SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2602.03486 · 2026

DeepDFA: Injecting Temporal Logic in Deep Learning for Sequential Subsymbolic Applications

Roberto Capobianco, Elena Umili, Francesco Argenziano

arXiv · PDF · Open in the Atlas

Code that ran

11 of 14 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 10 failures of our instrument; 3 no recorded run), measured 2026-11-21; 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/2602.03486.json · badge: /api/ran/2602.03486.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
KRLGroup/DeepDFAGrounding canonical (classifier label)
classifier basis: census
9 ran · 2 no recorded run
KRLGroup/NeuralRewardMachines community
Papers with Code archive
2 ran · 1 no recorded run
FunctionStatusWhere it lives
ProbabilisticAutoma Ran
ran on a synthesized input · constructed an object; no result was computed
KRLGroup/NeuralRewardMachines/RL/NRM/DeepAutoma.py
pointer only (licence: NONE) · get_code("1472729bb694a181")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KRLGroup/NeuralRewardMachines 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.

create_complete_set_traces_one_true_literal Ran
ran; our contract draft was wrong, not the code
KRLGroup/DeepDFAGrounding/create_dataset.py
pointer only (licence: NONE) · get_code("a4c200f8dd7d5bb5")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KRLGroup/DeepDFAGrounding 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.

create_complete_set_traces_one_true_literal_2 Ran
ran; our contract draft was wrong, not the code
KRLGroup/DeepDFAGrounding/create_dataset.py
pointer only (licence: NONE) · get_code("703bec97007e2772")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KRLGroup/DeepDFAGrounding 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.

create_mask_classifier Ran
ran; our contract draft was wrong, not the code
KRLGroup/DeepDFAGrounding/minimization.py
pointer only (licence: NONE) · get_code("10728c30a581790e")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KRLGroup/DeepDFAGrounding 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.

create_traces_set_one_true_literal_balanced Ran
ran; our contract draft was wrong, not the code
KRLGroup/DeepDFAGrounding/create_dataset.py
pointer only (licence: NONE) · get_code("c61d49927bf735ca")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KRLGroup/DeepDFAGrounding 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.

divide_args_n Ran
ran; our contract draft was wrong, not the code
KRLGroup/DeepDFAGrounding/DeepAutoma.py
pointer only (licence: NONE) · get_code("da98d518c543e5b0")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KRLGroup/DeepDFAGrounding 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.

final_states_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
KRLGroup/DeepDFAGrounding/losses.py
pointer only (licence: NONE) · get_code("62c688922c90223f")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KRLGroup/DeepDFAGrounding 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.

final_states_loss_log Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
KRLGroup/DeepDFAGrounding/losses.py
pointer only (licence: NONE) · get_code("aeb3a805ccbbd597")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KRLGroup/DeepDFAGrounding 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.

not_final_states_loss Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
KRLGroup/DeepDFAGrounding/losses.py
pointer only (licence: NONE) · get_code("bc8c5eb96017b698")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KRLGroup/DeepDFAGrounding 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.

set_seed Ran
ran; our contract draft was wrong, not the code
KRLGroup/DeepDFAGrounding/utils.py
pointer only (licence: NONE) · get_code("7067559cd6cbcff3")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KRLGroup/DeepDFAGrounding 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.

sftmx_with_temp Ran
ran; our contract draft was wrong, not the code
KRLGroup/NeuralRewardMachines/RL/NRM/DeepAutoma.py
pointer only (licence: NONE) · get_code("f4d06a59cfdfe5c9")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KRLGroup/NeuralRewardMachines 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.

eval_acceptance Not yet run
unverified (harvested, no recorded run)
KRLGroup/DeepDFAGrounding/utils.py
pointer only (licence: NONE) · get_code("fbd39e9fb8213265")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KRLGroup/DeepDFAGrounding 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. No invocation recorded.

eval_accuracy Not yet run
unverified (harvested, no recorded run)
KRLGroup/DeepDFAGrounding/utils.py
pointer only (licence: NONE) · get_code("99e1d633cb48cb20")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KRLGroup/DeepDFAGrounding 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. No invocation recorded.

transacc2pythomata Not yet run
unverified (harvested, no recorded run)
KRLGroup/NeuralRewardMachines/RL/NRM/DeepAutoma.py
pointer only (licence: NONE) · get_code("b20f158840390817")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, KRLGroup/NeuralRewardMachines 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. No invocation recorded.

Also present in other papers' code

Of 14 samples lifted from this paper's linked repositories, 14 carry a function identity and 0 do not. Of the 14 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 14 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 2026-11-21.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Integrating logical knowledge into deep neural network training is still a hard challenge, especially for sequential or temporally extended domains involving subsymbolic observations. To address this problem, we propose DeepDFA, a neurosymbolic framework that integrates high-level temporal logic-expressed as Deterministic Finite Automata (DFA) or Moore Machines-into neural architectures. DeepDFA models temporal rules as continuous, differentiable layers, enabling symbolic knowledge injection into subsymbolic domains. We demonstrate how DeepDFA can be used in two key settings: (i) static image sequence classification, and (ii) policy learning in interactive non-Markovian environments. Across extensive experiments, DeepDFA outperforms traditional deep learning models (e.g., LSTMs, GRUs, Transformers) and novel neuro-symbolic systems, achieving stateof-the-art results in temporal knowledge integration. These results highlight the potential of DeepDFA to bridge subsymbolic learning and symbolic reasoning in sequential tasks.

For agents

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

get_harvested_code_for_paper("2602.03486")
get_code_for_paper("2602.03486")
have("2602.03486")

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

curl https://syntology.ai/api/ran/2602.03486.json

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

[![Syntology run record](https://syntology.ai/api/ran/2602.03486.svg)](https://syntology.ai/paper/2602.03486)

Connect an agent — have() is free.