Two time domain surveys, recently funded as part of the Eric and Wendy Schmidt Observatory System: the Argus Array, in the optical, and the Deep Synoptic Array (DSA), in the radio, will transform gamma-ray burst (GRB) science via the serendipitous discovery of hundreds of GRB afterglows per year. In this work, we simulate DSA and Argus observations of GRB afterglows. We find that, of the long-duration GRBs (LGRBs) detected by the Fermi Gamma-ray Burst Monitor, (26 ± 3)% will yield afterglow detections with Argus and (44 ± 3)% with DSA, corresponding to rates of 51 ± 5 and 86 ± 8 per year, respectively. We also compute rates for both upcoming and proposed GRB monitors: the forthcoming StarBurst Multimessenger Pioneer, with 84 ± 6 detections per year in Argus and 158 ± 11 detections per year in DSA, and the Moon Burst Energetics All-sky Monitor (MoonBEAM) concept, with 90 ± 9 per year in Argus and 160 ± 14 per year in DSA. The observatory system will also detect 118 ± 10 optical and 199 ± 17 radio afterglows per year, independent of GRB triggers, exceeding the current annual rate with global follow-up. Afterglow counterparts to short-duration GRBs, originating from neutron star mergers, will be detected at 5%–10% of the LGRB afterglow rate, which is promising for multimessenger detections of gravitational wave sources and constraining the neutron star merger rate. The Argus Array, with its second–minute cadence, will detect afterglows before they peak ∼18% of the time, which will dramatically increase the sample of observed reverse shock and prompt optical emission.

The NSF-DOE Vera C. Rubin Observatory, Roman Space Telescope, Euclid, and other next-generation surveys will deliver imaging, spectroscopic, and time-domain data at scales that increasingly shift the bottleneck in astronomical machine learning (ML) projects from model design to infrastructure. We present Hyrax, an open-source, modular, GPU-enabled Python framework that supports the full ML lifecycle in astronomy: from data acquisition and training to inference and experiment comparison, with capabilities including multimodal dataset support, integrated vector databases for similarity search, and interactive two- and three-dimensional latent-space exploration for unsupervised discovery. We demonstrate Hyrax's versatility through five representative applications on real survey data: (i) unsupervised representation learning on ∼ 4×10^5 Rubin Legacy Survey of Space and Time (LSST) Data Preview 1 (DP1) galaxies, surfacing new merger and low-surface-brightness candidates missing from reference Euclid and Dark Energy Survey catalogs, while also isolating imaging artifacts – all without labeled training data; (ii) hybrid density-based clustering for identifying cluster-scale gravitational lens candidates in DP1 data; (iii) multimodal early-time transient classification in the Zwicky Transient Facility leveraging light curves, spectra, images, and metadata; (iv) supervised false-positive filtering in shift-and-stack searches for distant solar system objects in the Dark Energy Camera Ecliptic Exploration Project survey; and (v) supervised detection of semi-resolved dwarf galaxies in Hyper Suprime-Cam and LSST-like imaging using synthetic source injection. Together, these results demonstrate that Hyrax provides astronomy-specific ML infrastructure that enables systematic discovery and rapid methodological iteration across next-generation astronomical surveys.

