SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2603.14161 · 2026

Deep probabilistic model synthesis enables unified modeling of whole-brain neural activity across individual subjects

Misha Ahrens, William Bishop, James Fitzgerald, Luuk Hesselink, Bernhard Englitz

arXiv · PDF · Open in the Atlas

Code that ran

12 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; 1 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 10 failures of our instrument; 1 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/2603.14161.json · badge: /api/ran/2603.14161.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
neuro-will/probabilistic_model_synthesis canonical (classifier label)
classifier basis: census
12 ran · 1 no recorded run
FunctionStatusWhere it lives
align_intermediate_spaces Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
neuro-will/probabilistic_model_synthesis/probabilistic_model_synthesis/gaussian_nonlinear_dim_reduction.py
code served (permissive licence) · get_code("21b60694cade342e")
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 numpy as np
import copy

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

# Create small example arrays for the function parameters
# mn0: mean vector for model 0, shape (n_observed_dims,)
mn0 = np.array([0.1, 0.2, 0.3, 0.4])

# lm0: loading matrix for model 0, shape (n_observed_dims, n_intermediate_dims)
lm0 = np.array([
    [1.0, 0.5, 0.2],
    [0.3, 1.1, 0.4],
    [0.2, 0.3, 1.2],
    [0.5, 0.2, 0.3]
])

# mn1: mean vector for model 1, shape (n_observed_dims,)
mn1 = np.array([0.15, 0.25, 0.35, 0.45])

# lm1: loading matrix for model 1, shape (n_observed_dims, n_intermediate_dims)
lm1 = np.array([
    [1.1, 0.6, 0.25],
    [0.35, 1.2, 0.45],
    [0.25, 0.35, 1.3],
    [0.55, 0.25, 0.35]
])

# int_z0: latents in intermediate space for model 0, shape (n_samples, n_intermediate_dims)
int_z0 = np.array([
    [0.5, 0.3, 0.2],
    [0.6, 0.4, 0.1]
])

# int_z1: latents in intermediate space for model 1, shape (n_samples, n_intermediate_dims)
int_z1 = np.array([
    [0.55, 0.35, 0.25],
    [0.65, 0.45, 0.15]
])

# align_by_params: boolean flag for alignment method
align_by_params = True

ARGS = {
    "mn0": mn0,
    "lm0": lm0,
    "mn1": mn1,
    "lm1": lm1,
    "int_z0": int_z0,
    "int_z1": int_z1,
    "align_by_params": align_by_params
}
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 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
find_period_time_points Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
neuro-will/probabilistic_model_synthesis/probabilistic_model_synthesis/gnlr_ahrens_tools.py
code served (permissive licence) · get_code("7328ee8714f96496")
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 1, dtype family int, shape (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

# Create sample time stamps
cand_ts = np.array([1.0, 2.5, 3.7, 5.2, 7.1, 8.3, 9.9, 11.2])

# Create a labels dict structure that matches what label_periods would produce
# The function expects labels['ts'] to be an array of timestamps
# and labels['labels'][period] to be a list of dicts with 'slice' and 'shock' keys
period_ts_1 = np.array([1.0, 2.5, 3.7])
period_ts_2 = np.array([5.2, 7.1])
period_ts_3 = np.array([8.3, 9.9, 11.2])

labels = {
    'ts': np.concatenate([period_ts_1, period_ts_2, period_ts_3]),
    'labels': {
        'period_A': [
            {'slice': np.s_[0:3], 'shock': False},
            {'slice': np.s_[3:5], 'shock': True},
        ],
        'period_B': [
            {'slice': np.s_[5:8], 'shock': False},
        ]
    }
}

period = 'period_A'
shock = False

ARGS = {
    'cand_ts': cand_ts,
    'period': period,
    'shock': shock,
    'labels': labels
}
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 1, dtype family int, shape (3,) — shape (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_lr Ran
ran, honoured the contract we drafted
neuro-will/probabilistic_model_synthesis/probabilistic_model_synthesis/utilities.py
code served (permissive licence) · get_code("f179a4d97a2bf69b")
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 float, 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 torch
import torch.nn as nn
from torch.optim import SGD

torch.manual_seed(0)

# Create a simple model
model = nn.Linear(4, 2)

# Create an optimizer with a known learning rate
optimizer = SGD(model.parameters(), lr=0.01)

# Construct arguments
ARGS = {
    'optimizer': optimizer
}
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 float, 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_scalar_vl Ran
ran, violated the contract we drafted
neuro-will/probabilistic_model_synthesis/probabilistic_model_synthesis/utilities.py
code served (permissive licence) · get_code("909060a87062cd8c")
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 float, 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 torch
import numpy as np

torch.manual_seed(0)

