SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 1607.00148 · 2016

LSTM-based Encoder-Decoder for Multi-sensor Anomaly Detection

arXiv · PDF · Open in the Atlas

Code that ran

7 of 9 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; 0 honoured the contract we drafted, 0 violated it and 6 have no contract verdict; 1 failure of our instrument; 2 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/1607.00148.json · badge: /api/ran/1607.00148.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
PyLink88/RecAE community (classifier label)
classifier basis not recorded on the link
5 ran · 0 no recorded run
flaviagiammarino/encdec-ad-tensorflow community (classifier label)
classifier basis not recorded on the link
1 ran · 2 no recorded run
freedombenLiu/RNN-Time-series-Anomaly-Detection reimplementation (classifier label)
classifier basis: classifier_2025
1 ran · 0 no recorded run
FunctionStatusWhere it lives
MAEAUC_approx Ran
ran on a synthesized input
PyLink88/RecAE/graphs/losses/MAEAUCLoss.py
code served (permissive licence) · get_code("03a889e75902ecf2")
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 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)

# x: input tensor, shape (batch, height, width) or similar
# x_hat: reconstructed tensor, same shape as x
# y: labels tensor, shape (batch,) with values 1 or > 1
# lambda_auc: scalar weight for AUC term

batch_size = 2
height = 4
width = 3

x = torch.randn(batch_size, height, width)
x_hat = torch.randn(batch_size, height, width)

# y needs at least one label == 1 and at least one label > 1
# to test the main path with both err_n and err_a non-empty
y = torch.tensor([1, 2])

lambda_auc = 0.5

ARGS = {
    "x": x,
    "x_hat": x_hat,
    "y": y,
    "lambda_auc": lambda_auc,
}
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 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
MSEAUC_approx Ran
ran on a synthesized input
PyLink88/RecAE/graphs/losses/MSEAUCLoss.py
code served (permissive licence) · get_code("be6f61f79637e752")
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 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)

# x: input tensor, shape (batch, height, width)
# x_hat: reconstructed tensor, same shape as x
# y: labels tensor, shape (batch,) with values 1 or >1
# lambda_auc: scalar weight for AUC term

batch_size = 2
height = 4
width = 3

x = torch.randn(batch_size, height, width)
x_hat = torch.randn(batch_size, height, width)

# y needs to have some samples with y==1 and some with y>1
# to trigger the if branch
y = torch.tensor([1, 2])

lambda_auc = 0.5

ARGS = {
    "x": x,
    "x_hat": x_hat,
    "y": y,
    "lambda_auc": lambda_auc
}
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 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
checkpoints_folder Ran
ran on a synthesized input
PyLink88/RecAE/utils/checkpoints.py
code served (permissive licence) · get_code("9cd5486d4616a5a3")
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

class Config:
    def __init__(self, checkpoint_dir, exp_name):
        self.checkpoint_dir = checkpoint_dir
        self.exp_name = exp_name

# Create a temporary directory for checkpoint storage
temp_dir = tempfile.gettempdir()
checkpoint_base = os.path.join(temp_dir, "test_checkpoints_")

config = Config(
    checkpoint_dir=checkpoint_base,
    exp_name="experiment_001"
)

ARGS = {
    "config": config
}
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
get_batch Ran
ran; our contract draft was wrong, not the code
freedombenLiu/RNN-Time-series-Anomaly-Detection/1_train_predictor.py
code served (permissive licence) · get_code("566787f11a729568")
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 tuple, 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 argparse

torch.manual_seed(0)

# Create a minimal args object with required attributes
class Args:
    def __init__(self):
        self.bptt = 5  # backprop through time length

args_obj = Args()

# Create a source tensor (time-series data)
# Shape: (sequence_length,) - 1D tensor of values
source = torch.randn(20)

# Index for batch extraction
i = 0

ARGS = {
    'args': args_obj,
    'source': source,
    'i': i
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 2, 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
get_config_from_json Ran
ran on a synthesized input
PyLink88/RecAE/utils/config.py
code served (permissive licence) · get_code("0eecfc043f408288")
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 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 json
import tempfile
import os
from easydict import EasyDict

