# Finite-state machine

A finite-state machine is an abstract computational model with a finite set of states and a state-transition function.

This is one page of public article previews, not the complete archive. Follow Next page to continue. Summaries are not the original full articles.

## Evidence-Carrying Contracts for Safe Claim Composition in Data Marketplace Workflows

DevFeed: [Evidence-Carrying Contracts for Safe Claim Composition in Data Marketplace Workflows](<https://devfeed.tech/articles/evidence-carrying-contracts-for-safe-claim-composition-in-data-marketplace-workflows-142148.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.23276>)

Author: Duc-Trung Bui, Phuong-Chi Le, Quyet-Thang Huynh

Published: 2026-11-19T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [audit](<https://devfeed.tech/topics/audit.md>), [Finite-state machine](<https://devfeed.tech/topics/finite-state-machine.md>), [Test-driven development](<https://devfeed.tech/topics/tdd.md>)

Tags: [aggregation](<https://devfeed.tech/tags/aggregation.md>), [api](<https://devfeed.tech/tags/api.md>), [blocking](<https://devfeed.tech/tags/blocking.md>), [completeness](<https://devfeed.tech/tags/completeness.md>), [composition](<https://devfeed.tech/tags/composition.md>), [contracts](<https://devfeed.tech/tags/contracts.md>), [covers](<https://devfeed.tech/tags/covers.md>), [critical](<https://devfeed.tech/tags/critical.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [data](<https://devfeed.tech/tags/data.md>), [data-marketplace](<https://devfeed.tech/tags/data-marketplace.md>), [declarative](<https://devfeed.tech/tags/declarative.md>), [defects](<https://devfeed.tech/tags/defects.md>), [delivery](<https://devfeed.tech/tags/delivery.md>), [dependencies](<https://devfeed.tech/tags/dependencies.md>), [diagnostic](<https://devfeed.tech/tags/diagnostic.md>), [domain](<https://devfeed.tech/tags/domain.md>), [guarantees](<https://devfeed.tech/tags/guarantees.md>), [harness](<https://devfeed.tech/tags/harness.md>), [independent](<https://devfeed.tech/tags/independent.md>), [workflows](<https://devfeed.tech/tags/workflows.md>)

### AI overview

The paper proposes evidence-carrying claim contracts to prevent data marketplace workflows from promoting limited evidence--such as payment, policy presence, or API delivery--into unsupported transaction claims. Contracts declare assumptions, guarantees, blocking obligations, and evidence dependencies; a four-state model tracks requirements as supported, refuted, unresolved, or conflicting. Composition bounds claims by local limits and blocks full promotion while a critical obligation remains open. The authors report executable conformance checks across workflow configurations, revocations, alternative support, and aggregation schedules, plus an independent evaluator that agrees with the declarative oracle. The system preserves a full claim when valid alternative support remains and blocks it when support is absent. The evidence demonstrates conformance to declared contracts, not that the specifications are complete, evidence is authentic, or claims are legally valid.

### Source excerpt

arXiv:2611.23276v1 Announce Type: new Abstract: Data marketplace workflows cross organizational boundaries, where payment, policy presence, or API delivery may be promoted into transaction claims that the evidence does not support. We introduce evidence-carrying claim contracts: a lightweight assume-guarantee semantics declaring assumptions, guarantees, blocking obligations, and evidence dependencies. A conflict-sensitive four-state domain distinguishes supported, refuted, unresolved, and conflicting requirements. Safe composition bounds the transaction claim by the meet of local bounds and blocks full promotion while a critical obligation remains open. We establish local soundness, compositional boundedness, revocation safety, termination, and aggregation-order invariance for finite acyclic workflows. An executable conformance harness covers all 4,096 configurations (four states for each of six stages), 18 mutations, six basic revocations, 12 alternative-support scenarios, an eight-transition evidence trace, 2,880 aggregation schedules, 96 requirement-level and six interface checks. An independent operational evaluator agrees with the declarative oracle; mutation-sensitive campaigns detect all eight seeded defects, though no single campaign detects all. It issues no unsupported full claim, preserves a full claim under valid alternative support, and blocks it when none remains. Four diagnostic negative controls, not competitive baselines, issue 63-1,023 unsupported full claims. These results establish executable conformance to declared contracts, not specification completeness, evidence authenticity, or legal validity.

## Adaptive Wake-on-Radio Communication for Batteryless IoT Systems

DevFeed: [Adaptive Wake-on-Radio Communication for Batteryless IoT Systems](<https://devfeed.tech/articles/adaptive-wake-on-radio-communication-for-batteryless-iot-systems-137035.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.21248>)

Author: Hooman Sarvghadi, Juan Felipe Guti\\'errez G\\'omez, Negar Halakou, Nasrin Razmi, Andr\\'es G\\'omez

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Networking](<https://devfeed.tech/sources/arxiv-networking.md>)

Topics: [communications](<https://devfeed.tech/topics/communications.md>), [Internet of things](<https://devfeed.tech/topics/iot.md>), [Finite-state machine](<https://devfeed.tech/topics/finite-state-machine.md>)

Tags: [adaptive](<https://devfeed.tech/tags/adaptive.md>), [capacitor](<https://devfeed.tech/tags/capacitor.md>), [communication](<https://devfeed.tech/tags/communication.md>), [cs-ni](<https://devfeed.tech/tags/cs-ni.md>), [energy](<https://devfeed.tech/tags/energy.md>), [energy-harvesting](<https://devfeed.tech/tags/energy-harvesting.md>), [experiments](<https://devfeed.tech/tags/experiments.md>), [finite-state-machine](<https://devfeed.tech/tags/finite-state-machine.md>), [hardware](<https://devfeed.tech/tags/hardware.md>), [internet-of-things](<https://devfeed.tech/tags/internet-of-things.md>), [internet-of-things-iot](<https://devfeed.tech/tags/internet-of-things-iot.md>), [iot](<https://devfeed.tech/tags/iot.md>), [low-power](<https://devfeed.tech/tags/low-power.md>), [microcontroller](<https://devfeed.tech/tags/microcontroller.md>), [node](<https://devfeed.tech/tags/node.md>), [packet](<https://devfeed.tech/tags/packet.md>), [power](<https://devfeed.tech/tags/power.md>), [power-consumption](<https://devfeed.tech/tags/power-consumption.md>), [radio](<https://devfeed.tech/tags/radio.md>), [radio-communication](<https://devfeed.tech/tags/radio-communication.md>), [systems](<https://devfeed.tech/tags/systems.md>)

### AI overview

The framework adapts a batteryless IoT node's communication state to stored energy. Two voltage supervisors drive a finite state machine across Shutdown, Low-Power Listening (LPL), Transmit, and Receive modes; the transceiver's integrated Wake-on-Radio avoids additional wake-up hardware. The node combines a photovoltaic harvester, 570 μF capacitor, and microcontroller. At an LPL wake-up rate of 16 Hz, measured power was about 1.2 μW in Shutdown, 300 μW in LPL, 531 μW in Receive, and 627 μW in Transmit under the evaluated traffic conditions. Solar-powered experiments at 1.2 mW harvested input showed bidirectional communication with no packet losses across repeated runs. These results are limited to the reported evaluation conditions.

### Source excerpt

arXiv:2611.21248v1 Announce Type: new Abstract: Batteryless Internet of Things (IoT) systems powered by energy harvesting require communication mechanisms that dynamically adapt to fluctuating energy availability while maintaining ultra-low-power operation. This paper presents a Wake-on-Radio (WoR) communication framework for low-power intermittent IoT systems in which the node's communication state adapts to its stored energy. The framework uses a batteryless IoT node that integrates a photovoltaic harvester, a 570 $\mu$F capacitor, two voltage supervisors, and a microcontroller. The voltage supervisors drive an energy-aware finite state machine that switches the node between Shutdown, Low-Power Listening (LPL), Transmit, and Receive modes. The proposed system employs the integrated WoR capability of the transceiver, eliminating the need for additional wake-up hardware. For the evaluated traffic conditions and an LPL wake-up rate of 16 Hz, the measured power consumption is approximately 1.2 $\mu$W in the Shutdown mode, 300 $\mu$W during LPL, 531 $\mu$W for reception, and 627 $\mu$W for transmission. System-level experiments under solar-harvesting operation validate the proposed framework, demonstrating reliable bidirectional communication with no packet losses observed across repeated runs at a harvested input power of 1.2 mW.

## State-Machine Governance of Adaptive Enforcement: Evidence from a Paired-Scenario Evaluation

DevFeed: [State-Machine Governance of Adaptive Enforcement: Evidence from a Paired-Scenario Evaluation](<https://devfeed.tech/articles/state-machine-governance-of-adaptive-enforcement-evidence-from-a-paired-scenario-evaluation-139306.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.20583>)

Author: Ifeanyi Williams Agbedo, Yanzhen Qu

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>)

Topics: [Finite-state machine](<https://devfeed.tech/topics/finite-state-machine.md>), [ai security](<https://devfeed.tech/topics/ai-security.md>), [synthetic monitoring](<https://devfeed.tech/topics/synthetic-monitoring.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [accountability](<https://devfeed.tech/tags/accountability.md>), [adaptive](<https://devfeed.tech/tags/adaptive.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-assisted](<https://devfeed.tech/tags/ai-assisted.md>), [arm](<https://devfeed.tech/tags/arm.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [audit](<https://devfeed.tech/tags/audit.md>), [authorization](<https://devfeed.tech/tags/authorization.md>), [but](<https://devfeed.tech/tags/but.md>), [can](<https://devfeed.tech/tags/can.md>), [capability](<https://devfeed.tech/tags/capability.md>), [changes](<https://devfeed.tech/tags/changes.md>), [completeness](<https://devfeed.tech/tags/completeness.md>), [components](<https://devfeed.tech/tags/components.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [governance](<https://devfeed.tech/tags/governance.md>), [machine](<https://devfeed.tech/tags/machine.md>), [state](<https://devfeed.tech/tags/state.md>), [state-machine](<https://devfeed.tech/tags/state-machine.md>)

### AI overview

In 36 matched scripted scenarios with deterministic vendor-connector simulations, ZTGuard's state-machine-governed transition procedure scored higher on the study's Control measure than the operator-driven baseline: mean 0.972 (SD 0.131) versus 0.720 (SD 0.218). Control equally weighted traceability, accountability, audit-chain completeness, and reliable rollback. A paired Wilcoxon test found a difference (V = 359, p < .001); 26 pairs favored the governed procedure, nine tied, and one favored baseline. The results support utility in this controlled evaluation, not production readiness. The authors cite purposive sampling, scripted operators, simulated connectors, overlapping components, and arm-specific scoring rules as limitations.

### Source excerpt

arXiv:2611.20583v1 Announce Type: new Abstract: AI-assisted security systems can recommend rapid policy changes, but governing their execution requires explicit authorization, evidence, and recovery rules. This study evaluated a machine-verifiable, state-machine-governed transition procedure implemented in ZTGuard using 36 matched scripted scenarios and deterministic vendor-connector simulations. Each pair held the starting state, telemetry, AI recommendation, and scheduled vendor condition constant. The sole dependent variable, Control, was the equal-weight mean of traceability, accountability, audit-chain completeness, and reliable rollback capability. Mean Control was 0.720 (SD = 0.218) for the scripted operator-driven baseline and 0.972 (SD = 0.131) for the governed procedure. A two-tailed paired Wilcoxon signed-rank test yielded V = 359, p < .001, with a matched-pairs rank-biserial correlation of .899. Twenty-six pairs favored treatment, nine were tied, and one favored baseline. The findings support controlled artifact utility, not production readiness. Interpretation is limited by purposive sampling, scripted operators, simulated connectors, overlapping components, and arm-specific scoring rules.

