Toward decision-aware AI for LSST-scale time-domain astronomy

A. Gomboc; A. I. Malz; A. Mahabal; A. Melandri; A. Sasli; A. Tramuto; B. Fraga; C. R. Bom; F. Bianco; F. Fontinele Nunes

arxiv: 2606.05285 · v1 · pith:CSBAW3NSnew · submitted 2026-06-03 · 🌌 astro-ph.IM · astro-ph.HE· hep-ph

Toward decision-aware AI for LSST-scale time-domain astronomy

C. R. Bom , A. Mahabal , F. Bianco , P. Darc , B. Fraga , R. Bonito , S. Chaini , M. W. Coughlin

show 22 more authors

S. Dillmann F. Fontinele Nunes A. Gomboc N. Hernitschek X. Li F. Z. Majidi A. I. Malz A. Melandri V. Petrecca S. Piranomonte M. Rabus F. Ragosta O. Razim M. C. Rom\~ao N. Sarin A. Sasli V. A. Sre\'ckovi\'c A. Tramuto V. Vuj\v{c}i\'c M. J. Vyas Rubin LSST Transients Variable Stars Science Collaboration

This is my paper

Pith reviewed 2026-06-28 03:43 UTC · model grok-4.3

classification 🌌 astro-ph.IM astro-ph.HEhep-ph

keywords LSSTtime-domain astronomyfoundation modelsdecision theoryfollow-up allocationuncertainty-aware representationsagentic systems

0 comments

The pith

Foundation models paired with decision policies can maintain uncertainty-aware source states and allocate LSST follow-up resources to maximize long-term scientific value.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper argues that LSST-scale time-domain astronomy is better viewed as a partially observed dynamical environment than as a static labeling problem, because scientific return depends on follow-up decisions made under uncertainty and limited resources. It proposes that foundation models trained on heterogeneous time-domain data can produce survey-scale representations of source state that include uncertainty estimates. Decision-theoretic policies then allow principled and auditable choices about which targets to observe next. When these elements operate inside human-supervised agentic systems, AI becomes an active part of the inference loop rather than a post-processing classifier. This framing directly affects how observational resources are used and which scientific questions receive priority.

Core claim

The central claim is that foundation models trained on heterogeneous time-domain data can learn survey-scale representations of source state, while decision-theoretic policies support principled, auditable allocation of follow-up resources. Embedded within human-supervised agentic systems, these components position AI as part of the operational inference loop rather than as a downstream predictive tool. The way such systems represent belief, optimize utility, and expose their reasoning will shape observational efficiency, the distribution of scientific agency, and the scientific questions that receive priority.

What carries the argument

Foundation models that learn survey-scale representations of source state together with decision-theoretic policies for resource allocation, placed inside human-supervised agentic systems.

If this is right

Evolving uncertainty-aware representations of astrophysical sources become available at survey scale.
Follow-up actions are chosen to maximize long-term scientific value under finite resources.
Resource allocation becomes principled and auditable rather than heuristic.
AI components operate inside the inference loop and expose their reasoning to human supervisors.
Observational efficiency and the distribution of scientific agency are shaped by how belief and utility are represented.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

The same structure could support real-time revision of observing strategies as new alerts arrive.
Transparent decision policies might alter how different research groups gain access to follow-up facilities.
Integration with existing telescope scheduling software would require new interfaces between model outputs and human veto points.
Similar decision-aware loops could apply to other large transient surveys once their alert volumes reach comparable levels.

Load-bearing premise

That foundation models can be trained at LSST scale to produce uncertainty-aware representations and that decision-theoretic policies can be embedded in operational systems without introducing unmanageable biases or computational overhead.

What would settle it

An operational test showing that no foundation model produces usable uncertainty-aware representations across LSST-scale heterogeneous alerts without prohibitive cost, or that any embedded decision policy reduces net scientific output relative to current human-driven follow-up methods.

read the original abstract

The Vera C. Rubin Observatory's Legacy Survey of Space and Time (LSST) will generate approximately (10^7) alerts per night, pushing time-domain astronomy beyond pipelines that treat discovery as a static labeling problem. We argue that LSST is better understood as a partially observed dynamical environment, in which scientific return depends on the quality of follow-up decisions made under uncertainty and finite observational resources. The central challenge is therefore to maintain evolving, uncertainty-aware representations of astrophysical sources and to select actions that maximize long-term scientific value. We propose that foundation models trained on heterogeneous time-domain data can learn survey-scale representations of source state, while decision-theoretic policies support principled, auditable allocation of follow-up resources. Embedded within human-supervised agentic systems, these components position AI as part of the operational inference loop rather than as a downstream predictive tool. The way such systems represent belief, optimize utility, and expose their reasoning will shape observational efficiency, the distribution of scientific agency, including who participates in discovery and the scientific questions that receive priority.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Desk Editor's Note private letter to a colleague

Position paper framing LSST alerts as a decision problem under uncertainty, but with no data, tests, or derivations to back the proposal.

read the letter

This paper argues that LSST time-domain work needs to shift from static classification pipelines to dynamic, uncertainty-aware decision systems that use foundation models for source representations and decision-theoretic policies for follow-up allocation. It positions AI inside human-supervised agentic loops rather than as a post-processing step.

It correctly flags the alert volume problem and the fact that scientific return depends on which sources get follow-up under limited resources. The dynamical-environment framing is a reasonable way to describe the operational reality.

The main limitation is that the piece stays entirely at the level of advocacy. There are no equations, no small-scale experiments, no discussion of training data requirements for heterogeneous time-domain sets, and no analysis of how decision policies would actually be optimized or audited in practice. The assumptions about foundation models delivering usable uncertainty at LSST scale are stated but not examined.

Because the paper offers no new technical content, its value is limited to starting conversations inside the LSST transients community. Readers already working on alert brokers or follow-up scheduling will recognize the issues but will not find methods or results they can build on.

I would bring it to a reading group focused on survey operations to talk through the framing, but not to a methods-focused group. I would not cite it for any technical claim. It deserves peer review as a perspective or position article because the topic is timely for the collaboration, though it should be evaluated on those terms rather than as a research contribution.

Referee Report

2 major / 0 minor

Summary. The paper argues that LSST should be treated as a partially observed dynamical environment rather than a static classification task. It proposes that foundation models trained on heterogeneous time-domain data can learn survey-scale, uncertainty-aware representations of source state, while decision-theoretic policies enable auditable allocation of follow-up resources; these components are to be embedded in human-supervised agentic systems so that AI participates directly in the operational inference loop.

Significance. If the proposed integration of foundation models and decision-theoretic policies could be realized at LSST scale, it would shift AI from a downstream classifier to an active participant in observational strategy, potentially improving long-term scientific return under resource constraints. The manuscript itself, however, contains no empirical results, derivations, or feasibility tests, so the significance remains entirely prospective.

major comments (2)

[Abstract] Abstract, paragraph 3: the central claim that 'foundation models trained on heterogeneous time-domain data can learn survey-scale representations of source state' is advanced without any supporting architecture description, training regime, uncertainty quantification method, or scaling argument, rendering the proposal unsubstantiated.
[Abstract] Abstract, paragraph 3: the assertion that 'decision-theoretic policies support principled, auditable allocation of follow-up resources' is presented without any formulation of the utility function, state representation, or policy optimization procedure, so the load-bearing technical content is absent.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their review. The manuscript is a conceptual position paper that frames LSST-scale time-domain astronomy as a decision-making problem under partial observability and proposes high-level roles for foundation models and decision-theoretic policies. It does not claim to deliver implemented systems or empirical results. We respond to the major comments below.

read point-by-point responses

Referee: [Abstract] Abstract, paragraph 3: the central claim that 'foundation models trained on heterogeneous time-domain data can learn survey-scale representations of source state' is advanced without any supporting architecture description, training regime, uncertainty quantification method, or scaling argument, rendering the proposal unsubstantiated.

