SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2205.09263 · 2022

A Mutually Exciting Latent Space Hawkes Process Model for Continuous-time Networks

arXiv · PDF · Open in the Atlas

Code that ran

5 of 5 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, 0 violated it and 0 have no contract verdict; 3 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/2205.09263.json · badge: /api/ran/2205.09263.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
ideaslabut/latent-space-hawkes canonical (classifier label)
classifier basis: classifier_2025
5 ran · 0 no recorded run
FunctionStatusWhere it lives
actual_y Ran
ran, honoured the contract we drafted
ideaslabut/latent-space-hawkes/dynamic_link_pred.py
code served (permissive licence) · get_code("f37840550380634c")
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) and returned ndarray, ndim 2, dtype family float, 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 numpy as np

# Set random seed for reproducibility
np.random.seed(0)

# Define parameters for the actual_y function
n_nodes = 3

t0 = 5.0

delta = 10.0

# Create a timestamp array where each element [u, v] contains an array of timestamps
# for interactions between nodes u and v
timestamp = np.empty((n_nodes, n_nodes), dtype=object)

# Populate timestamp with arrays of timestamps
# Some pairs will have timestamps in the window [t0, t0+delta], others won't
for u in range(n_nodes):
    for v in range(n_nodes):
        if u == 0 and v == 1:
            # This pair has timestamps in the window [5, 15]
            timestamp[u, v] = np.array([6.0, 8.0, 12.0])
        elif u == 1 and v == 2:
            # This pair has timestamps in the window [5, 15]
            timestamp[u, v] = np.array([7.5, 14.0])
        elif u == 2 and v == 0:
            # This pair has timestamps outside the window
            timestamp[u, v] = np.array([1.0, 2.0, 20.0])
        else:
            # Other pairs have no timestamps
            timestamp[u, v] = np.array([])

ARGS = {
    "n_nodes": n_nodes,
    "t0": t0,
    "delta": delta,
    "timestamp": timestamp
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 (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
avg_run_length Ran
ran, honoured the contract we drafted
ideaslabut/latent-space-hawkes/LSH_generative.py
code served (permissive licence) · get_code("72144f2d1954da55")
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) and returned float64, 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

# Analyze the function:
# avg_run_length takes parameter P
# It accesses P.shape[0] (number of rows)
# It accesses P[i, j] and P[j, i] (2D indexing)
# Each P[i, j] should be a list or array-like that can be passed to run_length
# run_length expects two arguments u and v that can be concatenated with np.concatenate
# and checked with "in" operator

# Create a small 3x3 matrix where each element is a numpy array
P = np.empty((3, 3), dtype=object)

# Populate with small numpy arrays
# Make sure some pairs have non-empty arrays to trigger the run_length calculation
P[0, 0] = np.array([])
P[0, 1] = np.array([1, 3])
P[0, 2] = np.array([])
P[1, 0] = np.array([2, 4])
P[1, 1] = np.array([])
P[1, 2] = np.array([5])
P[2, 0] = np.array([])
P[2, 1] = np.array([6, 7])
P[2, 2] = np.array([])

ARGS = {
    "P": P
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, 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
degree_histogram_directed Ran
ran; our contract draft was wrong, not the code
ideaslabut/latent-space-hawkes/LSH_generative.py
code served (permissive licence) · get_code("5245976e253a7b22")
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) 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 networkx as nx

# Create a small directed graph for testing
G = nx.DiGraph()
G.add_edges_from([(0, 1), (0, 2), (1, 2), (2, 3), (3, 0)])

ARGS = {
    "G": G,
    "in_degree": False,
    "out_degree": False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
networkx — 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
predict_probs Ran
ran; our contract draft was wrong, not the code
ideaslabut/latent-space-hawkes/dynamic_link_pred.py
code served (permissive licence) · get_code("1d2e396113b35a9a")
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) and returned ndarray, ndim 2, dtype family float, 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 numpy as np
from scipy import integrate

np.random.seed(0)

# Parameters for predict_probs
n_nodes = 3
t0 = 5.0
delta = 2.0

# Create timestamp dictionary - for each (u,v) pair, store array of event times
timestamp = np.zeros((n_nodes, n_nodes), dtype=object)
for u in range(n_nodes):
    for v in range(n_nodes):
        # Create small arrays of event times, all less than t0 for filtering
        timestamp[u, v] = np.array([1.0, 2.5, 3.8])

# mu: baseline intensity for each (u,v) pair
mu = np.random.rand(n_nodes, n_nodes) * 0.5

# alpha: jump intensity [2 components for u->v and v->u]
alpha = np.array([0.3, 0.2])

# beta: decay parameters [3 components as used in loop]
beta = np.array([0.5, 0.7, 0.9])

# C: scaling parameters [3 components as used in loop]
C = np.array([0.1, 0.15, 0.2])

ARGS = {
    "n_nodes": n_nodes,
    "t0": t0,
    "delta": delta,
    "timestamp": timestamp,
    "mu": mu,
    "alpha": alpha,
    "beta": beta,
    "C": C,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy, scipy — 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 (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
univariate_cif Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
ideaslabut/latent-space-hawkes/dynamic_link_pred.py
code served (permissive licence) · get_code("d7cc9502906b61c0")
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) and returned float64, 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

# Construct valid arguments for univariate_cif

# t: current time point (scalar)
t = 5.0

# times: list of two arrays containing event times for two processes
times = [
    np.array([0.5, 1.2, 2.3, 3.1, 4.2]),  # t_uv: event times for first process
    np.array([0.8, 1.5, 2.8, 3.5, 4.0])   # t_vu: event times for second process
]

# mu: baseline intensity (scalar)
mu = 0.5

# alpha: jump intensities for two processes
alpha = np.array([0.3, 0.25])

# beta: decay parameters (array of length 3, used in loop range(3))
beta = np.array([0.1, 0.2, 0.15])

# C: scaling parameters for jump sizes (array of length 3, matches loop range(3))
C = np.array([0.5, 0.4, 0.35])

ARGS = {
    't': t,
    'times': times,
    'mu': mu,
    'alpha': alpha,
    'beta': beta,
    'C': C
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float64, 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 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 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 5 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

Networks and temporal point processes serve as fundamental building blocks for modeling complex dynamic relational data in various domains. We propose the latent space Hawkes (LSH) model, a novel generative model for continuous-time networks of relational events, using a latent space representation for nodes. We model relational events between nodes using mutually exciting Hawkes processes with baseline intensities dependent upon the distances between the nodes in the latent space and sender and receiver specific effects. We demonstrate that our proposed LSH model can replicate many features observed in real temporal networks including reciprocity and transitivity, while also achieving superior prediction accuracy and providing more interpretable fits than existing models.

For agents

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

get_harvested_code_for_paper("2205.09263")
get_code_for_paper("2205.09263")
have("2205.09263")

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

curl https://syntology.ai/api/ran/2205.09263.json

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

[![Syntology run record](https://syntology.ai/api/ran/2205.09263.svg)](https://syntology.ai/paper/2205.09263)

Connect an agent — have() is free.