SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2008.11790 · 2020

MutaGAN: A Seq2seq GAN Framework to Predict Mutations of Evolving Protein Populations

arXiv · PDF · Open in the Atlas

Code that ran

14 of 18 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, 1 violated it and 13 have no contract verdict; 0 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/2008.11790.json · badge: /api/ran/2008.11790.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
anuprulez/clade_prediction community (classifier label)
classifier basis not recorded on the link
12 ran · 4 no recorded run
1hachem/mutaGAN community (classifier label)
classifier basis not recorded on the link
2 ran · 0 no recorded run
FunctionStatusWhere it lives
call Ran
ran on a synthesized input
anuprulez/clade_prediction/encoder_decoder_attention.py
code served (permissive licence) · get_code("a179307e89c155b9")
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. 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 tensorflow as tf
import typing
from typing import Any, Tuple

ENC_DROPOUT = 0.7

class DecoderInput(typing.NamedTuple):
    new_tokens: Any
    enc_output: Any
    mask: Any

class DecoderOutput(typing.NamedTuple):
    logits: Any
    attention_weights: Any

class MockDecoder(tf.keras.Model):
    def __init__(self):
        super().__init__()
        self.embedding = tf.keras.layers.Embedding(input_dim=100, output_dim=4)
        self.gru = tf.keras.layers.Bidirectional(
            tf.keras.layers.GRU(units=3, return_sequences=True, return_state=True)
        )
        self.fc = tf.keras.layers.Dense(units=10)
    
    def call(self, inputs: DecoderInput, state=None, training=True) -> Tuple[DecoderOutput, tf.Tensor]:
        vectors = self.embedding(inputs.new_tokens)
        vectors = tf.keras.layers.Dropout(ENC_DROPOUT)(vectors, training=training)
        rnn_output, state_f, state_b = self.gru(vectors, initial_state=state, training=training)
        rnn_output = tf.keras.layers.Dropout(ENC_DROPOUT)(rnn_output, training=training)
        attention_weights = []
        logits = self.fc(rnn_output)
        return (DecoderOutput(logits, attention_weights), state_f, state_b)

decoder = MockDecoder()

new_tokens = tf.constant([[1, 2, 3], [4, 5, 6]], dtype=tf.int32)
enc_output = tf.random.normal([2, 3, 4])
mask = tf.ones([2, 3])

decoder_input = DecoderInput(
    new_tokens=new_tokens,
    enc_output=enc_output,
    mask=mask
)

ARGS = {
    "self": decoder,
    "inputs": decoder_input,
    "state": None,
    "training": True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is 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
combine_mutation Ran
ran on a synthesized input
anuprulez/clade_prediction/fetch_clades_mutations.py
code served (permissive licence) · get_code("9b7e2102240fb4e1")
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)

# Based on the function signature and implementation:
# combine_mutation(ch_ref, ch_pos, ch_alt)
# The function takes three parameters and formats them into a string
# ch_ref: reference character/allele (string)
# ch_pos: position (can be int or string)
# ch_alt: alternate character/allele (string)

ARGS = {
    'ch_ref': 'A',
    'ch_pos': 12345,
    'ch_alt': 'G'
}
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
compare_mutations Ran
ran on a synthesized input
anuprulez/clade_prediction/comparison_with_wuhan.py
code served (permissive licence) · get_code("81574ebc24b4093d")
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

# Analyzing the function:
# - parent: iterable of strings, each string is comma-separated integers
# - child: iterable of strings (or sequences), iterable of elements to compare
# - f_dict: dict mapping string representations of integers to characters
# - min_pos: integer for slicing start
# - max_pos: integer for slicing end

# Build small test data
parent = [
    "1,2,3,4,5",
    "2,3,4,5,6"
]

child = [
    [1, 3, 5, 7],
    [2, 4, 6, 8]
]

# f_dict maps string integer keys to single character values
# Some values should be 'X' to test the filtering logic
f_dict = {
    '1': 'A',
    '2': 'B',
    '3': 'C',
    '4': 'D',
    '5': 'E',
    '6': 'F',
    '7': 'X',
    '8': 'G'
}

min_pos = 1
max_pos = 4

ARGS = {
    'parent': parent,
    'child': child,
    'f_dict': f_dict,
    'min_pos': min_pos,
    'max_pos': max_pos
}
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
create_pf_model Ran
ran on a synthesized input
anuprulez/clade_prediction/neural_network.py
code served (permissive licence) · get_code("71684890ef30c730")
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 Functional. 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 tensorflow as tf

# Define arguments for create_pf_model
ARGS = {
    'seq_len': 10,
    'vocab_size': 100,
    'embedding_dim': 8,
    'enc_units': 16,
    'batch_size': 2
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Functional — a Functional output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a Functional 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
discriminator_loss Ran
ran on a synthesized input
anuprulez/clade_prediction/train_model.py
code served (permissive licence) · get_code("ded44dd1ac77a10e")
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 tensorflow as tf
import numpy as np

cross_entropy = tf.keras.losses.BinaryCrossentropy(from_logits=False)

def discriminator_loss(real_output, fake_output):
    real_loss = cross_entropy(tf.ones_like(real_output), real_output)
    fake_loss = cross_entropy(tf.zeros_like(fake_output), fake_output)
    return (real_loss, fake_loss)