# Test case 1: torch.Tensor input
tensor_input = torch.tensor([3.14], dtype=torch.float32)

# Test case 2: float input
float_input = 2.71

# Create ARGS dict with both parameter types to show the function works
# We'll test with the tensor case
ARGS = {
    "x": tensor_input
}
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 float, 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
label_periods Ran
ran; our contract draft was wrong, not the code
neuro-will/probabilistic_model_synthesis/probabilistic_model_synthesis/annotations.py
code served (permissive licence) · get_code("4e4ca1749ebd6dae")
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
from collections import OrderedDict

# Create a small stimulus array for testing
# The array should contain stimulus values that exist in stim_dict
# Let's create a sequence that includes multiple stimulus types
stim = np.array([
    0, 0, 0,  # black (black)
    3, 3, 3,  # white (white)
    16, 16,   # shock (shock)
    0, 0, 0,  # black
    3, 3, 3,  # white
    # Now a phototaxis section (min_l=200, so we need at least 200 points)
] + [3] * 100 + [1] * 100 + [2] * 100, dtype=np.uint8)  # white, phototaxis_right, phototaxis_left

# Extend to make sure we have enough points and varied patterns
stim = np.concatenate([
    stim,
    np.full(50, 4, dtype=np.uint8),  # grey (spontaneous)
    np.full(250, 10, dtype=np.uint8),  # omr_forward with some whites
])

ARGS = {
    'stim': stim,
    'min_l': 200
}
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
list_to_str Ran
ran; our contract draft was wrong, not the code
neuro-will/probabilistic_model_synthesis/probabilistic_model_synthesis/utilities.py
code served (permissive licence) · get_code("44d7518f5505a306")
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

# Simple list of floats to test the list_to_str function
x = [1.23456e-3, 4.56789e-2, 7.89012e-1, 3.45678e+0]

ARGS = {
    'x': x
}
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
load_fold_structure Ran
ran; our contract draft was wrong, not the code
neuro-will/probabilistic_model_synthesis/probabilistic_model_synthesis/data_utils.py
code served (permissive licence) · get_code("3d8b4e7cc22a5cc6")
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 tempfile
import json
from pathlib import Path

# Create temporary directory for test files
tmpdir = tempfile.TemporaryDirectory()
tmpdir_path = Path(tmpdir.name)

# Create a test JSON fold structure file
test_fold_data = {
    'fold_0': {
        'train': [0, 1, 2],
        'val': [3, 4],
        '__type__': 'slice',
        'start': 0,
        'stop': 10,
        'step': 2
    },
    'fold_1': {
        0: 'value_for_zero_key',
        'nested': {
            'data': [1, 2, 3]
        }
    }
}

json_file = tmpdir_path / "fold_structure.json"
with open(json_file, 'w', encoding='utf-8') as f:
    json.dump(test_fold_data, f)

# Create a test pickle file (legacy format)
import pickle
pickle_file = tmpdir_path / "fold_structure.pkl"
with open(pickle_file, 'wb') as f:
    pickle.dump(test_fold_data, f)

# Test with JSON file
ARGS = {
    'path': str(json_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
load_json_artifact Ran
ran; our contract draft was wrong, not the code
neuro-will/probabilistic_model_synthesis/probabilistic_model_synthesis/data_utils.py
code served (permissive licence) · get_code("ee3dd49b5243f2b1")
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
from pathlib import Path

# Create a temporary JSON file with test data
test_data = {
    "fold_0": {
        "train": [0, 1, 2],
        "val": [3, 4]
    },
    "metadata": {
        "slices": {
            "__type__": "slice",
            "start": 0,
            "stop": 10,
            "step": 2
        }
    },
    "numeric_keys": {
        "0": "value_zero",
        "1": "value_one",
        "2": "value_two"
    }
}

# Write to a temporary file
with tempfile.NamedTemporaryFile(mode='w', suffix='.json', delete=False, encoding='utf-8') as f:
    json.dump(test_data, f)
    temp_path = f.name

ARGS = {
    "path": temp_path
}
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
load_trusted_pickle Ran
ran; our contract draft was wrong, not the code
neuro-will/probabilistic_model_synthesis/probabilistic_model_synthesis/data_utils.py
code served (permissive licence) · get_code("0a08d9c16311dea7")
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 pickle
from pathlib import Path
import tempfile

# Create a temporary directory and file for testing
temp_dir = tempfile.mkdtemp()
temp_path = Path(temp_dir) / "test_pickle.pkl"