Authors: We agree that the abstract advances this claim at a conceptual level without technical specifications. The manuscript is structured as a position paper whose purpose is to argue that LSST should be treated as a partially observed dynamical environment and to identify the need for survey-scale, uncertainty-aware representations. Detailed architectures, training regimes, and scaling arguments are outside its scope; they would belong to subsequent technical work. The text therefore presents the claim as a forward-looking proposal rather than a substantiated result. revision: no
Referee: [Abstract] Abstract, paragraph 3: the assertion that 'decision-theoretic policies support principled, auditable allocation of follow-up resources' is presented without any formulation of the utility function, state representation, or policy optimization procedure, so the load-bearing technical content is absent.

Authors: We likewise acknowledge that no explicit utility function, state representation, or optimization procedure is supplied. The manuscript uses the phrase to indicate the type of formalism required for auditable follow-up decisions under resource constraints, consistent with its role as a high-level framing document. Deriving or optimizing such policies is left as future research; the current text only identifies the decision-theoretic gap in existing pipelines. revision: no

Circularity Check

0 steps flagged

No significant circularity; conceptual position paper with no derivations

full rationale

The manuscript advances a vision for embedding foundation models and decision-theoretic policies in LSST operations but presents no equations, fitted parameters, formal derivations, or quantitative results. All claims are forward-looking proposals (e.g., 'We propose that foundation models trained on heterogeneous time-domain data can learn survey-scale representations') rather than reductions of outputs to inputs. No self-citation chains, ansatzes, or uniqueness theorems are invoked as load-bearing steps. The derivation chain is therefore self-contained and non-circular by the paper's own structure.

Axiom & Free-Parameter Ledger

0 free parameters · 2 axioms · 0 invented entities

This is a position paper; the central claim rests on domain assumptions about ML scalability rather than new fitted parameters or invented entities.

axioms (2)

domain assumption Foundation models trained on heterogeneous time-domain data can learn survey-scale representations of source state.
Invoked as the basis for maintaining evolving uncertainty-aware representations (abstract).
domain assumption Decision-theoretic policies can support principled allocation of follow-up resources to maximize long-term scientific value.
Central premise for treating LSST as a partially observed dynamical environment (abstract).

pith-pipeline@v0.9.1-grok · 5883 in / 1375 out tokens · 43161 ms · 2026-06-28T03:43:54.541214+00:00 · methodology

discussion (0)

Reference graph

Works this paper leans on

62 extracted references · 23 canonical work pages · 2 internal anchors

[1]

C., Kulkarni, S

Bellm, E.C., Kulkarni, S.R., Graham, M.J.,et al.: The zwicky transient facility: System overview, performance, and first results. Publications of the Astronomical Society of the Pacific131(995), 018002 (2019). https: //doi.org/10.1088/1538-3873/aaecbe

work page doi:10.1088/1538-3873/aaecbe 2019
[2]

J., Laher, R

Masci, F.J., Laher, R.R., Rebbapragada, U.,et al.: The zwicky tran- sient facility: Data processing, products, and archive. Publications of the Astronomical Society of the Pacific131(995), 018003 (2019). https: //doi.org/10.1088/1538-3873/aae8ac

work page internal anchor Pith review doi:10.1088/1538-3873/aae8ac 2019
[3]

Publications of the Astronomical Society of the Pacific131(995), 018001 (2019)

Patterson, M.T., Bellm, E.C., Rusholme, B.,et al.: The zwicky tran- sient facility alert distribution system. Publications of the Astronomical Society of the Pacific131(995), 018001 (2019). https://doi.org/10.1088/ 1538-3873/aae904

2019
[4]

2009, PASJ, 61,

Ivezi´ c,ˇZ., Kahn, S.M., Tyson, J.A.,et al.: Lsst: From science drivers to ref- erence design and anticipated data products. The Astrophysical Journal Springer Nature 2021 LATEX template AI Perspective into Time-domain Astronomy13 873(2), 111 (2019). https://doi.org/10.3847/1538-4357/ab042c

work page doi:10.3847/1538-4357/ab042c 2021
[5]

Technical report, Vera C

Graham, M.L.: Lsst alerts: Key numbers (dmtn-102). Technical report, Vera C. Rubin Observatory (2024). https://doi.org/10.71929/rubin/ 2997858

work page doi:10.71929/rubin/ 2024
[6]

Bianco, F.B., Ivezi´ c,ˇZ., Jones, R.L., Graham, M.L., Marshall, P., Saha, A., Strauss, M.A., Yoachim, P., Ribeiro, T., Anguita, T., Bauer, A.E., Bauer, F.E., Bellm, E.C., Blum, R.D., Brandt, W.N., Brough, S., Cate- lan, M., Clarkson, W.I., Connolly, A.J., Gawiser, E., Gizis, J.E., Hloˇ zek, R., Kaviraj, S., Liu, C.T., Lochner, M., Mahabal, A.A., Mandelba...

work page doi:10.3847/1538-4365/ac3e72 2022
[7]

Publications of the Astronomical Society of the Pacific131, 118002 (2019)

Muthukrishna, D., Narayan, G., Mandel, K.S.,et al.: Rapid: Early clas- sification of explosive transients using deep learning. Publications of the Astronomical Society of the Pacific131, 118002 (2019). https://doi.org/ 10.1088/1538-3873/ab1609

work page doi:10.1088/1538-3873/ab1609 2019
[8]

AJ162(6), 275 (2021) arXiv:2109.13999 [astro-ph.IM]

Boone, K.: ParSNIP: Generative Models of Transient Light Curves with Physics-enabled Deep Learning. AJ162(6), 275 (2021) arXiv:2109.13999 [astro-ph.IM]. https://doi.org/10.3847/1538-3881/ac2a2d

work page doi:10.3847/1538-3881/ac2a2d 2021
[9]

MNRAS 491(3), 4277–4293 (2020) arXiv:1901.06384 [astro-ph.IM]

M¨ oller, A., de Boissi` ere, T.: SuperNNova: an open-source framework for Bayesian, neural network-based supernova classification. MNRAS 491(3), 4277–4293 (2020) arXiv:1901.06384 [astro-ph.IM]. https://doi. org/10.1093/mnras/stz3312

work page doi:10.1093/mnras/stz3312 2020
[10]

A&A692, 208 (2024) arXiv:2404.08798 [astro- ph.IM]

Fraga, B.M.O., Bom, C.R., Santos, A., Russeil, E., Leoni, M., Peloton, J., Ishida, E.E.O., M¨ oller, A., Blondin, S.: Transient classifiers for Fink: Benchmarks for LSST. A&A692, 208 (2024) arXiv:2404.08798 [astro- ph.IM]. https://doi.org/10.1051/0004-6361/202450370

work page doi:10.1051/0004-6361/202450370 2024
[11]

AJ 161(5), 242 (2021) arXiv:2008.03303 [astro-ph.IM]

F¨ orster, F., Cabrera-Vives, G., Castillo-Navarrete, E., Est´ evez, P.A., S´ anchez-S´ aez, P., Arredondo, J., Bauer, F.E., Carrasco-Davis, R., Cate- lan, M., Elorrieta, F., Eyheramendy, S., Huijse, P., Pignata, G., Reyes, E., Reyes, I., Rodr´ ıguez-Mancini, D., Ruz-Mieres, D., Valenzuela, C.,´Alvarez- Maldonado, I., Astorga, N., Borissova, J., Clocchiat...

arXiv 2021
[12]

In: Peck, A.B., Benn, C.R., Seaman, R.L

Saha, A., Matheson, T., Snodgrass, R., Kececioglu, J., Narayan, G., Seaman, R., Jenness, T., Axelrod, T.: ANTARES: a prototype tran- sient broker system. In: Peck, A.B., Benn, C.R., Seaman, R.L. (eds.) Observatory Operations: Strategies, Processes, and Systems V. Society of Photo-Optical Instrumentation Engineers (SPIE) Conference Series, vol. 9149, p. 91...

