Searcharxiv⌕ Search

arXiv subjects

Kentaro Nakamura

Publications and source records attributed to Kentaro Nakamura.

At least 19 recordsLinked to original sources

A General Statistical Framework for Attention and Manipulation Checks

Attention and manipulation checks are widely used in survey experiments to assess respondents' attentiveness and engagement with treatment, respectively. Yet these checks are subject to measurement error, which may itself depend on treatment when checks are administered after treatment exposure. Restricting analyses to respondents who pass these checks can therefore introduce substantial bias. We propose a general statistical framework for analyzing survey experiments with pre- or post-treatment attention and manipulation checks while accounting for measurement error. We show that three separate checks suffice to identify the proportion of respondents who would be attentive or successfully manipulated under treatment, provided that the checks are conditionally independent among treated respondents given their true, unobserved attentiveness or manipulation status and pre-treatment covariates. Under additional mild assumptions, this result also identifies the average treatment effect among respondents who would be attentive or successfully manipulated under treatment. Building on these identification results, we propose an estimator that allows flexible covariate modeling and establish its asymptotic normality. Applications to framing and digital media literacy experiments demonstrate how accounting for measurement error yields treatment effect estimates that are substantively different from those obtained using conventional approaches.

stat.ME↗

Observational Equivalence of LLM and Human Annotation

In this paper, we show that humans and large language models (LLMs) are observationally equivalent in coding texts. Recent LLMs agree with attentive humans at rates comparable to those observed among humans, and cross-LLM disagreement concentrates on texts that also divide humans. We demonstrate these patterns through replications of text-classification tasks from 14 peer-reviewed political science studies, with 13 LLMs, three human coders (Ph.D. students), and 165 crowd coders, independently applying identical codebooks. We further find that clarifying an underspecified codebook increases agreement among humans and between humans and LLMs. Together, these findings point to ambiguity in texts and coding rules as a shared source of disagreement and challenge the presumption that human labels should take precedence whenever humans and LLMs differ. We therefore argue that the central challenge of text annotation is not simply choosing between humans and LLMs, but developing coding rules that minimize ambiguity and accounting for the ambiguity that remains. To this end, we propose using cross-LLM disagreement to identify difficult cases, guide human review, and refine codebooks, and we develop ambiguity-aware bounds for downstream inference without requiring ground truth for every text.

cs.CL↗

GenAI Powered Dynamic Causal Inference with Unstructured Data

A growing number of scholars seek to estimate causal effects of unstructured data such as text, images, and video. However, existing methods typically treat each object as a single, static observation. We develop a statistical framework for dynamic causal inference with unstructured data by leveraging generative artificial intelligence (GenAI) models. Our approach enables researchers to estimate the causal effects of sequences of treatment features, including their positions within text and video. We first extract internal representations of unstructured objects from a GenAI model and then estimate a marginal structural model using a neural network architecture that jointly learns a deconfounder for each treatment feature in the sequence. Our semiparametric inference framework yields valid asymptotic confidence intervals. Simulation studies demonstrate that the proposed estimator recovers the target causal effects and that the confidence intervals achieve nominal coverage in finite samples. We further apply our method to a randomized experiment on the Hong Kong protests, showing that the effect of a treatment feature depends critically on its position within the text.

stat.ME↗

Causal Inference with Video Features as Treatments

We develop the first statistical methodology for causal inference with video features as treatments. Video is the most engaging content modality on the internet. A central causal question is how audience reactions change in response to treatment features that unfold over the course of a video. Unfortunately, standard causal inference methods are not applicable because confounding features are latent, high-dimensional, and dynamically related to both the treatment sequence and the outcome trajectory. To address these challenges, we first reproduce each video using a deep generative model and leverage the model's internal representations as learned, low-dimensional summaries of video content for causal estimation. We then establish that the average potential-outcome trajectory under dynamic stochastic interventions is nonparametrically identified. Lastly, we propose a consistent and asymptotically normal estimator based on a longitudinal neural network architecture. We empirically validate our approach by constructing a new causal inference benchmark consisting of $10{,}000$ Super Mario Bros. levels played by fixed Mario AI agents, where ground-truth causal effects are known by construction. Finally, we apply our method to television advertisements from the 2020 U.S. presidential campaign and find that increasing the probability of a candidate appearing over time leads to higher average viewer evaluations. With the proposed methodology, researchers can ask which visual features, appearing at which points in a video, influence audience responses, while benchmarking new methods against datasets with known ground-truth causal effects.

stat.AP↗

Leveraging Generative Artificial Intelligence for Causal Inference with Unstructured Data

