Search arXiv⌕ Search

SEARCH · Search arXiv

Search Search arXiv

Search indexed arXiv papers on artificial intelligence, large language models, computer vision and robotics. Read source abstracts and follow links to arXiv.

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

At least 1,711 records · Page 95Linked to original sources

The limits of magic-state distillation

Magic-state factories are a major cost of fault-tolerant quantum computing, yet how few noisy inputs they need is known only for restricted protocols. We show that, for tolerating input faults, any stabilizer protocol, however adaptive, postselected or multistage, is no better than a projection onto one stabilizer code, and that for rational targets a fault pattern is harmful exactly when its complement is. Searches over all codes show that quadratic distillation of one T state needs exactly nine inputs and that the eight-input CCZ factory is optimal. At order $d$, one T state needs $n\geq2d$.

quant-ph↗

A Grammar of French Civil Cassation: A Ground-Level Dataset and Tool

This paper presents a dataset of 121,536 ground-reasons pairs across 86,464 rulings of the five civil chambers of the French Court of Cassation (2016-2025). An appeal on points of law cannot itself be appealed and often decides a case for good. Understanding how the Court rules is thus crucial and can help lawyers who draft those appeals. Inside a ruling, every ground of appeal (a distinct legal complaint against the appealed decision) has its own answer from the Court. This answer is called the reasons and it belongs to one of a few doctrinal families. Using a deterministic pipeline, we pair each ground with its reasons and attach the pair to its family, according to the established French taxonomy. We obtain a descriptive grammar of civil cassation that shows which grounds succeed, which legal texts they refer to, and how both evolve over the decade. We release the dataset, the code and an interactive consultation tool.

cs.CL↗

Through a PRISM, Clearly: Step-Sequence Reasoning for Mistake Recognition in Procedural Videos

Procedural mistake recognition requires identifying deviations from valid multi-step activities. We study post-completion recognition from videos with benchmark-provided step boundaries. We introduce PRISM (Procedural mistake Recognition via Interpretable Semantic Modeling), which grounds video segments in language and maps their descriptions to procedural states using a lightweight hidden Markov model trained on correct executions. Reference alignment and semantic checks identify errors in step content and order. To support evaluation across heterogeneous benchmarks, we map dataset-specific annotations to four edit-based error types: insertion, deletion, substitution, and transposition. Across three benchmarks, we compare gold and VLM-generated descriptions in raw, semantic-role, and action-object forms. Decoder controls show consistent gains from the trained local decoder over nearest-candidate matching, with additional, dataset-dependent benefits from sequence decoding. Semantic role labeling improves Any-F1 in all six matched grounded comparisons, although the gains vary across datasets and do not translate into uniform improvements under separate configuration selection. These results establish language grounding as an effective interface for explicit procedural mistake reasoning and characterize the contributions of representation and decoding.

cs.CV↗

ProductWebBench: Evaluating Website Continuity Beyond Task Completion

Frontend coding agents are usually graded on one question: did the requested target get built. Real engineering changes carry a second obligation, because the rest of the site has to keep working. We call that second obligation website continuity, and introduce ProductWebBench, a benchmark that scores both on living frontend repositories: 320 Change tasks over existing code and 80 long-horizon Build tasks. Every task freezes a repository snapshot, staged requirements, browser evidence and deterministic checks before evaluation, and enters only once a reference passes every check and plausible-wrong ones fail. A simulated user reveals the requirements one stage at a time, and every check cleared earlier stays armed for the rest of the run. Across 8,737 runs from 13 models the two come apart: of the Change runs passing every requested-work check, 28.2% still fail a continuity check -- a blank route, horizontal overflow, console errors -- and 10.8% push a browser state they had already passed back to failing. Because the same checks also run on the untouched repository, each regression carries exact provenance, not a post-hoc label: on the 586 runs where both readings exist, 18.3% are caught breaking a verified state. Interaction is a further blind spot, failing in 29.5% of runs whose static DOM already passes. ProductWebBench therefore scores a patch against the living system it lands in, not the target alone.

cs.SE↗

Constraint Reasoning and Large Language Models Join Forces: Providing Contrastive Explanations for Real-World Optimisation-Based Applications

