arXiv subjects

Marius Silaghi

Publications and source records attributed to Marius Silaghi.

10 recordsLinked to original sources

arXiv2026

Rules Before Oracles: Auditable, User-Configurable Argument Selection for Deliberative Polling

In a deliberative poll, once submissions outnumber what anyone will read, some mechanism chooses which arguments each voter sees, acquiring much of the decision; practice delegates it to opaque learned rankers, so a voter cannot recompute or contest the exposure that shaped their vote. We ask whether it can be a published rule over publicly recomputable evidence with parameters held by the voter, treating legibility as an admissibility condition on usable mechanisms, not an objective traded against accuracy. We formalise a poll over bipolar justification sets, judging a slate by reason coverage, the order it arrives in, and captured endorsement mass; we give seven checkable criteria for a civic recommender and a rule meeting them: a one-hop reversed endorsement flow parameterised by a relation-weight function. An agentic simulator records every slate at every vote, over about 17,000 seed-paired runs. Served slates fall 0.035 short of a label-reading ceiling upper-bounding every selection procedure, opaque ones included: any unconstrained ranker's advantage is bounded and small. On coverage alone, with non-degenerate authoring, the rule is indistinguishable from a random slate, a null due to an order-blind, charity-blind instrument; on the other two it leads at every prefix by a margin widening with adversarial pressure and dominates on mass by a factor of 3.3. Once a realistic fraction of submissions carries no reasons, the coverage margin returns and grows. Label-homogeneous flooding collapses completeness from 0.81 to 0.34 under a flat weight policy, only to 0.44 under author-count normalisation, making the weight function a security control worth 10% of completeness. The choice between ranking arms is a position on a coverage-versus-mass frontier, not a fact, the kind of choice only a legible rule can hand to the person it affects. It maps onto an open-source peer-to-peer platform.

cs.AI↗

arXiv2026

TraceCoder: Explainable and Auditable Code Generation with Position-Key Snippet Versioning

Contemporary LLM-based coding agents produce code as black-box outputs: the rationale behind each line is hidden, the evolution of the code through benchmark-driven repair is ephemeral, and post-hoc auditing is impossible. We present a code generation concept that addresses these shortcomings through three complementary mechanisms: (i) a relational snippet-history schema that records, per repair event, the benchmark reference, round number, failure text, and LLM explanation, enabling full provenance queries; (ii) a browser-based visualisation tool that renders this history as heat-mapped, hover-annotated source code; and (iii) a competitive fractional position-key indexing scheme with tree-node delimiters that assigns stable, lexicographically-ordered identifiers to each code snippet, enabling fine-grained tracking without disrupting surrounding lines. We evaluate TraceCoder on 30 algorithmic programming tasks spanning string processing, mathematical computation, and data-structure manipulation, across two provider configurations. Of these, 10 exhaust the 6-iteration budget on tasks with subtle edge-case behaviour. Mean Chg% reaches 30%, three in ten code snippets carry a traceable repair-event row, compared to 21% when using Gemini 2.0 Flash as sole provider on a 20-task subset. Three detailed case studies demonstrate how the system explains which specific benchmark failures shaped each line of the final program. The proposed mechanism makes the internal "narrative" of automated code generation auditable and replayable, a property essential for trust and accountability in production deployments.

cs.AI↗

arXiv2026

Chronofy: A Temporal-Logical Decay Architecture for Information Validity in Time-Aware Retrieval-Augmented Generation

