pith. sign in

arxiv: 2505.09832 · v3 · submitted 2025-05-14 · 🌌 astro-ph.GA · astro-ph.CO· astro-ph.IM

LITMUS: Bayesian Lag Recovery in Reverberation Mapping with Fast Differentiable Models

Hugh G. McDougall , Tamara M. Davis , Benjamin J.S. Pope This is my paper

Pith reviewed 2026-05-22 14:50 UTC · model grok-4.3

classification 🌌 astro-ph.GA astro-ph.COastro-ph.IM
keywords reverberation mappinglag recoveryBayesian inferenceactive galactic nucleidamped random walktime series analysissupermassive black hole massesseasonal gaps
0
0 comments X

The pith

A Bayesian method for reverberation mapping recovers lags with high precision while identifying spurious detections from seasonal gaps.

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

The paper develops a Bayesian approach to extract time lags from brightness variations in active galactic nuclei. It models the variability as a damped random walk and maps the full posterior distribution over possible lag values. This mapping supplies both a precise lag estimate and an evidence integral that quantifies support for the lag model versus a null hypothesis of no real lag. The approach is evaluated on simulated light curves that include realistic seasonal gaps. If the central claim holds, it would make black-hole mass estimates from large monitoring campaigns more trustworthy by lowering the rate at which aliasing produces false lags.

Core claim

The paper claims that an algorithm for mapping the Bayesian posterior density built on the damped random walk model recovers lags from reverberation-mapping light curves with high precision and identifies spurious recoveries caused by seasonal observation windows, thereby reducing the false-positive rate.

What carries the argument

The algorithm that maps the Bayesian posterior density over lag values, which both constrains the lag and supplies evidence integrals for comparing the lag model against alternatives.

Load-bearing premise

The damped random walk model together with the seasonal gap pattern used in the mock data adequately captures the dominant sources of aliasing and false lag detections in real multi-year AGN campaigns.

What would settle it

Applying the method to real multi-year reverberation-mapping light curves and checking whether the recovered lags and false-positive identifications match independent black-hole mass measurements or results from simulations that use different variability models.

Figures

Figures reproduced from arXiv: 2505.09832 by Benjamin J.S. Pope, Hugh G. McDougall, Tamara M. Davis.

