SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.13074 · 2024

PIPPIN: Generating variable length full events from partons

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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 9 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/2406.13074.json · badge: /api/ran/2406.13074.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
rodem-hep/pippin canonical (classifier label)
classifier basis: census
10 ran · 1 no recorded run
FunctionStatusWhere it lives
get_fake_neutrinos Ran
ran; our contract draft was wrong, not the code
rodem-hep/pippin/src/physics.py
code served (permissive licence) · get_code("311d43729dd07375")
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 as T

T.manual_seed(0)

# The function regress_met calls order_by_pt, to_cartesian, and to_polar
# It takes met (batch, 4), neutrinos (batch, 2, 4), n_neutrinos (int)
# and returns either a tensor or tuple of tensors

# For get_fake_neutrinos:
# pc: (batch_size, n_obj, 4) - point cloud
# mask: (batch_size, n_obj) - bool mask
# pc_ref: (batch_size, n_part, 4) - reference point cloud
# mask_ref: (batch_size, n_part) - bool mask for reference
# channel: (batch_size,) - ByteTensor for decay channel

batch_size = 2
n_obj = 5
n_part = 8
feature_dim = 4

pc = T.randn(batch_size, n_obj, feature_dim)
mask = T.ones(batch_size, n_obj, dtype=T.bool)

pc_ref = T.randn(batch_size, n_part, feature_dim)
mask_ref = T.ones(batch_size, n_part, dtype=T.bool)

channel = T.tensor([1, 2], dtype=T.uint8)

ARGS = {
    "pc": pc,
    "mask": mask,
    "pc_ref": pc_ref,
    "mask_ref": mask_ref,
    "channel": channel,
}
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 — 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
masked_dequantize Ran
ran; our contract draft was wrong, not the code
rodem-hep/pippin/src/models/utils.py
code served (permissive licence) · get_code("4fb5b187eece9a28")
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 2, dtype family float, shape (2, 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 torch as T

T.manual_seed(0)

# Construct arguments for masked_dequantize
inputs = T.randn(2, 4)  # Small tensor: batch size 2, final dimension 4
mask = [True, False, True, False]  # Boolean mask for the final dimension
scale = 0.5
distribution = 'normal'

ARGS = {
    'inputs': inputs,
    'mask': mask,
    'scale': scale,
    'distribution': distribution
}
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 2, dtype family float, shape (2, 4) — shape (2, 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
masked_logit Ran
ran; our contract draft was wrong, not the code
rodem-hep/pippin/src/models/utils.py
code served (permissive licence) · get_code("3fbab752058e8b31")
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 2, dtype family float, shape (2, 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 torch as T

T.manual_seed(0)

# Create a small input tensor with shape (batch=2, features=4)
# Values should be in (0, 1) range for logit to work properly
inputs = T.tensor([
    [0.1, 0.5, 0.9, 0.3],
    [0.2, 0.7, 0.4, 0.8]
], dtype=T.float32)

# Create a mask as a list of booleans for the final dimension (4 features)
mask = [True, False, True, False]

# Small epsilon value to avoid division by zero
eps = 0.01

ARGS = {
    "inputs": inputs,
    "mask": mask,
    "eps": eps
}
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 2, dtype family float, shape (2, 4) — shape (2, 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
masked_round Ran
ran; our contract draft was wrong, not the code
rodem-hep/pippin/src/models/utils.py
code served (permissive licence) · get_code("b16920074d3f4faa")
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 2, dtype family float, shape (2, 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 torch as T

T.manual_seed(0)

# Create a small tensor with batch size 2 and final dimension 4
inputs = T.randn(2, 4, dtype=T.float32)

# Create a mask list that selects which indices in the final dimension to round
mask = [True, False, True, False]

ARGS = {
    "inputs": inputs,
    "mask": mask,
}
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 2, dtype family float, shape (2, 4) — shape (2, 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
no_inf Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
rodem-hep/pippin/src/utils.py
code served (permissive licence) · get_code("b62510122a630599")
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 1, dtype family float, shape (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
import torch as T

T.manual_seed(0)

# Create a test tensor with some NaN and inf values
x_tensor = T.tensor([1.0, 2.0, float('nan'), 4.0, float('inf'), 6.0])

# Create test arguments for no_inf function
ARGS = {
    'x': x_tensor,
    'skip_nan': 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 Tensor, ndim 1, dtype family float, shape (4,) — shape (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
regress_met Ran
ran; our contract draft was wrong, not the code
rodem-hep/pippin/src/physics.py
code served (permissive licence) · get_code("d6a6bce80190a80d")
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 3, 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 as T

T.manual_seed(0)

# Construct valid arguments for regress_met function
# The function takes: met (Tensor), neutrinos (Tensor), n_neutrinos (int)

# met: shape (batch_size, 4) in polar coordinates (pT, eta, phi, energy)
met = T.randn(2, 4)

# neutrinos: shape (batch_size, n_particles, 4) in polar coordinates
# For n_neutrinos=1, we need at least 1 neutrino per batch
# For n_neutrinos=2, we need at least 2 neutrinos per batch
neutrinos = T.randn(2, 3, 4)