We introduce GenAI-Powered Inference (GPI), a statistical framework for both causal and predictive inference using unstructured data, including text and images. GPI leverages open-source Generative Artificial Intelligence (GenAI) models---such as large language models and diffusion models---not only to generate unstructured data at scale but also to extract low-dimensional representations that are guaranteed to capture their underlying structure. Applying machine learning to these representations, GPI enables estimation of causal effects while quantifying associated estimation uncertainty. Unlike existing approaches to representation learning, GPI does not require fine-tuning of generative models, making it computationally efficient and broadly accessible. We illustrate the versatility of the GPI framework through three applications: (1) estimating the effects of Chinese social media censorship while adjusting for textual confounders, (2) isolating the impact of specific image features from that of other correlated features in the same image, and (3) assessing the persuasiveness of political rhetoric. An open-source software package is available for implementing GPI.

cs.LG↗

Anticyclotomic Iwasawa theory of CM elliptic curves at ramified primes

We propose an integral framework for the anticyclotomic Iwasawa theory of CM elliptic curves $E$ at primes $p$ ramified in the CM field. The $\varepsilon$-constants of the geometric specialisations of the associated $p$-adic conjugate symplectic self-dual deformation equidistribute between $\pm 1$ within every layer of the anticyclotomic tower, and none of the geometric specialisations are trianguline at $p$. We define signed Selmer groups via the Lagrangian local conditions arising from the local sign decomposition established in the prequel \cite{BKNO}, and our central result is the formulation and proof of an integral Iwasawa main conjecture relating one of them to the $p$-adic $L$-function $\mathscr{L}_p(E)$ constructed there. We further show that $\mathscr{L}_p(E)$ interpolates the central Hecke $L$-values of the twists with $\varepsilon$-constant $+1$, including twists of arbitrary infinity type, and relate its values at twists with $\varepsilon$-constant $-1$ to the $p$-adic logarithm of certain Selmer elements. This provides the first Iwasawa main conjecture in terms of a $p$-adic $L$-function and Selmer groups for a $p$-adic deformation admitting no trianguline geometric specialisation. The proofs rest on our resolution of a Rubin-type conjecture for the underlying local deformation, together with a theory of plus/minus local points along the anticyclotomic tower, based on the Gaussian plus/minus cyclotomic polynomials rooted in Gauss' Disquisitiones Arithmeticae.

math.NT↗

Causal Inference with Generative Artificial Intelligence: Application to Texts as Treatments

In this paper, we demonstrate how to enhance the validity of causal inference with unstructured high-dimensional treatments like texts, by leveraging the power of generative Artificial Intelligence (GenAI). Specifically, we propose to use a deep generative model such as large language models (LLMs) to efficiently generate treatments and use their internal representation for subsequent causal effect estimation. We show that the knowledge of this true internal representation helps disentangle the treatment features of interest, such as specific sentiments and certain topics, from other possibly unknown confounding features. Unlike existing methods, the proposed GenAI-Powered Inference (GPI) methodology eliminates the need to learn causal representation from the data, and hence produces more accurate and efficient estimates. We formally establish the conditions required for the nonparametric identification of the average treatment effect, propose an estimation strategy that avoids the violation of the overlap assumption, and derive the asymptotic properties of the proposed estimator through the application of double machine learning. Finally, using an instrumental variables approach, we extend the proposed GPI methodology to the settings in which the treatment feature is based on human perception. The GPI is also applicable to text reuse where an LLM is used to regenerate existing texts. We conduct simulation and empirical studies, using the generated text data from an open-source LLM, Llama 3, to illustrate the advantages of our estimator over state-of-the-art causal representation learning algorithms.

stat.AP↗

Surrogate Representation Inference for Text and Image Annotations

As researchers increasingly rely on machine learning models and LLMs to annotate unstructured data, such as texts or images, various approaches have been proposed to correct bias in downstream statistical analysis. However, existing methods tend to yield large standard errors and require some error-free human annotation. In this paper, I introduce Surrogate Representation Inference (SRI), which assumes that unstructured data fully mediate the relationship between human annotations and structured variables. The assumption is guaranteed by design provided that human coders rely only on unstructured data for annotation. Under this setting, I propose a neural network architecture that learns a low-dimensional representation of unstructured data such that the surrogate assumption remains to be satisfied. When multiple human annotations are available, SRI can be extended to further correct non-differential measurement errors that may exist in human annotations. Focusing on text-as-outcome settings, I formally establish the identification conditions and semiparametric efficient estimation strategies that enable learning and leveraging such a low-dimensional representation. Simulation studies and a real-world application demonstrate that SRI reduces standard errors by over 50% when machine learning classification accuracy is moderate and provides valid inference even when human annotations contain non-differential measurement errors.

cs.LG↗

A local sign decomposition for symplectic self-dual Galois representations of rank two