Figure 1
Figure 1. Figure 1: A demonstration of the sort of light curves that GP modelling can reconstruct from observations. For some time-series observations (error bars) a particular GP models the entire family of underlying light curves that exhibit the power spectral density of the GP, conditioned on how well they fit the observations. In this example the light curves is fit as a DRW with τ = 200d and σ = 1, both in arbitrary uni… view at source ↗
Figure 2
Figure 2. Figure 2: A demonstration of the source of the aliasing problem, specifically in the context of a parametric GP model. Top shows mock data with cadence, measurement uncertainty and baseline similar to OzDES with a DRW timescale of τ = 200d and a true lag of ∆t = 360d. From left to right the sub-panels show lags being tested at ∆t = 0d, 180d and 360d. The left panel is clearly a bad fit as near simultaneous observati… view at source ↗
Figure 3
Figure 3. Figure 3: A demonstration of the failure mode of the Affine-Invariant Ensemble Sampler (AIES), the MCMC proposal algorithm used by emcee, in multi-modal distributions. Both top and bottom panels are posterior distributions generated from the same mock data with a true lag at ∆t = 854d (dashed line), with the bottom panel being the result from the AIES, the same MCMC sampler as JAVELIN, while the top is found from ex… view at source ↗
Figure 4
Figure 4. Figure 4: A simplified demonstration of the operating principle behind LITMUS’s Laplace Quadrature for a case of only two free parameters (lag and DRW timescale). First, a 1D locus of conditional optima is traced out along the lag axis (orange line), finding the conditional optima at a discrete grid of lags (white points). At these points, the Laplace approximation is applied to divide the posterior up into a series… view at source ↗
Figure 5
Figure 5. Figure 5: A demonstration of the difference in the Laplace and SVI approximations, both attempting to emulate a Cauchy distribution (black solid line). The Laplace approximation (blue dotted line) creates a Gaussian that matches the curvature at the MAP of the true distribution, and in this case under-estimates the distribution everywhere else. The SVI approximation, here also fitting a Gaussian, instead tries to ge… view at source ↗
Figure 6
Figure 6. Figure 6: Mocks and evidence ratios for the demonstrative mock signals in the body of the text. The top panels shows the mock light curves for continuum (blue) and response (pink) signals. The left and right columns correspond to high and low SNR, while the rows from top to bottom show the mocks for a coupled response at a lag of ∆t = 540d, a decoupled response and a pure white noise response. The bottom panel shows… view at source ↗
Figure 7
Figure 7. Figure 7: A comparison of the posterior distributions for the lag error, i.e. the difference between true and recovered lag, comparing some of LITMUS’s aliasing-friendly methods, namely Nested Sampling (left panel) and the Laplace Quadrature (middle panel), to the JAVELIN-like AEIS (right panel). These plots are for mock sample 1 which has 440 mocks with true lags distributed uniformly over the range ∆t ∈ [0, 1000] … view at source ↗
Figure 8
Figure 8. Figure 8: A demonstration of how the Bayes factor acts as a measure of lag reliability. The top panel shows histograms of the Bayes factor evidence ratios for the decoupled mocks with no lag (grey), mocks with a lag that was successfully recovered (navy) and mocks that had an underlying lag but for which the posterior median of the recovery was more than 30 d from the ground truth. The bottom panel shows how the err… view at source ↗
Figure 1
Figure 1. Figure 1: An exaggerated demonstration of the grid smoothing algorithm for a simple multimodal function using α = 0.8 up to j = 5 iterations with 32 points. The top panel shows the true distribution (black) with its estimate from the first evenly spaced grid (red) and the final smoothed grid (blue). The bottom panel shows how the spacing of the grid updates over each iteration, progressing from top to bottom, with t… view at source ↗
Figure 1
Figure 1. Figure 1: Histogram of the run-times for the five fitting methods in LITMUS over all mocks, using the fitting parameters described in [PITH_FULL_IMAGE:figures/full_fig_p016_1.png] view at source ↗
read the original abstract

Reverberation mapping is a technique in which the mass of a Seyfert I galaxy's central supermassive black hole is estimated, along with the system's physical scale, from the timescale at which variations in brightness propagate through the galactic nucleus. This mapping allows for a long baseline of time measurements to extract spatial information beyond the angular resolution of our telescopes, and is the main means of constraining supermassive black hole masses at high redshift. The most recent generation of multi-year reverberation mapping campaigns for large numbers of active galactic nuclei (e.g. OzDES) have had to deal with persistent complications of identifying false positives, such as those arising from aliasing due to seasonal gaps in time-series data. We introduce LITMUS (Lag Inference Through the Mixed Use of Samplers), a modern lag recovery tool built on the "damped random walk" model of quasar variability, built in the autodiff framework JAX. LITMUS is purpose built to handle the multimodal aliasing of seasonal observation windows and provides evidence integrals for model comparison, a more quantified alternative to existing methods of lag validation. LITMUS also offers a flexible modular framework for extending modelling of AGN variability, and includes JAX-enabled implementations of other popular lag recovery methods like nested sampling and the interpolated cross correlation function. We test LITMUS on a number of mock light curves modelled after the OzDES sample and find that it recovers their lags with high precision and a successfully identifies spurious lag recoveries, reducing its false positive rate to drastically outperform the state of the art program JAVELIN. LITMUS's high performance is accomplished by an algorithm for mapping the Bayesian posterior density which both constrains the lag and offers a Bayesian framework for model null hypothesis testing.

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.

