SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2307.08240 · 2023

MIST-CF: Chemical formula inference from tandem mass spectra

arXiv · PDF · Open in the Atlas

Code that ran

14 of 17 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; 3 honoured the contract we drafted, 2 violated it and 1 has no contract verdict; 8 failures of our instrument; 3 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/2307.08240.json · badge: /api/ran/2307.08240.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
samgoldman97/mist-cf canonical (classifier label)
classifier basis: census
14 ran · 3 no recorded run
FunctionStatusWhere it lives
clamped_log_np Ran
ran; our contract draft was wrong, not the code
samgoldman97/mist-cf/src/mist_cf/common/misc_utils.py
code served (permissive licence) · get_code("3d86f40324ba0a2c")
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 float, shape (6,) 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
import torch

# Create a simple numpy array with positive values
x = np.array([0.1, 1.0, 10.0, 100.0, 0.5, 50.0])

# Define ARGS dict with all parameters
ARGS = {
    "x": x,
    "_min": -100
}
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 ndarray, ndim 1, dtype family float, shape (6,) — shape (6,) 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
cm2inch Ran
ran, violated the contract we drafted
samgoldman97/mist-cf/src/mist_cf/common/plot_utils.py
pointer only (licence: MIT); the stored copy get_code serves, from oval-group/statistical-robustness, is pointer only (licence: NONE) · get_code("a9cd3385008cabd7")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from oval-group/statistical-robustness, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

extract_ar Ran
ran; our contract draft was wrong, not the code
samgoldman97/mist-cf/src/mist_cf/fast_form_score/fast_form_data.py
code served (permissive licence) · get_code("bb4baa6a14cd5d15")
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 torch
import numpy as np

def extract_ar(form_str):
    """extract_ar."""
    forms = [i for i in form_str.split(',') if len(i) > 0]
    return forms

# The function takes a single parameter: form_str, which is a string
# It splits by comma and filters out empty strings
# We need to provide a simple string with comma-separated values

ARGS = {
    "form_str": "form1,form2,form3,form4"
}
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 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_data_dir Ran
ran; our contract draft was wrong, not the code
samgoldman97/mist-cf/src/mist_cf/common/misc_utils.py
code served (permissive licence) · get_code("2b795c71fe9f09a2")
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 PosixPath. 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 pathlib import Path

ARGS = {
    "dataset_name": "cifar10"
}
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 PosixPath — a PosixPath output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a PosixPath 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_instr_idx Ran
ran, honoured the contract we drafted
samgoldman97/mist-cf/src/mist_cf/common/chem_utils.py
code served (permissive licence) · get_code("7a4efff97c96f932")
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 int64, 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 numpy as np

instrument_to_type = {'Thermo Finnigan Velos Orbitrap': 'orbitrap', 'Thermo Finnigan Elite Orbitrap': 'orbitrap', 'Orbitrap Fusion Lumos': 'orbitrap', 'Q-ToF (LCMS)': 'qtof', 'Unknown (LCMS)': 'unknown', 'Ion Trap (LCMS)': 'iontrap', 'ion trap': 'iontrap', 'FTICR (LCMS)': 'fticr', 'Bruker Q-ToF (LCMS)': 'qtof', 'Orbitrap (LCMS)': 'orbitrap', 'ESI-Orbitrap': 'orbitrap', 'ESI-qTOF': 'qtof', 'ESI-qToF': 'qtof', 'ESI-qTof': 'qtof'}

instruments = sorted(list(set(instrument_to_type.values())))

instrument_to_idx = dict(zip(instruments, np.arange(len(instruments))))

def get_instr_idx(instrument: str) -> int:
    """ map instrument to its index in one hot encoding"""
    inst = instrument_to_type.get(instrument, 'uknown')
    return instrument_to_idx[inst]

ARGS = {
    'instrument': 'Thermo Finnigan Velos Orbitrap'
}
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 int64, 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
get_instr_tol Ran
ran, honoured the contract we drafted
samgoldman97/mist-cf/src/mist_cf/common/chem_utils.py
code served (permissive licence) · get_code("c8defd5c0d9ea9f0")
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

instrument_to_type = {'Thermo Finnigan Velos Orbitrap': 'orbitrap', 'Thermo Finnigan Elite Orbitrap': 'orbitrap', 'Orbitrap Fusion Lumos': 'orbitrap', 'Q-ToF (LCMS)': 'qtof', 'Unknown (LCMS)': 'unknown', 'Ion Trap (LCMS)': 'iontrap', 'ion trap': 'iontrap', 'FTICR (LCMS)': 'fticr', 'Bruker Q-ToF (LCMS)': 'qtof', 'Orbitrap (LCMS)': 'orbitrap', 'ESI-Orbitrap': 'orbitrap', 'ESI-qTOF': 'qtof', 'ESI-qToF': 'qtof', 'ESI-qTof': 'qtof'}

instrument_to_tol = {'qtof': 10, 'orbitrap': 5, 'iontrap': 15, 'fticr': 5, 'unknown': 15}

def get_instr_tol(instrument: str) -> int:
    """ map instrument to its mass tolerance"""
    inst = instrument_to_type.get(instrument, 'uknown')
    return instrument_to_tol[inst]

