SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2104.10869 · 2021

CrysXPP:An Explainable Property Predictor for Crystalline Materials

arXiv · PDF · Open in the Atlas

Code that ran

10 of 11 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; 2 honoured the contract we drafted, 1 violated it and 2 have no contract verdict; 5 failures of our instrument; 1 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/2104.10869.json · badge: /api/ran/2104.10869.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
iitkgpaiforscience/crysxpp canonical (classifier label)
classifier basis: census
8 ran · 1 no recorded run
kdmsit/CrysXPP community (classifier label)
classifier basis not recorded on the link
2 ran · 0 no recorded run
FunctionStatusWhere it lives
collate_pool Ran
ran; our contract draft was wrong, not the code
kdmsit/CrysXPP/src/data_prop.py
code served (permissive licence) · get_code("3f6dd8d427414044")
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 torch
import numpy as np

torch.manual_seed(0)

# Create sample data for a dataset list
# Each element is a tuple: ((atom_fea, nbr_fea, nbr_fea_idx), target, cif_id)

# First sample: 3 atoms
atom_fea_1 = torch.randn(3, 4)  # 3 atoms, 4 features each
nbr_fea_1 = torch.randn(3, 5, 6)  # 3 atoms, 5 neighbors, 6 neighbor features
nbr_fea_idx_1 = torch.LongTensor([[0, 1, 2, 1, 0],
                                   [1, 2, 0, 1, 2],
                                   [2, 0, 1, 2, 0]])  # 3 atoms, 5 neighbor indices
target_1 = torch.tensor([1.5])
cif_id_1 = "crystal_001"

# Second sample: 2 atoms
atom_fea_2 = torch.randn(2, 4)  # 2 atoms, 4 features each
nbr_fea_2 = torch.randn(2, 5, 6)  # 2 atoms, 5 neighbors, 6 neighbor features
nbr_fea_idx_2 = torch.LongTensor([[0, 1, 0, 1, 0],
                                   [1, 0, 1, 0, 1]])  # 2 atoms, 5 neighbor indices
target_2 = torch.tensor([2.3])
cif_id_2 = "crystal_002"

# Construct dataset_list
dataset_list = [
    ((atom_fea_1, nbr_fea_1, nbr_fea_idx_1), target_1, cif_id_1),
    ((atom_fea_2, nbr_fea_2, nbr_fea_idx_2), target_2, cif_id_2)
]

ARGS = {
    "dataset_list": dataset_list
}
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 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
disc_edge_feature Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
iitkgpaiforscience/crysxpp/src/data.py
code served (permissive licence) · get_code("6fa60cc510c79ce4")
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 3, dtype family float, shape (2, 2, 5) 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

# Construct arguments for disc_edge_feature
# The function expects:
# - edge: a 2D array where each element is a distance value (will be rounded to int)
# - data: a 2D array of indices (nbr_fea_idx)

# Create a small edge distance matrix (2x3 shape for distinction)
# Values represent distances that will be rounded
edge = np.array([
    [1.2, 2.8, 3.1],
    [0.9, 4.5, 2.3]
], dtype=float)

# Create corresponding neighbor feature indices (same shape as edge)
# These indices point to positions in the output tensor's second dimension
# Must be valid indices (0 to N-1 where N is the first dimension)
data = np.array([
    [0, 1, 0],
    [1, 0, 1]
], dtype=int)

ARGS = {
    "edge": edge,
    "data": data
}
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 3, dtype family float, shape (2, 2, 5) — shape (2, 2, 5) 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
disc_edge_feature Ran
ran, honoured the contract we drafted
iitkgpaiforscience/crysxpp/src/data_prop.py
code served (permissive licence) · get_code("754129e77312b15b")
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 (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 as np

# Create a small edge array with shape (2, 3)
# The function iterates over both dimensions and converts values to int,
# capping values >= 4 to 4
edge = np.array([
    [1.5, 3.2, 5.7],
    [2.1, 4.3, 6.9]
], dtype=float)

