SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1905.13613 · 2019

Regression Networks for Meta-Learning Few-Shot Classification

arXiv · PDF · Open in the Atlas

Code that ran

7 of 11 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; 1 honoured the contract we drafted, 0 violated it and 3 have no contract verdict; 3 failures of our instrument; 4 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/1905.13613.json · badge: /api/ran/1905.13613.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
ArnoutDevos/RegressionNet canonical (classifier label)
classifier basis: census
7 ran · 4 no recorded run
FunctionStatusWhere it lives
DBindex Ran
ran, honoured the contract we drafted
ArnoutDevos/RegressionNet/methods/baselinetrain.py
pointer only (licence: MIT); the stored copy get_code serves, from zoilsen/flor, is pointer only (licence: NONE) · get_code("c43e6e5f82ef6a4c")
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 zoilsen/flor, 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.

euclidean_dist Ran
ran; our contract draft was wrong, not the code
ArnoutDevos/RegressionNet/methods/protonet.py
code served (permissive licence) · get_code("4dd319c45d372246")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Sonnet 4.5, prompt python_fixture_v1) and returned Tensor, ndim 2, dtype family float, shape (2, 3) 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)

# Create two tensors with different numbers of samples but same feature dimension
# x: n samples with d features
# y: m samples with d features
# Using distinct sizes: n=2, m=3, d=4

x = torch.randn(2, 4)  # 2 samples, 4 features
y = torch.randn(3, 4)  # 3 samples, 4 features

ARGS = {
    'x': x,
    'y': y
}
Setup block drafted by
a language model, Claude Sonnet 4.5, prompt python_fixture_v1
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 float, shape (2, 3) — shape (2, 3) 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
euclidean_dist Ran
ran on a synthesized input
ArnoutDevos/RegressionNet/methods/regressionnet.py
code served (permissive licence) · get_code("f384eef54c9d7670")
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 float, shape (2, 3) 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)

# Analyze the function:
# - x: used with x.size(0), x.size(1), x.unsqueeze(1), x.expand(n, m, d)
#   Expected shape: (n, d) where n is batch size, d is dimension
# - y: used with y.size(1), y.size(2), subtracted from x
#   Expected shape: (?, m, d) where m is some dimension, d matches x's dimension
# The function computes euclidean distance between x and y

# Create small tensors with distinct sizes for clarity
# x: shape (2, 4) - batch size 2, dimension 4
x = torch.randn(2, 4)

# y: shape (?, 3, 4) - the function accesses y.size(1) for m and y.size(2) for d
# First dimension doesn't matter for the function logic, set to 1
# m = 3 (distinct from batch size 2)
# d = 4 (must match x's dimension)
y = torch.randn(1, 3, 4)

ARGS = {
    "x": x,
    "y": y,
}
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 float, shape (2, 3) — shape (2, 3) 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
get_assigned_file Ran
ran; our contract draft was wrong, not the code
ArnoutDevos/RegressionNet/io_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from zoilsen/flor, is pointer only (licence: NONE) · get_code("400a8db2fb9b1633")
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 zoilsen/flor, 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.

get_resume_file Ran
ran on a synthesized input
ArnoutDevos/RegressionNet/io_utils.py
code served (permissive licence) · get_code("4bd64c34ba45e089")
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 numpy as np
import os
import tempfile
import shutil

# Create a temporary directory with test checkpoint files
checkpoint_dir = tempfile.mkdtemp()

# Create some .tar files with epoch numbers as names
tar_files = ['1.tar', '5.tar', '10.tar', 'best_model.tar']
for tar_file in tar_files:
    open(os.path.join(checkpoint_dir, tar_file), 'w').close()

ARGS = {
    'checkpoint_dir': checkpoint_dir
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — 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
make_float_label Ran
ran on a synthesized input
ArnoutDevos/RegressionNet/methods/r2d2.py
code served (permissive licence) · get_code("73f677f8fc81903f")
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 float, shape (6, 3) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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
from torch.autograd import Variable

torch.manual_seed(0)

ARGS = {
    "n_way": 3,
    "n_samples": 2,
}
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 float, shape (6, 3) — shape (6, 3) 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
to_variable Ran
ran; our contract draft was wrong, not the code
ArnoutDevos/RegressionNet/methods/r2d2.py
code served (permissive licence) · get_code("989c91edb537cd8f")
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 float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. The code mentions cuda, and the harness aliases cuda to the CPU for every sample; whether this run needed that is 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
from torch.autograd import Variable

torch.manual_seed(0)

# Create a small tensor to pass to to_variable
x = torch.randn(2, 4)

# Define ARGS mapping all parameters of to_variable
ARGS = {
    'x': x
}
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 float, 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
ResNet10 Not yet run
unverified (harvested, no recorded run)
ArnoutDevos/RegressionNet/backbone.py
code served (permissive licence) · get_code("2582452f5ccbebc2")
How it ran

no invocation recorded.