ARGS = {
    'instrument': 'Thermo Finnigan Velos Orbitrap'
}
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
get_ion_idx Ran
ran, honoured the contract we drafted
samgoldman97/mist-cf/src/mist_cf/common/chem_utils.py
code served (permissive licence) · get_code("6c5e73cb477c83f7")
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 int64, 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 numpy as np

ION_LST = ['[M+H]+', '[M+Na]+', '[M+K]+', '[M-H2O+H]+', '[M+H3N+H]+', '[M]+', '[M-H4O2+H]+']

ion_to_idx = dict(zip(ION_LST, np.arange(len(ION_LST))))

def get_ion_idx(ionization: str) -> int:
    """ "map ionization to its index in one hot encoding"""
    return ion_to_idx[ionization]

ARGS = {
    'ionization': '[M+H]+'
}
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 int64, 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
get_rounded_masses Ran
ran, violated the contract we drafted
samgoldman97/mist-cf/src/mist_cf/decomp/sirius_decomp.py
code served (permissive licence) · get_code("7ec3536d0ceb8542")
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 numpy as np

ARGS = {
    "masses": [1.5, 2.7, 3.14159, 4.99999, 5.12345]
}
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 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_splits Ran
ran; our contract draft was wrong, not the code
samgoldman97/mist-cf/src/mist_cf/common/splitter.py
code served (permissive licence) · get_code("4f7b84bcfae202f9")
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 tempfile
import pandas as pd
import numpy as np
from pathlib import Path

# Create a temporary split file
with tempfile.NamedTemporaryFile(mode='w', suffix='.tsv', delete=False) as f:
    split_file_path = f.name
    # Write a TSV file with spec column and fold column
    f.write('spec\tfold1\n')
    f.write('sample_0\ttrain\n')
    f.write('sample_1\ttrain\n')
    f.write('sample_2\tval\n')
    f.write('sample_3\ttest\n')
    f.write('sample_4\ttest\n')

# Create names list that matches the split file
names = ['sample_0', 'sample_1', 'sample_2', 'sample_3', 'sample_4']

ARGS = {
    'names': names,
    'split_file': split_file_path,
    'key': 'spec'
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas — 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
max_thresh_spec Ran
ran; our contract draft was wrong, not the code
samgoldman97/mist-cf/src/mist_cf/common/parse_utils.py
code served (permissive licence) · get_code("ec84a9ba70c311b1")
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 (4, 2) 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 mass spectrometry spectrum
# Each row is [mass, intensity]
spec = np.array([
    [100.5, 0.001],  # Below intensity threshold
    [150.3, 0.05],   # High intensity
    [200.1, 0.008],  # Medium intensity
    [250.7, 0.002],  # Below intensity threshold
    [300.2, 0.12],   # Highest intensity
    [350.5, 0.004],  # Low intensity
], dtype=np.float32)

ARGS = {
    "spec": spec,
    "max_peaks": 100,
    "inten_thresh": 0.003,
}
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 (4, 2) — shape (4, 2) 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
parse_element_str Ran
ran; our contract draft was wrong, not the code
samgoldman97/mist-cf/src/mist_cf/decomp/sirius_decomp.py
code served (permissive licence) · get_code("b6896b30b438c83d")
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 re

def parse_element_str(el_str, max_default=999):
    """Accept el str and return a dict from el to dict(min=min,max=max)"""
    regex = '([A-Z][a-z]?)(\\[\\d+-?\\d*\\])?'
    matches = re.finditer(regex, el_str, re.MULTILINE)
    out = {}
    for matchNum, match in enumerate(matches, start=1):
        el = match.group(1)
        if match.group(2) is None:
            out[el] = dict(min=0, max=0)
        else:
            min_, max_ = match.group(2).strip('[]').split('-')
            if max_ == '':
                max_ = max_default
            out[el] = dict(min=int(min_), max=int(max_))
    return out


ARGS = {
    "el_str": "H[1-3]O[2-5]C[1-]",
    "max_default": 999
}
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
process_spec_file Ran
ran on a synthesized input
samgoldman97/mist-cf/src/mist_cf/common/parse_utils.py
code served (permissive licence) · get_code("a52ac883c5ef6b19")
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 float, shape (2000,) 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 pathlib import Path
import tempfile
import os

