SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1902.04057 · 2019

Deep autoregressive models for the efficient variational simulation of many-body quantum systems

arXiv · PDF · Open in the Atlas

Code that ran

8 of 14 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 8 have no contract verdict; 0 failures of our instrument; 6 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/1902.04057.json · badge: /api/ran/1902.04057.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
HUJI-Deep/FlowKet canonical (classifier label)
classifier basis: census
7 ran · 6 no recorded run
HUJI-Deep/PyKet community (classifier label)
classifier basis not recorded on the link
1 ran · 0 no recorded run
FunctionStatusWhere it lives
binary_array_to_decimal_array Ran
ran on a synthesized input
HUJI-Deep/FlowKet/src/flowket/exact/utils.py
code served (permissive licence) · get_code("a638d29d5194b836")
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 (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 numpy

# Create a small binary array
# Shape: (2, 3, 4) - batch of 2, sequence of 3, 4 binary digits
binary_digits = numpy.array([
    [[1, 0, 1, 1],
     [0, 1, 1, 0],
     [1, 1, 0, 1]],
    [[0, 0, 1, 0],
     [1, 0, 0, 1],
     [0, 1, 1, 1]]
], dtype='int32')

# out parameter - optional output array
out = None

ARGS = {
    'binary_digits': binary_digits,
    'out': out
}
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 (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
binary_to_decimal Ran
ran on a synthesized input
HUJI-Deep/FlowKet/src/flowket/exact/utils.py
code served (permissive licence) · get_code("7e7102caccea9b17")
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 int, ndim 0, dtype family int, 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)

# The function binary_to_decimal takes binary_digits as a parameter
# It iterates through binary_digits, checking if each element equals 1
# It treats the input as a sequence of binary digits (0s and 1s)
# and converts them to a decimal number using powers of 2

# Create a simple binary digit sequence
binary_digits = [1, 0, 1, 1]  # This represents binary 1011 = decimal 11

ARGS = {
    "binary_digits": binary_digits
}
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 int, ndim 0, dtype family int, 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
create_evaluation_config_parser Ran
ran on a synthesized input
HUJI-Deep/PyKet/experiments/run_evaluation.py
code served (permissive licence) · get_code("44c1a1d3b3681802")
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 ArgumentParser. 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 argparse
import tempfile
import os

torch_imported = False
try:
    import torch
    torch_imported = True
except ImportError:
    pass

# Create a temporary weights file path
temp_dir = tempfile.gettempdir()
weights_path = os.path.join(temp_dir, "dummy_weights.pth")

ARGS = {
    'depth': 5,
    'mini_batch_size': 32,
    'hilbert_state_shape': [8, 8, 4],
    'parser': None
}
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 ArgumentParser — a ArgumentParser output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ArgumentParser 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
decimal_to_binary Ran
ran on a synthesized input
HUJI-Deep/FlowKet/src/flowket/exact/utils.py
code served (permissive licence) · get_code("0a8afa31e956afe7")
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:
# - decimal: an integer that gets divided by 2 repeatedly (num_of_bits times)
# - num_of_bits: an integer specifying how many iterations
# - zero_one_base: a boolean flag that changes the output format

ARGS = {
    "decimal": 42,
    "num_of_bits": 8,
    "zero_one_base": False
}
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
evaluate Ran
ran on a synthesized input
HUJI-Deep/FlowKet/src/flowket/evaluation/evaluate.py
code served (permissive licence) · get_code("bd87d86fe6e4f1c6")
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
import tqdm

class DummyCallback:
    def on_batch_end(self, batch_idx, logs):
        logs['loss'] = 0.5 + batch_idx * 0.01
        logs['accuracy'] = 0.8 + batch_idx * 0.005
    
    def on_epoch_end(self, epoch_idx, logs):
        logs['val_loss'] = 0.6 + epoch_idx * 0.02

def dummy_generator():
    while True:
        yield None

ARGS = {
    'generator': dummy_generator(),
    'steps': 5,
    'callbacks': [DummyCallback(), DummyCallback()],
    'keys_to_progress_bar_mapping': {'loss': 'loss_display', 'accuracy': 'acc_display'},
    'verbose': True
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, 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
exact_evaluate Ran
ran on a synthesized input
HUJI-Deep/FlowKet/src/flowket/evaluation/evaluate.py
code served (permissive licence) · get_code("ff35221ff98250e0")
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

torch.manual_seed(0)

# Stand-in class for exact_variational
class ExactVariational(nn.Module):
    def __init__(self):
        super().__init__()
        self.num_of_batch_until_full_cycle = 5
        self.machine_updated_called = False
    
    def machine_updated(self):
        self.machine_updated_called = True

# Stand-in callback class
class Callback:
    def on_batch_end(self, batch_num, logs):
        logs['batch_end'] = batch_num
    
    def on_epoch_end(self, epoch, logs):
        logs['epoch_end'] = epoch

# Create instances
exact_variational = ExactVariational()
callbacks = [Callback(), Callback()]

ARGS = {
    'exact_variational': exact_variational,
    'callbacks': callbacks
}
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
load_optimizer_weights Ran
ran on a synthesized input
HUJI-Deep/FlowKet/src/flowket/callbacks/checkpoint.py
code served (permissive licence) · get_code("73323e8633472c4e")
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 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 torch.nn as nn
import pickle
import os
import tempfile

torch.manual_seed(0)