ARGS = {
    "edge": edge
}
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 (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
getActivation Ran
ran; our contract draft was wrong, not the code
iitkgpaiforscience/crysxpp/src/model.py
code served (permissive licence) · get_code("80cc71b697292968")
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 ReLU. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

torch.manual_seed(0)

ARGS = {
    'activation': 'relu'
}
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 ReLU — a ReLU output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a ReLU 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
get_data_loader Ran
ran on a synthesized input
iitkgpaiforscience/crysxpp/src/data.py
code served (permissive licence) · get_code("3564cd5a3000945a")
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 DataLoader. 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
from torch.utils.data import Dataset, DataLoader
from torch.utils.data.dataloader import default_collate
from torch.utils.data.sampler import SubsetRandomSampler

torch.manual_seed(0)

class SimpleDataset(Dataset):
    def __init__(self, size=10, feature_dim=4):
        self.size = size
        self.feature_dim = feature_dim
    
    def __len__(self):
        return self.size
    
    def __getitem__(self, idx):
        x = torch.randn(self.feature_dim)
        y = torch.tensor(idx % 2)
        return x, y

dataset = SimpleDataset(size=10, feature_dim=4)

ARGS = {
    "dataset": dataset,
    "collate_fn": default_collate,
    "train_size": 8,
    "batch_size": 2,
    "num_workers": 0,
    "pin_memory": False,
}
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 DataLoader — a DataLoader output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DataLoader 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
get_molecular_adj Ran
ran, honoured the contract we drafted
iitkgpaiforscience/crysxpp/src/data.py
code served (permissive licence) · get_code("747b83a5ce897be4")
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 (4, 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

# Analyze the function:
# - nbr_fea_idx: iterated over with range(N), accessed as edge_list[i]
#   Each edge_list[i] is iterated over (for j in edge_list[i])
#   j is used as an index into adj[i][j]
# - N: used in range(N) and to create adj matrix of shape (N, N)
# 
# So nbr_fea_idx should be a list-like structure of length N,
# where each element is an iterable of neighbor indices

# Construct a small example:
N = 4

# Create neighbor feature index: list of lists
# Each inner list contains neighbor indices for that atom
nbr_fea_idx = [
    [1, 2],        # atom 0 has neighbors 1 and 2
    [0, 2, 3],     # atom 1 has neighbors 0, 2, and 3
    [0, 1],        # atom 2 has neighbors 0 and 1
    [1]            # atom 3 has neighbor 1
]

ARGS = {
    "nbr_fea_idx": nbr_fea_idx,
    "N": N
}
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 (4, 4) — shape (4, 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
get_molecular_multigraph_adj Ran
ran, violated the contract we drafted
iitkgpaiforscience/crysxpp/src/data_prop.py
code served (permissive licence) · get_code("bf02b65c4f9c1778")
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 networkx as nx
import numpy as np

# The function expects 'data' to be an iterable where each element
# is itself an iterable of neighbor indices.
# This represents an adjacency structure for a molecular graph.

# Create a simple neighbor feature index structure
# data[i] should be a list of neighbor indices for node i
nbr_fea_idx_0 = [1, 2]  # node 0 connects to nodes 1 and 2
nbr_fea_idx_1 = [0, 2]  # node 1 connects to nodes 0 and 2
nbr_fea_idx_2 = [0, 1]  # node 2 connects to nodes 0 and 1

data = [nbr_fea_idx_0, nbr_fea_idx_1, nbr_fea_idx_2]

