SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.03824 · 2026

Quantifying Avian Morphological Evolution through Deep Representation Learning

Jiao Sun

arXiv · PDF · Open in the Atlas

Code that ran

5 of 12 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 0 have no contract verdict; 5 failures of our instrument; 7 no recorded run), measured 2026-11-22; 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/2602.03824.json · badge: /api/ran/2602.03824.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
sun-jiao/MetaFGNet canonical (classifier label)
classifier basis: census
5 ran · 6 no recorded run
sun-jiao/osea_morpho_evo community
Papers with Code archive
0 ran · 1 no recorded run
FunctionStatusWhere it lives
accuracy Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
sun-jiao/MetaFGNet/L_Bird_pretrain/trainer.py
code served (permissive licence) · get_code("4740868385958c9a")
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 list, ndim 2, 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

torch.manual_seed(0)

# Tiny batch size of 2, with 4 classes (logits dimension)
batch_size = 2
num_classes = 4

# Create output logits: shape (batch_size, num_classes) = (2, 4)
output = torch.randn(batch_size, num_classes)

# Create target labels: shape (batch_size,) = (2,)
# Labels should be in range [0, num_classes)
target = torch.tensor([1, 3])

# topk parameter - tuple of k values to compute accuracy for
topk = (1, 2)

ARGS = {
    "output": output,
    "target": target,
    "topk": topk,
}
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 list, ndim 2, dtype family float — a list 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
conv3x3 Ran
ran; our contract draft was wrong, not the code
sun-jiao/MetaFGNet/MetaFGNet_with_Sample_Selection/models/resnet.py
pointer only (licence: MIT); the stored copy get_code serves, from lixiaotong97/DSU, is pointer only (licence: NONE) · get_code("fac5364e2f53c6db")
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 lixiaotong97/DSU, 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.

meta_train_lr_update Ran
ran; our contract draft was wrong, not the code
sun-jiao/MetaFGNet/MetaFGNet_with_Sample_Selection/trainer.py
code served (permissive licence) · get_code("011c409643dde419")
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 list, ndim 2, 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 torch.nn as nn

torch.manual_seed(0)

# Create a small args config object
class Args:
    def __init__(self):
        self.schedule = [10, 20, 30, 40, 50]  # epoch thresholds for learning rate decay
        self.meta_train_lr = 0.001  # base meta learning rate
        self.gamma = 0.1  # decay factor

args = Args()

# Create meta_train_lr as a list of learnable learning rates
meta_train_lr = [0.01, 0.01, 0.01]

# Create grads_for_task_train as a list of batches, where each batch contains gradients
# The function uses grads_for_task_train[-1], so we need at least one batch
grads_for_task_train = [
    [torch.tensor([0.1, 0.2, 0.3]), torch.tensor([0.15, 0.25, 0.35]), torch.tensor([0.05, 0.1, 0.15])]
]

# Create grad_of_meta_test as a list of gradient tensors (one per learning rate)
grad_of_meta_test = [
    torch.tensor([0.05, 0.06, 0.07]),
    torch.tensor([0.04, 0.08, 0.09]),
    torch.tensor([0.03, 0.02, 0.01])
]

# Epoch number
epoch = 5

ARGS = {
    "args": args,
    "meta_train_lr": meta_train_lr,
    "grads_for_task_train": grads_for_task_train,
    "grad_of_meta_test": grad_of_meta_test,
    "epoch": epoch
}
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 list, ndim 2, dtype family float — a list 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
resnet18 Ran
ran; our contract draft was wrong, not the code
sun-jiao/MetaFGNet/MetaFGNet_with_Sample_Selection/models/resnet.py
code served (permissive licence) · get_code("6dab2ac606867db8")
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 torch.nn as nn
from unittest.mock import MagicMock

torch.manual_seed(0)

class Args:
    def __init__(self):
        self.pretrained = False
        self.num_classes_t = 10
        self.num_classes_s = 5
        self.auxiliary_dataset = 'custom'

ARGS = {
    'args': Args()
}
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 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
validate Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
sun-jiao/MetaFGNet/L_Bird_pretrain/trainer.py
code served (permissive licence) · get_code("45a5449799a76b66")
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 0, dtype family float, shape () 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
import torch.nn as nn
import os
import tempfile

torch.manual_seed(0)

# Create a minimal model
class SimpleModel(nn.Module):
    def __init__(self):
        super(SimpleModel, self).__init__()
        self.fc = nn.Linear(4, 10)
    
    def forward(self, x):
        return self.fc(x)

# Create a minimal criterion
criterion = nn.CrossEntropyLoss()

# Create a minimal val_loader with 2 batches of (input, target)
val_loader = [
    (torch.randn(2, 4), torch.tensor([0, 1])),
    (torch.randn(2, 4), torch.tensor([2, 3]))
]

# Create a minimal args object
class Args:
    def __init__(self):
        self.print_freq = 1
        self.log = tempfile.gettempdir()

args = Args()