Low-latency gravitational-wave alerts provide the greater multi-messenger community with information about the candidate events detected by the International Gravitational-Wave Network. Prompt release of data products such as the sky localization, false alarm rate, and pastro values allow astronomers to make informed decisions on which candidate gravitational-wave events merit target of opportunity follow-up. However, false alarms where a gravitational-wave candidate, or trigger, is the result of terrestrial noise, are an inherent part of gravitational-wave searches. In addition, with the presence of multiple gravitational-wave searches, different searches may have varying assessments of the significance of a given trigger. As a complement to quantities such as pastro, we provide a Machine Learning (ML) based approach to determining whether candidate events are astrophysical or terrestrial in nature. This ML classifier utilizes information provided by multiple low-latency search pipelines and downstream data products in its feature space, and is trained on a realistic real-time simulation campaign called the Mock Data Challenge (MDC). The Random Forest implementation has an Area Under the Receiver Operating Characteristic Curve (AUC) of 0.96 and accuracy of 0.90 on the MDC training set compared to pastro which had an AUC of 0.72 and an accuracy of 0.75. We tested on events from Advanced LIGO (aLIGO)'s, Advanced Virgo (AdVirgo)'s, and KAmioka GRAvitational-wave observatory (KAGRA)'s third observing run (O3) and got an AUC of 0.93 and accuracy of 0.86 compared to pastro which had an AUC of 0.82 and accuracy of 0.75.

The Luminous Fast Blue Optical Transient (LFBOT) AT2022tsd exhibited minutes-timescale optical flares in the tens of days following the initial transient event, likely due to a central engine -- either an accreting black hole or a magnetar. In this paper, we use data from the Transiting Exoplanet Survey Satellite (TESS) and the Zwicky Transient Facility (ZTF) to constrain the occurrence of similar flares in the 12 (of 14) known LFBOTs that had observational coverage with TESS from tens of days to thousands of days after the transient's initial emission. We find seven flare-like signals at the locations of four unique LFBOTs; all seven can likely be attributed to a solar system object (SSO) moving through the TESS aperture. Assuming all seven flares arise from SSOs, for the LFBOT AT2024qfm we rule out flaring with a similar timescale (40--65 d) and luminosity ($νL_ν\sim10^{43}$ erg s$^{-1}$) as in AT2022tsd, while for AT2022tsd itself we rule out flares between 380--430 d after the initial transient that were as luminous as the earlier flares. This observation suggests that the engine power in AT2022tsd declined or shut off on a timescale of hundreds of days. We also find that there is no late-time activity detectable in TESS thousands of days after the prototype LFBOT, AT2018cow. We discuss our constraints on the duty cycle of such flaring and then present estimates for the number of minutes-duration flares detectable with ongoing and upcoming high-cadence ($\ll1$ d) wide-field surveys.

Electron-capture supernovae (ECSNe) may arise from ONeMg-core collapse in super-asymptotic giant branch (sAGB) stars near the low-mass core-collapse limit (approximate to 8-10 M circle dot). At early times, models predict that ECSNe resemble low-mass red supergiant iron-core-collapse SNe, making the two channels difficult to distinguish. Nebular spectroscopy, however, can reveal differences in ejecta composition. We present a systematic sample of 19 nebular spectra of low-luminosity Type IIP (LLIIP) SNe from the Zwicky Transient Facility Census of the Local Universe survey, obtained 115-450 days after explosion. Their low velocities expose narrow lines blended in brighter SNe, which we identify and model to constrain progenitor properties. We find a strong correlation between the FWHM of H i lambda 6563 and peak luminosity, showing that LLIIP SNe occupy the low-energy end of the core-collapse population, but no correlation with plateau duration, suggesting that envelope and core properties are not tightly linked. Only one SN reaches the extremely low H i lambda 6563 widths predicted for the weakest similar to 9 M circle dot explosion models, implying that such low-energy events are intrinsically rare. Combining our sample with 118 literature nebular spectra of Type II SNe, we infer an IMF slope of 2.1 +/- 1.2. We also introduce an "ECSN score" based on the absence of He- and O-shell emission lines, and identify two plausible ECSN candidates, SN 2023bvj and SN 2024btj. However, neither shows the extremely narrow nebular lines predicted by current ECSN models. If ECSNe arise predominantly through the LLIIP channel, we infer an upper limit on the ECSN rate of less than or similar to(5-8) & times; 102 Gpc-3 yr-1, corresponding to a narrow sAGB progenitor mass window of Delta MsAGB less than or similar to 0.02-0.06 M circle dot.