Retrieval-Augmented Generation (RAG) systems retrieve and integrate external knowledge to ground large language model (LLM) outputs. However, current RAG architectures treat all retrieved facts as equally valid regardless of temporal provenance, leading to temporal hallucination, where plausible but obsolete facts corrupt the output. A clinical lab reading from yesterday is actionable; the same reading from six months ago is noise. We present Chronofy, a three-layer neuro-symbolic framework implementing the Temporal-Logical Decay Architecture (TLDA) that embeds temporal validity directly into the representation, retrieval, and reasoning layers of RAG systems. Layer 1 reserves a dedicated temporal subspace within Matryoshka embeddings to make fact age structurally irremovable from the representation. Layer 2 integrates learnable exponential decay functions into graph-based retrieval, where the decay coefficient $β_j$ is grounded in Bayesian decision theory as an approximation of twice the latent process mean-reversion rate. Layer 3 applies Signal Temporal Logic (STL) robustness functions to evaluate the temporal validity of retrieved knowledge, not LLM output confidence, and enforces the possibilistic weakest-link principle to bound output confidence by the most decayed evidence in the reasoning chain. We evaluate Chronofy on temporal knowledge graph forecasting benchmarks, the TimE temporal QA benchmark, and a domain-specific sensitivity analysis, demonstrating that explicit temporal decay modeling improves retrieval precision, reduces temporal hallucination, and enables principled data re-acquisition triggers when temporal context is insufficient.

cs.LG↗

arXiv2026

Evaluation of Alternative-Based Information Systems for Deliberative Polling using an Agentic Simulator

Deliberative polling promises to improve collective decision-making by exposing shareholders to a broad range of arguments before they vote. Yet ensuring that every voter encounters a representative sample of the reason space, the coverage problem, remains an open challenge, particularly at scale and in adversarial or strategically motivated electorates. This paper introduces a way of evaluating solutions using the LLM-based Agentic Bipolar Argumentation Simulator, grounded in a framework which formalises a poll as a six-tuple of endorsing and opposing justifications, attack and enhance relations, and shareholder- and relation-weights. ABAS simulates N autonomous shareholder agents, each assigned a latent opinion according to desired distributions in [-1, 1], who sequentially vote, choose or author justifications, and optionally submit argumentation-graph links. The simulator implements recommendations that rank existing justifications by their observable endorsement mass. It evaluates the mechanism's success by coverage, namely the fraction of the corpus reason-tag set represented in the K recommendations presented to each shareholder, as a solution to the NP-hard Subsuming Justification Problem. Reported experiments characterise how creativity rate (pown), recommendation size (K), argumentation density (plinks), and population size (N) affect coverage and corpus diversity. In an authenticated electorate where Sybil attacks are impossible and only the relation graph is gameable, we stress-test the scoring with coordinated strategic voting attacks: a tag-flood attack collapses coverage, while author-count relation weighting through a reversed-PageRank rule resists the flood markedly better than uniform weights.

cs.CY↗

arXiv2024

Robotic Ad-Hoc Networks

Practical robotic adhoc networks (RANETs), a type of mobile wireless adhoc networks (WANETs) supporting the WiFi-Direct modes common in internet of things and phone devices, is proposed based on a strategy of exploiting WiFi-Direct connection modes to overcome hardware restrictions. For a certain period of time the community was enthusiastic about the endless opportunities in fair, robust, efficient, and cheap communication created by the Adhoc mode of the WiFi IEEE 802.11 independent basic service set (IBSS) configuration that required no dedicated access points. The mode was a main enabler of wireless Adhoc networks (WANETS). This communication mode unfortunately did not get into the standard network cards present in IoT and mobile phones, likely due to the high energy consumption it exacts. Rather, such devices implement WiFi-Direct which is designed for star topologies. Several attempts were made to overcame the restriction and support WANETs, but they break at least the fairness and symmetry property, thereby reducing applicability. Here we show a solution for fair RANETs and evaluate the behavior of various strategies using simulations.

cs.RO↗

arXiv2024

Modeling the Feedback of AI Price Estimations on Actual Market Values

Public availability of Artificial Intelligence generated information can change the markets forever, and its factoring into economical dynamics may take economists by surprise, out-dating models and schools of thought. Real estate hyper-inflation is not a new phenomenon but its consistent and almost monotonous persistence over 12 years, coinciding with prominence of public estimation information from Zillow, a successful Mass Real Estate Estimator (MREE), could not escape unobserved. What we model is a repetitive theoretical game between the MREE and the home owners, where each player has secret information and expertise. If the intention is to keep housing affordable and maintain old American lifestyle with broad home-ownership, new challenges are defined. Simulations show that a simple restriction of MREE-style price estimation availability to opt-in properties may help partially reduce feedback loop by acting on its likely causes, as suggested by experimental simulation models. The conjecture that the MREE pressure on real estate inflation rate is correlated with the absolute MREE estimation errors, which is logically explainable, is then validated in simulations.