Referee Report

1 major / 2 minor

Summary. The manuscript introduces LITMUS, a JAX-based Bayesian framework for recovering time lags in reverberation mapping of AGN. It models quasar variability with a damped random walk, maps the posterior density over lag parameters to constrain the lag while handling multimodal aliasing from seasonal gaps, and computes evidence integrals for model comparison to flag spurious recoveries. The central empirical claim is that, on mock light curves constructed to match the OzDES sample, LITMUS recovers lags with high precision and reduces the false-positive rate substantially relative to JAVELIN.

Significance. If the performance advantage generalizes beyond the tested mocks, LITMUS would supply a modular, autodifferentiable platform that quantifies lag reliability through Bayesian evidence, which is a clear improvement over heuristic validation in existing tools. The JAX implementation and explicit support for extending the variability model are genuine strengths that could accelerate adoption in large surveys.

major comments (1)
  1. [Mock tests / Results] Mock tests section: the headline result that LITMUS 'drastically outperform[s] the state of the art program JAVELIN' in false-positive rate is demonstrated exclusively on light curves generated from the identical DRW model and OzDES seasonal gap pattern used inside LITMUS. This model-matched design verifies internal consistency of the posterior-mapping and evidence machinery but does not address robustness to the additional variability components (higher-order CARMA, broken power-law PSDs, non-stationarity) or gap structures that dominate real multi-year campaigns and are the dominant source of aliasing.
minor comments (2)
  1. [Abstract / Methods] The abstract states that LITMUS 'includes JAX-enabled implementations of other popular lag recovery methods like nested sampling and the interpolated cross correlation function'; the methods section should list the exact algorithms implemented, the interfaces provided, and whether any head-to-head timing or accuracy benchmarks were performed beyond the JAVELIN comparison.
  2. [Methods] Notation for the evidence integral and the posterior-mapping algorithm should be introduced with explicit equations rather than descriptive prose alone, to allow readers to verify the claimed independence from the fitted parameters.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for their constructive and detailed review of our manuscript. We address the major comment below and have revised the manuscript to better contextualize the scope and limitations of our mock tests.

read point-by-point responses

  1. Referee: Mock tests section: the headline result that LITMUS 'drastically outperform[s] the state of the art program JAVELIN' in false-positive rate is demonstrated exclusively on light curves generated from the identical DRW model and OzDES seasonal gap pattern used inside LITMUS. This model-matched design verifies internal consistency of the posterior-mapping and evidence machinery but does not address robustness to the additional variability components (higher-order CARMA, broken power-law PSDs, non-stationarity) or gap structures that dominate real multi-year campaigns and are the dominant source of aliasing.

    Authors: We agree that the mock tests presented in the manuscript generate light curves from the same damped random walk (DRW) model and OzDES seasonal gap pattern that are assumed within LITMUS. This design was selected to isolate and validate the performance of the posterior density mapping and Bayesian evidence calculations specifically for handling multimodal aliasing under a correctly specified variability model. In this controlled setting, the tests demonstrate that LITMUS can recover lags with high precision and substantially reduce false positives relative to JAVELIN when the DRW assumption holds. We acknowledge that these results do not directly evaluate robustness to model misspecification, including higher-order CARMA processes, broken power-law PSDs, non-stationarity, or different gap structures that may occur in real multi-year campaigns. In the revised manuscript, we have added explicit language in the Mock Tests section and a dedicated paragraph in the Discussion to clarify the assumptions of the tests, note this as a limitation, and identify robustness to more complex variability models as an important direction for future work. This revision ensures the claims are appropriately scoped without overstating generality. revision: yes

Circularity Check

0 steps flagged

No circularity detected in derivation or performance claims

full rationale

The LITMUS method is constructed from the standard damped random walk (DRW) model of AGN variability using JAX autodiff for posterior sampling and evidence integrals; these components are independent of the specific mock data generation. The performance claims (high-precision lag recovery and reduced false-positive rate versus JAVELIN) are empirical results obtained by applying the method to separate mock light curves generated under the same DRW plus OzDES gap structure. This constitutes standard internal-consistency validation under the paper's stated assumptions rather than a reduction of any derived quantity to its inputs by construction. No self-definitional steps, fitted-input predictions, or load-bearing self-citations appear in the derivation chain. The mock-based tests do not force the reported metrics; they verify that the Bayesian machinery recovers injected lags when the model is correctly specified.

