SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1902.08605 · 2019

Are Few-Shot Learning Benchmarks too Simple ? Solving them without Task Supervision at Test-Time

arXiv · PDF · Open in the Atlas

Code that ran

11 of 13 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 6 have no contract verdict; 5 failures 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/1902.08605.json · badge: /api/ran/1902.08605.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
gabrielhuang/centroid-networks community (classifier label)
classifier basis not recorded on the link
11 ran · 2 no recorded run
FunctionStatusWhere it lives
VGG11 Ran
ran on a synthesized input
gabrielhuang/centroid-networks/protonets/models/vgg.py
code served (permissive licence) · get_code("14e45238d8020ce8")
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 VGG. 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 torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    'out_dim': 10
}
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 VGG — a VGG output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a VGG 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
VGG8 Ran
ran on a synthesized input
gabrielhuang/centroid-networks/protonets/models/vgg.py
code served (permissive licence) · get_code("a9532ca039537e98")
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 VGG. 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 torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    'out_dim': 10
}
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 VGG — a VGG output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a VGG 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
VGGS Ran
ran on a synthesized input
gabrielhuang/centroid-networks/protonets/models/vgg.py
code served (permissive licence) · get_code("3d2f9346138279fe")
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 VGG. 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 torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    'out_dim': 10
}
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 VGG — a VGG output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a VGG 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
convert_array Ran
ran; our contract draft was wrong, not the code
gabrielhuang/centroid-networks/protonets/utils/log.py
code served (permissive licence) · get_code("4601716ebff8a67b")
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 dict. 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

# Analyze the function:
# - It takes a parameter 'd' which should be a dict
# - It iterates over d.items()
# - For each value v, it checks if v is a dict
# - If v is a dict, it converts each nested value vv to np.array
# - If v is not a dict, it converts v directly to np.array

# Create test data with both nested dicts and simple values
d = {
    "simple_list": [1, 2, 3, 4],
    "simple_value": 42,
    "nested_dict": {
        "inner_list": [1.0, 2.0, 3.0],
        "inner_value": 5
    },
    "another_nested": {
        "data1": [7, 8, 9],
        "data2": [10, 11, 12, 13]
    }
}

ARGS = {
    "d": d
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
euclidean_dist Ran
ran; our contract draft was wrong, not the code
gabrielhuang/centroid-networks/protonets/models/utils.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
evaluate Ran
ran on a synthesized input
gabrielhuang/centroid-networks/protonets/utils/model.py
code served (permissive licence) · get_code("22d34c26400fab75")
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 dict. 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 torch
import torch.nn as nn
from collections import defaultdict

torch.manual_seed(0)

# Define a simple meter class that tracks metrics
class SimpleMeter:
    def __init__(self):
        self.value = 0
    
    def reset(self):
        self.value = 0
    
    def add(self, val):
        if isinstance(val, torch.Tensor):
            self.value += val.item()
        else:
            self.value += val

# Define a minimal model with eval_loss method
class SimpleModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def eval_loss(self, sample):
        # Returns tuple of (loss, output_dict)
        # sample is a dict or batch object
        batch_size = 2
        dummy_loss = torch.tensor(0.5)
        output = {
            'metric1': 0.25,
            'metric2': 0.75,
        }
        return dummy_loss, output

# Create model
model = SimpleModel()

# Create data loader - list of sample dicts
data_loader = [
    {'input': torch.randn(2, 4)},
    {'input': torch.randn(2, 4)},
]

# Create meters dict
meters = {
    'metric1': SimpleMeter(),
    'metric2': SimpleMeter(),
}

ARGS = {
    'model': model,
    'data_loader': data_loader,
    'meters': meters,
    'desc': 'Evaluating',
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, tqdm — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
extract_meter_values Ran
ran; our contract draft was wrong, not the code
gabrielhuang/centroid-networks/protonets/utils/log.py
code served (permissive licence) · get_code("edcb0cddd78cf783")
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 dict. 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 torch
import torch.nn as nn


class MockMeter:
    """A simple meter that stores a value and returns it via value() method."""
    def __init__(self, val):
        self._val = val
    
    def value(self):
        return [self._val, "other_data"]


# Construct the meters dict with nested structure:
# meters[split_name][field_name] = meter_object
meters = {
    "train": {
        "loss": MockMeter(0.5),
        "accuracy": MockMeter(0.92),
    },
    "val": {
        "loss": MockMeter(0.3),
        "accuracy": MockMeter(0.95),
    },
    "test": {
        "loss": MockMeter(0.25),
    }
}

ARGS = {
    "meters": meters
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
log_sum_exp Ran
ran on a synthesized input
gabrielhuang/centroid-networks/protonets/models/wasserstein.py
code served (permissive licence) · get_code("62fa5972227f4654")
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)