work page doi:10.1117/12.2056988 2014
[13]

M¨ oller, A., Peloton, J., Ishida, E.E.O., Arnault, C., Bachelet, E., Blaineau, T., Boutigny, D., Chauhan, A., Gangler, E., Hernandez, F., Hrivnac, J., Leoni, M., Leroy, N., Moniez, M., Pateyron, S., Ramparison, A., Turpin, D., Ansari, R., Allam, T. Jr., Bajat, A., Biswas, B., Boucaud, A., Bre- geon, J., Campagne, J.-E., Cohen-Tanugi, J., Coleiro, A., Dor...

work page doi:10.1093/mnras/ 2021
[14]

ApJ 884(1), 83 (2019) arXiv:1905.07422 [astro-ph.HE]

Villar, V.A., Berger, E., Miller, G., Chornock, R., Rest, A., Jones, D.O., Drout, M.R., Foley, R.J., Kirshner, R., Lunnan, R., Mag- nier, E., Milisavljevic, D., Sanders, N., Scolnic, D.: Supernova Pho- tometric Classification Pipelines Trained on Spectroscopically Classi- fied Supernovae from the Pan-STARRS1 Medium-deep Survey. ApJ 884(1), 83 (2019) arXiv...

arXiv 2019
[15]

Machine Learning-based Brokers for Real-time Classification of the LSST Alert Stream

Narayan, G., Zaidi, T., Soraisam, M.D., Wang, Z., Lochner, M., Math- eson, T., Saha, A., Yang, S., Zhao, Z., Kececioglu, J., Scheidegger, C., Snodgrass, R.T., Axelrod, T., Jenness, T., Maier, R.S., Ridgway, S.T., Seaman, R.L., Evans, E.M., Singh, N., Taylor, C., Toeniskoetter, J., Welch, E., Zhu, S., ANTARES Collaboration: Machine-learning- based Brokers ...

work page internal anchor Pith review Pith/arXiv arXiv doi:10.3847/1538-4365/aab781 2018
[16]

A transformer-based embedding for the representation of light curves

Donoso-Oliva, C., Becker, I., Protopapas, P., Cabrera-Vives, G., Vishnu, M., Vardhan, H.: ASTROMER. A transformer-based embedding for the representation of light curves. A&A670, 54 (2023) arXiv:2205.01677 [astro-ph.IM]. https://doi.org/10.1051/0004-6361/202243928 Springer Nature 2021 LATEX template AI Perspective into Time-domain Astronomy15

work page doi:10.1051/0004-6361/202243928 2023
[17]

MNRAS531(4), 4990–5011 (2024) arXiv:2310.03024 [astro-ph.IM]

Parker, L., Lanusse, F., Golkar, S., Sarra, L., Cranmer, M., Bietti, A., Eickenberg, M., Krawezik, G., McCabe, M., Morel, R., Ohana, R., Pet- tee, M., R´ egaldo-Saint Blancard, B., Cho, K., Ho, S., Polymathic AI Collaboration: AstroCLIP: a cross-modal foundation model for galax- ies. MNRAS531(4), 4990–5011 (2024) arXiv:2310.03024 [astro-ph.IM]. https://do...

work page doi:10.1093/mnras/stae1450 2024
[18]

arXiv preprint arXiv:2405.14930 (2024)

Smith, M.J., Roberts, R.J., Angeloudi, E., Huertas-Company, M.: Astropt: Scaling large observation models for astronomy. arXiv preprint arXiv:2405.14930 (2024)

arXiv 2024
[19]

, keywords =

van Velzen, S., Gezari, S., Hammerstein, E., Roth, N., Frederick, S., Ward, C., Hung, T., Cenko, S.B., Stein, R., Perley, D.A., Taggart, K., Foley, R.J., Sollerman, J., Blagorodnova, N., Andreoni, I., Bellm, E.C., Brinnel, V., De, K., Dekany, R., Feeney, M., Fremling, C., Giomi, M., Golkhou, V.Z., Graham, M.J., Ho, A.Y.Q., Kasliwal, M.M., Kilpatrick, C.D....

work page doi:10.3847/1538-4357/abc258 2021
[20]

IEEE Transactions on Pattern Analysis and Machine Intelligence35(8), 1798–1828 (2013)

Bengio, Y., Courville, A., Vincent, P.: Representation learning: A review and new perspectives. IEEE Transactions on Pattern Analysis and Machine Intelligence35(8), 1798–1828 (2013). https://doi.org/10.1109/ TPAMI.2013.50

2013
[21]

MNRAS529(1), 732–747 (2024) arXiv:2309.08660 [astro-ph.IM]

Etsebeth, V., Lochner, M., Walmsley, M., Grespan, M.: Astronomaly at scale: searching for anomalies amongst 4 million galaxies. MNRAS529(1), 732–747 (2024) arXiv:2309.08660 [astro-ph.IM]. https://doi.org/10.1093/ mnras/stae496

arXiv 2024
[22]

Machine Learning: Science and Technology6(3), 035032 (2025)

Pandya, S., Patel, P., Nord, B.D., Walmsley, M., ´Ciprijanovi´ c, A.: Sidda: Sinkhorn dynamic domain adaptation for image classification with equiv- ariant neural networks. Machine Learning: Science and Technology6(3), 035032 (2025). https://doi.org/10.1088/2632-2153/adf701

work page doi:10.1088/2632-2153/adf701 2025
[23]

Gridach, J

Gridach, M., Nanavati, J., Zine El Abidine, K., Mendes, L., Mack, C.: Agentic AI for Scientific Discovery: A Survey of Progress, Challenges, and Future Directions. arXiv e-prints, 2503–08979 (2025) arXiv:2503.08979 [cs.CL]. https://doi.org/10.48550/arXiv.2503.08979

work page doi:10.48550/arxiv.2503.08979 2025
[24]

In: Forty-second International Conference on Machine Learning (2025)

Richens, J., Everitt, T., Abel, D.: General agents need world models. In: Forty-second International Conference on Machine Learning (2025)

2025
[25]

ACM Computing Surveys58(3), 1–38 (2025)

Ding, J., Zhang, Y., Shang, Y., Zhang, Y., Zong, Z., Feng, J., Yuan, Y., Su, Springer Nature 2021 LATEX template 16AI Perspective into Time-domain Astronomy H., Li, N., Sukiennik, N.,et al.: Understanding world or predicting future? a comprehensive survey of world models. ACM Computing Surveys58(3), 1–38 (2025)

2021
[26]

Proceedings of the national academy of sciences114(13), 3521–3526 (2017)

Kirkpatrick, J., Pascanu, R., Rabinowitz, N., Veness, J., Desjardins, G., Rusu, A.A., Milan, K., Quan, J., Ramalho, T., Grabska-Barwinska, A.,et al.: Overcoming catastrophic forgetting in neural networks. Proceedings of the national academy of sciences114(13), 3521–3526 (2017)

2017
[27]

arXiv e-prints, 2403–05175 (2024) arXiv:2403.05175 [stat.ML]

van de Ven, G.M., Soures, N., Kudithipudi, D.: Continual Learn- ing and Catastrophic Forgetting. arXiv e-prints, 2403–05175 (2024) arXiv:2403.05175 [stat.ML]. https://doi.org/10.48550/arXiv.2403.05175

work page doi:10.48550/arxiv.2403.05175 2024
[28]

arXiv e-prints, 2010–05941 (2020) arXiv:2010.05941 [astro-ph.IM]

Kennamer, N., Ishida, E.E.O., Gonzalez-Gaitan, S., de Souza, R.S., Ihler, A., Ponder, K., Vilalta, R., Moller, A., Jones, D.O., Dai, M., Krone- Martins, A., Quint, B., Sreejith, S., Malz, A.I., Galbany, L.: Active learning with RESSPECT: Resource allocation for extragalactic astro- nomical transients. arXiv e-prints, 2010–05941 (2020) arXiv:2010.05941 [as...