## Differentiable Exact Learning

DevFeed: [Differentiable Exact Learning](<https://devfeed.tech/articles/differentiable-exact-learning-137707.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.21486>)

Author: Hristo Papazov, Francesco D'Angelo, Nicolas Flammarion

Published: 2026-11-17T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Finite-state machine](<https://devfeed.tech/topics/finite-state-machine.md>), [Neural Network](<https://devfeed.tech/topics/neural-network.md>), [generalization in machine learning](<https://devfeed.tech/topics/generalization-in-machine-learning.md>), [Training AI Models](<https://devfeed.tech/topics/training-ai-models.md>)

Tags: [algorithms](<https://devfeed.tech/tags/algorithms.md>), [arithmetic](<https://devfeed.tech/tags/arithmetic.md>), [controller](<https://devfeed.tech/tags/controller.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-fl](<https://devfeed.tech/tags/cs-fl.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [environment](<https://devfeed.tech/tags/environment.md>), [finite-state](<https://devfeed.tech/tags/finite-state.md>), [learning](<https://devfeed.tech/tags/learning.md>), [machine](<https://devfeed.tech/tags/machine.md>), [protocol](<https://devfeed.tech/tags/protocol.md>), [replicate](<https://devfeed.tech/tags/replicate.md>), [simulation](<https://devfeed.tech/tags/simulation.md>), [stat-ml](<https://devfeed.tech/tags/stat-ml.md>), [state](<https://devfeed.tech/tags/state.md>), [target](<https://devfeed.tech/tags/target.md>), [traces](<https://devfeed.tech/tags/traces.md>), [tracking](<https://devfeed.tech/tags/tracking.md>), [train](<https://devfeed.tech/tags/train.md>), [training](<https://devfeed.tech/tags/training.md>), [universality](<https://devfeed.tech/tags/universality.md>)

### AI overview

The paper's approach combines a state-tracking controller, an unbounded external environment, and policy-trajectory observations (expert traces showing observations and actions but hiding internal states) to learn controllers that generalize to much longer tasks. Its Differentiable Finite-State Transducers (DFSTs) use multilinear updates, allow log-parallel training, and can emulate arbitrary finite-state controllers. Compact DFSTs trained on tiny datasets show extreme length generalization on arithmetic and universal simulation; the authors report similar results with RNNs and GRUs. They also extract interpretable discrete controllers from trained DFSTs and prove them equivalent to the target algorithms. For Softmax DFSTs, taking the argmax of transition probabilities yields controllers that provably perform binary arithmetic and universal Turing-machine simulation exactly. Exact-learning proofs for neural controllers require assumptions, which the authors say are empirically supported.

### Source excerpt

arXiv:2611.21486v1 Announce Type: cross Abstract: We introduce a framework for differentiable exact learning that couples an unbounded external environment to a state-tracking neural controller, which we train on policy-trajectory observations (PTOs): expert behavior traces that expose observations and actions while hiding internal states. In addition to the learning framework, we introduce Differentiable Finite-State Transducers (DFSTs) which use multilinear updates, support log-parallel training, and emulate arbitrary finite-state controllers, yielding computational universality through environmental interaction. From tiny training datasets, compact DFSTs achieve extreme length generalization on arithmetic and universal-simulation tasks. We replicate the success of DFSTs on RNNs and GRUs, thereby supporting a broader learning recipe: State-Tracking Controller + Unbounded External Environment + PTOs = Extreme Length Generalization. Beyond length generalization, our metric-extraction protocol recovers interpretable discrete controllers from trained DFSTs, which we prove equivalent to the target arithmetic and universal-simulation algorithms. Furthermore, for our Softmax DFST models, simply taking $\mathrm{argmax}$ over the transition probabilities yields discrete controllers which provably exactly perform universal Turing-machine simulation and binary arithmetic. Proving exact learning for the neural controllers requires assumptions, which we empirically support. We make our code, training recipes, model weights, and proof checkers publicly available at https://github.com/fanagor/DEL.

## Automata from Agent Traces: Failure and Next-Step Prediction

DevFeed: [Automata from Agent Traces: Failure and Next-Step Prediction](<https://devfeed.tech/articles/automata-from-agent-traces-failure-and-next-step-prediction-131960.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2608.23670>)

Author: Seonglae Cho, Franklin Cardenoso Fernandez, Umar Mohammed, Zekun Wu, Kleyton Da Costa, Ilham Wicaksono, Adriano Koshiyama

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Finite-state machine](<https://devfeed.tech/topics/finite-state-machine.md>), [agent observability](<https://devfeed.tech/topics/agent-observability.md>), [LLM observability](<https://devfeed.tech/topics/llm-observability.md>), [Multi-step AI processes](<https://devfeed.tech/topics/multi-step-ai-processes.md>)

Tags: [agent](<https://devfeed.tech/tags/agent.md>), [auditing](<https://devfeed.tech/tags/auditing.md>), [behavior](<https://devfeed.tech/tags/behavior.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-cl](<https://devfeed.tech/tags/cs-cl.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [datasets](<https://devfeed.tech/tags/datasets.md>), [deployment](<https://devfeed.tech/tags/deployment.md>), [failure](<https://devfeed.tech/tags/failure.md>), [finite-state](<https://devfeed.tech/tags/finite-state.md>), [finite-state-machine](<https://devfeed.tech/tags/finite-state-machine.md>), [model-agnostic](<https://devfeed.tech/tags/model-agnostic.md>), [monitor](<https://devfeed.tech/tags/monitor.md>), [monitoring](<https://devfeed.tech/tags/monitoring.md>), [next](<https://devfeed.tech/tags/next.md>), [prediction](<https://devfeed.tech/tags/prediction.md>), [runtime-monitoring](<https://devfeed.tech/tags/runtime-monitoring.md>), [safety](<https://devfeed.tech/tags/safety.md>), [structure](<https://devfeed.tech/tags/structure.md>), [topology](<https://devfeed.tech/tags/topology.md>), [traces](<https://devfeed.tech/tags/traces.md>)

### AI overview

The paper compresses agent trace corpora into compact finite-state machines (FSMs) to support both next-step and failure prediction. Across twelve public datasets, the FSMs had 7-43 states, replayed held-out traces with at least 0.997 fitness, showed near-identical topology across splits, and built in milliseconds. FSM-state context outperformed Agent Workflow Memory on every dataset with matched ground truth. Per-state behavioral features reached held-out AUROC up to 0.94; an online monitor ranked failing runs above passing ones using partial traces and could trigger early stopping. The authors report that behavioral topology appears more shaped by the deployment harness than by the LLM. These findings suggest a model-agnostic structure for auditing and runtime monitoring; the supplied abstract does not provide implementation details or broader evaluation limits.

### Source excerpt

arXiv:2608.23670v2 Announce Type: replace Abstract: LLM-based agents execute multi-step tasks, but their behavioral structure remains opaque: long unstructured traces resist the safety auditing and runtime monitoring that deployment requires. Existing approaches operate per-trace or success-only, so they miss the cross-run topology that links next-step and failure prediction. To recover that shared structure, we collapse an entire trace corpus into a single, compact finite-state machine (FSM) that serves as a structural substrate for the otherwise unpredictable behavior of LLM agents. Across twelve public datasets, the FSMs are compact (7-43 states), replay held-out data at >=0.997 fitness with near-identical topology across splits, and build in milliseconds. This substrate addresses both prediction goals. For next-step prediction, FSM-state context outperforms Agent Workflow Memory on every ground-truth-matched dataset. For failure prediction, per-state behavioral features reach held-out AUROC up to 0.94, and an online monitor ranks failing runs above passing ones from a partial trace, triggering early stopping well before completion. Behavioral topology thus appears shaped more by the deployment harness than by the LLM, providing a model-agnostic structural primitive for safety auditing and runtime monitoring.

## Al-Ghasali: A Computational Framework for Simulating Islamic Jurisprudential Rulings via Finite State Automata and Large Language Models

DevFeed: [Al-Ghasali: A Computational Framework for Simulating Islamic Jurisprudential Rulings via Finite State Automata and Large Language Models](<https://devfeed.tech/articles/al-ghasali-a-computational-framework-for-simulating-islamic-jurisprudential-rulings-via-finite-state-automata-and-large-language-models-132323.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.17235>)

Author: Elnaserledinellah Mahmoud Abdelwahab

Published: 2026-11-13T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Finite-state machine](<https://devfeed.tech/topics/finite-state-machine.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Hallucination detection](<https://devfeed.tech/topics/hallucination-detection.md>)

Tags: [architecture](<https://devfeed.tech/tags/architecture.md>), [compilation](<https://devfeed.tech/tags/compilation.md>), [complexity](<https://devfeed.tech/tags/complexity.md>), [controls](<https://devfeed.tech/tags/controls.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-fl](<https://devfeed.tech/tags/cs-fl.md>), [decidability](<https://devfeed.tech/tags/decidability.md>), [decoding](<https://devfeed.tech/tags/decoding.md>), [define](<https://devfeed.tech/tags/define.md>), [design](<https://devfeed.tech/tags/design.md>), [finite-state](<https://devfeed.tech/tags/finite-state.md>), [framework](<https://devfeed.tech/tags/framework.md>), [grammar](<https://devfeed.tech/tags/grammar.md>), [guarantees](<https://devfeed.tech/tags/guarantees.md>), [hierarchy](<https://devfeed.tech/tags/hierarchy.md>), [history](<https://devfeed.tech/tags/history.md>), [integration](<https://devfeed.tech/tags/integration.md>), [language-models](<https://devfeed.tech/tags/language-models.md>), [large-language-models](<https://devfeed.tech/tags/large-language-models.md>), [large-language-models-llms](<https://devfeed.tech/tags/large-language-models-llms.md>), [linear](<https://devfeed.tech/tags/linear.md>), [llm](<https://devfeed.tech/tags/llm.md>)

### AI overview

Al-Ghasali models closed Islamic jurisprudential chapters as deterministic finite state automata compiled from finite propositional Horn theories. The paper states this makes verdict extraction decidable and O(1) after compilation, including for hierarchical compositions; requirements such as Tartib are encoded as static states. For readable summaries, the FSA controls the LLM, whose output is constrained by a grammar built from the automaton's execution history, a bounded neutral lexicon, and valence locking. The authors claim these safeguards rule out decisional and juristic factual hallucination and semantic inversion. The supplied text is an abstract and does not provide implementation or empirical evaluation details.