# Create a small tensor with shape (2, 4, 3)
# Using distinct dimensions so they're unambiguous
u = torch.randn(2, 4, 3)

# dim parameter - reduce along dimension 1
dim = 1

ARGS = {
    "u": u,
    "dim": dim
}
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
naive_log_sum_exp Ran
ran on a synthesized input
gabrielhuang/centroid-networks/protonets/models/wasserstein.py
code served (permissive licence) · get_code("a79567140b527143")
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 1, dtype family float, shape (2,) 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 a small tensor for testing
# naive_log_sum_exp computes log(sum(exp(u))) along a dimension
# This is commonly used in log-sum-exp trick for numerical stability
u = torch.randn(2, 4)
dim = 1

ARGS = {
    "u": u,
    "dim": dim,
}
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 1, dtype family float, shape (2,) — shape (2,) 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
register_model Ran
ran; our contract draft was wrong, not the code
gabrielhuang/centroid-networks/protonets/models/factory.py
code served (permissive licence) · get_code("896ba48590068c68")
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 function. 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 torch
import torch.nn as nn

torch.manual_seed(0)

# The register_model function takes a single parameter: model_name (a string)
# It returns a decorator that registers a function in MODEL_REGISTRY
# The function body simply stores the function and returns it

model_name = "test_model"

ARGS = {
    "model_name": model_name
}
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 function — a function output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a function 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
render_meter_values Ran
ran; our contract draft was wrong, not the code
gabrielhuang/centroid-networks/protonets/utils/log.py
code served (permissive licence) · get_code("c0d75b572348ad84")
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 torch
import numpy as np

torch.manual_seed(0)

# Analyzing the function:
# - render_meter_values takes meter_values parameter
# - meter_values is a dict with keys representing splits
# - Each split maps to another dict with field names and numeric values
# - The function iterates through splits and fields, formatting each as a string
# - Values are formatted as floats with 6 decimal places

meter_values = {
    'train': {
        'loss': 0.456789,
        'accuracy': 0.987654,
        'f1_score': 0.876543
    },
    'val': {
        'loss': 0.567890,
        'accuracy': 0.965432,
        'f1_score': 0.854321
    }
}

ARGS = {
    'meter_values': meter_values
}
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 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
compute_sinkhorn Not yet run
unverified (harvested, no recorded run)
gabrielhuang/centroid-networks/protonets/models/wasserstein.py
code served (permissive licence) · get_code("1bda15d812c37228")
How it ran

no invocation recorded.

get_model Not yet run
unverified (harvested, no recorded run)
gabrielhuang/centroid-networks/protonets/models/factory.py
code served (permissive licence) · get_code("ab239f4a02eaeab3")
How it ran

no invocation recorded.

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 distinct functions with an identity, 9 are also present in other papers whose code we hold (4 with at least one paper dated earlier, 0 the same month, 6 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
1 dated earlier, 15 later · 2 only as an assembly brick
1703.05175 (2017-03)
Prototypical Networks for Few-shot Learning
1905.13613 (2019-05)
Regression Networks for Meta-Learning Few-Shot Classification
1912.07200 (2019-12)
A Broader Study of Cross-Domain Few-Shot Learning
and 13 more not named here
VGG11 1 other paper
1 dated earlier
1901.00544 (2019-01)
Multi-class Classification without Multi-class Labels
VGG8 1 other paper
1 dated earlier
1901.00544 (2019-01)
Multi-class Classification without Multi-class Labels
VGGS 1 other paper
1 dated earlier
1901.00544 (2019-01)
Multi-class Classification without Multi-class Labels
convert_array 1 other paper
1 later
2310.00451 (2023-10)
On the Role of Neural Collapse in Meta Learning Models for Few-shot Learning
extract_meter_values 1 other paper
1 later
2310.00451 (2023-10)
On the Role of Neural Collapse in Meta Learning Models for Few-shot Learning
get_model 1 other paper
1 later
2310.00451 (2023-10)
On the Role of Neural Collapse in Meta Learning Models for Few-shot Learning
register_model 1 other paper
1 later
2310.00451 (2023-10)
On the Role of Neural Collapse in Meta Learning Models for Few-shot Learning
render_meter_values 1 other paper
1 later
2310.00451 (2023-10)
On the Role of Neural Collapse in Meta Learning Models for 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 show that several popular few-shot learning benchmarks can be solved with varying degrees of success without using support set Labels at Test-time (LT). To this end, we introduce a new baseline called Centroid Networks, a modification of Prototypical Networks in which the support set labels are hidden from the method at test-time and have to be recovered through clustering. A benchmark that can be solved perfectly without LT does not require proper task adaptation and is therefore inadequate for evaluating few-shot methods. In practice, most benchmarks cannot be solved perfectly without LT, but running our baseline on any new combinations of architectures and datasets gives insights on the baseline performance to be expected from leveraging a good representation, before any adaptation to the test-time labels.

For agents

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

get_harvested_code_for_paper("1902.08605")
get_code_for_paper("1902.08605")
have("1902.08605")

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

curl https://syntology.ai/api/ran/1902.08605.json

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

[![Syntology run record](https://syntology.ai/api/ran/1902.08605.svg)](https://syntology.ai/paper/1902.08605)

Connect an agent — have() is free.