# Create a temporary directory structure
temp_dir = tempfile.mkdtemp()
spec_files_dir = Path(temp_dir) / 'spec_files'
spec_files_dir.mkdir(parents=True, exist_ok=True)

# Create a minimal SIRIUS format spec file
spec_content = """#INSTRUMENT TYPE Orbitrap
#PRECURSOR_MZ 500.0
#PRECURSOR_TYPE [M+H]+
>spectrum1
100.5 50.0
150.3 75.5
200.1 100.0
250.8 60.2
>spectrum2
110.2 45.0
160.5 80.0
210.3 95.5
260.1 55.0
"""

spec_file_path = spec_files_dir / 'test_spec.ms'
with open(spec_file_path, 'w') as f:
    f.write(spec_content)

# Define ARGS dictionary with all parameters for process_spec_file
ARGS = {
    'spec_name': 'test_spec',
    'num_bins': 2000,
    'upper_limit': 1000,
    'data_dir': Path(temp_dir)
}
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 float, shape (2000,) — shape (2000,) 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
random_split Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
samgoldman97/mist-cf/src/mist_cf/common/splitter.py
code served (permissive licence) · get_code("1ce22fc7117ae7bd")
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 list of names to split
names = ["molecule_" + str(i) for i in range(100)]

# Define split sizes (train, val, test)
split_sizes = (0.8, 0.1, 0.1)

# Construct the ARGS dictionary
ARGS = {
    "names": names,
    "split_sizes": split_sizes,
}
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
unravel_index Ran
ran; our contract draft was wrong, not the code
samgoldman97/mist-cf/src/mist_cf/common/misc_utils.py
code served (permissive licence) · get_code("3338dabc50f8f122")
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

torch.manual_seed(0)

# The function unravel_index converts a flat index into multi-dimensional indices
# given a shape tuple. It takes:
# - index: a tensor containing flat indices
# - shape: a tuple of dimensions

# Create a simple flat index tensor
index = torch.tensor(42, dtype=torch.int64)

# Create a shape tuple representing a 3D tensor with dimensions 5, 4, 3
shape = (5, 4, 3)

ARGS = {
    "index": index,
    "shape": shape,
}
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
chunked_parallel Not yet run
unverified (harvested, no recorded run)
samgoldman97/mist-cf/src/mist_cf/common/parallel_utils.py
code served (permissive licence) · get_code("6bf05accd83a54c0")
How it ran

no invocation recorded.

process_spec_file_unbinned Not yet run
unverified (harvested, no recorded run)
samgoldman97/mist-cf/src/mist_cf/common/parse_utils.py
code served (permissive licence) · get_code("6640791d28598124")
How it ran

no invocation recorded.

simple_parallel Not yet run
unverified (harvested, no recorded run)
samgoldman97/mist-cf/src/mist_cf/common/parallel_utils.py
code served (permissive licence) · get_code("4d717f8f5be31876")
How it ran

no invocation recorded.

Also present in other papers' code

Of 17 samples lifted from this paper's linked repositories, 17 carry a function identity and 0 do not. Of the 17 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 16 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
cm2inch 1 other paper
1 dated earlier
1811.07209 (2018-11)
A Statistical Approach to Assessing Neural Network Robustness

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

Chemical formula annotation for tandem mass spectrometry (MS/MS) data is the first step toward structurally elucidating unknown metabolites. While great strides have been made toward solving this problem, the current state-of-the-art method depends on time-intensive, proprietary, and expert-parameterized fragmentation tree construction and scoring. In this work we extend our previous spectrum Transformer methodology into an energy based modeling framework, MIST-CF, for learning to rank chemical formula and adduct assignments given an unannotated MS/MS spectrum. Importantly, MIST-CF learns in a data dependent fashion using a Formula Transformer neural network architecture and circumvents the need for fragmentation tree construction. We train and evaluate our model on a large open-access database, showing an absolute improvement of 10% top 1 accuracy over other neural network architectures. We further validate our approach on the CASMI2022 challenge dataset, achieving nearly equivalent performance to the winning entry within the positive mode category without any manual curation or post-processing of our results. These results demonstrate an exciting strategy to more powerfully leverage MS2 fragment peaks for predicting MS1 precursor chemical formula with data driven learning.

For agents

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

get_harvested_code_for_paper("2307.08240")
get_code_for_paper("2307.08240")
have("2307.08240")

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

curl https://syntology.ai/api/ran/2307.08240.json

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

[![Syntology run record](https://syntology.ai/api/ran/2307.08240.svg)](https://syntology.ai/paper/2307.08240)

Connect an agent — have() is free.