### Source excerpt

arXiv:2611.17235v1 Announce Type: new Abstract: This paper presents Al Ghasali, a computational framework designed to formalize and simulate Islamic jurisprudential (Fiqh) rulings. Building upon recent set theoretic formalizations of al sabr wa al Taqsim that extract minimal operational rules as simple Horn clause logical programs, this work proves that the semantics of closed Fiqh chapters collapse completely to deterministic Finite State Automata (FSA). We establish a formal computational hierarchy, demonstrating that restricting formalization to finite propositional Horn theories guarantees decidability and constant time (O(1)) verdict extraction after offline compilation. The framework formally proves that hierarchical compositions of sub-chapter FSAs preserve this O(1) complexity, and that temporal juristic requirements, such as Tartib (order), are deterministically flattened into static ontological states, preserving the memoryless property of the automaton. To generate human-readable juristic summaries, Al Ghasali incorporates Large Language Models (LLMs) via an architecture where the deterministic FSA strictly controls the probabilistic LLM. Crucially, the paper formulates sufficient design safety conditions for this FSA LLM integration, ensuring strict adherence to the epistemological boundaries of Usul al Fiqh. To neutralize the risk of LLM hallucination, the system employs a Grammar Guided Constrained Decoding mechanism. We formally define the mapping function that dynamically constructs unambiguous right linear grammars from the FSA execution history. The paper mathematically proves that this architecture, augmented by a Bounded Neutral Lexicon and Valence Locking, guarantees the absolute absence of Decisional Hallucination, Juristic Factual Hallucination, and Semantic Inversion reducing the LLM to a pure linguistic transformer of deterministic juristic facts

## Factor Rank: A Canonical Algebraic Generalization of Tree Decision Diagrams

DevFeed: [Factor Rank: A Canonical Algebraic Generalization of Tree Decision Diagrams](<https://devfeed.tech/articles/factor-rank-a-canonical-algebraic-generalization-of-tree-decision-diagrams-126026.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.10842>)

Author: Alexis de Colnet, Stefan Szeider

Published: 2026-11-10T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Finite-state machine](<https://devfeed.tech/topics/finite-state-machine.md>), [Representation learning](<https://devfeed.tech/topics/representation-learning.md>)

Tags: [boolean](<https://devfeed.tech/tags/boolean.md>), [canonical](<https://devfeed.tech/tags/canonical.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lo](<https://devfeed.tech/tags/cs-lo.md>), [decision](<https://devfeed.tech/tags/decision.md>), [equivalence-checking](<https://devfeed.tech/tags/equivalence-checking.md>), [factor](<https://devfeed.tech/tags/factor.md>), [lean](<https://devfeed.tech/tags/lean.md>), [linear](<https://devfeed.tech/tags/linear.md>), [matrix](<https://devfeed.tech/tags/matrix.md>), [rank](<https://devfeed.tech/tags/rank.md>)

### AI overview

Algebraic tree decision diagrams (ATDDs) replace TDD width, which counts distinct subfunctions at each vtree cut, with the rank of a cut matrix. Their maximum cut rank is the factor rank and equals ATDD width; every TDD converts to an ATDD of no greater width. The abstract claims ATDDs are exponentially more succinct than TDDs and quasi-polynomially more succinct than structured deterministic DNNFs, while providing a unique canonical representation for each Boolean function and vtree over the rationals, without genericity assumptions. This enables polynomial-time validation from tensors and equivalence checking by syntactic equality. Stated operations include model counting, weighted model counting, and testing whether a tree tensor network represents a Boolean function. A single-node vtree rotation changes only two ATDD tensors, and vtree changes are output-polynomial for both TDDs and ATDDs. Core results were formalized in Lean; prototype compilers provide initial empirical validation.

### Source excerpt

arXiv:2611.10842v1 Announce Type: new Abstract: Tree decision diagrams (TDDs), recently introduced by Capelli et al. (SAT 2026), are representations of Boolean functions. They generalize OBDDs by replacing variable orders with vtrees. The width of a TDD counts the distinct subfunctions across each vtree cut. Counting subfunctions is blind to linear structure. We introduce algebraic tree decision diagrams (ATDDs) by replacing this count with the rank of the cut matrix. The maximum of these ranks over all cuts, the factor rank, is exactly the width of the ATDD. Every TDD can be converted into an ATDD of no greater width. An ATDD is a tree tensor network in canonical form. ATDDs are exponentially more succinct than TDDs, and quasi-polynomially more succinct than structured deterministic DNNFs. Our main result is that this gain in succinctness does not cost canonicity. ATDDs are the first strict canonical form for a rank-based representation over arbitrary vtrees. For each function and vtree there is exactly one ATDD, over the rationals and without any genericity assumption. The canonicity admits a local characterization. Whether a tree tensor network is the ATDD of the Boolean function it computes can be checked in polynomial time from its tensors alone. Equivalence checking becomes a test of syntactic equality. The operation set includes polynomial-time model counting, weighted model counting, and a test whether a tree tensor network represents a Boolean function. Capelli et al. asked for the complexity of changing the vtree of a TDD and suggested local vtree changes. We answer the question. After a rotation of the vtree at one node, the new ATDD differs from the old one in two tensors only. Vtree change runs in output-polynomial time both for TDDs and for ATDDs. We formalize and verify our core results in Lean. We provide a prototype implementation of TDD and ATDD compilers as a first empirical validation.

## Keeping LLM Agents on Procedure: Executable Finite-State Control for Long-Horizon Instruction Fidelity

DevFeed: [Keeping LLM Agents on Procedure: Executable Finite-State Control for Long-Horizon Instruction Fidelity](<https://devfeed.tech/articles/keeping-llm-agents-on-procedure-executable-finite-state-control-for-long-horizon-instruction-fidelity-126036.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.10884>)

Author: Yutao Sun, Haokun Li, Mingshuai Chen, Guanyan Li, Zhongyi Wang, Shengchao Qin, Jianwei Yin

Published: 2026-11-10T05:00:00Z

Content type: news

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Finite-state machine](<https://devfeed.tech/topics/finite-state-machine.md>), [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [automation](<https://devfeed.tech/tags/automation.md>), [control](<https://devfeed.tech/tags/control.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [finite-state](<https://devfeed.tech/tags/finite-state.md>), [finite-state-machine](<https://devfeed.tech/tags/finite-state-machine.md>), [horizon](<https://devfeed.tech/tags/horizon.md>), [instructions](<https://devfeed.tech/tags/instructions.md>), [language-model](<https://devfeed.tech/tags/language-model.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-agents](<https://devfeed.tech/tags/llm-agents.md>), [procedural](<https://devfeed.tech/tags/procedural.md>), [reliability](<https://devfeed.tech/tags/reliability.md>), [runtime](<https://devfeed.tech/tags/runtime.md>), [small-models](<https://devfeed.tech/tags/small-models.md>), [state](<https://devfeed.tech/tags/state.md>), [state-machine](<https://devfeed.tech/tags/state-machine.md>), [study](<https://devfeed.tech/tags/study.md>), [swe-bench](<https://devfeed.tech/tags/swe-bench.md>), [tool](<https://devfeed.tech/tags/tool.md>), [work](<https://devfeed.tech/tags/work.md>)

### AI overview

The study reports that long-running LLM agents can drift from an SOP even when instructions are restated or a stopped run is resumed. Its executable finite-state machine stores workflow state outside the model context and enforces procedure at tool calls, state transitions, and turn endings. In preregistered 200-account SOP-Bench batches, Claude Haiku 4.5 with the FSM averaged 139 correct, procedure-following decisions versus 48 for the strongest baseline (95% CI for the difference: 46-130), maintaining its rate through the run. Across three models, gains tracked the amount of drift in plain agents. Haiku 4.5 with the FSM also averaged more such decisions than plain Claude Sonnet 4.6 at 38% of the cost. Additional analyses on SWE-bench Verified, τ²-bench, and staged and cross-context workflows are described as further evidence for execution control; details are not included in the supplied abstract.

### Source excerpt

arXiv:2611.10884v1 Announce Type: new Abstract: Much of the automation handed to language-model agents is procedural: each step needs little intelligence, but a long unattended run must follow a skill or SOP stated once at the start. We show that agents drift from such procedures over long runs, and that restating the instructions or resuming a stopped agent only moves the drift to another shortcut. We study an executable finite-state machine (FSM) that keeps the workflow state outside the model's context and enforces it at three points: tool calls, state transitions and the end of the agent's turn. In a pre-registered experiment on 200-account SOP-Bench batches, Claude Haiku 4.5 with the FSM decided on average 139 accounts correctly and by the procedure, against 48 for the strongest baseline (95% CI of the difference [46, 130]), and kept this rate to the end; across three models, the gain tracked how much the plain agent drifted. Because the runtime, not the model, supplies this long-horizon reliability, the FSM can let small models carry procedural work: Haiku 4.5 with it averaged more such decisions than plain Claude Sonnet 4.6 at 38% of the cost. Analyses on SWE-bench Verified, $\tau^2$-bench, and staged and cross-context workflows further suggest that reliable long-horizon automation can come from stronger execution control, not only stronger models.

## StockASkill: A Local-First AgentSkill for Intelligent Stock Selection

DevFeed: [StockASkill: A Local-First AgentSkill for Intelligent Stock Selection](<https://devfeed.tech/articles/stockaskill-a-local-first-agentskill-for-intelligent-stock-selection-124696.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.09528>)

Author: Xiangjing An, Zhibin Jiao, Aiting Chen

Published: 2026-11-09T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [AI Integration Strategies](<https://devfeed.tech/topics/ai-integration-strategies.md>), [Local AI](<https://devfeed.tech/topics/local-ai.md>), [Combinatorial optimization](<https://devfeed.tech/topics/combinatorial-optimization.md>), [Finite-state machine](<https://devfeed.tech/topics/finite-state-machine.md>)

Tags: [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [alpha](<https://devfeed.tech/tags/alpha.md>), [api](<https://devfeed.tech/tags/api.md>), [bias](<https://devfeed.tech/tags/bias.md>), [board](<https://devfeed.tech/tags/board.md>), [bottlenecks](<https://devfeed.tech/tags/bottlenecks.md>), [capital](<https://devfeed.tech/tags/capital.md>), [china](<https://devfeed.tech/tags/china.md>), [columnar](<https://devfeed.tech/tags/columnar.md>), [convex](<https://devfeed.tech/tags/convex.md>), [cross](<https://devfeed.tech/tags/cross.md>), [cross-border](<https://devfeed.tech/tags/cross-border.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [data](<https://devfeed.tech/tags/data.md>), [data-driven](<https://devfeed.tech/tags/data-driven.md>), [dependencies](<https://devfeed.tech/tags/dependencies.md>), [local-first](<https://devfeed.tech/tags/local-first.md>), [selection](<https://devfeed.tech/tags/selection.md>), [stock](<https://devfeed.tech/tags/stock.md>)

### AI overview

StockASkill is a local-first quantitative stock-selection tool built around DuckDB, with historical prices and financial disclosures covering China A-shares, Hong Kong, US equities, and ETFs. The abstract reports that screening more than 5,400 equities takes under 0.5 seconds, down from over 25 seconds, without ad-hoc network dependencies during analysis. Its pipeline combines a 7+1 factor model, an SLSQP optimizer using smooth CVaR drawdown surrogates and exact path projection, 100-share lot quantization, and a thesis lifecycle state machine. A zero-disk, typed JSON streaming interface supports LLM tool-calling. Reported 2018-2024 benchmarks include annualized Sharpe ratios above 1.48, Calmar ratios up to 2.17, and maximum drawdown reductions up to 85% versus benchmark indices. These are claims from the supplied abstract; the excerpt does not provide benchmark methodology or further validation details.

### Source excerpt

arXiv:2611.09528v1 Announce Type: new Abstract: Quantitative equity selection and portfolio construction in emerging and cross-border markets frequently suffer from computational bottlenecks, remote API fragility, survivorship bias, and rigid execution constraints such as discrete board lots and investor-mandated drawdown limits. In this paper, we present StockASkill, a local-first, full-data-driven AgentSkill engineered as a specialized Quant Co-Processor for autonomous AI agents and quantitative researchers. Tailored for agile portfolios (10^5 ~ 10^7 RMB) where discrete lot execution and capital protection are mandatory, StockASkill embeds a columnar DuckDB OLAP engine over 42.44 million historical price records and 186,432 financial disclosures spanning 26 years across China A-shares, Hong Kong, US equities, and ETFs. By eliminating ad-hoc network dependencies during analysis, StockASkill reduces cross-sectional screening latency across 5,400+ equities from over 25 seconds to sub-0.5 seconds (a 95%+ reduction). We formalize an end-to-end mathematical pipeline integrating a 7+1 factor alpha model, an SLSQP convex optimizer under smooth CVaR drawdown surrogates with exact path projection, dynamic 100-share board lot integer quantization, and an autonomous thesis lifecycle finite-state machine. Furthermore, we provide a zero-disk, strongly-typed JSON streaming interface designed for high-throughput LLM tool-calling. Open-sourced at https://github.com/axjing/stockaskill, comprehensive empirical benchmarks from 2018 to 2024 demonstrate that the architecture achieves annualized Sharpe ratios exceeding 1.48 and Calmar ratios up to 2.17, while reducing max drawdown by up to 85% relative to benchmark indices.

