SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1507.06594 · 2015

Neural NILM: Deep Neural Networks Applied to Energy Disaggregation

arXiv · PDF · Open in the Atlas

Code that ran

13 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; 1 honoured the contract we drafted, 0 violated it and 12 have no contract verdict; 0 failures of our instrument; 4 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/1507.06594.json · badge: /api/ran/1507.06594.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
JackKelly/neuralnilm_prototype canonical (classifier label)
classifier basis: census
8 ran · 4 no recorded run
joseluis1061/neuralnilm community (classifier label)
classifier basis not recorded on the link
5 ran · 0 no recorded run
FunctionStatusWhere it lives
flatten Ran
ran, honoured the contract we drafted
joseluis1061/neuralnilm/neuralnilm/utils.py
code served (permissive licence) · get_code("420aa2050ebb1f5d")
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 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 flatten takes a 2D list and flattens it to 1D
# It iterates through sublists and extracts items

_list = [[1, 2, 3], [4, 5], [6, 7, 8, 9]]

ARGS = {
    "_list": _list
}
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 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
get_colors Ran
ran on a synthesized input
JackKelly/neuralnilm_prototype/neuralnilm/plot.py
code served (permissive licence) · get_code("4888c794edf157be")
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 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
import numpy as np
from matplotlib.pyplot import cm

torch.manual_seed(0)

ARGS = {
    "n": 5
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib, 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 2, 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
gmm_pdf Ran
ran on a synthesized input
JackKelly/neuralnilm_prototype/neuralnilm/plot.py
code served (permissive licence) · get_code("a4f6cb53d5e3b59b")
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 (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
from scipy.stats import norm

# Create a small GMM with 3 components
n_components = 3
n_samples = 2

# Create parameters for 3 Gaussian components
mu = np.array([0.0, 2.0, -2.0])  # means for each component
sigma = np.array([0.5, 1.0, 0.8])  # standard deviations for each component
mixing = np.array([0.3, 0.5, 0.2])  # mixing weights (should sum to 1)

theta = (mu, sigma, mixing)

# Create sample data
x = np.array([0.5, 1.5])

ARGS = {
    "theta": theta,
    "x": x
}
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 ndarray, ndim 1, dtype family float, shape (2,) — shape (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
init_experiment Ran
ran on a synthesized input
JackKelly/neuralnilm_prototype/neuralnilm/experiment.py
code served (permissive licence) · get_code("baae6d0b0087030c")
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 os
import tempfile
import shutil

# Create a temporary base directory for testing
temp_base = tempfile.mkdtemp()

# Define arguments for init_experiment
base_path = temp_base
experiment = "test_experiment"
full_exp_name = "exp_test_001"

ARGS = {
    "base_path": base_path,
    "experiment": experiment,
    "full_exp_name": full_exp_name,
}
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
none_to_dict Ran
ran on a synthesized input
joseluis1061/neuralnilm/neuralnilm/utils.py
code served (permissive licence) · get_code("939a7d5f22a616bf")
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 torch

torch.manual_seed(0)

ARGS = {
    "data": None
}
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 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
none_to_list Ran
ran on a synthesized input
JackKelly/neuralnilm_prototype/neuralnilm/source.py
code served (permissive licence) · get_code("451649dabb32f0f5")
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

def none_to_list(x):
    return [] if x is None else x

# Test case 1: x is None
ARGS = {
    'x': None
}
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 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
none_to_list Ran
ran on a synthesized input
joseluis1061/neuralnilm/neuralnilm/utils.py
code served (permissive licence) · get_code("923e142fb8dee6cf")
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

torch.manual_seed(0)

ARGS = {
    "data": None
}
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 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
rectangle_filename Ran
ran on a synthesized input
JackKelly/neuralnilm_prototype/neuralnilm/disaggregate.py
code served (permissive licence) · get_code("658b9c2b1103edf5")
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.

from os.path import join, expanduser

ARGS = {
    'output_i': 42,
    'path': '~/tmp',
}
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
rectangularise Ran
ran on a synthesized input
JackKelly/neuralnilm_prototype/neuralnilm/rectangulariser.py
code served (permissive licence) · get_code("5432382b30150a20")
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, 5, 1) 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 sys

# Create sample data - 1D case with some variance
np.random.seed(0)
data_1d = np.random.randn(50).astype(np.float32)

# Create sample data - 2D case (batch_size=2, sequence_length=50, features=1)
data_2d = np.random.randn(2, 50, 1).astype(np.float32)

ARGS = {
    'data': data_2d,
    'n_segments': 5,
    'format': 'proportional'
}
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, 5, 1) — shape (2, 5, 1) 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
relative_error_in_total_energy Ran
ran on a synthesized input
joseluis1061/neuralnilm/neuralnilm/metrics.py
code served (permissive licence) · get_code("17e0b7c612ec0e93")
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

# The function takes two array-like parameters: output and target
# It computes the sum of each and then calculates relative error
# The arrays can be numpy arrays of any shape

output = np.array([1.5, 2.3, 0.8, 1.2])
target = np.array([1.4, 2.5, 0.9, 1.1])