We focus on optimisation-based Decision Support Systems in real-world applications. In this context, we aim to provide contrastive explanations that answer users' questions about recommendations based on the solution of an optimisation problem, specifically a Mixed-Integer Program (MIP). Addressing this endeavour is crucial to ensure human oversight of the decisions implemented, as required by international guidelines on trustworthy and responsible automated decision-making systems. We propose a novel methodology that combines constraint reasoning techniques and Large Language Models (LLMs) to generate contrastive explanations for optimisation problems encoded as MIPs. Although LLMs have shown impressive capabilities in Natural Language processing, they can produce incorrect answers due to reasoning limitations. To overcome these limitations, we leverage constraint reasoning techniques to distil the information necessary to produce an explanation, which is then passed as input to an LLM as the so-called graph of reasons. Such a graph captures the semantics and the relationships among constraints of the optimisation problem. Results on real-world scheduling domains show that incorporating constraint reasoning improves explanations generated by the LLM. In particular, using the graph of reasons enables the LLM to produce natural-language explanations that include more relevant reasons while reducing errors compared to explanations generated without this structure.

cs.AI↗

SetCommit: Coordinated Token Commitments for Few-Step Diffusion Language Model Decoding

Diffusion language models generate multiple token positions in parallel, but few-step decoding makes parallel commitment difficult: tokens that appear reliable individually may be jointly inconsistent, while premature commitments can prevent later context-dependent refinement. In this paper, we introduce SetCommit, a training-free method for coordinated parallel token commitment. Instead of selecting tokens independently by confidence, SetCommit selects a commitment set that balances token reliability against local joint commitment risk, preserving conditioning opportunities for subsequent denoising steps. It further performs budget-neutral local exchanges, replacing vulnerable earlier commitments when newly revealed context supports more reliable alternatives. SetCommit requires no retraining or architectural modification and is compatible with existing diffusion decoding strategies. Experiments with LLaDA-8B and Dream-7B on GSM8K, MATH-500, MBPP, and HumanEval show accuracy/pass@1 gains of up to 7.4 percentage points over native decoding at 32 model evaluations. At common quality targets, geometric-mean incremental speedups range from $1.44$ to $1.74\times$. Code is available at https://github.com/Kissmetothemoon/SetCommit.

cs.AI↗

RGraph-Eval: Task-Grounded Scene Graphs for Evaluating Robot Video Generation

Generated robot videos can look convincing while depicting the wrong interac- tion: a different object is moved, a grasp disappears, or a placement ends out- side its destination. We introduce RGraph-Eval, a reference-based framework that makes these discrepancies explicit through task-grounded temporal scene graphs. Unlike approaches that construct separate evidence representations for different evaluation dimensions, we organize task entities, interactions, and motion within a unified, interpretable scene graph representation. A foundation-model pipeline identifies manipulation roles, grounds persistent object masks, infers and verifies state transitions and action intervals, and reconstructs manipulated- object motion in three dimensions. Applying this representation to a generated video and a reference demonstration supports an interpretable RGraph-Eval score with visible-object, relation-change, and 3D path-shape components. We also introduce ShareRobot-SG, a collection of 1,000 manipulation scenes from ten ShareRobot sources annotated with the multimodal representation. Our eval- uation separates graph-generation quality from agreement with human video judgments, and includes comparisons with adapted SVG2 and SG-Ego, a bench- mark of three video generators. The framework connects robot-video assessment to the observable entities and interactions underlying a task, while making the graph annotations reusable beyond evaluation. Code will be publicly available at https://github.com/SashaDance/rgraph-eval.

cs.RO↗

Parton distribution functions of the proton in a hot isospin-asymmetric nuclear medium and finite nuclei

When a nucleon is bound in a nucleus, its quark distributions are modified, and the change in the spin-dependent distributions can differ in size from that in the spin-independent ones. We compute the unpolarized $f_1(x)$, helicity $g_1(x)$, and transversity $h_1(x)$ distributions of the $u$ and $d$ quarks in a proton immersed in hot and isospin-asymmetric nuclear matter. The proton is described in the diquark spectator model, with the medium effects entering through the effective quark, diquark, and proton masses computed using the chiral SU(3) quark mean field (CQMF) model. The axial and tensor charges are obtained for baryon densities up to saturation density and temperatures $T = 0$ and $0.1$ GeV, in both symmetric nuclear matter and pure neutron matter. The distributions are then carried to $^{40}$Ca, $^{56}$Fe, $^{197}$Au, and $^{208}$Pb at zero temperature through the local density approximation. In symmetric matter at saturation density and zero temperature, the peaks of the three $u$ quark distributions move toward larger $x$ and fall least for the unpolarized distribution and most for the transversity distribution, so the spin-dependent $u$ quark distributions are modified more strongly. Between vacuum and saturation density, the axial charge of the proton drops from $1.28$ to $0.844$, and the tensor charge of the $u$ quark decreases while that of the $d$ quark grows in magnitude. At the center of each nucleus, the axial charge of the proton rises from $0.699$ in $^{40}$Ca to $0.817$ in $^{208}$Pb as the central baryon density decreases, which suggests that the modification at the center follows the central density rather than the mass number.