ResNet18 Not yet run
unverified (harvested, no recorded run)
ArnoutDevos/RegressionNet/backbone.py
code served (permissive licence) · get_code("d58f228480b8a193")
How it ran

no invocation recorded.

ResNet34 Not yet run
unverified (harvested, no recorded run)
ArnoutDevos/RegressionNet/backbone.py
code served (permissive licence) · get_code("ff6c4f8a05abb1d3")
How it ran

no invocation recorded.

parse_args Not yet run
unverified (harvested, no recorded run)
ArnoutDevos/RegressionNet/io_utils.py
code served (permissive licence) · get_code("f7e86eb630fa9075")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 distinct functions with an identity, 7 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 7 later) and 4 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
euclidean_dist 16 other papers
2 dated earlier, 14 later · 2 only as an assembly brick
1703.05175 (2017-03)
Prototypical Networks for Few-shot Learning
1902.08605 (2019-02)
Are Few-Shot Learning Benchmarks too Simple ? Solving them without Task Supervision at Test-Time
1912.07200 (2019-12)
A Broader Study of Cross-Domain Few-Shot Learning
and 13 more not named here
ResNet10 4 other papers
4 later
1912.07200 (2019-12)
A Broader Study of Cross-Domain Few-Shot Learning
2010.06498 (2020-10)
Cross-Domain Few-Shot Learning by Representation Fusion
2110.05422 (2021-10)
Calibrate your listeners! Robust communication-based training for pragmatic speakers
and 1 more not named here
get_assigned_file 4 other papers
4 later
1912.07200 (2019-12)
A Broader Study of Cross-Domain Few-Shot Learning
2202.02471 (2022-02)
CLUSTER-INDUCED VORONOI DIAGRAMS: A GEOMETRIC APPROACH
2208.10930 (2022-08)
FS-BAN: Born-Again Networks for Domain Generalization Few-Shot Classification
and 1 more not named here
DBindex 2 other papers
2 later
2208.10930 (2022-08)
FS-BAN: Born-Again Networks for Domain Generalization Few-Shot Classification
2403.00567 (2024-03)
Flatten Long-Range Loss Landscapes for Cross-Domain Few-Shot Learning
ResNet18 2 other papers
2 later
2110.05422 (2021-10)
Calibrate your listeners! Robust communication-based training for pragmatic speakers
2202.02471 (2022-02)
CLUSTER-INDUCED VORONOI DIAGRAMS: A GEOMETRIC APPROACH
to_variable 2 other papers
2 later
1907.10244 (2019-07)
AdaCoF: Adaptive Collaboration of Flows for Video Frame Interpolation
2404.13153 (2024-04)
Motion-adaptive Separable Collaborative Filters for Blind Motion Deblurring
get_resume_file 1 other paper
1 later
1912.07200 (2019-12)
A Broader Study of Cross-Domain Few-Shot Learning

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 regression networks for the problem of few-shot classification, where a classifier must generalize to new classes not seen in the training set, given only a small number of examples of each class. In high dimensional embedding spaces the direction of data generally contains richer information than magnitude. Next to this, state-of-the-art few-shot metric methods that compare distances with aggregated class representations, have shown superior performance. Combining these two insights, we propose to meta-learn classification of embedded points by regressing the closest approximation in every class subspace while using the regression error as a distance metric. Similarly to recent approaches for few-shot learning, regression networks reflect a simple inductive bias that is beneficial in this limited-data regime and they achieve excellent results, especially when more aggregate class representations can be formed with multiple shots.

For agents

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

get_harvested_code_for_paper("1905.13613")
get_code_for_paper("1905.13613")
have("1905.13613")

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

curl https://syntology.ai/api/ran/1905.13613.json

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

[![Syntology run record](https://syntology.ai/api/ran/1905.13613.svg)](https://syntology.ai/paper/1905.13613)

Connect an agent — have() is free.