## Fast and General Automatic Differentiation for Finite-State Methods

DevFeed: [Fast and General Automatic Differentiation for Finite-State Methods](<https://devfeed.tech/articles/fast-and-general-automatic-differentiation-for-finite-state-methods-124377.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2602.12300>)

Author: Lucas Ondel Yang (LISN, CNRS), Caio Corro (INSA Rennes, IRISA, ARCHIMEDIA), Nicolas Denier (LISN), Martin Kocour (FIT / BUT, BUT), Tina Raissi (RWTH Aachen), Pablo Riera (ICC)

Published: 2026-11-09T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Finite-state machine](<https://devfeed.tech/topics/finite-state-machine.md>)

Tags: [algorithm](<https://devfeed.tech/tags/algorithm.md>), [algorithms](<https://devfeed.tech/tags/algorithms.md>), [automatic](<https://devfeed.tech/tags/automatic.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-fl](<https://devfeed.tech/tags/cs-fl.md>), [dynamic-programming](<https://devfeed.tech/tags/dynamic-programming.md>), [fast](<https://devfeed.tech/tags/fast.md>), [faster](<https://devfeed.tech/tags/faster.md>), [function](<https://devfeed.tech/tags/function.md>), [general](<https://devfeed.tech/tags/general.md>), [gradient](<https://devfeed.tech/tags/gradient.md>), [library](<https://devfeed.tech/tags/library.md>), [license](<https://devfeed.tech/tags/license.md>), [magnitude](<https://devfeed.tech/tags/magnitude.md>), [novel](<https://devfeed.tech/tags/novel.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [orders](<https://devfeed.tech/tags/orders.md>), [programming](<https://devfeed.tech/tags/programming.md>), [state](<https://devfeed.tech/tags/state.md>)

### AI overview

The "morphism-trick" integrates custom vector-Jacobian products into automatic differentiation for a wide range of semiring-based computations, enabling efficient, semiring-agnostic backward passes for dynamic programming. For finite-state methods, the authors introduce an algorithm to compute and differentiate the ⊕-sum of all path weights in a finite-state automaton. They report that their library computes gradients with respect to automaton weights orders of magnitude faster than state-of-the-art automatic differentiation systems, with minimal user effort. The implementations are released as open-source under a permissive license.

### Source excerpt

arXiv:2602.12300v2 Announce Type: replace-cross Abstract: We propose a new method, that we coined the ``morphism-trick'', to integrate custom implementations of vector-Jacobian products in automatic differentiation softwares, applicable to a wide range of semiring-based computations. Our approach leads to efficient and semiring-agnostic implementations of the backward pass of dynamic programming algorithms. For the particular case of finite-state methods, we introduce an algorithm that computes and differentiates the $\oplus$-sum of all paths' weight of a finite-state automaton. Results show that, with minimal effort from the user, our novel library allows computing the gradient of a function w.r.t. to the weights of a finite state automaton orders of magnitude faster than state-of-the-art automatic differentiation systems. Implementations are made available via an open-source library distributed under a permissive license.

## Why AI Agents Need State Machines to Coordinate Humans

DevFeed: [Why AI Agents Need State Machines to Coordinate Humans](<https://devfeed.tech/articles/why-ai-agents-need-state-machines-to-coordinate-humans-116248.md>)

Original publisher: [Read original article](<https://hackernoon.com/why-ai-agents-need-state-machines-to-coordinate-humans?source=rss>)

Author: Akshay Panchavati

Published: 2026-11-04T07:42:10Z

Content type: article

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [Finite-state machine](<https://devfeed.tech/topics/finite-state-machine.md>), [human in the loop agent](<https://devfeed.tech/topics/human-in-the-loop-agent.md>), [state-management](<https://devfeed.tech/topics/state-management.md>), [Persistence](<https://devfeed.tech/topics/persistence.md>), [Artificial Intelligence](<https://devfeed.tech/topics/ai.md>)

Tags: [agentic-ai-architecture](<https://devfeed.tech/tags/agentic-ai-architecture.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agent-architecture](<https://devfeed.tech/tags/ai-agent-architecture.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [autonomous-ai-agents](<https://devfeed.tech/tags/autonomous-ai-agents.md>), [dispatch](<https://devfeed.tech/tags/dispatch.md>), [finite-state-machine](<https://devfeed.tech/tags/finite-state-machine.md>), [human-in-the-loop](<https://devfeed.tech/tags/human-in-the-loop.md>), [llm](<https://devfeed.tech/tags/llm.md>), [proptech](<https://devfeed.tech/tags/proptech.md>), [state-machines](<https://devfeed.tech/tags/state-machines.md>)

### AI overview

For coordinating a tenant, plumber, and landlord who may reply late or change their minds, the article recommends a deterministic finite state machine (FSM) that stores job state in a database and controls transitions and actions. The LLM translates incoming messages into defined inputs, including `UNCLEAR`, and renders code-determined messages in natural language; it does not decide the next step or own the workflow state. This keeps approvals, scheduling, and follow-ups governed by readable rules even when human replies are delayed or ambiguous. The excerpt describes the design and a leaking-sink scenario, but does not specify the nine states or detail the surrounding structures for handling unreliable human inputs.

### Source excerpt

Most human-in-the-loop designs assume the human is an employee. Here is an FSM design where an LLM coordinates tenants, contractors, and landlords instead.

## Retrain, Alert, or Rollback? A Three-Response Decision Framework for Production ML Under Concept Drift

DevFeed: [Retrain, Alert, or Rollback? A Three-Response Decision Framework for Production ML Under Concept Drift](<https://devfeed.tech/articles/retrain-alert-or-rollback-a-three-response-decision-framework-for-production-ml-under-concept-drift-113521.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.02251>)

Author: Ali Sadeghian, Alireza Shafaei, Hamid Hadibeik, Babak Hossein Khalaj

Published: 2026-11-03T05:00:00Z

Content type: comparison

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>), [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [Model Development](<https://devfeed.tech/topics/model-development.md>), [model-deployment](<https://devfeed.tech/topics/model-deployment.md>), [Finite-state machine](<https://devfeed.tech/topics/finite-state-machine.md>), [Deployment Strategies](<https://devfeed.tech/topics/deployment-strategies.md>)

Tags: [alert](<https://devfeed.tech/tags/alert.md>), [availability](<https://devfeed.tech/tags/availability.md>), [canary](<https://devfeed.tech/tags/canary.md>), [concept-drift](<https://devfeed.tech/tags/concept-drift.md>), [cost](<https://devfeed.tech/tags/cost.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [detection](<https://devfeed.tech/tags/detection.md>), [framework](<https://devfeed.tech/tags/framework.md>), [harness](<https://devfeed.tech/tags/harness.md>), [latency](<https://devfeed.tech/tags/latency.md>), [ml](<https://devfeed.tech/tags/ml.md>), [model](<https://devfeed.tech/tags/model.md>), [monitor](<https://devfeed.tech/tags/monitor.md>), [operator](<https://devfeed.tech/tags/operator.md>), [policy](<https://devfeed.tech/tags/policy.md>), [production](<https://devfeed.tech/tags/production.md>), [production-ml](<https://devfeed.tech/tags/production-ml.md>), [promotion](<https://devfeed.tech/tags/promotion.md>), [protocol](<https://devfeed.tech/tags/protocol.md>), [quality](<https://devfeed.tech/tags/quality.md>), [rollback](<https://devfeed.tech/tags/rollback.md>)

### AI overview

RAR frames production drift response as a choice among retraining, alerting and monitoring, or rollback, with explicit triggers and costs. Retraining requires detected drift, available labels, and measured degradation; candidates must pass a two-stage canary, while corruption and quality rollbacks lead to separate hold states. In comparisons across 13 streams and six baselines, RAR did not dominate: retrain-heavy policies led when retraining was cheap, while at higher costs RAR beat detector-triggered retraining, periodic retraining, and no response on four streams within bounded cost windows. Results versus a cost-aware policy were mixed, and RAR had lower net utility on most semi-synthetic streams. Removing the canary increased utility on 11 of 13 streams at ρ=1. The abstract reports a post-hoc case where cause-specific hold release resumed adaptation when a single cooldown did not.

### Source excerpt

arXiv:2611.02251v1 Announce Type: cross Abstract: When a deployed model degrades under concept drift, an operator can retrain it, raise an alert and monitor, or roll back. Yet most drift-adaptation methods consider only retraining. We present RAR (Retrain-Alert-Rollback), a state machine that gives each response an explicit trigger and cost. Retraining is gated on drift detection, label availability, and measured degradation. Every retrained model must pass a two-stage canary before promotion, and corruption-triggered and quality-triggered rollbacks enter different hold states. Under a prospectively specified protocol we compare RAR with six baselines, including a cost-aware retraining policy, on 13 streams: eight real public streams and five semi-synthetic streams derived from them. RAR does not dominate. At low retraining cost, retrain-heavy baselines lead, and no policy's rank differs significantly from RAR's. At higher cost, RAR beats detector-triggered retraining, periodic retraining, and no response simultaneously on four streams, each within a bounded cost window. Its advantage over detector-triggered retraining is consistent with a latency-feasibility condition stated in advance. Against the cost-aware policy, results are heterogeneous. RAR retrains before true drift onsets one eighth to one third as often as detector-triggered retraining, but at lower net utility on most semi-synthetic streams. On H2's designated corruption stream (a registered follow-up), rollbacks fire yet RAR loses to retraining baselines. At $\rho = 1$, removing the canary, and thus rollback, raises utility on 11 of 13 streams. On a post-hoc follow-up stream, cause-specific hold release resumes adaptation where a single cooldown does not. We provide the harness, configurations, and per-cell results for reproduction.

## Robust Reward Machine Learning and Execution in Noisy Environments

DevFeed: [Robust Reward Machine Learning and Execution in Noisy Environments](<https://devfeed.tech/articles/robust-reward-machine-learning-and-execution-in-noisy-environments-114486.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2611.01063>)

Author: Roko Parac, Lorenzo Nodari, Daniel Furelos-Blanco, Leo Ardon, Federico Cerutti, Alessandra Russo

Published: 2026-11-03T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Reinforcement learning](<https://devfeed.tech/topics/reinforcement-learning.md>), [Finite-state machine](<https://devfeed.tech/topics/finite-state-machine.md>)

Tags: [continuous](<https://devfeed.tech/tags/continuous.md>), [coverage](<https://devfeed.tech/tags/coverage.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [environment](<https://devfeed.tech/tags/environment.md>), [events](<https://devfeed.tech/tags/events.md>), [execution](<https://devfeed.tech/tags/execution.md>), [exploits](<https://devfeed.tech/tags/exploits.md>), [finite-state-machines](<https://devfeed.tech/tags/finite-state-machines.md>), [history](<https://devfeed.tech/tags/history.md>), [learning](<https://devfeed.tech/tags/learning.md>), [logic](<https://devfeed.tech/tags/logic.md>), [machine](<https://devfeed.tech/tags/machine.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [policy](<https://devfeed.tech/tags/policy.md>), [real-world](<https://devfeed.tech/tags/real-world.md>), [recurrent](<https://devfeed.tech/tags/recurrent.md>), [recurrent-neural-networks](<https://devfeed.tech/tags/recurrent-neural-networks.md>), [reward](<https://devfeed.tech/tags/reward.md>), [rms](<https://devfeed.tech/tags/rms.md>), [robust](<https://devfeed.tech/tags/robust.md>), [spaces](<https://devfeed.tech/tags/spaces.md>)

### AI overview

Prob-IRM learns reward machines from noisy proposition histories and uses them for policy learning in discrete and continuous environments. It represents histories as inductive logic programming examples, favoring RMs that cover low-uncertainty histories; learning is interleaved with policy optimization. A belief over RM states guides when to relearn and supplies additional rewards. In evaluations across varying label-noise levels, Prob-IRM performed comparably to handcrafted-RM baselines and outperformed recurrent neural network history encoders. The supplied abstract does not report quantitative results or details of the evaluation environments.