ARGS = {
    "data": data
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
networkx, 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_train_val_test_loader Ran
ran on a synthesized input
kdmsit/CrysXPP/src/data_prop.py
code served (permissive licence) · get_code("9673d28023c7d8d8")
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 numpy as np
from torch.utils.data import Dataset, DataLoader
from torch.utils.data.dataloader import default_collate
from torch.utils.data.sampler import SubsetRandomSampler

torch.manual_seed(0)

class SimpleDataset(Dataset):
    def __init__(self, size=100):
        self.size = size
        self.data = torch.randn(size, 4)
        self.labels = torch.randint(0, 2, (size,))
    
    def __len__(self):
        return self.size
    
    def __getitem__(self, idx):
        return self.data[idx], self.labels[idx]

dataset = SimpleDataset(size=100)

ARGS = {
    'dataset': dataset,
    'collate_fn': default_collate,
    'batch_size': 16,
    'train_ratio': 0.7,
    'val_ratio': 0.1,
    'test_ratio': 0.2,
    'return_test': True,
    'num_workers': 0,
    'pin_memory': False,
    'train_size': None,
    'test_size': None,
}
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 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
sanitize Ran
ran; our contract draft was wrong, not the code
iitkgpaiforscience/crysxpp/src/prop.py
code served (permissive licence) · get_code("f997a9a7c06ccbbf")
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 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)

# Create small 1D tensors for input_var and reference
# The function uses these as 1D tensors with indexing operations
input_var = torch.tensor([1.0, 2.0, 3.0, 4.0])
reference = torch.tensor([5.0, 6.0, 1000000.0, 8.0])

ARGS = {
    "input_var": input_var,
    "reference": reference,
    "return_diff": False
}
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 2, 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
sparse_loss Ran
ran; our contract draft was wrong, not the code
iitkgpaiforscience/crysxpp/src/prop.py
code served (permissive licence) · get_code("f2b4c1cbe71051af")
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. 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

torch.manual_seed(0)

class SimplePropModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.linear = nn.Linear(4, 3)
    
    def forward(self, x):
        return self.linear(x)

prop_model = SimplePropModel()
input_tensor = torch.randn(2, 4)

ARGS = {
    "prop_model": prop_model,
    "input": input_tensor
}
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
mae Not yet run
unverified (harvested, no recorded run)
iitkgpaiforscience/crysxpp/src/prop.py
code served (permissive licence) · get_code("be7ec3c87b0c2292")
How it ran

no invocation recorded.

Also present in other papers' code

Of 11 samples lifted from this paper's linked repositories, 11 carry a function identity and 0 do not. Of the 11 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, 1 later) and 10 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
collate_pool 2 other papers
1 dated earlier, 1 later
2003.10580 (2020-03)
Meta Pseudo Labels
2602.04075 (2026-02)
Thermodynamic assessment of machine learning models for solid-state synthesis prediction

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

Repositories linked to this paper

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

Abstract

We present a deep-learning framework, CrysXPP, to allow rapid prediction of electronic, magnetic and elastic properties of a wide range of materials with reasonable precision. Although our work is consistent with several recent attempts to build deep learning-based property predictors, it overcomes some of their limitations. CrysXPP lowers the need for a large volume of tagged data to train a deep learning model by intelligently designing an autoencoder CrysAE and passing the structural information to the property prediction process. The autoencoder in turn is trained on a huge volume of untagged crystal graphs, the designed loss function helps in capturing all their important structural and chemical information. Moreover, CrysXPP uses only a small amount of tagged data for property prediction, and also trains a feature selector that provides interpretability to the results obtained. We demonstrate that CrysXPP convincingly performs better than all the competing and recent baseline algorithms across seven diverse set of properties. Most notably, when given a small amount of experimental data, CrysXPP is consistently able to outperform conventional DFT. We release the large pretrained model CrysAE so that it could be fine-tuned using small amount of tagged data by the research community on various applications with restricted data source.

For agents

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

get_harvested_code_for_paper("2104.10869")
get_code_for_paper("2104.10869")
have("2104.10869")

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

curl https://syntology.ai/api/ran/2104.10869.json

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

[![Syntology run record](https://syntology.ai/api/ran/2104.10869.svg)](https://syntology.ai/paper/2104.10869)

Connect an agent — have() is free.