# Create a temporary JSON file with valid configuration
temp_dir = tempfile.mkdtemp()
json_file_path = os.path.join(temp_dir, 'config.json')

config_data = {
    'learning_rate': 0.001,
    'batch_size': 32,
    'num_epochs': 10,
    'model': {
        'hidden_size': 256,
        'num_layers': 2
    },
    'dataset': 'cifar10'
}

with open(json_file_path, 'w') as f:
    json.dump(config_data, f)

ARGS = {
    'json_file': json_file_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
easydict — 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 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
process_config Ran
ran on a synthesized input
PyLink88/RecAE/utils/config.py
code served (permissive licence) · get_code("11a203c922b46983")
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 EasyDict. 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 json
import tempfile
import os
from easydict import EasyDict

# Create a temporary JSON config file
temp_dir = tempfile.mkdtemp()
config_file_path = os.path.join(temp_dir, "config.json")

config_data = {
    "exp_name": "test_experiment",
    "model": "resnet50",
    "learning_rate": 0.001,
    "batch_size": 32,
    "epochs": 100
}

with open(config_file_path, 'w') as f:
    json.dump(config_data, f)

ARGS = {
    "json_file": config_file_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
easydict — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EasyDict — a EasyDict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a EasyDict 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
sequences_to_time_series Ran
ran on a synthesized input
flaviagiammarino/encdec-ad-tensorflow/encdec_ad_tensorflow/model.py
code served (permissive licence) · get_code("81150672c807200f")
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 EagerTensor, ndim 2, dtype family float, shape (6, 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 tensorflow as tf
import numpy as np

# The function expects a TensorFlow tensor with shape (batch_size, sequence_length, feature_dim)
# It reshapes it to (batch_size * sequence_length, feature_dim)

# Create a small 3D tensor: (batch=2, sequence=3, features=4)
x = tf.constant(np.random.randn(2, 3, 4).astype(np.float32))

ARGS = {
    'x': x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, tensorflow — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type EagerTensor, ndim 2, dtype family float, shape (6, 4) — shape (6, 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
get_anomaly_scores Not yet run
unverified (harvested, no recorded run)
flaviagiammarino/encdec-ad-tensorflow/encdec_ad_tensorflow/model.py
code served (permissive licence) · get_code("0fd05327039d35fc")
How it ran

no invocation recorded.

time_series_to_sequences Not yet run
unverified (harvested, no recorded run)
flaviagiammarino/encdec-ad-tensorflow/encdec_ad_tensorflow/model.py
code served (permissive licence) · get_code("2cd277ef3cf65386")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 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 8 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
get_batch 1 other paper
1 later
1711.00614 (2017-11)
A Multimodal Anomaly Detector for Robot-Assisted Feeding Using an LSTM-based Variational Autoencoder

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

Mechanical devices such as engines, vehicles, aircrafts, etc., are typically instrumented with numerous sensors to capture the behavior and health of the machine. However, there are often external factors or variables which are not captured by sensors leading to time-series which are inherently unpredictable. For instance, manual controls and/or unmonitored environmental conditions or load may lead to inherently unpredictable time-series. Detecting anomalies in such scenarios becomes challenging using standard approaches based on mathematical models that rely on stationarity, or prediction models that utilize prediction errors to detect anomalies. We propose a Long Short Term Memory Networks based Encoder-Decoder scheme for Anomaly Detection (EncDec-AD) that learns to reconstruct 'normal' time-series behavior, and thereafter uses reconstruction error to detect anomalies. We experiment with three publicly available quasi predictable time-series datasets: power demand, space shuttle, and ECG, and two real-world engine datasets with both predictive and unpredictable behavior. We show that EncDec-AD is robust and can detect anomalies from predictable, unpredictable, periodic, aperiodic, and quasi-periodic time-series. Further, we show that EncDec-AD is able to detect anomalies from short time-series (length as small as 30) as well as long time-series (length as large as 500).

For agents

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

get_harvested_code_for_paper("1607.00148")
get_code_for_paper("1607.00148")
have("1607.00148")

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

curl https://syntology.ai/api/ran/1607.00148.json

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

[![Syntology run record](https://syntology.ai/api/ran/1607.00148.svg)](https://syntology.ai/paper/1607.00148)

Connect an agent — have() is free.