Modern wide-field time-domain surveys facilitate the study of transient, variable and moving phenomena by conducting image differencing and relaying alerts to their communities. Machine learning tools have been used on data from these surveys and their precursors for more than a decade, and convolutional neural networks (CNNs), which make predictions directly from input images, saw particularly broad adoption through the 2010s. Since then, continually rapid advances in computer vision have transformed the standard practices around using such models. It is now commonplace to use standardized architectures pre-trained on large corpora of everyday images (e.g., ImageNet). In contrast, time-domain astronomy studies still typically design custom CNN architectures and train them from scratch. Here, we explore the effects of adopting various pre-training regimens and standardized model architectures on the performance of alert classification. We find that the resulting models match or outperform a custom, specialized CNN like what is typically used for filtering alerts. Moreover, our results show that pre-training on galaxy images from Galaxy Zoo tends to yield better performance than pre-training on ImageNet or training from scratch. We observe that the design of standardized architectures are much better optimized than the custom CNN baseline, requiring significantly less time and memory for inference despite having more trainable parameters. On the eve of the Legacy Survey of Space and Time and other image-differencing surveys, these findings advocate for a paradigm shift in the creation of vision models for alerts, demonstrating that greater performance and efficiency, in time and in data, can be achieved by adopting the latest practices from the computer vision field.

Rapid and reliable detection and dissemination of source parameter estimation data products from gravitational-wave events, especially sky localization, is critical for maximizing the potential of multimessenger astronomy. Machine learning based detection and parameter estimation algorithms are emerging as production ready alternatives to traditional approaches. Here, we report validation studies of AMPLFI, a likelihood-free inference solution to low-latency parameter estimation of binary black holes. We use simulated signals added into data from the LIGO-Virgo-KAGRA's (LVK's) third observing run (O3) to compare sky localization performance with BAYESTAR, the algorithm currently in production for rapid sky localization of candidates from matched-filter pipelines. We demonstrate sky localization performance, measured by searched area and volume, to be equivalent with BAYESTAR. We show accurate reconstruction of source parameters with uncertainties for use in distributing low-latency coarse-grained chirp mass information. In addition, we analyze several candidate events reported by the LVK in the third gravitational-wave transient catalog (GWTC-3) and show consistency with the LVK's analysis. Altogether, we demonstrate AMPLFI's ability to produce data products for low-latency public alerts.

We present multiwavelength observations and analysis of six luminous fast blue optical transients (LFBOTs) discovered in Zwicky Transient Facility (ZTF) survey data. We identified these LFBOTs from their fast light-curve evolution (t_1/2≤ 12d), blue colors at peak brightness (g-r≤-0.5mag), a visible host galaxy, high optical luminosity (M_g<-20), and an X-ray or radio detection. With the exception of AT2024aehp (ZTF24abygbss), these transients exhibit peaks in their 10GHz radio light curves at t_rest≈ 50-100 d, with peak radio luminosities ranging from 10^38-10^40 erg s^-1. Modeling the radio emission as synchrotron radiation indicates a fast (v=0.1-0.3c) shock in a dense (n_e≈10^3-10^4 cm^-3) medium. The X-ray emission varies by ≈2 orders of magnitude in luminosity (10^42-10^44 erg s^-1) at t_rest∼20d. Analysis of the host-galaxy photometry and spectroscopy for each transient shows that they are predominantly nonnuclear (a few kpc offset) with star-forming host galaxies of stellar masses 10^9-10^11 ,M_⊙. Unlike all other LFBOTs to date, AT2024aehp exhibited a luminous (M<-19mag) plateau in the optical light curve; spectra during this plateau phase showed a featureless blue continuum. The 6-15 GHz radio emission of AT2024aehp brightened by over an order of magnitude from t_rest≈70d to t_rest≈130d. The mostly consistent radio behavior between optically selected LFBOTs implies a similar circumburst medium, leading us to prefer a progenitor scenario in which mass is lost in a consistent way shortly prior to the terminal event, such as a massive star merging with a compact object.