Axiom & Free-Parameter Ledger

1 free parameters · 1 axioms · 0 invented entities

The central claim rests on the damped random walk being an adequate description of AGN variability and on the mock datasets faithfully reproducing the aliasing statistics of real OzDES-like campaigns; no new physical entities are introduced.

free parameters (1)
  • DRW damping timescale and amplitude
    Standard parameters of the damped random walk model that must be fitted or marginalized over for each light curve.
axioms (1)
  • domain assumption Quasar variability is adequately described by a damped random walk stochastic process.
    This is the explicit modeling choice stated in the abstract as the foundation for all lag recovery.

pith-pipeline@v0.9.0 · 5865 in / 1304 out tokens · 55884 ms · 2026-05-22T14:50:14.767263+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Forward citations

Cited by 1 Pith paper

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. AMIGO: a Data-Driven Calibration of the JWST Interferometer

    astro-ph.IM 2025-10 unverdicted novelty 7.0

    AMIGO is an end-to-end differentiable forward model of JWST AMI that corrects detector systematics to recover high-precision astrometry and detect close high-contrast companions.

Reference graph

Works this paper leans on

65 extracted references · 65 canonical work pages · cited by 1 Pith paper · 3 internal anchors

  1. [1]

    2023, ARA&A, 61, 329

    Aigrain, S., & Foreman-Mackey, D. 2023, ARA&A, 61, 329

    work page 2023

  2. [2]

    Albert, J. G. 2020, JAXNS: a high-performance nested sampling package based on JAX, arXiv:2012.15286

    work page arXiv 2020

  3. [3]

    2022, Nature Reviews Methods Primers, 2, doi:10.1038/s43586-022-00121-x

    Ashton, G., Bernstein, N., Buchner, J., et al. 2022, Nature Reviews Methods Primers, 2, doi:10.1038/s43586-022-00121-x

    work page doi:10.1038/s43586-022-00121-x 2022

  4. [4]

    A Conceptual Introduction to Hamiltonian Monte Carlo

    Betancourt, M. 2018, A Conceptual Introduction to Hamiltonian Monte Carlo, arXiv:1701.02434

    work page internal anchor Pith review Pith/arXiv arXiv 2018

  5. [5]

    D., & McKee, C

    Blandford, R. D., & McKee, C. F. 1982, ApJ, 255, 419

    work page 1982

  6. [6]

    2018, JAX: composable transformations of Python+NumPy programs

    Bradbury, J., Frostig, R., Hawkins, P., et al. 2018, JAX: composable transformations of Python+NumPy programs

    work page 2018

  7. [7]

    Broyden, C. G. 1970, IMA Journal of Applied Mathematics, 6, 222

    work page 1970

  8. [8]

    M., Bentz, M

    Cackett, E. M., Bentz, M. C., & Kara, E. 2021, iScience, 24, 102557

    work page 2021

  9. [9]

    M., Horne, K., & Winkler, H

    Cackett, E. M., Horne, K., & Winkler, H. 2007, Monthly Notices of the Royal Astronomical Society, 380, 669–682

    work page 2007

  10. [10]

    J., Kriss, G

    Dehghanian, M., Ferland, G. J., Kriss, G. A., et al. 2019, The Astrophysical Journal, 877, 119

    work page 2019

  11. [11]

    J., et al

    Ding, X., Treu, T., Shajib, A. J., et al. 2020, Time Delay Lens Modeling Challenge: I. Experimental Design, arXiv:1801.01506

    work page arXiv 2020

  12. [12]