### Source excerpt

arXiv:2611.01063v1 Announce Type: cross Abstract: Background: Reward machines (RMs) represent non-Markovian reward functions as finite-state machines over high-level propositional events. Traditionally, these events are generated by a deterministic labelling function that maps environment states to proposition sets. However, real-world labelling functions are inherently noisy. Objectives: Design and implement a method that learns RMs in the presence of noisy labelling functions and exploits them for policy learning in both discrete and continuous environments. Methods: We propose Prob-IRM, a method that learns RMs from noisy proposition histories using inductive logic programming (ILP) and exploits them for policy learning. Noisy proposition histories are represented as training examples for ILP, which learns an RM that maximises coverage of low-uncertainty histories. RM learning is interleaved with policy optimisation. Prob-IRM uses a belief over RM states to determine when to relearn the RM and to provide additional guiding rewards. Results: Prob-IRM is evaluated on environments with discrete and continuous state spaces under varying levels of labelling noise. Prob-IRM performs comparably to baselines using handcrafted RMs and outperforms approaches that use recurrent neural networks to encode history, despite operating with noisy labels. Conclusions: Prob-IRM represents a step towards deploying reward machines in noisy, real-world environments.

## Certified Splitting: Decidability and Anchor Supply for Maximal-Munch Tokenization

DevFeed: [Certified Splitting: Decidability and Anchor Supply for Maximal-Munch Tokenization](<https://devfeed.tech/articles/certified-splitting-decidability-and-anchor-supply-for-maximal-munch-tokenization-113767.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.08854>)

Author: Nicklas Nidh\\"ogg

Published: 2026-11-03T05:00:00Z

Content type: article

Language: en

Sources: [arXiv: Distributed Computing](<https://devfeed.tech/sources/arxiv-distributed-computing.md>)

Topics: [tokenization](<https://devfeed.tech/topics/tokenization.md>), [content defined chunking](<https://devfeed.tech/topics/content-defined-chunking.md>), [Regular expression](<https://devfeed.tech/topics/regular-expression.md>), [Finite-state machine](<https://devfeed.tech/topics/finite-state-machine.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [anchor](<https://devfeed.tech/tags/anchor.md>), [arithmetic](<https://devfeed.tech/tags/arithmetic.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [audits](<https://devfeed.tech/tags/audits.md>), [boundary](<https://devfeed.tech/tags/boundary.md>), [budget](<https://devfeed.tech/tags/budget.md>), [campaign](<https://devfeed.tech/tags/campaign.md>), [certificate](<https://devfeed.tech/tags/certificate.md>), [certification](<https://devfeed.tech/tags/certification.md>), [commit](<https://devfeed.tech/tags/commit.md>), [completeness](<https://devfeed.tech/tags/completeness.md>), [covering](<https://devfeed.tech/tags/covering.md>), [cs-dc](<https://devfeed.tech/tags/cs-dc.md>), [cs-fl](<https://devfeed.tech/tags/cs-fl.md>), [cs-pl](<https://devfeed.tech/tags/cs-pl.md>), [decidability](<https://devfeed.tech/tags/decidability.md>), [either](<https://devfeed.tech/tags/either.md>), [follow](<https://devfeed.tech/tags/follow.md>), [free](<https://devfeed.tech/tags/free.md>), [input](<https://devfeed.tech/tags/input.md>), [inside](<https://devfeed.tech/tags/inside.md>), [tokenization](<https://devfeed.tech/tags/tokenization.md>)

### AI overview

The paper defines certified byte windows whose occurrences identify safe starting points for independent maximal-munch scans, preserving sequential token boundaries without speculation or a fixup pass. It decides certification from the token set using two methods: an online method with a completeness cutoff for literal vocabularies, and an offline armed-run verifier for arbitrary regular token sets. It also derives bounds on boundary movement after edits, gives exact conditions for delimiter-based cuts, and presents tools to measure anchor-free spans and detect boundary differences between token sets. The abstract says the results have executable checks and that a threaded scanner in the munch library reproduced the sequential boundary stream on an archived campaign corpus.

### Source excerpt

arXiv:2610.08854v2 Announce Type: replace-cross Abstract: A certificate is a window of bytes with an origin inside it such that, wherever the window occurs in a completely tokenizable input, the token covering the window's final byte begins at that origin. Certification is decided from the token set alone, and a certificate's occurrences mark where work may soundly begin. This paper decides certification and applies it to cuts, edits and audits. It is decided two ways, online with a completeness cutoff for literal vocabularies and offline through an armed-run verifier for arbitrary regular token sets. Either route, under a declared window budget, yields the anchor inventory, with a counterexample on each refutation. Cutting a completely tokenizable input at certified anchors and scanning the chunks independently reproduces the sequential segmentation, with no speculation or fixup pass. A tokenizability-preserving byte substitution moves boundaries only strictly between the certified anchors witnessed in the unchanged bytes on either side of it. For tokens of length at most L, an edit at p moves no boundary at or below p - L + 1. Cutting at every occurrence of a delimiter is sound exactly when it occurs only at token starts, and cutting after every occurrence exactly when it occurs only at token ends. Two instruments follow. The anchor-free span of a finite certified inventory is decided bounded or not with its exact supremum, three for the UTF-8 shape; and a differential auditor decides whether two token sets place different boundaries on an input both tokenize, with a differing input. Every theorem carries an executable check. Every measurement is a named program's output or arithmetic on such outputs, and each program ships with the paper or is pinned by commit in the munch library. That library's threaded scanner splits the archived campaign corpus at certified anchors and reproduces the sequential boundary stream byte for byte.

## Your Billing Migration is Really a State Machine

DevFeed: [Your Billing Migration is Really a State Machine](<https://devfeed.tech/articles/your-billing-migration-is-really-a-state-machine-106891.md>)

Original publisher: [Read original article](<https://hackernoon.com/your-billing-migration-is-really-a-state-machine?source=rss>)

Author: naresh goyal

Published: 2026-10-29T21:45:46Z

Content type: tutorial

Language: en

Sources: [HackerNoon](<https://devfeed.tech/sources/hackernoon.md>)

Topics: [Finite-state machine](<https://devfeed.tech/topics/finite-state-machine.md>), [data migrations](<https://devfeed.tech/topics/data-migrations.md>)

Tags: [about](<https://devfeed.tech/tags/about.md>), [account](<https://devfeed.tech/tags/account.md>), [advanced](<https://devfeed.tech/tags/advanced.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [ai-deployment](<https://devfeed.tech/tags/ai-deployment.md>), [ai-gtm-strategy](<https://devfeed.tech/tags/ai-gtm-strategy.md>), [ai-orchestration](<https://devfeed.tech/tags/ai-orchestration.md>), [all](<https://devfeed.tech/tags/all.md>), [architect](<https://devfeed.tech/tags/architect.md>), [billing](<https://devfeed.tech/tags/billing.md>), [billing-system-design](<https://devfeed.tech/tags/billing-system-design.md>), [business-systems](<https://devfeed.tech/tags/business-systems.md>), [cpq](<https://devfeed.tech/tags/cpq.md>), [cpqsoftware](<https://devfeed.tech/tags/cpqsoftware.md>), [enterprise-technology](<https://devfeed.tech/tags/enterprise-technology.md>), [erp](<https://devfeed.tech/tags/erp.md>), [fine](<https://devfeed.tech/tags/fine.md>), [gtm-engineering](<https://devfeed.tech/tags/gtm-engineering.md>), [machine](<https://devfeed.tech/tags/machine.md>), [migration](<https://devfeed.tech/tags/migration.md>), [provisioning](<https://devfeed.tech/tags/provisioning.md>), [records](<https://devfeed.tech/tags/records.md>), [salesforce-cpq](<https://devfeed.tech/tags/salesforce-cpq.md>), [state](<https://devfeed.tech/tags/state.md>), [state-machine](<https://devfeed.tech/tags/state-machine.md>), [subscription](<https://devfeed.tech/tags/subscription.md>)

### AI overview

The migration's records moved successfully, but mismatched subscription state across quoting, billing, provisioning, and ERP caused duplicate invoices, false churn reports, and mistimed access. The architect's fixes were to define explicit states and allowed transitions with one system owning each transition; classify payment failure as Suspended rather than Cancelled; and trigger provisioning from the order's financially recognized Activated state. The account also recommends profiling and cleaning source data before configuration, using phased cutover with record-level validation and a read-only legacy system for comparison, bypassing new pricing rules for migrated history, and running old and new revenue schedules in parallel until finance signs off on consecutive clean cycles. Parallel runs take longer, and the excerpt presents them as supporting audit readiness. These are lessons from one large migration, not evidence that every implementation will behave identically.

### Source excerpt

Records moved fine. State broke everything. An architect's guide to modeling subscription state across billing, provisioning, and ERP before you migrate.

## Concordat: Typed Sessions for LLM Agents

DevFeed: [Concordat: Typed Sessions for LLM Agents](<https://devfeed.tech/articles/concordat-typed-sessions-for-llm-agents-103274.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.37461>)

Author: Milad Sikaroudi

Published: 2026-10-28T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Agent Harness](<https://devfeed.tech/topics/agent-harness.md>), [Large Language Model](<https://devfeed.tech/topics/llm.md>), [Finite-state machine](<https://devfeed.tech/topics/finite-state-machine.md>), [LLM security](<https://devfeed.tech/topics/llm-security.md>)

Tags: [actions](<https://devfeed.tech/tags/actions.md>), [agent](<https://devfeed.tech/tags/agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [airline](<https://devfeed.tech/tags/airline.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-ma](<https://devfeed.tech/tags/cs-ma.md>), [large-language-models](<https://devfeed.tech/tags/large-language-models.md>), [library](<https://devfeed.tech/tags/library.md>), [llm](<https://devfeed.tech/tags/llm.md>), [llm-agents](<https://devfeed.tech/tags/llm-agents.md>), [model](<https://devfeed.tech/tags/model.md>), [open-source](<https://devfeed.tech/tags/open-source.md>), [prompt](<https://devfeed.tech/tags/prompt.md>), [protocol](<https://devfeed.tech/tags/protocol.md>), [protocols](<https://devfeed.tech/tags/protocols.md>), [python](<https://devfeed.tech/tags/python.md>), [sessions](<https://devfeed.tech/tags/sessions.md>), [split](<https://devfeed.tech/tags/split.md>), [state](<https://devfeed.tech/tags/state.md>), [subclass](<https://devfeed.tech/tags/subclass.md>), [token](<https://devfeed.tech/tags/token.md>), [tools](<https://devfeed.tech/tags/tools.md>)

### AI overview

Concordat enforces agent action rules at runtime through finite-state protocols: each turn exposes only currently legal tools, rejects out-of-protocol calls before side effects, reserves human decisions for requests, and accounts for token and tool-call budgets across handoffs. Protocols are checked at definition, and subclasses that could bypass a parent protocol are rejected. In a tau-bench airline evaluation with simulated pressure to skip confirmation, standard agents changed bookings without the required "yes" in 13 of 50 tasks with gpt-4.1 and 29 of 128 task-runs with Claude Haiku 5.5; Concordat agents did so zero times, with no significant task-success difference. The benchmark reward missed most violations. The evidence provided is an abstract/excerpt.