On November 12th, 2025 the LIGO–Virgo–KAGRA (LVK) collaboration reported gravitational waves (GWs) from a compact object merger candidate (S251112cm) with at least one sub-solar mass component. Using the Dark Energy Camera (DECam), the Fraunhofer Telescope at Wendelstein Observatory (FTW), and the Zwicky Transient Facility (ZTF), we surveyed 56% of the GW localization region beginning 2.4 hours after the GW alert. We find no kilonova (KN) counterpart, and use radiative-transfer models to rule out 42% (ZTF), 68% (DECam), and 92% (FTW) of the KN models as possible emission from this GW candidate. Within the recently proposed disk-fragmentation (“superkilonova”) model for generating sub-solar mass neutron star mergers from stellar core-collapse, the delay between the supernova explosion time and the GW merger time is estimated to be less than a few days. Searching this time window prior to the GW event, we identify and spectroscopically classify a IIb supernova (SN 2025adtq), with a spatial association odds ratio of log_10ℐ≈ 4.8, a chance coincidence probability of ∼2–9%, and an estimated explosion time ∼2 days prior to S251112cm. SN 2025adtq is the second Type IIb supernova found in spatial and temporal coincidence with a sub-solar mass GW candidate, following the previously reported S250818k/SN 2025ulz association; jointly, we measure an odds ratio that favors the association hypothesis over the null, however, when conditioned on finding a coincident supernova by chance, the odds ratio disfavors association. Together, these results provide suggestive but inconclusive evidence for the superkilonova formation channel.

With the arrival of ever higher throughput wide-field surveys and a multitude of multi-messenger and multi-wavelength instruments to complement them, software capable of harnessing these associated data streams is urgently required. To meet these needs, a number of community supported alert brokers have been built, currently focused on processing of Zwicky Transient Facility (ZTF; similar to 105-106 alerts per night) with an eye toward Vera C. Rubin Observatory's Legacy Survey of Space and Time (LSST; similar to 2 & times; 107 alerts per night). Building upon the system that successfully ran in production for ZTF's first seven years of operation, we introduce Burst & Outburst Observations Monitor (BOOM), an analysis framework focused on real-time, joint brokering of these alert streams. BOOM harnesses the performance of a Rust-based software stack relying on a non-relational MongoDB database combined with a Valkey in-memory processing queue and a Kafka cluster for message sharing. With this system, we demonstrate feature parity with the existing ZTF system with a throughput similar to 7 & times; higher. We describe the workflow that enables the real-time processing as well as the results with custom filters we have built to demonstrate the system's capabilities. In conclusion, we present the development roadmap for both BOOM and Babamul-the public-facing LSST alert broker built atop BOOM-as we begin the Rubin era.

The Zwicky Transient Facility Census of the Local Universe survey yielded a sample of 330 Type IIP supernovae (SNe) with well-constrained peak luminosities. In paper I, we measured their luminosity function and volumetric rate. Here (paper II), we present the largest systematic study of lightcurve properties for Type IIP SNe from a volume-limited survey, analyzing a selected subset of 129 events, including 16 low-luminosity Type IIP (LLIIP) SNe with Mr,peak >= -16 mag. We find that plateau slope correlates with peak brightness, with many LLIIP SNe showing positive slopes-suggesting smaller progenitor radii and distinct density profiles compared to brighter Type IIP SNe. The plateau duration shows only a weak dependence on peak brightness, likely suggesting binary interaction. One SN exhibits a plateau-to-tail drop of >3.5 mag, consistent with an electron-capture or failed SN with very low or zero nickel mass. We derive explosion and progenitor parameters of the entire Type IIP SN sample using semi-analytical and radiation-hydrodynamical models. Based on radiation-hydrodynamical model fitting, LLIIP SNe are characterized by low nickel masses (0.001-0.025 M-circle dot), low explosion energies (0.1-0.28 & times; 10(51 )erg), low ejecta masses ( 8.1(-1.7)(+0.8) M-circle dot), and ZAMS masses below 11 M-circle dot. In comparison, the full Type IIP SN sample spans a wider range with nickel masses (0.001-0.222 M-circle dot), explosion energies (0.10-4.43 & times; 10(51 )erg), ejecta masses (5.4-24.8 M-circle dot), and ZAMS masses (9.3-16.7 M-circle dot). We find strong correlations between peak brightness, explosion energy, and nickel mass that extend to the low-luminosity end. We conclude that LLIIP SNe represent the faint, low-energy end of the Type IIP population and originate from the lowest-mass core-collapse progenitors.

