SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2110.03014 · 2021

Active Learning of Markov Decision Processes using Baum-Welch algorithm (Extended)

arXiv · PDF · Open in the Atlas

Code that ran

7 of 8 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 5 have no contract verdict; 1 failure 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/2110.03014.json · badge: /api/ran/2110.03014.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
Rapfff/Learning-Probabilistic-models canonical (classifier label)
classifier basis: classifier_2025
2 ran · 0 no recorded run
rapfff/jajapy community (classifier label)
classifier basis not recorded on the link
5 ran · 1 no recorded run
FunctionStatusWhere it lives
computeProbas Ran
ran, honoured the contract we drafted
Rapfff/Learning-Probabilistic-models/EM_and_BW_algorithms/src/learning/Active_Learning_MDP.py
pointer only (licence: NONE) · get_code("8a0ac0e2a0e0b257")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Rapfff/Learning-Probabilistic-models 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.

folderFromParameters Ran
ran; our contract draft was wrong, not the code
Rapfff/Learning-Probabilistic-models/EM_and_BW_algorithms/experiment/active_vs_passive/huge_experiment.py
pointer only (licence: NONE) · get_code("d6d038cff9ee747d")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, Rapfff/Learning-Probabilistic-models 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.

labelsForRandomModel Ran
ran on a synthesized input
rapfff/jajapy/jajapy/base/Base_MC.py
code served (permissive licence) · get_code("5b0c0c230cf18ef4")
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.

from random import choices, seed

def labelsForRandomModel(nb_states: int, labelling: list, sseed: int=None) -> list:
    if 'init' in labelling:
        msg = "The label 'init' cannot be used: it is reserved for initial states."
        raise SyntaxError(msg)
    if nb_states < len(labelling):
        print('WARNING: the size of the labelling is greater than the', end=' ')
        print('number of states. The last labels will not be assigned to', end=' ')
        print('any states.')
    if nb_states > len(labelling):
        print('WARNING: the size of the labelling is lower than the', end=' ')
        print('number of states. The labels for the last states will', end=' ')
        print('be chosen randomly.')
    if sseed != None:
        seed(sseed)
    labelling = labelling[:min(len(labelling), nb_states)] + choices(labelling, k=nb_states - len(labelling))
    labelling.append('init')
    seed()
    return labelling

ARGS = {
    'nb_states': 5,
    'labelling': ['state_a', 'state_b', 'state_c'],
    'sseed': 42
}
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 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
loadParametricModel Ran
ran on a synthesized input
rapfff/jajapy/jajapy/base/Parametric_Model.py
code served (permissive licence) · get_code("a7ff59c573d8a803")
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
import numpy as np
from io import StringIO

# Create a mock file object that the function will read from
mock_file_content = """test_model
[[1.0, 2.0], [3.0, 4.0]]
{'state_0': 'label_a', 'state_1': 'label_b'}
{'param_1': 0.5, 'param_2': 0.3}
{'param_1': 0, 'param_2': 1}
['param_1', 'param_2']
['x + y', 'x * y + z']
"""

f = StringIO(mock_file_content)

ARGS = {
    'f': f
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, sympy, 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
normalize Ran
ran on a synthesized input
rapfff/jajapy/jajapy/base/tools.py
code served (permissive licence) · get_code("8dbd6f57b0c99afb")
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

# Test with a list of floats
ll_list = [0.5, 1.5, 2.0]

# Test with a 1-D numpy array
ll_array = np.array([0.25, 0.75, 1.0, 0.5])

ARGS = {
    "ll": ll_list
}
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
normpdf Ran
ran on a synthesized input
rapfff/jajapy/jajapy/base/tools.py
code served (permissive licence) · get_code("eb6cb2c5ef1ede24")
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 float64, ndim 0, 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.

from scipy.stats import norm

# Define arguments for normpdf function
x = 0.5
params = [0.0, 1.0]  # mean=0.0, sd=1.0
variation = 0.01

ARGS = {
    "x": x,
    "params": params,
    "variation": variation
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
scipy — 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 — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
resolveRandom Ran
ran on a synthesized input
rapfff/jajapy/jajapy/base/tools.py
code served (permissive licence) · get_code("765918ddb958d369")
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.

from random import random
from numpy import nditer, array, ndarray, nonzero

# The function resolveRandom takes a list of probabilities and returns the index
# of the chosen one according to those probabilities.
# It uses: array(), cumsum(), nonzero(), random(), and list indexing.

# Create a valid probability distribution (sums to 1.0)
probability_list = [0.2, 0.6, 0.15, 0.05]

ARGS = {
    "m": probability_list
}
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
loadSet Not yet run
unverified (harvested, no recorded run)
rapfff/jajapy/jajapy/base/Set.py
code served (permissive licence) · get_code("990aa6763c219705")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 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 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.

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

Cyber-physical systems (CPSs) are naturally modelled as reactive systems with nondeterministic and probabilistic dynamics. Model-based verification techniques have proved effective in the deployment of safety-critical CPSs. Central for a successful application of such techniques is the construction of an accurate formal model for the system. Manual construction can be a resource-demanding and error-prone process, thus motivating the design of automata learning algorithms to synthesise a system model from observed system behaviours. This paper revisits and adapts the classic Baum-Welch algorithm for learning Markov decision processes and Markov chains. For the case of MDPs, which typically demand more observations, we present a model-based active learning sampling strategy that choses examples which are most informative w.r.t.\ the current model hypothesis. We empirically compare our approach with state-of-the-art tools and demonstrate that the proposed active learning procedure can significantly reduce the number of observations required to obtain accurate models.

For agents

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

get_harvested_code_for_paper("2110.03014")
get_code_for_paper("2110.03014")
have("2110.03014")

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

curl https://syntology.ai/api/ran/2110.03014.json

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

[![Syntology run record](https://syntology.ai/api/ran/2110.03014.svg)](https://syntology.ai/paper/2110.03014)

Connect an agent — have() is free.