We prove the existence of a new structure on the first Galois cohomology of generic families of symplectic self-dual $p$-adic representations of $G_{\mathbb{Q}_p}$ of rank two (a local sign decomposition): a functorial decomposition into free rank one Lagrangian submodules which encodes the $p$-adic variation of Bloch--Kato subgroups via completed epsilon constants, mirroring a symplectic structure. The local sign decomposition has diverse local as well as global arithmetic consequences. This includes compatibility of the Mazur--Rubin arithmetic local constant and completed epsilon constants, answering a question of Mazur and Rubin. The compatibility leads to new cases of the $p$-parity conjecture for Hilbert modular forms at supercuspidal primes $p$. We also formulate and prove an analogue of Rubin's conjecture over ramified quadratic extensions of $\mathbb{Q}_p$. Using it, we construct an integral $p$-adic $L$-function for anticyclotomic deformation of a CM elliptic curve at primes $p$ ramified in the CM field.

math.NT↗

Observation of Rayleigh scattering by simplified optical correlation-domain reflectometry without frequency shifter

We present a method for measuring the transmission loss of an optical fiber using simplified optical correlation-domain reflectometry. By intentionally lowering the spatial resolution of the system, we observe the Rayleigh scattered signal for the first time without the need for a frequency shifter. Using this method, we simultaneously measure the transmission loss, location, and loss of faulty connections along a 10-km-long fiber under test by performing distributed reflected-power measurements of Rayleigh scattering and Fresnel reflection.

physics.optics↗

Local epsilon conjecture and p-adic differential equations

Laurent Berger attached a p-adic differential equation N_rig(M) with a Frobenius structure to an arbitrary de Rham (phi, Gamma)-module over a Robba ring. In this article, we compare the local epsilon conjecture for the cyclotomic deformation of M with that of N_rig(M). We first define an isomorphism between the fundamental lines of their cyclotomic deformations using the second author's results on the big exponential map. As a main result of the article, we show that this isomorphism enables us to reduce the local epsilon conjecture for the cyclotomic deformation of M to that of N_rig(M).

math.NT↗

High-speed high-resolution optical correlation-domain reflectometry without using electrical spectrum analyzer

We propose a newly configured optical correlation-domain reflectometry (OCDR) without the use of an electrical spectrum analyzer (ESA) for high-speed distributed reflectivity measurement with an enhanced spatial resolution. First, the operation of ESA-free OCDR is analyzed by numerical simulation, the results of which show the potential of the configuration to perform distributed reflectivity measurement with an improved spatial resolution. Subsequently, the simulation results are verified by comparison experiments, where distributed reflectivity measurements along a 32-m-long single-mode fiber joint with multiple connectors are performed using both conventional (with averaging) and ESA-free OCDR configurations (without averaging) at a repetition rate of 100 Hz. The widths of the reflectivity peaks experimentally obtained by the conventional and ESA-free OCDR configurations are 22.9 cm and 7.0 cm, respectively. Finally, we experimentally evaluated the performance of the ESA-free OCDR at higher repetition rates, achieving 6.3-cm spatial resolution at a repetition rate of 1 kHz. This result indicates that the ESA-free OCDR can perform a distributed reflectivity measurement with an improved spatial resolution at a higher operation speed than ever.

physics.optics↗

Zeta morphisms for rank two universal deformations

In this article, we construct zeta morphisms for the universal deformations of odd absolutely irreducible two dimensional mod p Galois representations satisfying some mild assumptions, and prove that our zeta morphisms interpolate Kato's zeta morphisms for Galois representations associated to Hecke eigen cusp newforms. The existence of such morphisms was predicted by Kato's generalized Iwasawa main conjecture. Based on Kato's original construction, we construct our zeta morphisms using many deep results in the theory of p-adic (local and global) Langlands correspondence for GL_{2/Q}. As an application of our zeta morphisms and the resent article {KLP19}, we prove a theorem which roughly states that, under some mu=0 assumption, Iwasawa main conjecture without p-adic L-function for f holds if this conjecture holds for one g which is congruent to f.

math.NT↗

Hibikino-Musashi@Home 2020 Team Description Paper

Our team, Hibikino-Musashi@Home (HMA), was founded in 2010. It is based in Japan in the Kitakyushu Science and Research Park. Since 2010, we have annually participated in the RoboCup@Home Japan Open competition in the open platform league (OPL). We participated as an open platform league team in the 2017 Nagoya RoboCup competition and as a domestic standard platform league (DSPL) team in the 2017 Nagoya, 2018 Montreal, and 2019 Sydney RoboCup competitions. We also participated in the World Robot Challenge (WRC) 2018 in the service-robotics category of the partner-robot challenge (real space) and won first place. Currently, we have 20 members from eight different laboratories within the Kyushu Institute of Technology. In this paper, we introduce the activities that have been performed by our team and the technologies that we use.

cs.RO↗