ARGS = {
    "output": output,
    "target": target,
}
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 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
scores Ran
ran on a synthesized input
joseluis1061/neuralnilm/neuralnilm/scores.py
code served (permissive licence) · get_code("7eed19a0c9917f3f")
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 numpy as np
import pandas as pd
import seaborn as sns
import matplotlib
matplotlib.use('Agg')  # Use non-interactive backend to avoid display issues

# Create sample data for Y_pred and Y_test
# Y_pred should have shape (n_samples, 3) with columns [class_0_score, class_1_score, confidence]
# Y_test should have shape (n_samples, 2) with binary indicators [is_class_0, is_class_1]

np.random.seed(0)

# Generate Y_pred: 5 samples, 3 columns (scores for class 0, class 1, and activation/confidence)
Y_pred = np.array([
    [0.8, 0.1, 0.9],   # Predicted class 0 with high confidence
    [0.2, 0.7, 0.85],  # Predicted class 1 with high confidence
    [0.3, 0.4, 0.05],  # Low confidence (below threshold)
    [0.6, 0.3, 0.92],  # Predicted class 0 with high confidence
    [0.1, 0.8, 0.88],  # Predicted class 1 with high confidence
], dtype=np.float32)

# Generate Y_test: 5 samples, 2 columns (ground truth binary indicators)
Y_test = np.array([
    [1, 0],  # Actually class 0
    [0, 1],  # Actually class 1
    [1, 0],  # Actually class 0
    [1, 0],  # Actually class 0
    [0, 1],  # Actually class 1
], dtype=np.float32)

ARGS = {
    'Y_pred': Y_pred,
    'Y_test': Y_test,
    'activation_threshold': 0.1,
    'plot_results': False,
    'print_results': False,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
matplotlib, numpy, pandas, seaborn — 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
start_and_end_and_mean Ran
ran on a synthesized input
JackKelly/neuralnilm_prototype/neuralnilm/rectangulariser.py
code served (permissive licence) · get_code("ea8d6dc5401a7fdb")
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, 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

# Test case 1: 1D array
data_1d = np.array([0.0, 0.005, 0.02, 0.015, 0.003, 0.0], dtype=np.float32)

# Test case 2: 3D array (batch_size=2, seq_len=5, n_outputs=3)
data_3d = np.random.rand(2, 5, 3).astype(np.float32) * 0.1
# Ensure some values exceed threshold so the logic branches correctly
data_3d[0, 1:3, 0] = 0.05
data_3d[0, 2:4, 1] = 0.02
data_3d[1, 1, 2] = 0.03

ARGS = {
    "data": data_3d
}
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, 3, 3) — shape (2, 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
timestamp_to_int Ran
ran on a synthesized input
JackKelly/neuralnilm_prototype/neuralnilm/source.py
code served (permissive licence) · get_code("d162caef2dd02939")
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 pandas as pd

ARGS = {
    "ts": "2023-01-15 10:30:45"
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
pandas — 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
across_all_appliances Not yet run
unverified (harvested, no recorded run)
JackKelly/neuralnilm_prototype/neuralnilm/metrics.py
code served (permissive licence) · get_code("0917d7643d29acf7")
How it ran

no invocation recorded.

plot_disaggregate_start_stop_end Not yet run
unverified (harvested, no recorded run)
JackKelly/neuralnilm_prototype/neuralnilm/plot.py
code served (permissive licence) · get_code("5ca93f198a4b01dd")
How it ran

no invocation recorded.

quantize Not yet run
unverified (harvested, no recorded run)
JackKelly/neuralnilm_prototype/neuralnilm/source.py
code served (permissive licence) · get_code("a4c12d1effb52c55")
How it ran

no invocation recorded.

run_metrics Not yet run
unverified (harvested, no recorded run)
JackKelly/neuralnilm_prototype/neuralnilm/metrics.py
code served (permissive licence) · get_code("c81045c760ae5c9e")
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 (0 with at least one paper dated earlier, 0 the same month, 1 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
flatten 1 other paper
1 later
2210.06183 (2022-10)
Transfer Learning on Heterogeneous Feature Spaces for Treatment Effects Estimation

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

Energy disaggregation estimates appliance-by-appliance electricity consumption from a single meter that measures the whole home's electricity demand. Recently, deep neural networks have driven remarkable improvements in classification performance in neighbouring machine learning fields such as image classification and automatic speech recognition. In this paper, we adapt three deep neural network architectures to energy disaggregation: 1) a form of recurrent neural network called `long short-term memory' (LSTM); 2) denoising autoencoders; and 3) a network which regresses the start time, end time and average power demand of each appliance activation. We use seven metrics to test the performance of these algorithms on real aggregate power data from five appliances. Tests are performed against a house not seen during training and against houses seen during training. We find that all three neural nets achieve better F1 scores (averaged over all five appliances) than either combinatorial optimisation or factorial hidden Markov models and that our neural net algorithms generalise well to an unseen house.

For agents

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

get_harvested_code_for_paper("1507.06594")
get_code_for_paper("1507.06594")
have("1507.06594")

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

curl https://syntology.ai/api/ran/1507.06594.json

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

[![Syntology run record](https://syntology.ai/api/ran/1507.06594.svg)](https://syntology.ai/paper/1507.06594)

Connect an agent — have() is free.