arXiv subjects

Kosuke Aizawa

Publications and source records attributed to Kosuke Aizawa.

4 recordsLinked to original sources

arXiv2026

AI's Capability in Assisting Scientific Research in Physics, Astrophysics, and Cosmology I: Literature Review

We investigate how well large language models (LLMs) can assist with literature reviews for scientific research. We perform a controlled study of eight expert-conceived research projects across the areas of physics, astrophysics, and cosmology. Each project has a defined background and goal, and human experts and AI prompters are asked to perform identical literature review tasks in parallel. We compare the relevant literature selected by humans with that selected by mid-2025 LLMs (ChatGPT-4o, ChatGPT Deep Research, and Gemini). We find the overlap between human- and AI-selected references to be small ($<$6\%), indicating that AI models do not yet reproduce a competent expert search on their own, though they have the potential to complement literature searches by humans. We then assess the reliability and completeness of AI-generated candidate references, distinguishing two types of hallucination: fabrications (references to nonexistent papers) and metadata mismatches (real papers with one or more incorrect fields). We find that while fabricated references make up 3\% of the AI-generated references, 64\% are real papers with at least one incorrect field (title, author, year, journal, DOI, or link), indicating that the mid-2025 models require systematic verification. However, the performance is significantly improved for the 2026 model ChatGPT Pro 5.5, with a single-project test showing zero fabrication or metadata mismatches.

astro-ph.IM↗

arXiv2026

AI's Capability in Assisting Scientific Research in Physics, Astrophysics, and Cosmology II: Project Planning and Proposal Evaluation

We investigate how well large language models (LLMs) can assist scientific project planning and proposal evaluation. One-page project plans were independently generated for eight expert-conceived research projects in physics, astrophysics, and cosmology by human researchers and three contemporary LLMs (ChatGPT, Claude, and DeepSeek; mid-2025 models, used with their default tool access). The resulting 32 proposals were blindly evaluated by four human reviewers and two newer frontier LLMs (Claude Opus 4.8 and ChatGPT Pro 5.5) using a four-aspect evaluation rubric. Reviewers were also asked to identify whether each proposal was written by a human or an AI. Human reviewers rated human- and AI-written proposals similarly overall, whereas both AI reviewers scored AI-written proposals about one point higher (on a five-point scale) than human-written proposals. Human reviewers correctly identified human- and AI-written proposals 72% and 79% of the time, respectively, while both AI reviewers correctly classified all 32 proposals (100%). These results suggest that current LLMs can produce project plans comparable to human-written ones in the eyes of human reviewers, but that AI reviewers show a systematic preference for AI-generated proposals. Our results suggest caution when deploying LLMs widely in proposal preparation and evaluation.

cs.CL↗

arXiv2026

Silicon-based vacuum window for millimeter and submillimeter-wave astrophysics

We designed, fabricated, and characterized the properties of a silicon-based vacuum window suitable for millimeter-wave astrophysical applications. The window, which has a diameter of 124 mm, optically active diameter of 68 mm, and thickness of about 4 mm, gives an average transmittance and reflectance of 99% and 1%, respectively, a fractional bandwidth of 67%. Absorptive loss is below the detection limit of our measurement. The anti-reflection coating is made with laser ablated sub-wavelength structures (SWS), and the measured transmittance and reflectance values agree with modeling based on the measured SWS shapes. The window has been integrated into DESHIMA v2.0, an astrophysics instrument that took year-long observations with the Atacama Submillimeter Telescope Experiment.

astro-ph.IM↗

arXiv2025

Prototype sub-wavelength structure anti-reflection coating on alumina filters for ground-based CMB telescopes

We present designs and fabrication of sub-wavelength anti-reflection (AR) structures on alumina for infrared absorptive filters with passbands near 30, 125, and 250 GHz. These bands are widely used by ground-based instruments measuring the cosmic microwave background radiation. The designs are tuned to provide reflectance of 2% or less for fractional bandwidths between 51% and 72%, with each of the three primary bands containing two sub-bands. We make the sub-wavelength structures (SWS), which resemble a two-dimensional array of pyramids, using laser ablation. We measure the shapes of the fabricated pyramids and show that for incidence angles up to 20 degrees the predicted in-band average reflectance is 2% or less, in agreement with the design. The band average instrumental polarization is less than $3\times 10^{-3}$.

astro-ph.IM↗