work page doi:10.48550/arxiv.2010.05941 2010
[29]

PASA42, 057 (2025) arXiv:2502.19555 [astro-ph.IM]

M¨ oller, A., Ishida, E., Peloton, J., Vidal Vel´ azquez, O., Soon, J., Martin, B., Cluver, M., Leoni, M., Taylor, E.N.: Real-time active learning for opti- mised spectroscopic follow-up: Enhancing early SN Ia classification with the Fink broker. PASA42, 057 (2025) arXiv:2502.19555 [astro-ph.IM]. https://doi.org/10.1017/pasa.2025.20

work page doi:10.1017/pasa.2025.20 2025
[30]

Artificial intelligence101(1-2), 99–134 (1998)

Kaelbling, L.P., Littman, M.L., Cassandra, A.R.: Planning and acting in partially observable stochastic domains. Artificial intelligence101(1-2), 99–134 (1998)

1998
[31]

Sutton, R.S., Barto, A.G.,et al.: Reinforcement Learning: An Introduc- tion vol. 1. MIT press Cambridge, ??? (1998)

1998
[32]

The Astrophysical Journal995(1), 4 (2025)

Shah, V.G., Gagliano, A., Malanchev, K., Narayan, G., Malz, A.I., Col- laboration, L.D.E.S.: Oracle: A real-time, hierarchical, deep learning photometric classifier for the lsst. The Astrophysical Journal995(1), 4 (2025)

2025
[33]

In: International Conference on Machine Learning, pp

Foster, A., Ivanova, D.R., Malik, I., Rainforth, T.: Deep adaptive design: Amortizing sequential bayesian experimental design. In: International Conference on Machine Learning, pp. 3384–3395 (2021). PMLR

2021
[34]

Advances in neural information processing systems29(2016) Springer Nature 2021 LATEX template AI Perspective into Time-domain Astronomy17

Hadfield-Menell, D., Russell, S.J., Abbeel, P., Dragan, A.: Cooperative inverse reinforcement learning. Advances in neural information processing systems29(2016) Springer Nature 2021 LATEX template AI Perspective into Time-domain Astronomy17

2016
[35]

rubin observatory

Andreoni, I., Margutti, R., Salafia, O.S., Parazin, B., Villar, V.A., Cough- lin, M.W., Yoachim, P., Mortensen, K., Brethauer, D., Smartt, S.,et al.: Target-of-opportunity observations of gravitational-wave events with vera c. rubin observatory. The Astrophysical Journal Supplement Series 260(1), 18 (2022)

2022
[36]

Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences383(2294) (2025)

Nicholl, M., Andreoni, I.: Electromagnetic follow-up of gravitational waves: review and lessons learned. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences383(2294) (2025)

2025
[37]

The Astrophysical Journal960(2), 122 (2024)

Annis, J., Garcia, A., Palmese, A., Sherman, N., Soares-Santos, M., Santana-Silva, L., Morgan, R., Bechtol, K., Davis, T.,et al.: Designing an optimal kilonova search using decam for gravitational-wave events. The Astrophysical Journal960(2), 122 (2024)

2024
[38]

Monthly Notices of the Royal Astronomical Society495(4), 4366–4371 (2020)

Almualla, M., Coughlin, M.W., Anand, S., Alqassimi, K., Guessoum, N., Singer, L.P.: Dynamic scheduling: target of opportunity observations of gravitational wave events. Monthly Notices of the Royal Astronomical Society495(4), 4366–4371 (2020)

2020
[39]

Astronomy and Computing33, 100423 (2020)

Fluke, C.J., Hegarty, S.E., MacMahon, C.-M.: Understanding the human in the design of cyber-human discovery systems for data-driven astronomy. Astronomy and Computing33, 100423 (2020)

2020
[40]

In: Journal of Physics: Conference Series, vol

Albertsson, K., Altoe, P., Anderson, D., Andrews, M., Araque Espinosa, J.P., Aurisano, A., Basara, L., Bevan, A., Bhimji, W., Bonacorsi, D.,et al.: Machine learning in high energy physics community white paper. In: Journal of Physics: Conference Series, vol. 1085, p. 022008 (2018). IOP Publishing

2018
[41]

Nature Communications13(1), 3876 (2022)

Pandi, A., Diehl, C., Yazdizadeh Kharrazi, A., Scholz, S.A., Bobkova, E., Faure, L., Nattermann, M., Adam, D., Chapin, N., Foroughijabbari, Y., et al.: A versatile active learning workflow for optimization of genetic and metabolic networks. Nature Communications13(1), 3876 (2022)

2022
[42]

Journal of Machine Learning Research9(2) (2008)

Krause, A., Singh, A., Guestrin, C.: Near-optimal sensor placements in gaussian processes: Theory, efficient algorithms and empirical studies. Journal of Machine Learning Research9(2) (2008)

2008
[43]

Technical report, USDOE Office of Science (SC), Washington, DC (United States) (2019)

Baker, N., Alexander, F., Bremer, T., Hagberg, A., Kevrekidis, Y., Najm, H., Parashar, M., Patra, A., Sethian, J., Wild, S., et al.: Workshop report on basic research needs for scientific machine learning: Core technologies for artificial intelligence. Technical report, USDOE Office of Science (SC), Washington, DC (United States) (2019)

2019
[44]

arXiv preprint arXiv:2108.07258 (2021)

Bommasani, R., Hudson, D.A., Adeli, E., Altman, R., Arora, S., von Springer Nature 2021 LATEX template 18AI Perspective into Time-domain Astronomy Arx, S., Bernstein, M.S., Bohg, J., Bosselut, A., Brunskill, E., et al.: On the opportunities and risks of foundation models. arXiv preprint arXiv:2108.07258 (2021)

Pith/arXiv arXiv 2021
[45]

Philosophy of Science 67(4), 559–579 (2000)

Douglas, H.: Inductive risk and values in science. Philosophy of Science 67(4), 559–579 (2000). https://doi.org/10.1086/392855

work page doi:10.1086/392855 2000
[46]

University of Chicago Press, Chicago (2004)

Bourdieu, P.: Science of Science and Reflexivity. University of Chicago Press, Chicago (2004)

2004
[47]

Future Generation Computer Systems59, 95– 104 (2016)

Djorgovski, S.G., Graham, M.J., Donalek, C., Mahabal, A.A., Drake, A.J., Turmon, M., Fuchs, T.: Real-time data mining of massive data streams from synoptic sky surveys. Future Generation Computer Systems59, 95– 104 (2016). https://doi.org/10.1016/j.future.2015.10.013

work page doi:10.1016/j.future.2015.10.013 2016
[48]

arXiv e-prints, 2311–17143 (2023) arXiv:2311.17143 [astro-ph.IM]

Huang, H., Muthukrishna, D., Nair, P., Zhang, Z., Fausnaugh, M., Majumder, T., Foley, R.J., Ricker, G.R.: Predicting the Age of Astronom- ical Transients from Real-Time Multivariate Time Series. arXiv e-prints, 2311–17143 (2023) arXiv:2311.17143 [astro-ph.IM]. https://doi.org/10. 48550/arXiv.2311.17143

arXiv 2023
[49]

A&A 650, 195 (2021) arXiv:1909.13260 [astro-ph.IM]

Ishida, E.E.O., Kornilov, M.V., Malanchev, K.L., Pruzhinskaya, M.V., Volnova, A.A., Korolev, V.S., Mondon, F., Sreejith, S., Malancheva, A.A., Das, S.: Active anomaly detection for time-domain discoveries. A&A 650, 195 (2021) arXiv:1909.13260 [astro-ph.IM]. https://doi.org/10.1051/ 0004-6361/202037709

arXiv 2021
[50]