hep-ph↗

WildDepth-v2: A Synchronized RGB--LiDAR--Radar Dataset and Benchmark for Metric Depth, Motion, and Tracking of Wildlife

Measuring animal distance and motion in metric units underpins abundance estimation, morphometrics, and movement ecology, yet monocular video lacks metric scale and wildlife datasets lack metric ground truth. We present WildDepth 2, extending the synchronized RGB-LiDAR WildDepth dataset in three directions. (i) Imaging radar: 37 RGB-LiDAR-4D-radar sequences (19,716 frames) with per-point Doppler velocity and a measured error budget, to our knowledge the first imaging-radar wildlife recordings. (ii) Benchmarking: a frozen, checksummed hidden test set for RGB-only distance estimation and RGB+sparse-LiDAR depth completion, evaluated separately on animal and background pixels. (iii) Motion and tracking: metric 3D trajectories obtained by lifting 2D tracks using LiDAR, radar, or monocular depth. Across 48,723 animal frames, object-level radar calibration improves monocular depth over scene-level LiDAR calibration without requiring LiDAR at inference (AbsRel 0.120 vs. 0.198), although animal-level LiDAR remains more accurate (0.052). Across 431 tracks, once-per-track radar scaling reduces 3D position error four-fold (2.20 to 0.58 m) and distance-sampling detection-function bias from -13% to -2%, matching once-per-track LiDAR calibration. Transferring radar Doppler onto LiDAR produces motion masks 3.7 times denser than radar alone at 72% precision, reduces moving-animal LiDAR accumulation error by 37%, and estimates radial speed (r = 0.60), albeit with approximately 50% underestimation.

cs.CV↗

Quantitative positivity properties of the temperature in multi-dimensional thermoviscoelastic systems

We consider the classical model for small-strain thermoviscoelastic evolution in isotropic Kelvin-Voigt materials with inertia, as given by $$\begin{cases} u_{tt} = μΔu_t + (λ+μ)\nabla\nabla\cdot u_t + \hatμΔu + (\hatλ+\hatμ)\nabla\nabla\cdot u - B\nablaΘ, \\ κΘ_t = DΔΘ+ μ|\nabla u_t|^2 + (λ+μ)|\mathrm{div}\,u_t|^2 - BΘ\,\mathrm{div}\,u_t. \end{cases}$$ Recently, Winkler (arXiv:2602.05964) established global-in-time solvability for an initial value problem in smoothly bounded multi-dimensional domains $Ω$ under homogeneous Dirichlet boundary conditions for the displacement variable $u$, and homogeneous Neumann boundary conditions for the temperature $Θ$, allowing the heat capacity $κ$ to depend on $Θ$. Moreover, it was shown there that the corresponding temperature is positive a.e. in $Ω\times(0,\infty)$. In the present work, we strengthen this positivity result by deriving a quantitative lower bound for $Θ$. Our analysis applies to heat capacities $κ$ with power-law scaling for small arguments, precisely: either $κ(ξ)\simξ^α$ for some $α\ge 0$, or $κ(ξ)\geξ$, in a suitable neighborhood of $ξ=0$. Under these structural assumptions on $κ$, we show that for every $τ>0$ and $T>τ$ there exists $c(τ,T)>0$ such that $Θ(x,t)\ge c(τ,T)$ for a.e. $(x,t)\inΩ\times(τ,T)$.

math.AP↗

Delta N-gram: Forward-Only Continual Writing into a Language Model's Native N-gram Memory

