SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.06489 · 2024

Probing out-of-distribution generalization in machine learning for materials

arXiv · PDF · Open in the Atlas

Code that ran

2 of 2 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; 0 failures of our instrument; 0 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/2406.06489.json · badge: /api/ran/2406.06489.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
janosh/pymatviz canonical (classifier label)
classifier basis: census
2 ran · 0 no recorded run
FunctionStatusWhere it lives
get_cn_from_symbol Ran
ran, honoured the contract we drafted
janosh/pymatviz/pymatviz/chem_env.py
code served (permissive licence) · get_code("21dbf05ecc7cc7c9")
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

# Based on the function, we need:
# 1. ce_symbol: str - a ChemEnv symbol string
# 2. symbol_cn_mapping: dict[str, int] - mapping from symbols to coordination numbers

# The function uses:
# - ce_symbol "in" lookup against symbol_cn_mapping
# - ce_symbol == 'S:1' comparison
# - ce_symbol.startswith('M:') method
# - ce_symbol.split(':') method
# - int() conversion on split result
# - max() function with 0

# Create test cases that exercise different code paths
ce_symbol = 'T:4'  # A standard ChemEnv symbol
symbol_cn_mapping = {
    'T:4': 4,      # Tetrahedral
    'O:6': 6,      # Octahedral
    'S:1': 1,      # Single
    'M:8': 8,      # Cubic
}

ARGS = {
    'ce_symbol': ce_symbol,
    'symbol_cn_mapping': symbol_cn_mapping,
}
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
is_structure_like Ran
ran, violated the contract we drafted
janosh/pymatviz/pymatviz/process_data.py
code served (permissive licence) · get_code("3f9a0eecec4db55a")
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 bool, 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
from typing import Any

# Create a simple stand-in class that mimics a structure-like object
# We'll create a mock object that won't match any real structure classes
class MockStructure:
    """A mock structure object for testing"""
    pass

# Create instances to test
mock_obj = MockStructure()
non_structure_obj = "not a structure"
dict_obj = {"key": "value"}
list_obj = [1, 2, 3]
int_obj = 42
none_obj = None

# The function takes a single parameter: obj (Any)
# Test with various objects
ARGS = {
    "obj": mock_obj
}
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 bool, 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

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 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 2 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

Scientific machine learning (ML) endeavors to develop generalizable models with broad applicability. However, the assessment of generalizability is often based on heuristics. Here, we demonstrate in the materials science setting that heuristics based evaluations lead to substantially biased conclusions of ML generalizability and benefits of neural scaling. We evaluate generalization performance in over 700 out-of-distribution tasks that features new chemistry or structural symmetry not present in the training data. Surprisingly, good performance is found in most tasks and across various ML models including simple boosted trees. Analysis of the materials representation space reveals that most tasks contain test data that lie in regions well covered by training data, while poorly-performing tasks contain mainly test data outside the training domain. For the latter case, increasing training set size or training time has marginal or even adverse effects on the generalization performance, contrary to what the neural scaling paradigm assumes. Our findings show that most heuristically-defined out-of-distribution tests are not genuinely difficult and evaluate only the ability to interpolate. Evaluating on such tasks rather than the truly challenging ones can lead to an overestimation of generalizability and benefits of scaling.

For agents

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

get_harvested_code_for_paper("2406.06489")
get_code_for_paper("2406.06489")
have("2406.06489")

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

curl https://syntology.ai/api/ran/2406.06489.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.06489.svg)](https://syntology.ai/paper/2406.06489)

Connect an agent — have() is free.