SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1810.03642 · 2018

Fast Context Adaptation via Meta-Learning

arXiv · PDF · Open in the Atlas

Code that ran

4 of 6 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 1 failure of our instrument; 2 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/1810.03642.json · badge: /api/ran/1810.03642.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
lmzintgraf/cavia canonical (classifier label)
classifier basis: census
4 ran · 2 no recorded run
FunctionStatusWhere it lives
get_path_from_args Ran
ran on a synthesized input
lmzintgraf/cavia/classification/utils.py
code served (permissive licence) · get_code("a39b5e376f92ae7b")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned str. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import hashlib
import copy
import argparse

class MockArgs:
    """Mock argparse Namespace object with required attributes."""
    def __init__(self):
        self.rerun = False
        self.learning_rate = 0.001
        self.batch_size = 32
        self.epochs = 10
        self.model_name = "test_model"

ARGS = {
    "args": MockArgs()
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type str — a str output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a str output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
load_obj Ran
ran; our contract draft was wrong, not the code
lmzintgraf/cavia/classification/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from zhuhai-ustc/limeattack, is pointer only (licence: NONE) · get_code("b91a5961fb87cb5e")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from zhuhai-ustc/limeattack, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

ravel_index Ran
ran on a synthesized input
lmzintgraf/cavia/regression/tasks_celebA.py
code served (permissive licence) · get_code("89fb86181260288b")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned tuple, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import numpy as np

torch.manual_seed(0)

# Analyzing the function:
# - x: a numeric value used in division (x / img_size[1])
# - y: a numeric value used in modulo operation (y % img_size[1])
# - img_size: a tuple/list with at least 2 elements (accessed as img_size[0] and img_size[1])

x = torch.tensor(10.0)
y = torch.tensor(25.0)
img_size = (480, 640)

ARGS = {
    "x": x,
    "y": y,
    "img_size": img_size
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
unravel_index Ran
ran on a synthesized input
lmzintgraf/cavia/regression/tasks_celebA.py
code served (permissive licence) · get_code("258b1b7ff84d66c0")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family int, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Construct arguments for unravel_index(x, y, img_size)
# The function performs: ((x - 1) * img_size[1] + y).long()
# So x and y should be tensors, img_size should be a tuple/list with at least 2 elements

x = torch.tensor([[1, 2, 3, 4], [5, 6, 7, 8]], dtype=torch.float32)
y = torch.tensor([[10, 20, 30, 40], [50, 60, 70, 80]], dtype=torch.float32)
img_size = (5, 3)  # (height, width) - img_size[1] is the width

ARGS = {
    "x": x,
    "y": y,
    "img_size": img_size
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family int, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
eval Not yet run
unverified (harvested, no recorded run)
lmzintgraf/cavia/regression/maml.py
code served (permissive licence) · get_code("b7c25efc0fb87bb0")
How it ran

no invocation recorded.

eval_cavia Not yet run
unverified (harvested, no recorded run)
lmzintgraf/cavia/regression/cavia.py
code served (permissive licence) · get_code("1a684062cd8f4961")
How it ran

no invocation recorded.

Also present in other papers' code

Of 6 samples lifted from this paper's linked repositories, 6 carry a function identity and 0 do not. Of the 6 distinct functions with an identity, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 1 later) and 5 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
load_obj 6 other papers
1 dated earlier, 5 later
1608.02214 (2016-08)
Robsut Wrod Reocginiton via semi-Character Recurrent Neural Network
1902.11020 (2019-02)
DPOD: 6D Pose Object Detector and Refiner
2005.12210 (2020-05)
How Useful are Reviews for Recommendation? A Critical Review and Potential Improvements
and 3 more not named here

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

We propose CAVIA for meta-learning, a simple extension to MAML that is less prone to meta-overfitting, easier to parallelise, and more interpretable. CAVIA partitions the model parameters into two parts: context parameters that serve as additional input to the model and are adapted on individual tasks, and shared parameters that are meta-trained and shared across tasks. At test time, only the context parameters are updated, leading to a low-dimensional task representation. We show empirically that CAVIA outperforms MAML for regression, classification, and reinforcement learning. Our experiments also highlight weaknesses in current benchmarks, in that the amount of adaptation needed in some cases is small.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("1810.03642")
get_code_for_paper("1810.03642")
have("1810.03642")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/1810.03642.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/1810.03642.svg)](https://syntology.ai/paper/1810.03642)

Connect an agent — have() is free.