Time-domain surveys discover thousands of transients per year, but the spectroscopic identification of rare and physically peculiar objects remains rate-limited by closed-set classifiers that confidently assign every input to a known class – including spectra that genuinely belong to no known class. We present the framework, a confidence-aware infrastructure for spectroscopic transient classification built around three coupled modules: a hierarchical spectral classifier that operates directly on observer-frame spectra without requiring host-galaxy redshift or spectral phase as inputs; an anomaly detection layer () that non-linearly combines 16 embedding-space anomaly scores spanning four physically motivated families; and a conformal uncertainty quantification layer (). We validate the framework on a held-out evaluation set of 289 rare and out-of-taxonomy transients spanning 11 classes deliberately excluded from training, chosen to span the full physical diversity of the rare-anomaly population: AGN-related outliers, GRB-related events, gap transients, novae, and peculiar supernovae. Through five astrophysically distinct failure modes of closed-set classifiers, we show that classifier-internal uncertainty and embedding-based anomaly detection are structurally complementary axes of confidence rather than alternative implementations of the same estimator. We further introduce AD-stratified Mondrian conformal prediction (AD-MCP) within , achieving uniform conditional coverage across anomaly-score strata where vanilla Mondrian under-covers in the operational regime. This establishes the methodological infrastructure for confidence-aware spectroscopic discovery in the Vera C. Rubin Observatory era.

The forthcoming launch of the Ultraviolet Transient Astronomy Satellite (ULTRASAT) will transform our understanding of the transient ultraviolet sky by increasing our ability to identify transients due to its unprecedented 204 deg2 field of view. While rapid (extragalactic) transients are a priority science area for the mission, flaring stars and AGN can often contaminate searches for such objects. To prepare for these challenges, the Zwicky Transient Facility (ZTF)-ULTRASAT experiment observed five fields at high cadence over three nights, in close proximity to ULTRASAT's three northern high-cadence fields. A real-time filter identified seven transient candidates, of which five were presistent variable sources and two were spurious. Periods and amplitudes derived from the ZRF Source Classifcation Project (SCoPe) showed that three candidates were RR Lyrae stars with short periods and high amplitudes, while the remaining two displayed flairing behavior. We demonstrate that short-timescale, high-amplitude variables can sysematically mimic transient alerts in high-cadence UV surveys, and we provide a concrete startegy to this contamination using pre-existing machine learning catalogs.

Modeled gravitational wave searches correlate the strain data with a bank of gravitational wave template waveforms to make detections of gravitational wave candidates, and these results are processed by downstream tools to calculate the likely sky location and distance of the source of the candidates. This is crucial for multi-messenger efforts, since it informs astronomers where to point their telescopes to facilitate electromagnetic follow-up of the gravitational wave candidates. We present a novel method to improve the low-latency results of the GstLAL gravitational wave search pipeline, and thus improving sky location estimates of low-latency candidates. This method involves ingesting the GstLAL low-latency results, and performing a small targeted hierarchical search to recover the candidates with more accurate parameters, in a medium-latency timescale (few seconds to five minutes). To test our method, we perform a GstLAL low-latency analysis on forty days of data from the third observing run of LIGO, Virgo, and KAGRA, and show that our method improves the GstLAL results by 5.38