Our previous analysis found that a model's native hashed N-gram table is where continual updates disturb the base least, but its writes needed backpropagation and changed the pretrained table. We present Delta N-gram, a forward-only write path into that table. The pretrained table T^0 is never modified. Evidence is written into a sparse patch Δon the rows it addresses: a 4.1M-parameter writer emits a target and a gate per (position, hash head) event, and a block-averaged delta rule keeps each row a convex combination of its old value and the gated targets. The writer is trained offline on raw text with the pretraining objective; at use time writing takes forward passes only, and clearing Δrestores the original model. A 0.6B prototype trained to answer questions keeps 16/16 facts after a second write; online gradient writes keep 2--4/16. We study two writers: a plain writer that encodes evidence with the T^0-only model, and a delta writer that reads its current memory while encoding. On Qwen3.8-Flash-Next, the plain writer's memory is document-specific: on 64 held-out news events it lowers continuation NLL by 0.068 nats/token against empty memory and by 0.024 against another document's memory, and 0.063 and 0.013 after 16 intervening articles. The delta writer's memory is more document-specific and keeps more of it under distraction (70% vs 54%). Over 35,000 writes on our previous seven-task chain both writers stay stable and the delta writer drifts less (layer-2 math drift 176% vs 188%); later accuracy changes by -0.26/-0.52pp (-7.29pp for gradient updates) and small-k_i drift is 17.9/17.5% (39.2%). Acquisition is negative, and general-input drift reaches 32.8% (20.75%): format rows read by every example grow to 4--12 times their pretrained norm. Zeroing eight such rows removes over 98% of layer-2 drift on math inputs, together with their NLL gain.

cs.CL↗

Entropy-production cost limits hierarchical decision-making in homing pigeon flocks

Collective decision-making requires individuals to reconcile diverse, often conflicting opinions to reach a common course of action. However, within a group, they rarely exert equal influence, leading to non-reciprocal communication patterns manifested as leader-follower relationships and social hierarchies. Here, using homing pigeon flocks as a model system, we develop a trajectory-based framework to infer and quantify hierarchy within navigating living collectives. We find that while small flocks exhibit pronounced hierarchy, increasing flock size progressively weakens it, driving the collection toward more egalitarian decision-making. We provide a physical basis of this observation using a thermodynamic framework in which non-reciprocal communication between birds carries an information-entropy cost. Our calculations reveal that hierarchy weakening observed in larger flocks is a direct consequence of maintaining a constant per-individual entropy production rate across flock sizes. Together, these results suggest that constraints on information-processing capacity may play an important role in the collective dynamics of living organisms.

cond-mat.soft↗

The often overlooked role of sound in liquid thermal transport

Formulated a hundred years ago, the Bridgman formula for thermal conductivity of liquids postulates a proportionality between sound velocity and thermal conductivity. This designates phonons as heat carriers in a liquid. Its empirical success has been under-appreciated and its conceptual implications overlooked. It is not mentioned in well-known condensed-matter textbook. Here, we review its origin, its links to hydrodynamic Euler equations and to the fundamental paradox surrounding the parabolic heat equation and its fate across the quantum-classical crossover.

cond-mat.mtrl-sci↗

Open dynamics with a moving hole: inhomogeneous IFS and exponential separation condition

Let $\mathcal F=\{f_i(x)=r_i x+t_i\}_{i=0}^{b-1}$ be a self-similar iterated function system (IFS) on $\mathbb R$ with $b\ge 3$, and let $K_{\mathcal F}$ be the associated self-similar set. Given $m\in\mathbb N$, for any sequence $ω=ω^0ω^1\ldots$ with each $ω^i\in \{0,1,\ldots,b-1\}^m$ a block of length $m$, let \[ K_{\mathcal F}^ω:=π_{\mathcal F}\left(\{(d_i)\in \{0,1,\ldots,b-1\}^{\mathbb N}: d_{k+1}d_{k+2}\ldots d_{k+m}\neω^k\quad\forall k\ge 0\}\right), \] where $π_{\mathcal F}$ is the natural coding map from $\{0,1,\ldots,b-1\}^{\mathbb N}$ to $K_{\mathcal F}$. The set $K_{\mathcal F}^ω$ is called the survivor set of an open dynamical system with a moving hole related to $ω$. When $\mathcal F$ is a homogeneous IFS satisfying the open set condition (OSC), the dimensions of $K_{\mathcal F}^ω$ were determined by the first author, Sun and Wang (Adv. Math., 2026). In this paper we generalize these results to inhomogeneous IFSs. When $\mathcal F$ satisfies the OSC, we give explicit formulae for the dimensions of $K_{\mathcal F}^ω$. In particular, we show that the packing dimension and upper box-counting dimension of $K_{\mathcal F}^ω$ always coincide, while the Hausdorff dimension and lower box-counting dimension of $K_{\mathcal F}^ω$ are not necessarily equal, which is different from the homogeneous case. Furthermore, when $\mathcal F$ satisfies the exponential separation condition and the similarity dimension $s_{\mathcal F}\le 1$, we are able to determine the Hausdorff dimension of $K_{\mathcal F}^ω$. Finally, we apply our results to badly approximable numbers and non-recurrence points in the setting of inhomogeneous IFS satisfying the OSC.