    2021, Monthly Notices of the Royal Astronomical Society, 503, 1096–1123

    Ding, X., Treu, T., Birrer, S., et al. 2021, Monthly Notices of the Royal Astronomical Society, 503, 1096–1123

    work page 2021

  13. [13]

    2021, PyROA: Modeling quasar light curves, Astrophysics Source Code Library, record ascl:2107.012

    Donnan, F. 2021, PyROA: Modeling quasar light curves, Astrophysics Source Code Library, record ascl:2107.012

    work page 2021

  14. [14]

    D., Pendleton, B

    Duane, S., Kennedy, A. D., Pendleton, B. J., & Roweth, D. 1987, Physics Letters B, 195, 216

    work page 1987

  15. [15]

    M., Denney, K

    Fausnaugh, M. M., Denney, K. D., Barth, A. J., et al. 2016, ApJ, 821, 56

    work page 2016

  16. [16]

    P., & Bridges, M

    Feroz, F., Hobson, M. P., & Bridges, M. 2009, MNRAS, 398, 1601

    work page 2009

  17. [17]

    1970, The Computer Journal, 13, 317

    Fletcher, R. 1970, The Computer Journal, 13, 317

    work page 1970

  18. [18]

    W., Lang, D., & Goodman, J

    Foreman-Mackey, D., Hogg, D. W., Lang, D., & Goodman, J. 2013, Publications of the Astronomical Society of the Pacific, 125, 306

    work page 2013

  19. [19]

    2022, dfm/tinygp: tinygp v0.2.2, doi:10.5281/zenodo.6473662

    Foreman-Mackey, D., Yadav, S., Tronsgaard, R., Schmerler, S., & theorashid. 2022, dfm/tinygp: tinygp v0.2.2, doi:10.5281/zenodo.6473662

    work page doi:10.5281/zenodo.6473662 2022

  20. [20]

    M., & Peterson, B

    Gaskell, C. M., & Peterson, B. M. 1987, ApJS, 65, 1

    work page 1987

  21. [21]

    1970, Mathematics of Computation, 24, 23

    Goldfarb, D. 1970, Mathematics of Computation, 24, 23

    work page 1970

  22. [22]

    2010, Communications in Applied Mathematics and Computational Science, 5, 65

    Goodman, J., & Weare, J. 2010, Communications in Applied Mathematics and Computational Science, 5, 65

    work page 2010

  23. [23]

    J., Martini, P., Watson, L

    Grier, C. J., Martini, P., Watson, L. C., et al. 2013, ApJ, 773, 90

    work page 2013

  24. [24]

    J., Trump, J

    Grier, C. J., Trump, J. R., Shen, Y., et al. 2017, ApJ, 851, 21

    work page 2017

  25. [25]

    J., Shen, Y., Horne, K., et al

    Grier, C. J., Shen, Y., Horne, K., et al. 2019, The Astrophysical Journal, 887, 38

    work page 2019

  26. [26]

    J., Hobson, M

    Handley, W. J., Hobson, M. P., & Lasenby, A. N. 2015, MNRAS, 453, 4384

    work page 2015

  27. [27]

    R., Millman, K

    Harris, C. R., Millman, K. J., van der Walt, S. J., et al. 2020, Nature, 585, 357 Hern´ andez Santisteban, J. V., Edelson, R., Horne, K., et al. 2020, MNRAS, 498, 5399

    work page 2020

  28. [28]

    Hinton, S. R. 2016, The Journal of Open Source Software, 1, 00045

    work page 2016

  29. [29]

    K., Martini, P., Davis, T

    Hoormann, J. K., Martini, P., Davis, T. M., et al. 2019, Monthly Notices of the Royal Astronomical Society, 487, 3650–3663

    work page 2019

  30. [30]

    Hunter, J. D. 2007, Computing in Science & Engineering, 9, 90

    work page 2007

  31. [31]