### Source excerpt

arXiv:2610.37461v1 Announce Type: new Abstract: Agents built on large language models are increasingly allowed to take consequential actions: cancelling bookings, issuing refunds, changing accounts. The rules that govern those actions, such as "obtain the customer's explicit confirmation before changing anything", are usually stated in the prompt and followed only as reliably as the model chooses to follow them. We present Concordat, a Python library that treats an agent as an object whose interface is a finite-state protocol, in the spirit of typestate and session types, and enforces that protocol on the model at run time. On every turn the model is offered only the tools that are legal in the current protocol state, calls outside that set are rejected before they have side effects, decisions reserved for humans can only be requested, and token and tool-call budgets are charged and split linearly across handoffs. Protocols are checked when they are defined, and a subclass of an agent is rejected if it could bypass its parent's protocol, a behavioural form of Liskov substitution. We evaluate a Concordat agent against the standard agent of tau-bench on its 50 airline tasks, adding simulated customers who pressure the agent to skip confirmation. The standard agent made changes without the required "yes" in 13 of 50 tasks with gpt-4.1 and in 29 of 128 task-runs with Claude Haiku 5.5; the Concordat agent made none, with no significant difference in task success. tau-bench's own reward did not detect most of these violations. Concordat is open source.

## Log-Derivative Trick for Parametric Markov Chains

DevFeed: [Log-Derivative Trick for Parametric Markov Chains](<https://devfeed.tech/articles/log-derivative-trick-for-parametric-markov-chains-103985.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.36655>)

Author: Arthur Gall, Ichiro Hasuo, Thomas Seiller

Published: 2026-10-28T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Finite-state machine](<https://devfeed.tech/topics/finite-state-machine.md>), [VAE](<https://devfeed.tech/topics/vae.md>)

Tags: [approximation](<https://devfeed.tech/tags/approximation.md>), [bias](<https://devfeed.tech/tags/bias.md>), [bottlenecks](<https://devfeed.tech/tags/bottlenecks.md>), [case-studies](<https://devfeed.tech/tags/case-studies.md>), [continuous](<https://devfeed.tech/tags/continuous.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-lo](<https://devfeed.tech/tags/cs-lo.md>), [estimator](<https://devfeed.tech/tags/estimator.md>), [evaluations](<https://devfeed.tech/tags/evaluations.md>), [execution](<https://devfeed.tech/tags/execution.md>), [framework](<https://devfeed.tech/tags/framework.md>), [generation](<https://devfeed.tech/tags/generation.md>), [global](<https://devfeed.tech/tags/global.md>), [gradient](<https://devfeed.tech/tags/gradient.md>), [horizon](<https://devfeed.tech/tags/horizon.md>), [limits](<https://devfeed.tech/tags/limits.md>), [linear](<https://devfeed.tech/tags/linear.md>), [local](<https://devfeed.tech/tags/local.md>), [loops](<https://devfeed.tech/tags/loops.md>), [markov](<https://devfeed.tech/tags/markov.md>), [materialization](<https://devfeed.tech/tags/materialization.md>), [monte-carlo](<https://devfeed.tech/tags/monte-carlo.md>)

### AI overview

The paper proposes a Monte Carlo gradient estimator for optimizing expected rewards and reachability probabilities in parametric Markov chains. It applies a measure-theoretic version of the log-derivative trick to sampled trajectories, using local transition probabilities or densities and their derivatives, without materializing the global state space or solving large linear systems. The authors claim unbiased estimates under almost-sure termination and standard regularity conditions. The framework extends beyond finite discrete chains to continuous and general σ-finite state spaces. Reported evaluations on synthetic discrete and continuous-state cases show reduced execution time and scalability beyond existing solvers; the abstract gives no specific benchmarks.

### Source excerpt

arXiv:2610.36655v1 Announce Type: new Abstract: Optimizing expected rewards and reachability probabilities in parametric Markov chains (pMCs) is central to the analysis and synthesis of probabilistic systems with loops. While traditional symbolic synthesis approaches--such as parameter lifting and rational function generation--suffer from scalability bottlenecks, gradient-based optimization emerges as an effective alternative. However, existing gradient-based techniques still rely on symbolic gradient computation--such as solving large linear systems--over the global state space, inheriting scalability limits. Finite-horizon approximation is possible but introduces uncontrollable bias. In this paper, we introduce a scalable Monte Carlo gradient estimator based on a measure-theoretic generalization of the log-derivative trick. We prove that our estimator provides unbiased gradient estimates under almost-sure termination and standard regularity conditions. Crucially, our method avoids global state-space materialization and linear system solving entirely: it operates purely along sampled trajectories, requiring only black-box evaluations of local transition probabilities (or densities) and their derivatives. Unlike existing pMC techniques that are fundamentally restricted to finite discrete systems, our measure-theoretic framework naturally extends to continuous and general $\sigma$-finite state spaces. Empirical evaluations on synthetic discrete pMCs and continuous-state case studies demonstrate that our method scales to state spaces far beyond the reach of existing solvers, significantly reducing execution time without introducing bias.

## SmartBAN on Silicon by Structured Behavioral Modeling

DevFeed: [SmartBAN on Silicon by Structured Behavioral Modeling](<https://devfeed.tech/articles/smartban-on-silicon-by-structured-behavioral-modeling-101653.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2608.29036>)

Author: Masato Yoshimi, Takahiro Ito, Kento Tanaka, Hirokazu Tanaka

Published: 2026-10-27T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Networking](<https://devfeed.tech/sources/arxiv-networking.md>)

Topics: [implementation](<https://devfeed.tech/topics/implementation.md>), [software-architecture](<https://devfeed.tech/topics/software-architecture.md>), [Zephyr RTOS](<https://devfeed.tech/topics/zephyr-rtos.md>), [Finite-state machine](<https://devfeed.tech/topics/finite-state-machine.md>), [Bluetooth LE](<https://devfeed.tech/topics/bluetooth-le.md>)

Tags: [architecture](<https://devfeed.tech/tags/architecture.md>), [bluetooth-low-energy](<https://devfeed.tech/tags/bluetooth-low-energy.md>), [concurrent](<https://devfeed.tech/tags/concurrent.md>), [cortex-m33](<https://devfeed.tech/tags/cortex-m33.md>), [cs-ni](<https://devfeed.tech/tags/cs-ni.md>), [delivery](<https://devfeed.tech/tags/delivery.md>), [energy](<https://devfeed.tech/tags/energy.md>), [measurements](<https://devfeed.tech/tags/measurements.md>), [modeling](<https://devfeed.tech/tags/modeling.md>), [protocol](<https://devfeed.tech/tags/protocol.md>), [rtos](<https://devfeed.tech/tags/rtos.md>), [soc](<https://devfeed.tech/tags/soc.md>)

### AI overview

The work presents a commercial-hardware SmartBAN implementation on a Nordic nRF54L15 using Zephyr RTOS. Its four-layer architecture uses a hardware abstraction layer as the intended portability boundary, while Hub and Node Mealy automata define concrete phase-control and connection-lifecycle behavior left unspecified by the standard. Tests with 16 Nodes over 25 hours achieved over 99.99% packet delivery and exercised all but one transition; the single observed disconnection led to timeout-triggered reconnection. The current model fit measurements when populated with measured state currents, while datasheet currents underestimated average use, mainly in the radio-off state, attributed to implementation overhead. In the same-SoC comparison, SmartBAN kept frame spacing within 1.1 ms of its interval but lost some frames; BLE lost none, deferred some transmissions by one or two intervals, and used less than half the average current. These results apply to the tested configuration.

### Source excerpt

arXiv:2608.29036v2 Announce Type: replace Abstract: Wireless body area networks (WBANs) underpin the Internet of Medical Things (IoMT). IEC/ETSI SmartBAN defines a lightweight time-division multiple access (TDMA) protocol, yet published implementations on commercial hardware remain partial. The standard specifies frame formats but leaves device-internal behavior in phase control, connection lifecycle, and slot timing unspecified. We present an operational SmartBAN realization on a commercial wireless system-on-chip (Nordic nRF54L15, Arm Cortex-M33, Zephyr RTOS) that implements initial connection, scheduled uplink, and timeout-based disconnection detection through a four-layer software architecture whose hardware abstraction layer is the intended portability boundary. Hub and Node Mealy automata supply one concrete design for the unspecified phase control and connection lifecycle, as a blueprint for the firmware's event-driven dispatch. Validation with 16 concurrent Nodes over 25 hours shows conformance across every transition the build exercises (all but one), >99.99% packet delivery, and timeout-triggered reconnection after the single observed disconnection. An analytical current model fits the measurements once it uses measured state currents; with datasheet currents it underestimates the average, mostly in the radio-off state, whose current we attribute to implementation-level overhead rather than the hardware. A same-SoC comparison with Bluetooth Low Energy (BLE) shows how each protocol departs from its schedule: SmartBAN, configured to send a fresh sample every interval instead of retransmitting, kept each Node's frame spacing within 1.1 ms of the interval but lost some frames; BLE lost none but deferred some by one or two intervals, and drew less than half SmartBAN's average current.

## A2ABreak: Systematic Security Analysis of the A2A Protocol

DevFeed: [A2ABreak: Systematic Security Analysis of the A2A Protocol](<https://devfeed.tech/articles/a2abreak-systematic-security-analysis-of-the-a2a-protocol-101360.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2609.10871>)

Author: Alireza Lotfi, Mirza Masfiqur Rahman, Imtiaz Karim, Elisa Bertino

Published: 2026-10-27T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Cryptography and Security](<https://devfeed.tech/sources/arxiv-cryptography-and-security.md>), [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [A2A protocol](<https://devfeed.tech/topics/a2a-protocol.md>), [Multi Agent Systems](<https://devfeed.tech/topics/multi-agent-systems.md>), [Finite-state machine](<https://devfeed.tech/topics/finite-state-machine.md>), [Security](<https://devfeed.tech/topics/security.md>)

Tags: [a2a](<https://devfeed.tech/tags/a2a.md>), [a2a-protocol](<https://devfeed.tech/tags/a2a-protocol.md>), [agent2agent](<https://devfeed.tech/tags/agent2agent.md>), [agents](<https://devfeed.tech/tags/agents.md>), [ai](<https://devfeed.tech/tags/ai.md>), [ai-agents](<https://devfeed.tech/tags/ai-agents.md>), [analysis](<https://devfeed.tech/tags/analysis.md>), [autonomous](<https://devfeed.tech/tags/autonomous.md>), [autonomous-ai-agents](<https://devfeed.tech/tags/autonomous-ai-agents.md>), [communication](<https://devfeed.tech/tags/communication.md>), [compliance](<https://devfeed.tech/tags/compliance.md>), [context](<https://devfeed.tech/tags/context.md>), [credential-harvesting](<https://devfeed.tech/tags/credential-harvesting.md>), [cs-cr](<https://devfeed.tech/tags/cs-cr.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [data-exfiltration](<https://devfeed.tech/tags/data-exfiltration.md>), [delegation](<https://devfeed.tech/tags/delegation.md>), [formal](<https://devfeed.tech/tags/formal.md>), [formalized](<https://devfeed.tech/tags/formalized.md>), [framework](<https://devfeed.tech/tags/framework.md>), [llm](<https://devfeed.tech/tags/llm.md>), [security](<https://devfeed.tech/tags/security.md>)

### AI overview

A2ABreak reports 11 protocol-level vulnerabilities in A2A that a specification-compliant adversary can exploit without implementation flaws. The framework uses LLM-assisted extraction of a verified finite-state machine from the natural-language specification (37 states, 76 transitions, and 929 formalized statements), then applies adversarial verification. Reported examples include cross-client context injection through unprotected context identifiers, credential harvesting after identity loss in delegation chains, and data exfiltration via agents making unattested capability claims. Against manual expert review, it achieves 73.3% precision and 84.6% F1; a zero-shot LLM baseline on the same specification yielded no confirmed findings. These are abstract-level claims; the supplied text does not detail mitigations or individual vulnerability analyses.