math.DS↗

Quasinormal modes of Type I perturbations of dilaton-Euler-Heisenberg black holes

We study the type I quasinormal modes (QNMs) of magnetically charged dilaton--Euler--Heisenberg (dEH) black holes, where axial gravitational and polar electromagnetic perturbations are coupled. Direct integration and Chebyshev pseudospectral methods give consistent QNM frequencies for the fundamental branches continued from Schwarzschild at $\ell=1,2,3$. Varying $α$ at fixed $ζ=α-β$ changes the spectrum on the same background. The damping response depends on charge and multipole and can have opposite signs for the two coupled branches. For $ζ<0$, dipole damping decreases with charge toward horizon merger. For $ζ>0$, the Type I charge range extends beyond the complementary polarization's local angular-gradient bound. All tracked modes remain damped in the nonextremal ranges, supporting the stability of these branches.

gr-qc↗

Post-Audit Mirage: Identifiability Limits of Offline Agent Verification

Offline tests can fail to reveal whether an agent update will remain safe after deployment. We operationalize this post-audit mirage using matched safe and harmful lifecycles that expose identical verifier-visible evidence while an isolated scorer records opposite deployment truth. Our theorem applies standard observational-equivalence and indistinguishability ideas to this executable audit boundary and states the resulting error-abstention tradeoff. The Post-Audit Mirage benchmark makes that boundary executable across authorization, scheduling, and shared-capacity environments. IdentifiedRangeMonitor uses fresh group-labelled harm outcomes to return deploy, hold, cannot determine, or unsupported. Experiments show that monitoring can recover the missing distinction in favorable settings but may remain undecided for rare groups, small effects, or missing observations. Verifier-agent evaluation must therefore test both calculation validity and whether the available evidence supports the deployment decision.

cs.AI↗

Music Between Two Minds: Individual Signatures, Shared States, and the Emergence of Creative Interaction

Some of the most valued forms of human creativity arise between people-in conversation, collaboration, and improvised music-yet how two minds jointly regulate the flow of novelty in real time remains unknown. Here we examined the information dynamics of interpersonal improvisation using 986 professional jazz improvisations. Pitch-based fluctuations of uncertainty and surprise behaved as signatures of individual identity: the two partners differed within 90% of takes, performers were identifiable from single solos and the separation between partners persisted undiminished across turns and takes. Rhythm-based fluctuations showed the reverse organization: partners were statistically indistinguishable within a take yet shifted together from take to take, and this shared state drifted gradually as each performance progressed, with each performer moving away from their own past at the same rate as from their partner's. Beyond joint drift, solo hand-offs revealed turn-by-turn complementarity: when one performer exceeded their own average surprise in the predictive dynamics of improvisation, the partner's next solo fell below their own, in both pitch and rhythm and in all duos. Improvising pairs thus neither fuse into one system nor remain two independent ones: they preserve individual melodic voices while sharing a rhythmic state, within which moment-to-moment push-pull continually rebalances their interaction. Individuality and togetherness thus coexist, carried by different musical dimensions, a measurable organization of creativity that emerges between minds.

q-bio.NC↗

The Hardy-Littlewood-type equivalence problem and its applications

The main purpose of this paper is to resolve the Hardy-Littlewood-type equivalence problem. In particular, we show that a Hardy-Littlewood-type theorem holds for arbitrary majorants in the case \(p\in(1,\infty)\), and that the equivalence holds in the case \(p=1\). For the proof, we employ new functional analytic approaches based on Fourier series, the Hilbert transform, and the uniform boundedness principle. Those proof methods are completely different from those of Dyakonov [Acta Math., 178 (1997), 143-167] and Pavlović [Acta Math., 183 (1999), 141-143]. In addition, we present several representative applications that improve a series of known results.

math.CV↗