    S., Netzer, H., et al

    Kaspi, S., Smith, P. S., Netzer, H., et al. 2000, The Astrophysical Journal, 533, 631–649

    work page 2000

  32. [32]

    C., Bechtold, J., & Siemiginowska, A

    Kelly, B. C., Bechtold, J., & Siemiginowska, A. 2009, ApJ, 698, 895

    work page 2009

  33. [33]

    2015, Monthly Notices of the Royal Astronomical Society: Letters, 456, L109–L112

    King, A. 2015, Monthly Notices of the Royal Astronomical Society: Letters, 456, L109–L112

    work page 2015

  34. [34]

    Adam: A Method for Stochastic Optimization

    Kingma, D. P., & Ba, J. 2017, Adam: A Method for Stochastic Optimization, arXiv:1412.6980

    work page internal anchor Pith review Pith/arXiv arXiv 2017

  35. [35]

    2014, The Astrophysical Journal, 788, 159 Koz lowski, S., Kochanek, C

    Koshida, S., Minezaki, T., Yoshii, Y., et al. 2014, The Astrophysical Journal, 788, 159 Koz lowski, S., Kochanek, C. S., Udalski, A., et al. 2010, ApJ, 708, 927

    work page 2014

  36. [36]

    2016, The Astrophysical Journal, 831, 206

    Li, Y.-R., Wang, J.-M., & Bai, J.-M. 2016, The Astrophysical Journal, 831, 206

    work page 2016

  37. [37]

    E., Davis, T

    Lidman, C., Tucker, B. E., Davis, T. M., et al. 2020, Monthly Notices of the Royal Astronomical Society, 496, 19–35

    work page 2020

  38. [38]

    L., Ivezi´ c, ˇZ ., Kochanek, C

    MacLeod, C. L., Ivezi´ c, ˇZ ., Kochanek, C. S., et al. 2010, The Astrophysical Journal, 721, 1014

    work page 2010

  39. [39]

    2023, MNRAS, 520, 2009

    Malik, U., Sharp, R., Penton, A., et al. 2023, MNRAS, 520, 2009

    work page 2023

  40. [40]

    McDougall, H. e. a. 2025, IN PREPARATION - TO BE UPDATED UPON SUBMISSION

    work page 2025

  41. [41]

    W., Rosenbluth, M

    Metropolis, N., Rosenbluth, A. W., Rosenbluth, M. N., Teller, A. H., & Teller, E. 1953, The Journal of Chemical Physics, 21, 1087

    work page 1953

  42. [42]

    2019, The Astrophysical Journal, 886, 150

    Minezaki, T., Yoshii, Y., Kobayashi, Y., et al. 2019, The Astrophysical Journal, 886, 150

    work page 2019

  43. [43]

    Neal, R. M. 1996, Monte Carlo Implementation (New York, NY: Springer New York), 55–98

    work page 1996

  44. [44]

    M., et al

    Penton, A., Malik, U., Davis, T. M., et al. 2021, Monthly Notices of the Royal Astronomical Society, 509, 4008–4023

    work page 2021

  45. [45]

    G., Davis, T

    Penton, A., McDougall, H. G., Davis, T. M., et al. 2025, IN PREPARATION - TO BE UPDATED UPON SUBMISSION, 000–000

    work page 2025

  46. [46]

    Peterson, B. M. 1993, PASP, 105, 247

    work page 1993

  47. [47]

    Composable Effects for Flexible and Accelerated Probabilistic Programming in NumPyro

    Phan, D., Pradhan, N., & Jankowiak, M. 2019, Composable Effects for Flexible and Accelerated Probabilistic Programming in NumPyro, doi:10.48550/ARXIV.1912.11554

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.1912.11554 2019

  48. [48]

    2009, Journal of the Royal Statistical Society Series B, 71, 319

    Rue, H., Martino, S., & Chopin, N. 2009, Journal of the Royal Statistical Society Series B, 71, 319

    work page 2009

  49. [49]