Many traditional algorithms applied in gravitational-wave astronomy rely on the assumption of Gaussian noise, a condition not always met. To meet this need, this study extends a robust statistical framework, advancing previous work on heavy-tailed likelihoods, that adapts the hyperbolic likelihood method for full frequency domain applications. The framework is designed to maintain high performance under ideal conditions while improving robustness against non-Gaussian noise and outliers in real-world data. We demonstrate the efficacy of this approach through two key case studies. The first case study analyzes a massive black hole binary merger in simulated Laser Interferometer Space Antenna (LISA) data with Gaussian noise, showing that the extended hyperbolic likelihood method performs comparably to the more commonly used Whittle likelihood. The second case study examines a stellar-mass black hole binary merger using real ground-based gravitational-wave data containing non-Gaussian noise or overlapping signals, where our framework exhibits increased robustness and yields more accurate parameter estimations. Our results show that the hyperbolic likelihood better captures the true noise distribution, providing a flexible and physically motivated alternative for GW data analysis across current and future detectors.

The Vera C. Rubin Observatory's Legacy Survey of Space and Time (LSST) will produce unprecedented volumes of heterogeneous astronomical data (images, catalogs, and alerts) that challenge traditional analysis pipelines. The LSST Dark Energy Science Collaboration (DESC) aims to derive robust constraints on dark energy and dark matter from these data, requiring methods that are statistically powerful, scalable, and operationally reliable. Artificial intelligence and machine learning (AI/ML) are already embedded across DESC science workflows, from photometric redshifts and transient classification to weak lensing inference and cosmological simulations. Yet their utility for precision cosmology hinges on trustworthy uncertainty quantification, robustness to covariate shift and model misspecification, and reproducible integration within scientific pipelines. This white paper surveys the current landscape of AI/ML across DESC's primary cosmological probes and cross-cutting analyses, revealing that the same core methodologies and fundamental challenges recur across disparate science cases. Since progress on these cross-cutting challenges would benefit multiple probes simultaneously, we identify key methodological research priorities, including Bayesian inference at scale, physics-informed methods, validation frameworks, and active learning for discovery. With an eye on emerging techniques, we also explore the potential of the latest foundation model methodologies and LLM-driven agentic AI systems to reshape DESC workflows, provided their deployment is coupled with rigorous evaluation and governance. Finally, we discuss critical software, computing, data infrastructure, and human capital requirements for the successful deployment of these new methodologies, and consider associated risks and opportunities for broader coordination with external actors.

The General Coordinates Network (GCN) is NASA’s time-domain and multimessenger alert system. GCN distributes two data products: automated “Notices” and human-generated “Circulars” that report the observations of high-energy and multimessenger astronomical transients. The flexible and nonstructured format of GCN Circulars, comprising more than 40,500 Circulars accumulated over three decades, makes it challenging to manually extract observational information, such as redshift or observed wave bands. In this work, we employ large language models (LLMs) to facilitate the automated parsing of transient reports. We develop a neural topic modeling pipeline with open-source tools for the automatic clustering and summarization of astrophysical topics in the Circulars archive. Using neural topic modeling and contrastive fine-tuning, we classify Circulars based on their observation wave bands and messengers. Additionally, we separate gravitational-wave event clusters and their electromagnetic counterparts from the Circulars archive. Finally, using the open-source Mistral model, we implement a system to automatically extract gamma-ray burst (GRB) redshift information from the Circulars archive, without the need for any training. Evaluation against the manually curated Neil Gehrels Swift Observatory GRB table shows that our simple system, with the help of prompt-tuning, output parsing, and retrieval augmented generation (RAG), can achieve an accuracy of 97.2% for redshift-containing Circulars. Our neural search-enhanced RAG pipeline accurately retrieved 96.8% of redshift Circulars from the manually curated archive. Our study demonstrates the potential of LLMs to automate and enhance astronomical text mining and provides a foundational work for future advances in transient alert analysis.