Annual Review of Astronomy and Astrophysics53(1), 247– 278 (2015)

Marshall, P.J., Lintott, C.J., Fletcher, L.N.: Ideas for citizen science in astronomy. Annual Review of Astronomy and Astrophysics53(1), 247– 278 (2015)

2015
[51]

In: The Science of Citizen Science, pp

Paleco, C., Garc´ ıa Peter, S., Salas Seoane, N., Kaufmann, J., Argyri, P.: Inclusiveness and diversity in citizen science. In: The Science of Citizen Science, pp. 261–281. Springer, ??? (2021)

2021
[52]

Royal Society Open Science11(5), 231309 (2024)

Wehn, U., Ajates, R., Mandeville, C., Somerwill, L., Kragh, G., Haklay, M.: Opening science to society: how to progress societal engagement into (open) science policies. Royal Society Open Science11(5), 231309 (2024)

2024
[53]

University of Chicago press, ??? (2019)

Collins, H.: Tacit and Explicit Knowledge. University of Chicago press, ??? (2019)

2019
[54]

Human factors52(3), 381–410 (2010)

Parasuraman, R., Manzey, D.H.: Complacency and bias in human use of automation: An attentional integration. Human factors52(3), 381–410 (2010)

2010
[55]

Data Science1(1-2), 119–129 (2017)

Gil, Y.: Thoughtful artificial intelligence: Forging a new partnership for Springer Nature 2021 LATEX template AI Perspective into Time-domain Astronomy19 data science and scientific discovery. Data Science1(1-2), 119–129 (2017)

2021
[56]

In: Observatory Operations: Strategies, Processes, and Systems V, vol

Jones, R.L., Yoachim, P., Chandrasekharan, S., Connolly, A.J., Cook, K.H., Ivezic, ˇZ., Krughoff, K.S., Petry, C., Ridgway, S.T.: The lsst met- rics analysis framework (maf). In: Observatory Operations: Strategies, Processes, and Systems V, vol. 9149, pp. 118–135 (2014). SPIE

2014
[57]

2025, Monthly Notices of the Royal Astronomical Society, 544, 3799, doi: 10.1093/mnras/staf1833 pandas development team, T

OpenUniverse, LSST Dark Energy Science Collaboration, Roman HLIS Project Infrastructure, Roman Rapid Project Infrastructure Team, Roman Supernova Cosmology Project Infrastructure Team, Alarcon, A., Aldoroty, L., Beltz-Mohrmann, G., Bera, A., Blazek, J., Bogart, J., Brae- unlich, G., Broughton, A., Cao, K., Chiang, J., Chisari, N.E., Desai, V., Fang, Y., G...

work page doi:10.1093/mnras/staf1833 2025
[58]

The Astrophysical Journal Supplement Series253(1), 31 (2021)

DESC), L.D.E.S.C.L., Abolfathi, B., Alonso, D., Armstrong, R., Aubourg, ´E., Awan, H., Babuji, Y.N., Bauer, F.E., Bean, R., Beckett, G.,et al.: The lsst desc dc2 simulated sky survey. The Astrophysical Journal Supplement Series253(1), 31 (2021)

2021
[59]

Astronomy & Astrophysics631, 147 (2019)

Nordin, J., Brinnel, V., Van Santen, J., Bulla, M., Feindt, U., Franck- owiak, A., Fremling, C., Gal-Yam, A., Giomi, M., Kowalski, M.,et al.: Transient processing and analysis using ampel: alert management, pho- tometry, and evaluation of light curves. Astronomy & Astrophysics631, 147 (2019)

2019
[60]

Monthly Notices of the Royal Astronomical Society507(2), 1746–1761 (2021)

Eifler, T., Miyatake, H., Krause, E., Heinrich, C., Miranda, V., Hirata, C., Xu, J., Hemmati, S., Simet, M., Capak, P.,et al.: Cosmology with the roman space telescope–multiprobe strategies. Monthly Notices of the Royal Astronomical Society507(2), 1746–1761 (2021)

2021
[61]

arXiv preprint arXiv:2308.04485 (2023)

Burns, E., Coughlin, M., Ackley, K., Andreoni, I., Bizouard, M.-A., Broekgaarden, F., Christensen, N.L., d’Ammando, F., DeLaunay, J., Fleischhack, H., et al.: Gamma-ray transient network science analysis group report. arXiv preprint arXiv:2308.04485 (2023)

arXiv 2023
[62]

Astronomy and Computing40, 100582 (2022)

Sambruna, R.M., Schlieder, J.E., Kocevski, D., Caputo, R., Hui, M.C., Markwardt, C.B., Powell, B.P., Racusin, J.L., Roberts, C., Singer, L.P., Springer Nature 2021 LATEX template 20AI Perspective into Time-domain Astronomy et al.: The nasa multi-messenger astrophysics science support center (mossaic). Astronomy and Computing40, 100582 (2022)

2021

[1] [1]

C., Kulkarni, S

Bellm, E.C., Kulkarni, S.R., Graham, M.J.,et al.: The zwicky transient facility: System overview, performance, and first results. Publications of the Astronomical Society of the Pacific131(995), 018002 (2019). https: //doi.org/10.1088/1538-3873/aaecbe

work page doi:10.1088/1538-3873/aaecbe 2019

[2] [2]

J., Laher, R

Masci, F.J., Laher, R.R., Rebbapragada, U.,et al.: The zwicky tran- sient facility: Data processing, products, and archive. Publications of the Astronomical Society of the Pacific131(995), 018003 (2019). https: //doi.org/10.1088/1538-3873/aae8ac

work page internal anchor Pith review doi:10.1088/1538-3873/aae8ac 2019

[3] [3]

Publications of the Astronomical Society of the Pacific131(995), 018001 (2019)

Patterson, M.T., Bellm, E.C., Rusholme, B.,et al.: The zwicky tran- sient facility alert distribution system. Publications of the Astronomical Society of the Pacific131(995), 018001 (2019). https://doi.org/10.1088/ 1538-3873/aae904

2019

[4] [4]

2009, PASJ, 61,

Ivezi´ c,ˇZ., Kahn, S.M., Tyson, J.A.,et al.: Lsst: From science drivers to ref- erence design and anticipated data products. The Astrophysical Journal Springer Nature 2021 LATEX template AI Perspective into Time-domain Astronomy13 873(2), 111 (2019). https://doi.org/10.3847/1538-4357/ab042c

work page doi:10.3847/1538-4357/ab042c 2021

[5] [5]

Technical report, Vera C

Graham, M.L.: Lsst alerts: Key numbers (dmtn-102). Technical report, Vera C. Rubin Observatory (2024). https://doi.org/10.71929/rubin/ 2997858

work page doi:10.71929/rubin/ 2024

[6] [6]

Bianco, F.B., Ivezi´ c,ˇZ., Jones, R.L., Graham, M.L., Marshall, P., Saha, A., Strauss, M.A., Yoachim, P., Ribeiro, T., Anguita, T., Bauer, A.E., Bauer, F.E., Bellm, E.C., Blum, R.D., Brandt, W.N., Brough, S., Cate- lan, M., Clarkson, W.I., Connolly, A.J., Gawiser, E., Gizis, J.E., Hloˇ zek, R., Kaviraj, S., Liu, C.T., Lochner, M., Mahabal, A.A., Mandelba...

work page doi:10.3847/1538-4365/ac3e72 2022

[7] [7]

Publications of the Astronomical Society of the Pacific131, 118002 (2019)

Muthukrishna, D., Narayan, G., Mandel, K.S.,et al.: Rapid: Early clas- sification of explosive transients using deep learning. Publications of the Astronomical Society of the Pacific131, 118002 (2019). https://doi.org/ 10.1088/1538-3873/ab1609

work page doi:10.1088/1538-3873/ab1609 2019

[8] [8]

