The Inference Report

Ground-based astronomical observations frequently contain streaks produced by artificial satellites, space debris, and potentially Near-Earth Objects (NEOs). While machine-learning models can reliably detect these features, their practical adoption in observatory operations is often limited by the lack of integrated tools for visual inspection, validation, workflow management, and structured data storage. This paper presents the StreakMind Workbench, a framework that applies MLOps practices to bridge research-oriented machine-learning pipelines with routine observatory operations. Rather than introducing new detection algorithms, the Workbench addresses a software-engineering challenge in astronomical computing: maintaining a single authoritative source of scientific processing code while providing astronomers with an operational environment for workflow execution and result inspection. Integrated with the reference StreakMind AI model of Carrillo et al. (2026) and implemented in Python using PyQt5, the Workbench supports the complete workflow from FITS ingestion to database storage, including inference, result inspection, database exploration, training management, and Minor Planet Center formatted observations. Validation on 273 images from La Sagra Observatory demonstrates successful end-to-end workflows while maintaining consistency with the underlying StreakMind scientific code. The platform facilitates operational use of a research ML pipeline in meter-class observatories and moderate-scale campaigns, supporting Space Situational Awareness and planetary defence.

Context: We developed a probabilistic machine learning method with the aim of performing the O(10)-way classification of low- and high-resolution spectra of stellar and extragalactic targets for the upcoming 4MOST survey. In fulfilment of the survey requirements, this method should be able to express uncertainty in the input data as well as uncertainty introduced in its prediction. Aims: Four different methods are explored: (1) convolutional neural networks (CNNs), (2) the Dirichlet distribution, (3) Monte Carlo dropout (MCD), (4) Bayesian neural Networks (BNNs) + variational inference (VI). Training and validation was performed using labelled spectra from the SDSS database and a custom 4MOST mock dataset. All the methods were compared in terms of the same metrics: accuracy, area under the curve (AUC), expected calibration error (ECE), Shannon entropy, negative log-likelihood (NLL), Brier score, training time, and inference time. Methods: A CNN with simple architecture and about 20,000 parameters was trained to achieve classification accuracies of 91.5% on SDSS data and 92.8% on 4MOST mock data. The direct Dirichlet prediction and VI models tested provide uncertainties on class membership probabilities, but they confuse classes more often. The MCD on a CNN is found to be the most suitable; it boosts the point-estimate accuracies to 92.6% and 93.9%, while still providing fast training and sufficiently fast inference. Compared to a standard CNN, the method additionally provides well-calibrated uncertainties at marginal extra cost.

Domain-specialized language models are widely used for scientific question answering, but stronger general-purpose systems raise a sharper question: when does domain-specific fine-tuning remain valuable for open-ended scientific reasoning? We study this in astronomy with a curated QA benchmark from publicly available 2017--2026 Olympiad-style materials. The free-response subset contains 300 questions, including 204 text-only and 96 image-linked examples. We compare open-weight and API-served general-purpose, multimodal, and astronomy-specialized models using judge-based correctness and complementary reference metrics. Strong general-purpose models establish the highest correctness baseline in this testbed, while analyses of metric agreement, judge sensitivity, benchmark composition, and modality reveal variation not captured by a single leaderboard. These results motivate treating domain specialization as a task- and deployment-dependent property and highlight the role of domain-specific evaluation in determining which models, capabilities, and evaluation criteria are appropriate for scientific workflows.

Language models leave a distinctive vocabulary in the prose they help write, and we measure how much of the astronomy literature now carries it. From the full text of 207,111 astro-ph papers spanning 2015 to mid-2026, we count those words in each paper and model the counts, in proportion to paper length, as a mixture of assisted and unassisted writing in a hierarchical Bayesian model. Papers from before 2020 calibrate the unassisted rate, and the 392 papers that disclose model use calibrate the assisted one. Our answer depends on how often these words would appear today if nobody used a model, a rate that must be modeled rather than observed, so we extend it past 2020 under three assumptions and report all three. For 2025 that gives $54^{+8}_{-8}\,(\mathrm{stat},\,95\%)\,^{+26}_{-0}\,(\mathrm{sys,\ background})$% of papers, the second error being the spread across the three. The estimate stays at or above 36% when we vary that choice, the calibration, and the requirement that adoption only rises. A word list built from the astro-ph corpus, keeping only words that rose across every subfield, leaves 2025 in the same range. Assisted writing is also getting harder to see, since authors adapt to the words that reveal it and the marker excess more than halves between 2023 and 2026. Our model allows for that fading, so it can separate a fainter trace from reduced use. More than half of recent astro-ph papers therefore carry a language-model trace, while only 0.81% of 2025 papers disclose it, one declaration for every $\sim$66 papers with a trace.

Learned surrogates for expensive inner solver blocks are a widely pursued route to faster multiphysics simulation. We report a controlled, end-to-end negative result and identify three structural barriers, none of them a deficiency of the network we trained. The testbed is the implicit Newton solve coupling energy-dependent neutrino radiation to matter in a general-relativistic radiation-hydrodynamics code, its most expensive physics routine per call. First, per-call cost and share of runtime are different quantities, and only the second bounds acceleration. An exclusive self-time profile puts the target block at 16.9% of critical-rank wall clock, capping any surrogate at ~1.2x by Amdahl's law. A surrogate 5.8x cheaper per call merely ties the solver, and the configuration stable enough to run without fallback reaches only parity. Second, offline accuracy cannot rank surrogates for deployment: across fourteen networks the pooled Spearman error-versus-survival correlation (rho = +0.73) is a between-family confound that vanishes under control (rho = -0.04). Third, a correct out-of-distribution gate cannot accelerate a loop that leaves its training distribution. We give the break-even deferral fraction in closed form: because the visited states sit 73x off the data manifold, the gate defers 96.8 to 99.7% of cells, almost invariant to surrogate quality. Including its own cost, the gated loop is a 0.94 to 0.96x slowdown. We further separate stability from fidelity: a never-crashing gated run accumulates a linear -19.9% density bias over 6000 steps. The error is a directed, ballistically accumulating bias, not the variance-driven divergence the autoregressive literature targets.

Microlensing can reveal populations of faint compact objects that are otherwise difficult to detect. Depending on their design, all-sky surveys have the potential to search for these objects across the sky. The Transiting Exoplanet Survey Satellite (TESS), primarily designed to detect transiting exoplanets, also provides near all-sky coverage with high cadence. In this work, we use TESS data to search for microlensing candidates using both traditional and machine-learning methods and to identify associated false positives in high-cadence surveys. Microlensify is a physics-informed, transformer-based variational autoencoder trained on simulated single-lens microlensing light curves and real TESS Sector 12 data. The model classifies events, reconstructs light curves, and estimates microlensing event durations. Applied to $\sim 5.6$ million TESS light curves, it identified between $0.036\%$ and $1.89\%$ as microlensing candidates across different TESS pipelines. After applying microlensing detection metrics and cross-matching with SIMBAD, we obtained a final list of candidates and identified false positives including long-period variables, Mira variables, cataclysmic variables, red giants, and transients. We also found Gaussian-like peaks caused by asteroid crossings, a potential source of false positives in high-cadence microlensing surveys. The model also predicts event duration with an accuracy of $R^2 = 0.97$. The model was further tested on published events from different ground-based microlensing surveys, confirming 92.7% as microlensing, demonstrating its applicability across surveys with different cadences.