In March 2026, the Einstein Probe (EP) discovered its most nearby (z = 0.0343) Fast X-ray Transient (FXT), EP260321a, the first EP FXT to provide a strong match to expectations for X-ray ”shock breakout” (SBO) emission. Here, we present our multi-wavelength follow-up campaign of EP260321a and its broad-line Type Ic (Ic-BL) supernova (SN) counterpart, SN 2026gzf, the first Type Ic-BL SN with a definitive X-ray SBO. We show that our radio follow-up extending over 5.8 - 54.5 days post-FXT rules out an on-axis jet counterpart of isotropic-equivalent kinetic energy E_K > 10^49 erg for circumburst densities n > 10^-2 cm^-3 and constrains radio synchrotron emission from the fastest-moving SN ejecta. In addition, we derive the properties of SN 2026gzf and its host galaxy from our well-sampled optical data and compare them with those of optically discovered Type Ic-BL SNe, finding that SN2026gzf is well within the 90

Inferring the dimension of a model - the number of components needed to explain data - jointly with the parameters is a pervasive problem, from counting sources in an image to mixture modeling, and reversible-jump Markov chain Monte Carlo solves it exactly but mixes slowly. Learned proposals are well established at fixed dimension, but whether they can accelerate the dimension-changing moves themselves has remained largely untested. We show that the answer has a structural origin: the optimal proposal for the dimension-changing birth move is a different object in different phases of the run. While the fit is being assembled it must match the current residual - a state-dependent quantity no state-independent network can represent - but at equilibrium it degenerates to the posterior's single-component marginal, which is exactly the distribution an adaptive normalizing flow learns from the sampler's own history. A learned state-independent birth proposal is therefore useless in one phase and optimal in the other. Controlled experiments confirm the attribution: applied with an exact Metropolis–Hastings correction that leaves the target invariant for any network, the learned births leave acceptance rates unchanged yet accelerate model-order mixing - in a ten-seed benchmark they meet a pre-specified stopping rule in six of ten runs, typically several times sooner, where a strong hand-tuned baseline meets it in one (one-sided p=0.03) - and an isolation experiment shows the same flow deployed within-model buys nothing. Making no domain-specific assumptions, the same sampler counts sources in a noisy image and reconstructs signals across scientific domains, including gravitational waves from ground- and space-based detectors and a scalp EEG recording. We release the method as HyperWave, an open-source package.

We present optical/UV photometric and spectroscopic observations, as well as X-ray and radio follow-up, of the extraordinary event AT2019cmw. With a peak bolometric luminosity of similar to 10(45.6) erg s(-1), it is one of the most luminous thermal transients ever discovered. Extensive spectroscopic follow-up post-peak showed only a featureless continuum throughout its evolution. This, combined with its nuclear location, blue colour at peak and lack of prior evidence of an AGN in its host lead us to interpret this event as a 'featureless' tidal disruption event (TDE). It displays photometric evolution atypical of most TDEs, cooling from similar to 30 to similar to 10kK in the first similar to 300 d post-peak, with potential implications for future photometric selection of candidate TDEs. No X-ray or radio emission is detected, placing constraints on the presence of on-axis jetted emission or a visible inner-accretion disc. Modelling the optical light curve with existing theoretical prescriptions, we find that AT2019cmw may be the result of the disruption of a star in the tens of solar masses by a supermassive black hole (SMBH). Combined with a lack of detectable star formation in its host galaxy, it could imply the existence of a localized region of star formation around the SMBH. This could provide a new window to probe nuclear star formation and the shape of the initial mass function (IMF) in close proximity to SMBHs out to relatively high redshifts.