AJ162(6), 275 (2021) arXiv:2109.13999 [astro-ph.IM]

Boone, K.: ParSNIP: Generative Models of Transient Light Curves with Physics-enabled Deep Learning. AJ162(6), 275 (2021) arXiv:2109.13999 [astro-ph.IM]. https://doi.org/10.3847/1538-3881/ac2a2d

work page doi:10.3847/1538-3881/ac2a2d 2021

[9] [9]

MNRAS 491(3), 4277–4293 (2020) arXiv:1901.06384 [astro-ph.IM]

M¨ oller, A., de Boissi` ere, T.: SuperNNova: an open-source framework for Bayesian, neural network-based supernova classification. MNRAS 491(3), 4277–4293 (2020) arXiv:1901.06384 [astro-ph.IM]. https://doi. org/10.1093/mnras/stz3312

work page doi:10.1093/mnras/stz3312 2020

[10] [10]

A&A692, 208 (2024) arXiv:2404.08798 [astro- ph.IM]

Fraga, B.M.O., Bom, C.R., Santos, A., Russeil, E., Leoni, M., Peloton, J., Ishida, E.E.O., M¨ oller, A., Blondin, S.: Transient classifiers for Fink: Benchmarks for LSST. A&A692, 208 (2024) arXiv:2404.08798 [astro- ph.IM]. https://doi.org/10.1051/0004-6361/202450370

work page doi:10.1051/0004-6361/202450370 2024

[11] [11]

AJ 161(5), 242 (2021) arXiv:2008.03303 [astro-ph.IM]

F¨ orster, F., Cabrera-Vives, G., Castillo-Navarrete, E., Est´ evez, P.A., S´ anchez-S´ aez, P., Arredondo, J., Bauer, F.E., Carrasco-Davis, R., Cate- lan, M., Elorrieta, F., Eyheramendy, S., Huijse, P., Pignata, G., Reyes, E., Reyes, I., Rodr´ ıguez-Mancini, D., Ruz-Mieres, D., Valenzuela, C.,´Alvarez- Maldonado, I., Astorga, N., Borissova, J., Clocchiat...

arXiv 2021

[12] [12]

In: Peck, A.B., Benn, C.R., Seaman, R.L

Saha, A., Matheson, T., Snodgrass, R., Kececioglu, J., Narayan, G., Seaman, R., Jenness, T., Axelrod, T.: ANTARES: a prototype tran- sient broker system. In: Peck, A.B., Benn, C.R., Seaman, R.L. (eds.) Observatory Operations: Strategies, Processes, and Systems V. Society of Photo-Optical Instrumentation Engineers (SPIE) Conference Series, vol. 9149, p. 91...

work page doi:10.1117/12.2056988 2014

[13] [13]

M¨ oller, A., Peloton, J., Ishida, E.E.O., Arnault, C., Bachelet, E., Blaineau, T., Boutigny, D., Chauhan, A., Gangler, E., Hernandez, F., Hrivnac, J., Leoni, M., Leroy, N., Moniez, M., Pateyron, S., Ramparison, A., Turpin, D., Ansari, R., Allam, T. Jr., Bajat, A., Biswas, B., Boucaud, A., Bre- geon, J., Campagne, J.-E., Cohen-Tanugi, J., Coleiro, A., Dor...

work page doi:10.1093/mnras/ 2021

[14] [14]

ApJ 884(1), 83 (2019) arXiv:1905.07422 [astro-ph.HE]

Villar, V.A., Berger, E., Miller, G., Chornock, R., Rest, A., Jones, D.O., Drout, M.R., Foley, R.J., Kirshner, R., Lunnan, R., Mag- nier, E., Milisavljevic, D., Sanders, N., Scolnic, D.: Supernova Pho- tometric Classification Pipelines Trained on Spectroscopically Classi- fied Supernovae from the Pan-STARRS1 Medium-deep Survey. ApJ 884(1), 83 (2019) arXiv...

arXiv 2019

[15] [15]

Machine Learning-based Brokers for Real-time Classification of the LSST Alert Stream

Narayan, G., Zaidi, T., Soraisam, M.D., Wang, Z., Lochner, M., Math- eson, T., Saha, A., Yang, S., Zhao, Z., Kececioglu, J., Scheidegger, C., Snodgrass, R.T., Axelrod, T., Jenness, T., Maier, R.S., Ridgway, S.T., Seaman, R.L., Evans, E.M., Singh, N., Taylor, C., Toeniskoetter, J., Welch, E., Zhu, S., ANTARES Collaboration: Machine-learning- based Brokers ...

work page internal anchor Pith review Pith/arXiv arXiv doi:10.3847/1538-4365/aab781 2018

[16] [16]

A transformer-based embedding for the representation of light curves

Donoso-Oliva, C., Becker, I., Protopapas, P., Cabrera-Vives, G., Vishnu, M., Vardhan, H.: ASTROMER. A transformer-based embedding for the representation of light curves. A&A670, 54 (2023) arXiv:2205.01677 [astro-ph.IM]. https://doi.org/10.1051/0004-6361/202243928 Springer Nature 2021 LATEX template AI Perspective into Time-domain Astronomy15

work page doi:10.1051/0004-6361/202243928 2023

[17] [17]

MNRAS531(4), 4990–5011 (2024) arXiv:2310.03024 [astro-ph.IM]

Parker, L., Lanusse, F., Golkar, S., Sarra, L., Cranmer, M., Bietti, A., Eickenberg, M., Krawezik, G., McCabe, M., Morel, R., Ohana, R., Pet- tee, M., R´ egaldo-Saint Blancard, B., Cho, K., Ho, S., Polymathic AI Collaboration: AstroCLIP: a cross-modal foundation model for galax- ies. MNRAS531(4), 4990–5011 (2024) arXiv:2310.03024 [astro-ph.IM]. https://do...

work page doi:10.1093/mnras/stae1450 2024

[18] [18]

arXiv preprint arXiv:2405.14930 (2024)

Smith, M.J., Roberts, R.J., Angeloudi, E., Huertas-Company, M.: Astropt: Scaling large observation models for astronomy. arXiv preprint arXiv:2405.14930 (2024)

arXiv 2024

[19] [19]

, keywords =

van Velzen, S., Gezari, S., Hammerstein, E., Roth, N., Frederick, S., Ward, C., Hung, T., Cenko, S.B., Stein, R., Perley, D.A., Taggart, K., Foley, R.J., Sollerman, J., Blagorodnova, N., Andreoni, I., Bellm, E.C., Brinnel, V., De, K., Dekany, R., Feeney, M., Fremling, C., Giomi, M., Golkhou, V.Z., Graham, M.J., Ho, A.Y.Q., Kasliwal, M.M., Kilpatrick, C.D....

work page doi:10.3847/1538-4357/abc258 2021

[20] [20]

IEEE Transactions on Pattern Analysis and Machine Intelligence35(8), 1798–1828 (2013)

Bengio, Y., Courville, A., Vincent, P.: Representation learning: A review and new perspectives. IEEE Transactions on Pattern Analysis and Machine Intelligence35(8), 1798–1828 (2013). https://doi.org/10.1109/ TPAMI.2013.50

2013

[21] [21]

MNRAS529(1), 732–747 (2024) arXiv:2309.08660 [astro-ph.IM]

Etsebeth, V., Lochner, M., Walmsley, M., Grespan, M.: Astronomaly at scale: searching for anomalies amongst 4 million galaxies. MNRAS529(1), 732–747 (2024) arXiv:2309.08660 [astro-ph.IM]. https://doi.org/10.1093/ mnras/stae496

arXiv 2024

[22] [22]

Machine Learning: Science and Technology6(3), 035032 (2025)