# Create small batch of real and fake discriminator outputs
# Batch size: 2, output dim: 4
# Outputs are probabilities (0-1 range) since from_logits=False
real_output = tf.constant([[0.9, 0.85, 0.95, 0.88], [0.92, 0.87, 0.91, 0.89]], dtype=tf.float32)
fake_output = tf.constant([[0.1, 0.15, 0.12, 0.18], [0.08, 0.14, 0.11, 0.16]], dtype=tf.float32)

ARGS = {
    "real_output": real_output,
    "fake_output": fake_output,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — 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
generator_loss Ran
ran, violated the contract we drafted
anuprulez/clade_prediction/train_model.py
code served (permissive licence) · get_code("694eab49f2d16df0")
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 EagerTensor, ndim 0, dtype family float, shape () 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 tensorflow as tf
import numpy as np

# Set random seed for reproducibility
tf.random.set_seed(0)

# Create a small fake_output tensor
# The function uses tf.ones_like(fake_output) and passes it through cross_entropy
# cross_entropy expects logits or probabilities, so we need a tensor with shape (batch, ...)
# Let's create a batch of 2 samples with 4 values each
fake_output = tf.constant(
    [[0.1, 0.2, 0.3, 0.4],
     [0.5, 0.6, 0.7, 0.8]],
    dtype=tf.float32
)

ARGS = {
    "fake_output": fake_output
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, 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
get_POS Ran
ran on a synthesized input
anuprulez/clade_prediction/common_mut_tr_gen.py
code served (permissive licence) · get_code("e467f7788d72a508")
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 1, dtype family int; 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)

# Analyze the function:
# - get_POS takes mut_dict as parameter
# - It extracts keys from mut_dict
# - For each key, it splits by '>' and takes the second part (index [1])
# - Converts to int, collects unique values, and returns sorted list

# The mut_dict keys should be strings with format "something>number"
# where "number" is an integer that can be extracted

mut_dict = {
    "A>5": "value1",
    "B>3": "value2",
    "C>5": "value3",
    "D>1": "value4",
    "E>3": "value5",
}

ARGS = {
    "mut_dict": mut_dict,
}
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 list, ndim 1, dtype family int — 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
get_frac_seq_mat Ran
ran on a synthesized input
anuprulez/clade_prediction/create_plots.py
code served (permissive licence) · get_code("d9835f90f03c1b68")
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 ndarray, ndim 2, dtype family int, shape (3, 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 numpy as np

ARGS = {
    "list_seq": [
        "10,20,30,40,50",
        "11,21,31,41,51",
        "12,22,32,42,52"
    ],
    "min_pos": 1,
    "max_pos": 4
}
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 ndarray, ndim 2, dtype family int, shape (3, 3) — shape (3, 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_item Ran
ran on a synthesized input
anuprulez/clade_prediction/fetch_clades_mutations.py
code served (permissive licence) · get_code("d07b5ad7e24e5427")
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

def get_item(item):
    ref_pos_alt = [char for char in item]
    ref = ref_pos_alt[0]
    alt = ref_pos_alt[-1]
    pos = int(''.join(ref_pos_alt[1:len(ref_pos_alt) - 1]))
    return (ref, alt, pos)

ARGS = {
    "item": "A123T"
}
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
get_path_all_gen_files Ran
ran on a synthesized input
anuprulez/clade_prediction/analyse_generated_seqs.py
code served (permissive licence) · get_code("8e9ecf5dfc8df936")
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 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 glob
import tempfile
import os

# Create a temporary directory structure to mimic the expected path
temp_dir = tempfile.mkdtemp()
test_results_dir = os.path.join(temp_dir, 'test_results', '18_02_22_0', 'model_generated_sequences')
os.makedirs(test_results_dir, exist_ok=True)

# Create some dummy CSV files
for i in range(3):
    csv_file = os.path.join(test_results_dir, f'generated_{i}.csv')
    with open(csv_file, 'w') as f:
        f.write('dummy,data\n')

# Set the data_path to point to our temp directory
data_path = os.path.join(temp_dir, 'test_results', '18_02_22_0', '')

ARGS = {
    'path': os.path.join(data_path, 'model_generated_sequences')
}
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 list, ndim 1, 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
get_vocab Ran
ran on a synthesized input
1hachem/mutaGAN/src/encode.py
code served (permissive licence) · get_code("2af3d0d3b56301ba")
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 numpy as np
from typing import List

# Create a simple stand-in class for sequence records
class SequenceRecord:
    def __init__(self, seq):
        self.seq = seq