# Instantiate model
model = SimpleModel()

epoch = 1

ARGS = {
    'val_loader': val_loader,
    'model': model,
    'criterion': criterion,
    'epoch': epoch,
    'args': args
}
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 0, dtype family float, shape () — shape () 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
accuracy Not yet run
unverified (harvested, no recorded run)
sun-jiao/MetaFGNet/Fine_tune_for_final_results/trainer.py
pointer only (licence: MIT); the stored copy get_code serves, from kkonstantinidis/ByzShield, is pointer only (licence: NONE) · get_code("4d3faaaa1c706b0b")
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 kkonstantinidis/ByzShield, 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. No invocation recorded.

compute_second_order_grad Not yet run
unverified (harvested, no recorded run)
sun-jiao/MetaFGNet/MetaFGNet_with_Sample_Selection/trainer.py
code served (permissive licence) · get_code("142f598a1f3d6f96")
How it ran

no invocation recorded.

reconstruct_ancestral_states Not yet run
unverified (harvested, no recorded run)
sun-jiao/osea_morpho_evo/src/disparity_through_time.py
pointer only (licence: NONE) · get_code("4f8882056692155d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, sun-jiao/osea_morpho_evo 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. No invocation recorded.

resnet34 Not yet run
unverified (harvested, no recorded run)
sun-jiao/MetaFGNet/MetaFGNet_with_Sample_Selection/models/resnet.py
code served (permissive licence) · get_code("0b2e2b5913407728")
How it ran

no invocation recorded.

train Not yet run
unverified (harvested, no recorded run)
sun-jiao/MetaFGNet/MetaFGNet_with_Sample_Selection/trainer.py
code served (permissive licence) · get_code("98d6f3bacdbea87a")
How it ran

no invocation recorded.

train Not yet run
unverified (harvested, no recorded run)
sun-jiao/MetaFGNet/MetaFGNet_without_Sample_Selection/trainer.py
code served (permissive licence) · get_code("3236c67cd90174fa")
How it ran

no invocation recorded.

validate Not yet run
unverified (harvested, no recorded run)
sun-jiao/MetaFGNet/Fine_tune_for_final_results/trainer.py
code served (permissive licence) · get_code("2d5685265ba77d35")
How it ran

no invocation recorded.

Also present in other papers' code

Of 12 samples lifted from this paper's linked repositories, 12 carry a function identity and 0 do not. Of the 12 distinct functions with an identity, 5 are also present in other papers whose code we hold (5 with at least one paper dated earlier, 1 the same month, 1 later) and 7 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
conv3x3 686 other papers
674 dated earlier, 2 the same month, 10 later · 31 only as an assembly brick
1406.2661 (2014-06)
Generative Adversarial Networks
1409.0575 (2014-09)
ImageNet Large Scale Visual Recognition Challenge
1412.6572 (2014-12)
Explaining and Harnessing Adversarial Examples
and 683 more not named here
accuracy 23 other papers
23 dated earlier
1603.07285 (2016-03)
A guide to convolution arithmetic for deep learning
1608.07017 (2016-08)
Ambient Sound Provides Supervision for Visual Learning
1608.08710 (2016-08)
Pruning Filters for Efficient ConvNets
and 20 more not named here
accuracy 2 other papers
2 dated earlier
Wang_Practical_Network_Acceleration_With_Tiny_Sets_CVPR_2023_paper (2023 (year only))
Practical Network Acceleration with Tiny Sets
2308.07163 (2023-08)
HyperSparse Neural Networks: Shifting Exploration to Exploitation through Adaptive Regularization
resnet18 1 other paper
1 dated earlier
1807.10916 (2018-07)
Fine-Grained Visual Categorization using Meta-Learning Optimization with Sample Selection of Auxiliary Data
resnet34 1 other paper
1 dated earlier
1807.10916 (2018-07)
Fine-Grained Visual Categorization using Meta-Learning Optimization with Sample Selection of Auxiliary Data

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

The evolution of biological morphology is fundamentally linked to ecological adaptation and species survival, yet traditional morphological evolution relies on landmark-based geometric morphometrics, a process constrained by subjective manual annotation, strict requirements for anatomical homology, and an inability to easily quantify complex, nonrigid traits such as plumage and texture. To overcome these limitations, we propose a scalable, landmark-free morphometric framework driven by deep learning. By extracting high-dimensional feature vectors from a Convolutional Neural Network (ResNet34) trained on images of over 10,000 bird species, we project raw visual semantics into a highdimensional morphospace. Even without a priori taxonomic knowledge, this visual morphospace naturally recovers classical hierarchical taxonomy and effectively captures both homology and convergence. Analyses reveal a highly significant phylogenetic signal within the network's embeddings, with principal components correlating strongly with established ecological and morphological traits. Furthermore, by implementing a novel spherical Ancestral State Reconstruction algorithm, we uncover a pronounced "early-burst" pattern of disparity following the K-Pg mass extinction, supporting the niche-filling hypothesis of adaptive radiation.

For agents

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

get_harvested_code_for_paper("2602.03824")
get_code_for_paper("2602.03824")
have("2602.03824")

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

curl https://syntology.ai/api/ran/2602.03824.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.03824.svg)](https://syntology.ai/paper/2602.03824)

Connect an agent — have() is free.