unverified · 12c044306a7432d7
  2. VariableState helper · level 0 · unverified · fc567dbf68a97f9c
  3. _mini_batches sampler · level 1 · ran · our draft was wrong · a9fca842e7dce3dc
  4. _sample_mini_dataset sampler · level 1 · ran · our draft was wrong · 8a4d810f710c7156
  5. _split_train_test data_transform · level 1 · ran · our draft was wrong · d91fc29b93983a36
  6. average_vars helper · level 1 · ran · violated contract · 59c0d53cfcbb2398
  7. interpolate_vars helper · level 1 · ran · our draft was wrong · b6a6811d1b4f3cb1
  8. add_vars helper · level 1 · ran · our draft was wrong · 4e38232a76ab2c21
  9. scale_vars helper · level 1 · ran · violated contract · 546a058c2eeefb61
  10. subtract_vars helper · level 1 · ran · our draft was wrong · 3880e32be4fd7c7f

harvested Assembly for Reptile (graph method: Reptile). 10 bricks; individually on a fixture: 8 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; 6 where Syntology's instrument failed) · 2 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. Reptile entry · level 0 · unverified · d215ca39171d7e6a
  2. Variable_ helper · level 1 · ran; the contract check could not run (RAISES) · e2090b8a7ed2f304
  3. average_vars helper · level 1 · ran · our draft was wrong · 634c4ae3d42d183d
  4. clone_model helper · level 1 · ran · our draft was wrong · 5756a43251ee78a0
  5. get_loss loss · level 1 · ran; the contract check could not run (RAISES) · 1aec86f12ed5bdbf
  6. get_optimizer update_rule · level 1 · ran · our draft was wrong · 4119f639d71237d9
  7. interpolate_vars helper · level 1 · ran · our draft was wrong · e1d757cc1d97469e
  8. predict_label metric · level 1 · ran · honoured contract · 1e9509d17fafd962
  9. MiniimagenetModel model · level 1 · ran · 8d746ce18ec482a7
  10. argument_parser helper · level 0 · unverified · e5b4fcff02414010

harvested Assembly for Reptile (graph method: Reptile). 9 bricks; individually on a fixture: 6 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 2 violated, 0 with no contract checked; 4 where Syntology's instrument failed) · 3 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. Reptile entry · level 0 · unverified · 862a81450c933234
  2. VariableState helper · level 0 · unverified · fc567dbf68a97f9c
  3. average_vars helper · level 1 · ran · violated contract · 59c0d53cfcbb2398
  4. interpolate_vars helper · level 1 · ran · our draft was wrong · b6a6811d1b4f3cb1
  5. padCols helper · level 1 · ran; the contract check could not run (RAISES) · 663789fdc8b48fc7
  6. savePlot helper · level 0 · unverified · a2a852379817fd88
  7. add_vars helper · level 1 · ran · our draft was wrong · 4e38232a76ab2c21
  8. scale_vars helper · level 1 · ran · violated contract · 546a058c2eeefb61
  9. subtract_vars helper · level 1 · ran · our draft was wrong · 3880e32be4fd7c7f

harvested Assembly for Reptile (graph method: Reptile). 5 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) · 2 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. train_meta entry · level 0 · unverified · 9ad33249189e3716
  2. inner_loop helper · level 0 · unverified · 649f40959e38546d
  3. get_rays_shapenet helper · level 1 · ran · our draft was wrong · 874a035aef959ab0
  4. sample_points helper · level 1 · ran · our draft was wrong · ee6a21f2e9ccd76e
  5. volume_render helper · level 1 · ran; the contract check could not run (RAISES) · ea9eecfceada7f03

harvested Assembly for Reptile (graph method: Reptile). 3 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) · 2 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. reptile entry · level 0 · unverified · a7a5b0bb081fdc90
  2. perform_k_training_steps update_rule · level 0 · unverified · 7c5446461cabc053
  3. sample_task sampler · level 1 · ran · 38ba8a7c486030e7

harvested Assembly for Reptile (graph method: Reptile). 7 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) · 4 unverified. The assembly has not been run end-to-end.

one of 8 siblings

  1. train_reptile entry · level 0 · unverified · 7ce7bf6a46593388
  2. SineModel helper · level 1 · ran · 4c7e734776a0037f
  3. compute_loss helper · level 0 · unverified · ac866a5f88b92797
  4. copy_model helper · level 1 · ran · our draft was wrong · 5b32ff71531a63f4
  5. np_to_tensor helper · level 1 · ran · our draft was wrong · 6898b2b8e89e013c
  6. train_batch helper · level 0 · unverified · 6ccf8109b819b534
  7. loss_function helper · level 0 · unverified · 97d6ee1a0025a4d4

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

one of 8 siblings

  1. GBML entry · level 0 · unverified · c2a3170df7df4870

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

one of 8 siblings

  1. interpolate_vars entry · level 1 · ran · our draft was wrong · b6a6811d1b4f3cb1
  2. add_vars helper · level 1 · ran · our draft was wrong · 4e38232a76ab2c21
  3. scale_vars helper · level 1 · ran · violated contract · 546a058c2eeefb61
  4. subtract_vars helper · level 1 · ran · our draft was wrong · 3880e32be4fd7c7f

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="1803.02999") returns these assemblies with each brick's role and wiring (how to connect).

Tasks

Few-Shot Image ClassificationFew-Shot LearningMeta-Learning

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Few-Shot Image Classification Mini-Imagenet 10-way (1-shot) Reptile+BN Accuracy 32.0 #11 of 14 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 10-way (1-shot) Reptile Accuracy 31.1 #14 of 14 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 10-way (5-shot) Reptile+BN Accuracy 47.6 #12 of 14 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 10-way (5-shot) Reptile Accuracy 44.7 #14 of 14 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 5-way (1-shot) Reptile + Transduction Accuracy 49.97 #100 of 105 Archive leaderboard report
Few-Shot Image Classification Mini-Imagenet 5-way (5-shot) Reptile + Transduction Accuracy 65.99 #90 of 95 Archive leaderboard report
Few-Shot Image Classification OMNIGLOT - 1-Shot, 20-way Reptile + Transduction Accuracy 89.43% #18 of 20 Archive leaderboard report
Few-Shot Image Classification OMNIGLOT - 1-Shot, 5-way Reptile + Transduction Accuracy 97.68 #17 of 17 Archive leaderboard report
Few-Shot Image Classification OMNIGLOT - 5-Shot, 20-way Reptile + Transduction Accuracy 97.12% #18 of 19 Archive leaderboard report
Few-Shot Image Classification OMNIGLOT - 5-Shot, 5-way Reptile + Transduction Accuracy 99.48 #13 of 16 Archive leaderboard report
Few-Shot Image Classification Tiered ImageNet 10-way (1-shot) Reptile+BN Accuracy 35.3 #10 of 13 Archive leaderboard report
Few-Shot Image Classification Tiered ImageNet 10-way (1-shot) Reptile Accuracy 33.7 #13 of 13 Archive leaderboard report
Few-Shot Image Classification Tiered ImageNet 10-way (5-shot) Reptile+BN Accuracy 52.0 #12 of 13 Archive leaderboard report
Few-Shot Image Classification Tiered ImageNet 10-way (5-shot) Reptile Accuracy 48.0 #13 of 13 Archive leaderboard report
Image Classification Tiered ImageNet 5-way (5-shot) Reptile + BN Accuracy 71.03 #3 of 7 Archive leaderboard report
Image Classification Tiered ImageNet 5-way (5-shot) Reptile Accuracy 66.47 #7 of 7 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

MAML

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