# Create sample sequences with various characters from the vocabulary
sequences = [
    SequenceRecord("VIGD"),
    SequenceRecord("CSBZ"),
    SequenceRecord("NFAMEJPQK"),
]

ARGS = {
    "sequences": sequences
}
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 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
read_json Ran
ran on a synthesized input
1hachem/mutaGAN/utils/utils.py
code served (permissive licence) · get_code("dc880616a10bffc7")
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 json
import tempfile
import os

# Create a temporary JSON file with test data
temp_dir = tempfile.mkdtemp()
test_file = os.path.join(temp_dir, "test.json")

test_data = {
    "key1": "value1",
    "key2": [1, 2, 3],
    "key3": {"nested": "object"}
}

with open(test_file, 'w') as f:
    json.dump(test_data, f)

ARGS = {
    "file": test_file
}
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 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
read_json Ran
ran on a synthesized input
anuprulez/clade_prediction/comparison_with_wuhan.py
code served (permissive licence) · get_code("b2ab6cedad111e4d")
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 json
import tempfile
import os

# Create a temporary JSON file with valid content
temp_file = tempfile.NamedTemporaryFile(mode='w', suffix='.json', delete=False)
json_data = {"key": "value", "number": 42, "array": [1, 2, 3]}
json.dump(json_data, temp_file)
temp_file.close()

ARGS = {
    "file_path": temp_file.name
}
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 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
wasserstein_loss Ran
ran on a synthesized input
anuprulez/clade_prediction/train_model.py
code served (permissive licence) · get_code("0dea6a4fd298ee87")
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 EagerTensor, ndim 0, dtype family float, shape () 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 tensorflow as tf
import numpy as np

# Set seed for reproducibility
np.random.seed(0)
tf.random.set_seed(0)

# Create small valid tensors for wasserstein_loss
# y_true and y_pred should have the same shape
# The function multiplies them element-wise and reduces to a mean
batch_size = 2
dim = 4

y_true = tf.constant(np.random.randn(batch_size, dim).astype(np.float32))
y_pred = tf.constant(np.random.randn(batch_size, dim).astype(np.float32))

ARGS = {
    "y_true": y_true,
    "y_pred": y_pred,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, 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
make_disc_par_gen_model Not yet run
unverified (harvested, no recorded run)
anuprulez/clade_prediction/neural_network.py
code served (permissive licence) · get_code("a89a1950be074cac")
How it ran

no invocation recorded.

make_generator_model Not yet run
unverified (harvested, no recorded run)
anuprulez/clade_prediction/neural_network.py
code served (permissive licence) · get_code("df9c791b35996ec0")
How it ran

no invocation recorded.

read_wuhan_hu_1_spike Not yet run
unverified (harvested, no recorded run)
anuprulez/clade_prediction/comparison_with_wuhan.py
code served (permissive licence) · get_code("2eff351d33712372")
How it ran

no invocation recorded.

recursive_branch Not yet run
unverified (harvested, no recorded run)
anuprulez/clade_prediction/fetch_clades_mutations.py
code served (permissive licence) · get_code("b5bcb33681468538")
How it ran

no invocation recorded.

Also present in other papers' code

Of 18 samples lifted from this paper's linked repositories, 18 carry a function identity and 0 do not. Of the 18 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, 0 later) and 17 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
generator_loss 1 other paper
1 dated earlier
1610.00768 (2016-10)
Technical Report on the CleverHans v2.1.0 Adversarial Examples Library

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 ability to predict the evolution of a pathogen would significantly improve the ability to control, prevent, and treat disease. Despite significant progress in other problem spaces, deep learning has yet to contribute to the issue of predicting mutations of evolving populations. To address this gap, we developed a novel machine learning framework using generative adversarial networks (GANs) with recurrent neural networks (RNNs) to accurately predict genetic mutations and evolution of future biological populations. Using a generalized time-reversible phylogenetic model of protein evolution with bootstrapped maximum likelihood tree estimation, we trained a sequence-to-sequence generator within an adversarial framework, named MutaGAN, to generate complete protein sequences augmented with possible mutations of future virus populations. Influenza virus sequences were identified as an ideal test case for this deep learning framework because it is a significant human pathogen with new strains emerging annually and global surveillance efforts have generated a large amount of publicly available data from the National Center for Biotechnology Information's (NCBI) Influenza Virus Resource (IVR). MutaGAN generated "child" sequences from a given "parent" protein sequence with a median Levenshtein distance of 2.00 amino acids. Additionally, the generator was able to augment the majority of parent proteins with at least one mutation identified within the global influenza virus population. These results demonstrate the power of the MutaGAN framework to aid in pathogen forecasting with implications for broad utility in evolutionary prediction for any protein population.

For agents

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

get_harvested_code_for_paper("2008.11790")
get_code_for_paper("2008.11790")
have("2008.11790")

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

curl https://syntology.ai/api/ran/2008.11790.json

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

[![Syntology run record](https://syntology.ai/api/ran/2008.11790.svg)](https://syntology.ai/paper/2008.11790)

Connect an agent — have() is free.