# n_neutrinos: integer indicating how many neutrinos to process
# The function checks for n_neutrinos == 1 or n_neutrinos == 2
n_neutrinos = 2

ARGS = {
    "met": met,
    "neutrinos": neutrinos,
    "n_neutrinos": n_neutrinos
}
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 3, 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
reload_original_config Ran
ran; our contract draft was wrong, not the code
rodem-hep/pippin/src/config.py
code served (permissive licence) · get_code("f937c965008ed7b5")
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 DictConfig. 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 omegaconf import OmegaConf, DictConfig
from pathlib import Path
import tempfile
import os

torch.manual_seed(0)

# Create a temporary directory and a temporary config file
temp_dir = tempfile.mkdtemp()
original_config_path = os.path.join(temp_dir, "original_config.yaml")

# Write a sample original config to the temporary file
original_config_content = """
model:
  name: test_model
  layers: 3
  job_id: 0
  do_test_loop: false
  loss_delay_n: 0
train:
  epochs: 100
  lr: 0.001
test:
  batch_size: 32
"""

with open(original_config_path, "w") as f:
    f.write(original_config_content)

# Create the current config with the path to the original config
cfg = OmegaConf.create({
    "cfg_path": original_config_path,
    "full_resume": True,
    "train": True,
    "test": False,
    "job_id": 42,
    "seed": 123,
    "model": {
        "job_id": 99,
        "do_test_loop": True,
        "loss_delay_n": 5,
        "name": "current_model",
        "layers": 5
    }
})

ARGS = {
    "cfg": cfg
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
lightning, omegaconf, torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type DictConfig — a DictConfig output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a DictConfig output the recorded ndim 1 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
str2timedelta Ran
ran; our contract draft was wrong, not the code
rodem-hep/pippin/src/utils.py
code served (permissive licence) · get_code("d0c6230b4f20b6d0")
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 timedelta. 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 datetime

def str2timedelta(dmhs: str) -> datetime.timedelta:
    """Convert a string in the format "d:h:m:s" to a timedelta object."""
    d, h, m, s = map(int, dmhs.split(':'))
    return datetime.timedelta(days=d, hours=h, minutes=m, seconds=s)


ARGS = {
    "dmhs": "5:12:30:45"
}
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 timedelta — a timedelta output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a timedelta 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
timedelta2str Ran
ran; our contract draft was wrong, not the code
rodem-hep/pippin/src/utils.py
code served (permissive licence) · get_code("33cbb2da069d062d")
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 datetime

# Create a timedelta object with specific days, hours, minutes, and seconds
td = datetime.timedelta(days=5, hours=3, minutes=42, seconds=17)

ARGS = {
    "td": td
}
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 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
try_ks Ran
ran, honoured the contract we drafted
rodem-hep/pippin/src/metrics.py
code served (permissive licence) · get_code("c8cf6ad921dc8d51")
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 numpy as np
from scipy import stats

def try_ks(f, *args, **kwargs):
    """"
    Try to compute a function and extract f().statistic.
    Suitable for Kolmogorov-Smirnov distance.
    Return infinity if it fails.
    """
    try:
        return f(*args, **kwargs).statistic
    except:
        return np.inf


# Create a simple function that returns an object with a .statistic attribute
class KSResult:
    def __init__(self, statistic_value):
        self.statistic = statistic_value


def sample_function(data1, data2):
    """Mock function that returns a KS test result"""
    # Simulate a KS test result
    ks_statistic = 0.25
    return KSResult(ks_statistic)


# Prepare sample data for the function
sample_data_1 = np.array([1.0, 2.0, 3.0, 4.0, 5.0])
sample_data_2 = np.array([1.5, 2.5, 3.5, 4.5, 5.5])

ARGS = {
    'f': sample_function,
    'args': (sample_data_1, sample_data_2),
    'kwargs': {}
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, scipy — 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
instantiate_collection Not yet run
unverified (harvested, no recorded run)
rodem-hep/pippin/src/config.py
code served (permissive licence) · get_code("34961ebe02f1032e")
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, 0 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
instantiate_collection 1 other paper
1 dated earlier
2303.05376 (2023-03)
PC-JeDi: Diffusion for Particle Cloud Generation in High Energy Physics

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

This paper presents a novel approach for directly generating full events at detector-level from parton-level information, leveraging cutting-edge machine learning techniques. To address the challenge of multiplicity variations between parton and reconstructed object spaces, we employ transformers, score-based models and normalizing flows. Our method tackles the inherent complexities of the stochastic transition between these two spaces and achieves remarkably accurate results. The combination of innovative techniques and the achieved accuracy demonstrates the potential of our approach in advancing the field and opens avenues for further exploration. This research contributes to the ongoing efforts in high-energy physics and generative modelling, providing a promising direction for enhanced precision in fast detector simulation.

For agents

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

get_harvested_code_for_paper("2406.13074")
get_code_for_paper("2406.13074")
have("2406.13074")

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

curl https://syntology.ai/api/ran/2406.13074.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.13074.svg)](https://syntology.ai/paper/2406.13074)

Connect an agent — have() is free.