Pandya, S., Patel, P., Nord, B.D., Walmsley, M., ´Ciprijanovi´ c, A.: Sidda: Sinkhorn dynamic domain adaptation for image classification with equiv- ariant neural networks. Machine Learning: Science and Technology6(3), 035032 (2025). https://doi.org/10.1088/2632-2153/adf701

work page doi:10.1088/2632-2153/adf701 2025

[23] [23]

Gridach, J

Gridach, M., Nanavati, J., Zine El Abidine, K., Mendes, L., Mack, C.: Agentic AI for Scientific Discovery: A Survey of Progress, Challenges, and Future Directions. arXiv e-prints, 2503–08979 (2025) arXiv:2503.08979 [cs.CL]. https://doi.org/10.48550/arXiv.2503.08979

work page doi:10.48550/arxiv.2503.08979 2025

[24] [24]

In: Forty-second International Conference on Machine Learning (2025)

Richens, J., Everitt, T., Abel, D.: General agents need world models. In: Forty-second International Conference on Machine Learning (2025)

2025

[25] [25]

ACM Computing Surveys58(3), 1–38 (2025)

Ding, J., Zhang, Y., Shang, Y., Zhang, Y., Zong, Z., Feng, J., Yuan, Y., Su, Springer Nature 2021 LATEX template 16AI Perspective into Time-domain Astronomy H., Li, N., Sukiennik, N.,et al.: Understanding world or predicting future? a comprehensive survey of world models. ACM Computing Surveys58(3), 1–38 (2025)

2021

[26] [26]

Proceedings of the national academy of sciences114(13), 3521–3526 (2017)

Kirkpatrick, J., Pascanu, R., Rabinowitz, N., Veness, J., Desjardins, G., Rusu, A.A., Milan, K., Quan, J., Ramalho, T., Grabska-Barwinska, A.,et al.: Overcoming catastrophic forgetting in neural networks. Proceedings of the national academy of sciences114(13), 3521–3526 (2017)

2017

[27] [27]

arXiv e-prints, 2403–05175 (2024) arXiv:2403.05175 [stat.ML]

van de Ven, G.M., Soures, N., Kudithipudi, D.: Continual Learn- ing and Catastrophic Forgetting. arXiv e-prints, 2403–05175 (2024) arXiv:2403.05175 [stat.ML]. https://doi.org/10.48550/arXiv.2403.05175

work page doi:10.48550/arxiv.2403.05175 2024

[28] [28]

arXiv e-prints, 2010–05941 (2020) arXiv:2010.05941 [astro-ph.IM]

Kennamer, N., Ishida, E.E.O., Gonzalez-Gaitan, S., de Souza, R.S., Ihler, A., Ponder, K., Vilalta, R., Moller, A., Jones, D.O., Dai, M., Krone- Martins, A., Quint, B., Sreejith, S., Malz, A.I., Galbany, L.: Active learning with RESSPECT: Resource allocation for extragalactic astro- nomical transients. arXiv e-prints, 2010–05941 (2020) arXiv:2010.05941 [as...

work page doi:10.48550/arxiv.2010.05941 2010

[29] [29]

PASA42, 057 (2025) arXiv:2502.19555 [astro-ph.IM]

M¨ oller, A., Ishida, E., Peloton, J., Vidal Vel´ azquez, O., Soon, J., Martin, B., Cluver, M., Leoni, M., Taylor, E.N.: Real-time active learning for opti- mised spectroscopic follow-up: Enhancing early SN Ia classification with the Fink broker. PASA42, 057 (2025) arXiv:2502.19555 [astro-ph.IM]. https://doi.org/10.1017/pasa.2025.20

work page doi:10.1017/pasa.2025.20 2025

[30] [30]

Artificial intelligence101(1-2), 99–134 (1998)

Kaelbling, L.P., Littman, M.L., Cassandra, A.R.: Planning and acting in partially observable stochastic domains. Artificial intelligence101(1-2), 99–134 (1998)

1998

[31] [31]

Sutton, R.S., Barto, A.G.,et al.: Reinforcement Learning: An Introduc- tion vol. 1. MIT press Cambridge, ??? (1998)

1998

[32] [32]

The Astrophysical Journal995(1), 4 (2025)

Shah, V.G., Gagliano, A., Malanchev, K., Narayan, G., Malz, A.I., Col- laboration, L.D.E.S.: Oracle: A real-time, hierarchical, deep learning photometric classifier for the lsst. The Astrophysical Journal995(1), 4 (2025)

2025

[33] [33]

In: International Conference on Machine Learning, pp

Foster, A., Ivanova, D.R., Malik, I., Rainforth, T.: Deep adaptive design: Amortizing sequential bayesian experimental design. In: International Conference on Machine Learning, pp. 3384–3395 (2021). PMLR

2021

[34] [34]

Advances in neural information processing systems29(2016) Springer Nature 2021 LATEX template AI Perspective into Time-domain Astronomy17

Hadfield-Menell, D., Russell, S.J., Abbeel, P., Dragan, A.: Cooperative inverse reinforcement learning. Advances in neural information processing systems29(2016) Springer Nature 2021 LATEX template AI Perspective into Time-domain Astronomy17

2016

[35] [35]

rubin observatory

Andreoni, I., Margutti, R., Salafia, O.S., Parazin, B., Villar, V.A., Cough- lin, M.W., Yoachim, P., Mortensen, K., Brethauer, D., Smartt, S.,et al.: Target-of-opportunity observations of gravitational-wave events with vera c. rubin observatory. The Astrophysical Journal Supplement Series 260(1), 18 (2022)

2022

[36] [36]

Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences383(2294) (2025)

Nicholl, M., Andreoni, I.: Electromagnetic follow-up of gravitational waves: review and lessons learned. Philosophical Transactions of the Royal Society A: Mathematical, Physical and Engineering Sciences383(2294) (2025)

2025

[37] [37]

The Astrophysical Journal960(2), 122 (2024)

Annis, J., Garcia, A., Palmese, A., Sherman, N., Soares-Santos, M., Santana-Silva, L., Morgan, R., Bechtol, K., Davis, T.,et al.: Designing an optimal kilonova search using decam for gravitational-wave events. The Astrophysical Journal960(2), 122 (2024)

2024

[38] [38]

Monthly Notices of the Royal Astronomical Society495(4), 4366–4371 (2020)

Almualla, M., Coughlin, M.W., Anand, S., Alqassimi, K., Guessoum, N., Singer, L.P.: Dynamic scheduling: target of opportunity observations of gravitational wave events. Monthly Notices of the Royal Astronomical Society495(4), 4366–4371 (2020)

2020

[39] [39]

Astronomy and Computing33, 100423 (2020)

Fluke, C.J., Hegarty, S.E., MacMahon, C.-M.: Understanding the human in the design of cyber-human discovery systems for data-driven astronomy. Astronomy and Computing33, 100423 (2020)

2020

[40] [40]

In: Journal of Physics: Conference Series, vol

Albertsson, K., Altoe, P., Anderson, D., Andrews, M., Araque Espinosa, J.P., Aurisano, A., Basara, L., Bevan, A., Bhimji, W., Bonacorsi, D.,et al.: Machine learning in high energy physics community white paper. In: Journal of Physics: Conference Series, vol. 1085, p. 022008 (2018). IOP Publishing

2018

[41] [41]

Nature Communications13(1), 3876 (2022)

Pandi, A., Diehl, C., Yazdizadeh Kharrazi, A., Scholz, S.A., Bobkova, E., Faure, L., Nattermann, M., Adam, D., Chapin, N., Foroughijabbari, Y., et al.: A versatile active learning workflow for optimization of genetic and metabolic networks. Nature Communications13(1), 3876 (2022)

2022

[42] [42]

Journal of Machine Learning Research9(2) (2008)

Krause, A., Singh, A., Guestrin, C.: Near-optimal sensor placements in gaussian processes: Theory, efficient algorithms and empirical studies. Journal of Machine Learning Research9(2) (2008)

2008

[43] [43]