### Source excerpt

arXiv:2609.10871v3 Announce Type: replace Abstract: The Agent2Agent (A2A) protocol, now governed by the Linux Foundation, is an open standard that enables autonomous AI agents to discover, authenticate with, and delegate tasks to one another across organizational boundaries. Designed to complement the Model Context Protocol (MCP) for tool integration, A2A is rapidly emerging as the horizontal communication layer of the multi-agent ecosystem. Yet the protocol's security has received no systematic analysis. This paper presents A2ABreak, the first rigorous systematic security analysis of the A2A protocol. We introduce a novel framework that utilizes an LLM-assisted extraction of a verified finite-state machine directly from the natural-language specification, producing a unified model of 37 states and 76 transitions from 929 formalized statements, and then systematically reasons over this model to discover protocol-level vulnerabilities through adversarial verification, under a full-compliance assumption. Our analysis uncovers 11 new vulnerabilities, each exploitable by a specification-compliant adversary without requiring any implementation flaw. Among the findings are cross-client context injection through unprotected context identifiers, credential harvesting via multi-hop identity loss in delegation chains, and data exfiltration through rogue agents advertising unattested capability claims. A2ABreak achieves 73.3% precision and 84.6% F1 against manual expert review, while a zero-shot LLM baseline operating over the same specification produces zero confirmed findings, demonstrating that explicit formal grounding is essential for sound protocol security analysis.

## Certified Split Windows for Parallel Lexing: Recovering Boundaries Where No Byte Certifies

DevFeed: [Certified Split Windows for Parallel Lexing: Recovering Boundaries Where No Byte Certifies](<https://devfeed.tech/articles/certified-split-windows-for-parallel-lexing-recovering-boundaries-where-no-byte-certifies-101586.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2608.09761>)

Author: Nicklas Nidh\\"ogg

Published: 2026-10-27T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Distributed Computing](<https://devfeed.tech/sources/arxiv-distributed-computing.md>)

Topics: [Automaton](<https://devfeed.tech/topics/automaton.md>), [Finite-state machine](<https://devfeed.tech/topics/finite-state-machine.md>)

Tags: [certificate](<https://devfeed.tech/tags/certificate.md>), [cs-dc](<https://devfeed.tech/tags/cs-dc.md>), [cs-fl](<https://devfeed.tech/tags/cs-fl.md>), [cs-pl](<https://devfeed.tech/tags/cs-pl.md>), [lexer](<https://devfeed.tech/tags/lexer.md>), [local](<https://devfeed.tech/tags/local.md>), [model](<https://devfeed.tech/tags/model.md>), [parallel](<https://devfeed.tech/tags/parallel.md>), [profile](<https://devfeed.tech/tags/profile.md>), [pspace](<https://devfeed.tech/tags/pspace.md>), [scanner](<https://devfeed.tech/tags/scanner.md>), [semantic](<https://devfeed.tech/tags/semantic.md>), [serial](<https://devfeed.tech/tags/serial.md>), [split](<https://devfeed.tech/tags/split.md>), [stream](<https://devfeed.tech/tags/stream.md>), [string](<https://devfeed.tech/tags/string.md>), [tables](<https://devfeed.tech/tags/tables.md>), [token](<https://devfeed.tech/tags/token.md>), [using](<https://devfeed.tech/tags/using.md>), [window](<https://devfeed.tech/tags/window.md>), [windows](<https://devfeed.tech/tags/windows.md>)

### AI overview

The paper extends certified parallel-lexing boundaries from single bytes to bounded windows that reveal where the token covering the window's final byte began. It models possible maximal-munch scanner histories and decides reachability exactly within a finite quotient: positive results are sound semantic certificates for flat, completely tokenizable input, while negative results are limited by the conservative model. Certificates depend on an asserted occurrence witness and may otherwise be vacuous. In 400 random token sets, 322 of 337 sets with no byte certificate gained a witnessed window; every exact-empty case in the predecessor study gained one of two to four bytes. Analysis uses compiled tables once after automaton construction, without input. The existence problem is PSPACE-complete, and shortest windows can be exponentially long in the square root of the number of live states.

### Source excerpt

arXiv:2608.09761v3 Announce Type: replace-cross Abstract: A certified split point lets a parallel lexer cut unlexed input at a single byte with the serial token stream provably preserved, but several conventional token sets in the predecessor's controlled study certify no byte once string, comment, or whitespace-run forms are included (arXiv:2608.03473v2). We generalize from a byte to a bounded window, a byte string after which the position where the current token began is known, regardless of surrounding context. We certify the directly usable form of that recovery, namely that the token covering the window's final byte begins at the reported origin. The certificate is conditional on occurrence and may be vacuous; every applicability figure counts only windows carrying an asserted completely tokenizable occurrence witness. We give a conservative model of a maximal-munch scanner's possible histories across a window, prove it sound, and decide reachability in that model exactly by exhausting a finite quotient of its reachable configurations. Within the flat, completely tokenizable scope, model-positive answers are semantic certificates; negatives are relative to the model, which deliberately refuses some windows a greedy scanner would allow. Whether the model certifies any window, plain or witnessed, is PSPACE-complete, and a shortest window can need $2^{\Omega(\sqrt{n})}$ bytes over n live states. Two smaller searches decide plain model existence, the second shipped in release 2.2.0 of munch. In a sample of 400 random token sets, 322 of the 337 sets certifying no byte gain a witnessed window, with zero inconclusive searches, and every exact-empty row of the predecessor's study gains a witnessed window of two to four bytes. The analysis runs once after automaton construction, using only the compiled tables and no input. A boundary profile marks each gap of a window forced, crossed or open, and a window-local cut is sound exactly at forced gaps.

## Certified Split Points for Parallel Lexing: Exact and Modulo Discarded Tokens

DevFeed: [Certified Split Points for Parallel Lexing: Exact and Modulo Discarded Tokens](<https://devfeed.tech/articles/certified-split-points-for-parallel-lexing-exact-and-modulo-discarded-tokens-101582.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2608.03473>)

Author: Nicklas Nidh\\"ogg

Published: 2026-10-27T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Distributed Computing](<https://devfeed.tech/sources/arxiv-distributed-computing.md>)

Topics: [dfa](<https://devfeed.tech/topics/dfa.md>), [Finite-state machine](<https://devfeed.tech/topics/finite-state-machine.md>)

Tags: [cs-dc](<https://devfeed.tech/tags/cs-dc.md>), [cs-fl](<https://devfeed.tech/tags/cs-fl.md>), [cs-pl](<https://devfeed.tech/tags/cs-pl.md>), [parallel](<https://devfeed.tech/tags/parallel.md>), [points](<https://devfeed.tech/tags/points.md>), [split](<https://devfeed.tech/tags/split.md>), [tokenization](<https://devfeed.tech/tags/tokenization.md>), [tokens](<https://devfeed.tech/tags/tokens.md>)

### AI overview

The paper gives two DFA-based conditions for splitting longest-match lexing across chunks without recovering each chunk's entry state. An exact certificate guarantees that every occurrence of a byte begins a token and preserves token kinds and lengths, but strings, comments, or whitespace may eliminate useful certificates. A more permissive, constant-time test guarantees equivalence after removing declared discarded tokens; it is sound but can be incomplete. It recovers newline for a conventional C-like tokenization and tab, newline, and carriage return for JSON, while rejecting newline with unrestricted block comments. Safety is decidable in PSPACE for general token automata and polynomial time for literal vocabularies; unsafe bytes have replayable counterexamples. In tests on 15 token sets, the second condition was exact. The reported single-machine benchmark reached 92.6-95.3% efficiency at eight threads and 3.46-3.94x end-to-end speedup at four threads.

### Source excerpt

arXiv:2608.03473v4 Announce Type: replace-cross Abstract: Table-driven DFA lexing is sequential, since each transition depends on the previous byte's state. Scanning one input in parallel needs each chunk's entry state, which existing methods recover by simulation, speculation, prescanning, or overlap. We give two conditions under which none is needed. For a longest-match scanner restarting from q0 at every token boundary, a byte b is a certified split symbol when no reachable state other than q0 has a b-transition whose target can reach acceptance, and q0 is not re-entrant if it has one. Every occurrence of such a byte in completely tokenizable input begins a token, so chunks starting there reproduce the serial sequence of kinds and lengths. The condition is necessary and sufficient, but one string, comment, or whitespace run can remove every useful certificate. Comments and whitespace are usually discarded, so we weaken the guarantee to equality after deleting a declared discarded set and give a second condition, a precomputed constant-time one-bit test. It is sound but incomplete and more permissive, strictly so on suitable token sets and discarded sets. It recovers newline for a conventional C-like tokenization and tab, newline and carriage return for JSON, and refuses newline where block comments are unrestricted. Safety modulo the discarded set is decidable in PSPACE for every token automaton and in polynomial time for literal vocabularies, and every unsafe byte has a replayable counterexample. On the fifteen token sets studied the second condition is already exact. Splitting at exact certificates in munch reaches 92.6-95.3% parallel efficiency at eight threads on a restricted CPU set and a 512 MiB corpus, and a 3.46-3.94x end-to-end speedup at four threads, on one machine. It turns delimiter-based parallel lexing from a language-specific assumption into a property a compiler checks.