    1978, The Annals of Statistics, 6, 461

    Schwarz, G. 1978, The Annals of Statistics, 6, 461

    work page 1978

  50. [50]

    E., Jiang, Y.-F., Yao, P

    Secunda, A., Greene, J. E., Jiang, Y.-F., Yao, P. Z., & Zoghbi, A. 2023, ApJ, 956, 81

    work page 2023

  51. [51]

    I., & Sunyaev, R

    Shakura, N. I., & Sunyaev, R. A. 1973, A&A, 24, 337

    work page 1973

  52. [52]

    Shanno, D. F. 1970, Mathematics of Computation, 24, 647

    work page 1970

  53. [53]

    N., Dawson, K

    Shen, Y., Brandt, W. N., Dawson, K. S., et al. 2015, ApJS, 216, 4

    work page 2015

  54. [54]

    B., Horne, K., et al

    Shen, Y., Hall, P. B., Horne, K., et al. 2019, The Astrophysical Journal Supplement Series, 241, 34

    work page 2019

  55. [55]

    J., Horne, K., et al

    Shen, Y., Grier, C. J., Horne, K., et al. 2023, The Sloan Digital Sky Survey Reverberation Mapping Project: Key Results, arXiv:2305.01014

    work page arXiv 2023

  56. [56]

    2006, Bayesian Analysis, 1, 833

    Skilling, J. 2006, Bayesian Analysis, 1, 833

    work page 2006

  57. [57]

    M., et al

    Starkey, D., Horne, K., Fausnaugh, M. M., et al. 2017, ApJ, 835, 65

    work page 2017

  58. [58]

    A., Horne, K., & Villforth, C

    Starkey, D. A., Horne, K., & Villforth, C. 2015, Monthly Notices of the Royal Astronomical Society, 456, 1960–1973

    work page 2015

  59. [59]

    2006, ApJ, 639, 46

    Suganuma, M., Yoshii, Y., Kobayashi, Y., et al. 2006, ApJ, 639, 46

    work page 2006

  60. [60]

    M., Fabian, A

    Uttley, P., Cackett, E. M., Fabian, A. C., Kara, E., & Wilkins, D. R. 2014, The Astronomy and Astrophysics Review, 22, doi:10.1007/s00159-014-0072-0 van Niekerk, J., Krainski, E., Rustand, D., & Rue, H. 2022, A new avenue for Bayesian inference with INLA, arXiv:2204.06797 Van Rossum, G., & Drake, F. L. 2009, Python 3 Reference Manual (Scotts Valley, CA: C...

    work page doi:10.1007/s00159-014-0072-0 2014

  61. [61]

    Woo, J.-H., Yoon, Y., Park, S., Park, D., & Kim, S. C. 2015, The Astrophysical Journal, 801, 38

    work page 2015

  62. [62]

    S., Peterson, B

    Yu, Z., Kochanek, C. S., Peterson, B. M., et al. 2019, Monthly Notices of the Royal Astronomical Society, 491, 6045–6064

    work page 2019

  63. [63]

    2021, Monthly Notices of the Royal Astronomical Society, 507, 3771–3788 —

    Yu, Z., Martini, P., Penton, A., et al. 2021, Monthly Notices of the Royal Astronomical Society, 507, 3771–3788 —. 2023, Monthly Notices of the Royal Astronomical Society, 522, 4132–4147

    work page 2021

  64. [64]

    S., Koz lowski, S., & Udalski, A

    Zu, Y., Kochanek, C. S., Koz lowski, S., & Udalski, A. 2013, The Astrophysical Journal, 765, 106

    work page 2013

  65. [65]

    S., & Peterson, B

    Zu, Y., Kochanek, C. S., & Peterson, B. M. 2010, JAVELIN: Just Another Vehicle for Estimating Lags In Nuclei, Astrophysics Source Code Library, record ascl:1010.007, ascl:1010.007 —. 2011, ApJ, 735, 80

    work page 2010