Technical report, USDOE Office of Science (SC), Washington, DC (United States) (2019)

Baker, N., Alexander, F., Bremer, T., Hagberg, A., Kevrekidis, Y., Najm, H., Parashar, M., Patra, A., Sethian, J., Wild, S., et al.: Workshop report on basic research needs for scientific machine learning: Core technologies for artificial intelligence. Technical report, USDOE Office of Science (SC), Washington, DC (United States) (2019)

2019

[44] [44]

arXiv preprint arXiv:2108.07258 (2021)

Bommasani, R., Hudson, D.A., Adeli, E., Altman, R., Arora, S., von Springer Nature 2021 LATEX template 18AI Perspective into Time-domain Astronomy Arx, S., Bernstein, M.S., Bohg, J., Bosselut, A., Brunskill, E., et al.: On the opportunities and risks of foundation models. arXiv preprint arXiv:2108.07258 (2021)

Pith/arXiv arXiv 2021

[45] [45]

Philosophy of Science 67(4), 559–579 (2000)

Douglas, H.: Inductive risk and values in science. Philosophy of Science 67(4), 559–579 (2000). https://doi.org/10.1086/392855

work page doi:10.1086/392855 2000

[46] [46]

University of Chicago Press, Chicago (2004)

Bourdieu, P.: Science of Science and Reflexivity. University of Chicago Press, Chicago (2004)

2004

[47] [47]

Future Generation Computer Systems59, 95– 104 (2016)

Djorgovski, S.G., Graham, M.J., Donalek, C., Mahabal, A.A., Drake, A.J., Turmon, M., Fuchs, T.: Real-time data mining of massive data streams from synoptic sky surveys. Future Generation Computer Systems59, 95– 104 (2016). https://doi.org/10.1016/j.future.2015.10.013

work page doi:10.1016/j.future.2015.10.013 2016

[48] [48]

arXiv e-prints, 2311–17143 (2023) arXiv:2311.17143 [astro-ph.IM]

Huang, H., Muthukrishna, D., Nair, P., Zhang, Z., Fausnaugh, M., Majumder, T., Foley, R.J., Ricker, G.R.: Predicting the Age of Astronom- ical Transients from Real-Time Multivariate Time Series. arXiv e-prints, 2311–17143 (2023) arXiv:2311.17143 [astro-ph.IM]. https://doi.org/10. 48550/arXiv.2311.17143

arXiv 2023

[49] [49]

A&A 650, 195 (2021) arXiv:1909.13260 [astro-ph.IM]

Ishida, E.E.O., Kornilov, M.V., Malanchev, K.L., Pruzhinskaya, M.V., Volnova, A.A., Korolev, V.S., Mondon, F., Sreejith, S., Malancheva, A.A., Das, S.: Active anomaly detection for time-domain discoveries. A&A 650, 195 (2021) arXiv:1909.13260 [astro-ph.IM]. https://doi.org/10.1051/ 0004-6361/202037709

arXiv 2021

[50] [50]

Annual Review of Astronomy and Astrophysics53(1), 247– 278 (2015)

Marshall, P.J., Lintott, C.J., Fletcher, L.N.: Ideas for citizen science in astronomy. Annual Review of Astronomy and Astrophysics53(1), 247– 278 (2015)

2015

[51] [51]

In: The Science of Citizen Science, pp

Paleco, C., Garc´ ıa Peter, S., Salas Seoane, N., Kaufmann, J., Argyri, P.: Inclusiveness and diversity in citizen science. In: The Science of Citizen Science, pp. 261–281. Springer, ??? (2021)

2021

[52] [52]

Royal Society Open Science11(5), 231309 (2024)

Wehn, U., Ajates, R., Mandeville, C., Somerwill, L., Kragh, G., Haklay, M.: Opening science to society: how to progress societal engagement into (open) science policies. Royal Society Open Science11(5), 231309 (2024)

2024

[53] [53]

University of Chicago press, ??? (2019)

Collins, H.: Tacit and Explicit Knowledge. University of Chicago press, ??? (2019)

2019

[54] [54]

Human factors52(3), 381–410 (2010)

Parasuraman, R., Manzey, D.H.: Complacency and bias in human use of automation: An attentional integration. Human factors52(3), 381–410 (2010)

2010

[55] [55]

Data Science1(1-2), 119–129 (2017)

Gil, Y.: Thoughtful artificial intelligence: Forging a new partnership for Springer Nature 2021 LATEX template AI Perspective into Time-domain Astronomy19 data science and scientific discovery. Data Science1(1-2), 119–129 (2017)

2021

[56] [56]

In: Observatory Operations: Strategies, Processes, and Systems V, vol

Jones, R.L., Yoachim, P., Chandrasekharan, S., Connolly, A.J., Cook, K.H., Ivezic, ˇZ., Krughoff, K.S., Petry, C., Ridgway, S.T.: The lsst met- rics analysis framework (maf). In: Observatory Operations: Strategies, Processes, and Systems V, vol. 9149, pp. 118–135 (2014). SPIE

2014

[57] [57]

2025, Monthly Notices of the Royal Astronomical Society, 544, 3799, doi: 10.1093/mnras/staf1833 pandas development team, T

OpenUniverse, LSST Dark Energy Science Collaboration, Roman HLIS Project Infrastructure, Roman Rapid Project Infrastructure Team, Roman Supernova Cosmology Project Infrastructure Team, Alarcon, A., Aldoroty, L., Beltz-Mohrmann, G., Bera, A., Blazek, J., Bogart, J., Brae- unlich, G., Broughton, A., Cao, K., Chiang, J., Chisari, N.E., Desai, V., Fang, Y., G...

work page doi:10.1093/mnras/staf1833 2025

[58] [58]

The Astrophysical Journal Supplement Series253(1), 31 (2021)

DESC), L.D.E.S.C.L., Abolfathi, B., Alonso, D., Armstrong, R., Aubourg, ´E., Awan, H., Babuji, Y.N., Bauer, F.E., Bean, R., Beckett, G.,et al.: The lsst desc dc2 simulated sky survey. The Astrophysical Journal Supplement Series253(1), 31 (2021)

2021

[59] [59]

Astronomy & Astrophysics631, 147 (2019)

Nordin, J., Brinnel, V., Van Santen, J., Bulla, M., Feindt, U., Franck- owiak, A., Fremling, C., Gal-Yam, A., Giomi, M., Kowalski, M.,et al.: Transient processing and analysis using ampel: alert management, pho- tometry, and evaluation of light curves. Astronomy & Astrophysics631, 147 (2019)

2019

[60] [60]

Monthly Notices of the Royal Astronomical Society507(2), 1746–1761 (2021)

Eifler, T., Miyatake, H., Krause, E., Heinrich, C., Miranda, V., Hirata, C., Xu, J., Hemmati, S., Simet, M., Capak, P.,et al.: Cosmology with the roman space telescope–multiprobe strategies. Monthly Notices of the Royal Astronomical Society507(2), 1746–1761 (2021)

2021

[61] [61]

arXiv preprint arXiv:2308.04485 (2023)

Burns, E., Coughlin, M., Ackley, K., Andreoni, I., Bizouard, M.-A., Broekgaarden, F., Christensen, N.L., d’Ammando, F., DeLaunay, J., Fleischhack, H., et al.: Gamma-ray transient network science analysis group report. arXiv preprint arXiv:2308.04485 (2023)

arXiv 2023

[62] [62]

Astronomy and Computing40, 100582 (2022)

Sambruna, R.M., Schlieder, J.E., Kocevski, D., Caputo, R., Hui, M.C., Markwardt, C.B., Powell, B.P., Racusin, J.L., Roberts, C., Singer, L.P., Springer Nature 2021 LATEX template 20AI Perspective into Time-domain Astronomy et al.: The nasa multi-messenger astrophysics science support center (mossaic). Astronomy and Computing40, 100582 (2022)

2021