# Create a minimal model with optimizer and required methods
class MinimalModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
        self.optimizer = None
        self._train_function_made = False
    
    def forward(self, x):
        return self.linear(x)
    
    def _make_train_function(self):
        self._train_function_made = True
    
    def set_weights(self, weights):
        pass

# Create model instance
model = MinimalModel()

# Create a minimal optimizer with set_weights method
class MinimalOptimizer:
    def __init__(self):
        self.weights = None
    
    def set_weights(self, weight_values):
        self.weights = weight_values

model.optimizer = MinimalOptimizer()

# Create temporary directory and file with optimizer state
temp_dir = tempfile.gettempdir()
test_filepath = os.path.join(temp_dir, 'test_optimizer_state')

# Create valid optimizer state to pickle
weight_values = [torch.randn(3, 4), torch.randn(3)]
epoch = 5
batch = 10

with open(test_filepath + '_optimizer.pkl', 'wb') as f:
    pickle.dump((weight_values, epoch, batch), f)

ARGS = {
    'model': model,
    'filepath': test_filepath
}
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 int — 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
mean_logs Ran
ran on a synthesized input
HUJI-Deep/FlowKet/src/flowket/evaluation/evaluate.py
code served (permissive licence) · get_code("2d57cd32707a434a")
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

# Construct sample logs data
logs_arr = [
    {"loss": 0.5, "accuracy": 0.85, "f1": 0.82},
    {"loss": 0.3, "accuracy": 0.90, "f1": 0.88},
    {"loss": 0.4, "accuracy": 0.87, "f1": 0.85},
]

ARGS = {
    "logs_arr": logs_arr,
    "keys": None,
}
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
average_ensemble_op Not yet run
unverified (harvested, no recorded run)
HUJI-Deep/FlowKet/src/flowket/machines/ensemble.py
code served (permissive licence) · get_code("091b441af6ec0bdd")
How it ran

no invocation recorded.

build_ensemble Not yet run
unverified (harvested, no recorded run)
HUJI-Deep/FlowKet/src/flowket/machines/ensemble.py
code served (permissive licence) · get_code("74cf9794fad07afc")
How it ran

no invocation recorded.

causal_conv_1d Not yet run
unverified (harvested, no recorded run)
HUJI-Deep/FlowKet/src/flowket/machines/complex_values_simple_conv_net_autoregressive_1D.py
code served (permissive licence) · get_code("a35c7fc5ed3c1bbf")
How it ran

no invocation recorded.

equal_up_down_spins_function Not yet run
unverified (harvested, no recorded run)
HUJI-Deep/FlowKet/src/flowket/layers/spins_invariants.py
code served (permissive licence) · get_code("36871cc719fda491")
How it ran

no invocation recorded.

keras_conditional_wave_functions_to_wave_function Not yet run
unverified (harvested, no recorded run)
HUJI-Deep/FlowKet/src/flowket/machines/abstract_machine.py
code served (permissive licence) · get_code("9173b8ec72f44dc7")
How it ran

no invocation recorded.

probabilistic_ensemble_op Not yet run
unverified (harvested, no recorded run)
HUJI-Deep/FlowKet/src/flowket/machines/ensemble.py
code served (permissive licence) · get_code("a4692fe88775e370")
How it ran

no invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 14 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.

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

Artificial Neural Networks were recently shown to be an efficient representation of highly-entangled many-body quantum states. In practical applications, neural-network states inherit numerical schemes used in Variational Monte Carlo, most notably the use of Markov-Chain Monte-Carlo (MCMC) sampling to estimate quantum expectations. The local stochastic sampling in MCMC caps the potential advantages of neural networks in two ways: (i) Its intrinsic computational cost sets stringent practical limits on the width and depth of the networks, and therefore limits their expressive capacity; (ii) Its difficulty in generating precise and uncorrelated samples can result in estimations of observables that are very far from their true value. Inspired by the state-of-the-art generative models used in machine learning, we propose a specialized Neural Network architecture that supports efficient and exact sampling, completely circumventing the need for Markov Chain sampling. We demonstrate our approach for two-dimensional interacting spin models, showcasing the ability to obtain accurate results on larger system sizes than those currently accessible to neural-network quantum states.

For agents

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

get_harvested_code_for_paper("1902.04057")
get_code_for_paper("1902.04057")
have("1902.04057")

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

curl https://syntology.ai/api/ran/1902.04057.json

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

[![Syntology run record](https://syntology.ai/api/ran/1902.04057.svg)](https://syntology.ai/paper/1902.04057)

Connect an agent — have() is free.