# Create some test data to pickle
test_data = {
    "model_weights": torch.randn(4, 3),
    "metadata": {"epoch": 42, "loss": 0.5},
    "list": [1, 2, 3, 4, 5]
}

# Save the test data to a pickle file
with open(temp_path, 'wb') as f:
    pickle.dump(test_data, f)

ARGS = {
    "path": temp_path
}
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
make_blue_red_c_map Ran
ran; our contract draft was wrong, not the code
neuro-will/probabilistic_model_synthesis/probabilistic_model_synthesis/visualization.py
code served (permissive licence) · get_code("3afd6980fefe343e")
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 LinearSegmentedColormap. 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 matplotlib.colors as mcolors

ARGS = {
    "n": 256,
    "inc_transp": False,
    "gentle": False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type LinearSegmentedColormap — a LinearSegmentedColormap output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a LinearSegmentedColormap 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
orthonormalize Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
neuro-will/probabilistic_model_synthesis/probabilistic_model_synthesis/fa.py
code served (permissive licence) · get_code("c7ab64adf63013f0")
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 numpy as np

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

# Create a loading matrix of shape (n_obs_vars, n_latents) = (5, 3)
# This represents the relationship between observed variables and latent factors
lm = np.random.randn(5, 3)

# Create latents of shape (n_samples, n_latents) = (7, 3)
# This represents the inferred loadings for samples
latents = np.random.randn(7, 3)

# Define arguments dictionary
ARGS = {
    "lm": lm,
    "latents": latents,
    "unit_len_columns": True
}
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 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
stim_to_binary_array Ran
ran; our contract draft was wrong, not the code
neuro-will/probabilistic_model_synthesis/probabilistic_model_synthesis/annotations.py
code served (permissive licence) · get_code("34d31610da69d37e")
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 float, shape (10, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import numpy as np
from collections import OrderedDict

# Define the stimulus dictionary (same as in the function module)
stim_dict = OrderedDict([('black', 0), ('phototaxis_right', 1), ('phototaxis_left', 2), ('white', 3), ('grey', 4), ('omr_backward', 9), ('omr_forward', 10), ('omr_right', 11), ('omr_left', 12), ('dot', 13), ('looming_left', 14), ('looming_right', 15), ('shock', 16), ('red_blue_right', 21), ('red_blue_left', 22), ('red_red', 23)])

# Create a 1-d array of stimulus values
# Using time points with different stimulus codes from stim_dict
stim = np.array([0, 1, 1, 2, 3, 0, 1, 4, 9, 10], dtype=int)

# Create a sequence of stimulus condition strings to represent
stim_conds = ['black', 'phototaxis_right', 'white', 'omr_forward']

ARGS = {
    'stim': stim,
    'stim_conds': stim_conds
}
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 float, shape (10, 4) — shape (10, 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
cone_and_projected_interval_sample Not yet run
unverified (harvested, no recorded run)
neuro-will/probabilistic_model_synthesis/probabilistic_model_synthesis/simulation.py
code served (permissive licence) · get_code("b237cb830d0aa7b2")
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, 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 12 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
get_lr 5 other papers
5 dated earlier
1911.13299 (2019-11)
What's Hidden in a Randomly Weighted Neural Network?
2110.14068 (2021-10)
Drawing Robust Scratch Tickets: Subnetworks with Inborn Robustness Are Found within Randomly Initialized Networks
2111.12330 (2021-11)
Hidden-Fold Networks: Random Recurrent Residuals Using Sparse Supermasks
and 2 more not named here

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

Repositories linked to this paper

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

Abstract

Many disciplines need quantitative models that synthesize experimental data across multiple instances of the same general system. For example, neuroscientists must combine data from the brains of many individual animals to understand the species' brain in general. However, typical machine learning models treat one system instance at a time. Here we introduce a machine learning framework, deep probabilistic model synthesis (DPMS), that leverages system properties auxiliary to the model to combine data across system instances. DPMS specifically uses variational inference to learn a conditional prior distribution and instance-specific posterior distributions over model parameters that respectively tie together the system instances and capture their unique structure. DPMS can synthesize a wide variety of model classes, such as those for regression, classification, and dimensionality reduction, and we demonstrate its ability to improve upon singleinstance models on synthetic data and whole-brain neural activity data from larval zebrafish.

For agents

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

get_harvested_code_for_paper("2603.14161")
get_code_for_paper("2603.14161")
have("2603.14161")

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

curl https://syntology.ai/api/ran/2603.14161.json

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

[![Syntology run record](https://syntology.ai/api/ran/2603.14161.svg)](https://syntology.ai/paper/2603.14161)

Connect an agent — have() is free.