econ.GN↗

arXiv2017

POMDPs for Robotic Arm Search and Reach to Known Objects

We propose an approach based on probabilistic models, in particular POMDPs, to plan optimized search processes of known objects by intelligent eye in hand robotic arms. Searching and reaching for a known object (a pen, a book, or a hammer) in one's office is an operation that humans perform frequently in their daily activities. There is no reason why intelligent robotic arms would not encounter this problem frequently in the various applications in which they are expected to serve. The problem suffers from uncertainties coming both from the lack of information about the position of the object, from noisy sensors, imperfect models of the target object, of imperfect models of the environment, and from approximations in computations. The use of probabilistic models helps us to mitigate at least a few of these challenges, approaching optimality for this important task.

cs.RO↗

arXiv2017

Distributed Constraint Problems for Utilitarian Agents with Privacy Concerns, Recast as POMDPs

Privacy has traditionally been a major motivation for distributed problem solving. Distributed Constraint Satisfaction Problem (DisCSP) as well as Distributed Constraint Optimization Problem (DCOP) are fundamental models used to solve various families of distributed problems. Even though several approaches have been proposed to quantify and preserve privacy in such problems, none of them is exempt from limitations. Here we approach the problem by assuming that computation is performed among utilitarian agents. We introduce a utilitarian approach where the utility of each state is estimated as the difference between the reward for reaching an agreement on assignments of shared variables and the cost of privacy loss. We investigate extensions to solvers where agents integrate the utility function to guide their search and decide which action to perform, defining thereby their policy. We show that these extended solvers succeed in significantly reducing privacy loss without significant degradation of the solution quality.

cs.AI↗

arXiv2016

Utilitarian Distributed Constraint Optimization Problems

Privacy has been a major motivation for distributed problem optimization. However, even though several methods have been proposed to evaluate it, none of them is widely used. The Distributed Constraint Optimization Problem (DCOP) is a fundamental model used to approach various families of distributed problems. As privacy loss does not occur when a solution is accepted, but when it is proposed, privacy requirements cannot be interpreted as a criteria of the objective function of the DCOP. Here we approach the problem by letting both the optimized costs found in DCOPs and the privacy requirements guide the agents' exploration of the search space. We introduce Utilitarian Distributed Constraint Optimization Problem (UDCOP) where the costs and the privacy requirements are used as parameters to a heuristic modifying the search process. Common stochastic algorithms for decentralized constraint optimization problems are evaluated here according to how well they preserve privacy. Further, we propose some extensions where these solvers modify their search process to take into account their privacy requirements, succeeding in significantly reducing their privacy loss without significant degradation of the solution quality.

cs.AI↗

arXiv2016

DisCSPs with Privacy Recast as Planning Problems for Utility-based Agents

Privacy has traditionally been a major motivation for decentralized problem solving. However, even though several metrics have been proposed to quantify it, none of them is easily integrated with common solvers. Constraint programming is a fundamental paradigm used to approach various families of problems. We introduce Utilitarian Distributed Constraint Satisfaction Problems (UDisCSP) where the utility of each state is estimated as the difference between the the expected rewards for agreements on assignments for shared variables, and the expected cost of privacy loss. Therefore, a traditional DisCSP with privacy requirements is viewed as a planning problem. The actions available to agents are: communication and local inference. Common decentralized solvers are evaluated here from the point of view of their interpretation as greedy planners. Further, we investigate some simple extensions where these solvers start taking into account the utility function. In these extensions we assume that the planning problem is further restricting the set of communication actions to only the communication primitives present in the corresponding solver protocols. The solvers obtained for the new type of problems propose the action (communication/inference) to be performed in each situation, defining thereby the policy.

cs.AI↗