## DConstrain: Compiling Context-Parameterized Transitions for Diffusion Language Model Constrained Decoding

DevFeed: [DConstrain: Compiling Context-Parameterized Transitions for Diffusion Language Model Constrained Decoding](<https://devfeed.tech/articles/dconstrain-compiling-context-parameterized-transitions-for-diffusion-language-model-constrained-decoding-98134.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.30920>)

Author: Shidong Cao, Jing Ma, Wenhao Chai, Yuchen Tian, Lun Du, Da Zheng

Published: 2026-10-23T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>)

Topics: [Decoding](<https://devfeed.tech/topics/decoding.md>), [LLM optimization](<https://devfeed.tech/topics/llm-optimization.md>), [Finite-state machine](<https://devfeed.tech/topics/finite-state-machine.md>), [LLM evaluation / benchmarking](<https://devfeed.tech/topics/llm-evaluation-benchmarking.md>)

Tags: [abstract](<https://devfeed.tech/tags/abstract.md>), [aggregation](<https://devfeed.tech/tags/aggregation.md>), [arxiv](<https://devfeed.tech/tags/arxiv.md>), [benchmarks](<https://devfeed.tech/tags/benchmarks.md>), [but](<https://devfeed.tech/tags/but.md>), [can](<https://devfeed.tech/tags/can.md>), [cause](<https://devfeed.tech/tags/cause.md>), [compatibility](<https://devfeed.tech/tags/compatibility.md>), [compilation](<https://devfeed.tech/tags/compilation.md>), [concrete](<https://devfeed.tech/tags/concrete.md>), [context](<https://devfeed.tech/tags/context.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [decoding](<https://devfeed.tech/tags/decoding.md>), [deferred](<https://devfeed.tech/tags/deferred.md>), [diffusion](<https://devfeed.tech/tags/diffusion.md>), [distribution](<https://devfeed.tech/tags/distribution.md>), [effect](<https://devfeed.tech/tags/effect.md>), [effects](<https://devfeed.tech/tags/effects.md>), [language](<https://devfeed.tech/tags/language.md>), [language-model](<https://devfeed.tech/tags/language-model.md>), [model](<https://devfeed.tech/tags/model.md>)

### AI overview

DConstrain enables exact constrained decoding for diffusion language models while supporting arbitrary schema property order. It compiles token consumption into local grammar states and keeps stack operations, environment guards, deferred parsing, and field histories symbolic for runtime binding, avoiding offline enumeration of field subsets. Runtime successor construction can overlap with the model forward pass, and grouping tokens by compiled effect allows reuse across parser contexts. The paper says score aggregation and token restoration preserve both the Viterbi optimum and the ungrouped token-labeled path distribution. Across three benchmarks and two DLM families, it reports compiling all BFCL schemas, versus 71.30-85.81% for an optimized finite-state baseline; on BFCL, latency falls 6.65-46.26x with 100% schema validity, while DiffusionGemma accuracy rises from 37.27% with fixed order to 81.56% with arbitrary order.

### Source excerpt

arXiv:2610.30920v1 Announce Type: new Abstract: Diffusion language models (DLMs) decode multiple tokens in parallel, so individually valid tokens can be incompatible together under a schema. Exact joint inference over a grammar graph enforces compatibility, but it requires token-labeled successors across many hypothetical parser configurations. Encoding stacks and field histories in compiled states can cause exponential growth, which forces prior exact decoders to fix property orders and exclude valid outputs. We present DConstrain, which compiles schemas into context-parameterized transition programs. Cold compilation specializes token consumption to local grammar states while retaining context-dependent stack operations, environment guards, and caller-dependent deferred parsing symbolically. Tracking field histories as runtime values supports arbitrary property order without enumerating field subsets offline. At runtime, warm compilation binds reached configurations to these programs to construct exact successors, overlapping with the model forward pass because graph construction requires no model scores. Furthermore, token-effect grouping merges tokens with identical compiled effects before runtime contexts are bound, so groups are reused across stacks and environments even when concrete successors differ. Objective-specific score aggregation and token restoration provably preserve both the Viterbi optimum and the token-labeled path distribution of ungrouped inference. Across three benchmarks and two DLM families, DConstrain compiles 100% of BFCL schemas under arbitrary property orders, whereas an optimized finite-state baseline compiles only 71.30-85.81%. Under arbitrary property order, it reduces BFCL end-to-end decoding latency by 6.65-46.26 times with 100% schema validity and raises DiffusionGemma's BFCL accuracy from 37.27% under fixed order to 81.56%.

## Adaptive Skill Granularity for Coding Agents: Runtime Routing and Macro-to-Micro Recovery

DevFeed: [Adaptive Skill Granularity for Coding Agents: Runtime Routing and Macro-to-Micro Recovery](<https://devfeed.tech/articles/adaptive-skill-granularity-for-coding-agents-runtime-routing-and-macro-to-micro-recovery-96665.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.31461>)

Author: Dingxuan Zhang, Yanhui Jiang, Jun Wang, Hefeng Zhou

Published: 2026-10-23T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Artificial Intelligence](<https://devfeed.tech/sources/arxiv-artificial-intelligence.md>), [arXiv: Software Engineering](<https://devfeed.tech/sources/arxiv-software-engineering.md>)

Topics: [agentic-coding](<https://devfeed.tech/topics/agentic-coding.md>), [Agent Skills](<https://devfeed.tech/topics/agent-skills.md>), [Finite-state machine](<https://devfeed.tech/topics/finite-state-machine.md>)

Tags: [abstraction](<https://devfeed.tech/tags/abstraction.md>), [adaptive](<https://devfeed.tech/tags/adaptive.md>), [agents](<https://devfeed.tech/tags/agents.md>), [coding-agents](<https://devfeed.tech/tags/coding-agents.md>), [control](<https://devfeed.tech/tags/control.md>), [controller](<https://devfeed.tech/tags/controller.md>), [cs-ai](<https://devfeed.tech/tags/cs-ai.md>), [cs-se](<https://devfeed.tech/tags/cs-se.md>), [execution](<https://devfeed.tech/tags/execution.md>), [failure](<https://devfeed.tech/tags/failure.md>), [failure-recovery](<https://devfeed.tech/tags/failure-recovery.md>), [framework](<https://devfeed.tech/tags/framework.md>), [policy](<https://devfeed.tech/tags/policy.md>), [process](<https://devfeed.tech/tags/process.md>), [protocol](<https://devfeed.tech/tags/protocol.md>), [recovery](<https://devfeed.tech/tags/recovery.md>), [robustness](<https://devfeed.tech/tags/robustness.md>), [route](<https://devfeed.tech/tags/route.md>), [routing](<https://devfeed.tech/tags/routing.md>), [runtime](<https://devfeed.tech/tags/runtime.md>), [skills](<https://devfeed.tech/tags/skills.md>), [state](<https://devfeed.tech/tags/state.md>)

### AI overview

Adaptive Skill Granularity routes coding-agent tasks among primitive tool calls, macro skills, and hybrid execution based on task structure, execution state, and macro failures. It combines a feature-based granularity controller with a finite-state recovery executor. In a deterministic coding-agent protocol evaluated by verifier-defined success, total cost, and process metrics, fixed macro execution was efficient when applicable but brittle under mismatch. Runtime routing and explicit macro-to-micro recovery improved robustness and recovered controlled macro failures that fixed-granularity execution left unresolved. The evidence provided is an abstract and does not give further implementation or quantitative results.

### Source excerpt

arXiv:2610.31461v1 Announce Type: cross Abstract: Reusable skills allow large language model agents to package task-specific procedures, tool affordances, and execution guidance into modular units. Prior work has largely studied how agents retrieve, compose, or synthesize skills before execution. In coding agents, however, execution poses an additional runtime control problem: the same task may be solved through primitive tool calls, macro skills, or hybrid execution that starts with a macro and falls back to micro-level recovery. We introduce Adaptive Skill Granularity, a framework that treats skill granularity as an action-abstraction policy conditioned on task structure, execution state, and macro-skill failures. The system combines a feature-based granularity controller and a finite-state recovery executor. We evaluate the framework with a deterministic coding-agent protocol using verifier-defined success, total cost, and process metrics such as macro adoption, failure recovery, route match, and transition correctness. Results show that fixed macro execution is efficient when applicable but brittle under mismatch, while runtime routing and explicit macro-to-micro recovery improve robustness and recover controlled macro failures that fixed-granularity execution leaves unresolved. Our findings suggest that skill libraries for coding agents should be treated not only as retrievable resources, but also as controllable, verifiable, and recoverable execution abstractions.

## Towards Interaction State Recognition in Sensorized Gecko-Inspired Adhesive Interfaces for Orbital Servicing

DevFeed: [Towards Interaction State Recognition in Sensorized Gecko-Inspired Adhesive Interfaces for Orbital Servicing](<https://devfeed.tech/articles/towards-interaction-state-recognition-in-sensorized-gecko-inspired-adhesive-interfaces-for-orbital-servicing-94246.md>)

Original publisher: [Read original article](<https://arxiv.org/abs/2610.27141>)

Author: Eduart Abdullahu, Francesco Grella, Carol Martinez

Published: 2026-10-21T04:00:00Z

Content type: article

Language: en

Sources: [arXiv: Machine Learning](<https://devfeed.tech/sources/arxiv-machine-learning.md>)

Topics: [Robot Manipulation](<https://devfeed.tech/topics/robot-manipulation.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Finite-state machine](<https://devfeed.tech/topics/finite-state-machine.md>)

Tags: [autonomous](<https://devfeed.tech/tags/autonomous.md>), [awareness](<https://devfeed.tech/tags/awareness.md>), [capture](<https://devfeed.tech/tags/capture.md>), [classification](<https://devfeed.tech/tags/classification.md>), [cs-lg](<https://devfeed.tech/tags/cs-lg.md>), [cs-ro](<https://devfeed.tech/tags/cs-ro.md>), [embedded](<https://devfeed.tech/tags/embedded.md>), [evaluation](<https://devfeed.tech/tags/evaluation.md>), [framework](<https://devfeed.tech/tags/framework.md>), [interaction](<https://devfeed.tech/tags/interaction.md>), [interfaces](<https://devfeed.tech/tags/interfaces.md>), [lightweight](<https://devfeed.tech/tags/lightweight.md>), [machine](<https://devfeed.tech/tags/machine.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [models](<https://devfeed.tech/tags/models.md>), [offline](<https://devfeed.tech/tags/offline.md>), [online](<https://devfeed.tech/tags/online.md>), [random](<https://devfeed.tech/tags/random.md>), [real-time](<https://devfeed.tech/tags/real-time.md>), [realtime](<https://devfeed.tech/tags/realtime.md>), [recognition](<https://devfeed.tech/tags/recognition.md>), [state](<https://devfeed.tech/tags/state.md>)

### AI overview

The framework uses embedded capacitive sensing to classify five interaction states--idle, proximity, contact, engaged, and disengaged--in sensorized gecko-inspired adhesive interfaces for orbital servicing. Across six lightweight models, Random Forest had the highest offline accuracy at 95.65%. For online deployment, pairing it with a rule-based state machine raised accuracy from 78.02% to 93.14%, with a macro F1-score of 0.9343 and a 53 ms inference cycle. The abstract presents physics-consistent state constraints as improving real-time robustness; these results are a step toward interaction-aware robotic capture.

### Source excerpt

arXiv:2610.27141v1 Announce Type: cross Abstract: Reliable contact establishment remains a critical challenge for autonomous on-orbit servicing (OOS), particularly when interacting with non-cooperative targets. Gecko-inspired dry adhesives provide a lightweight, passive, and residue-free solution for robotic capture in space, yet current systems operate in open loop, without the ability to estimate their own contact or adhesion state during interaction. This paper presents a real-time interaction-awareness framework that enables sensorized gecko-inspired adhesive interfaces to estimate their contact state throughout the adhesion lifecycle using embedded capacitive sensing. Five discrete interaction states (idle, proximity, contact, engaged, and disengaged) are classified using experimentally collected and augmented sensor data, enabling a comparative evaluation of six lightweight machine learning models suitable for embedded deployment. Among the evaluated models, Random Forest achieved the highest offline classification accuracy of 95.65%. For online deployment, combining Random Forest with a rule-based state machine improved accuracy from 78.02% to 93.14%, achieving a macro F1-score of 0.9343 while maintaining a 53 ms inference cycle. These results demonstrate that incorporating physics-consistent state constraints significantly improves robustness during realtime inference, representing a step toward interaction-aware capture in future autonomous orbital servicing missions.

[Next page](<https://devfeed.tech/topics/finite-state-machine.md?cursor=WyIyMDI2LTEwLTIxVDA0OjAwOjAwKzAwOjAwIiwgImE4OTM4Y2IxLTliMjMtNDZhMS05YjIzLTMxYzQ5NDA2NTViYyJd>)