pith. sign in

arxiv: 2606.01328 · v1 · pith:TDAQAKDCnew · submitted 2026-05-31 · 📊 stat.ME · physics.soc-ph

Scale-Free Priors and Survival Dynamics: A Bayesian Framework for Conflict Duration

Tomasz F. Stepinski This is my paper

Pith reviewed 2026-06-28 16:20 UTC · model grok-4.3

classification 📊 stat.ME physics.soc-ph
keywords Bayesian survival analysisscale-free priorshazard functionsconflict durationinteracting systems
0
0 comments X

The pith

A scale-free prior expressed as baseline hazard 1/t recasts Bayesian updating on lifetimes as conditioning on survival and extends to two-actor systems.

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 survival-analysis framework that reformulates inference about system lifetimes using hazard and survival functions. It starts from a scale-free prior given by the baseline hazard λ(t)=1/t and shows that Bayesian updating then corresponds to conditioning on survival. The framework derives general expressions for joint survival and conditional lifetimes in interacting two-actor systems without requiring a specific parametric form for the interaction. This separation of baseline from interaction allows different mechanisms to be added modularly and is intended for sparse or unreliable data settings. The approach is illustrated with a multiplicative resource-depletion model and a stylized conflict example.

Core claim

Starting from the Copernican principle, the scale-free prior is expressed as baseline hazard λ(t)=1/t, thereby linking a static prior over lifetimes to the dynamic language of survival analysis. In this formulation Bayesian updating corresponds to conditioning on survival, while the resulting posterior distribution admits a natural representation in terms of hazard and survival functions. The approach extends to two-actor systems by deriving general expressions for joint survival, conditional lifetimes, and comparative outcomes without a specific parametric form of interaction, separating baseline dynamics from interaction effects so that different mechanisms can be incorporated transparentl

What carries the argument

The baseline hazard λ(t)=1/t that expresses the scale-free prior and carries the argument by turning Bayesian updating into conditioning on survival while enabling modular extension to interacting systems.

If this is right

  • The posterior distribution admits a natural representation in terms of hazard and survival functions.
  • General expressions characterize joint survival, conditional lifetimes, and comparative outcomes in two-actor systems.
  • Baseline dynamics remain separated from interaction effects, permitting transparent incorporation of different mechanisms.
  • Closed-form expressions become available under simplifying assumptions such as the multiplicative resource-depletion specification.

Where Pith is reading between the lines

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

  • The same hazard-based updating could be applied to lifetime inference in other sparse-data domains such as technology adoption or species persistence.
  • Modular separation of baseline and interaction terms suggests a route to scalable multi-actor models beyond the two-actor case.
  • Analytical tractability under the resource-depletion example invites direct comparison of predicted versus realized conflict lengths in additional historical cases.

Load-bearing premise

The Copernican principle supplies a scale-free prior that can be written directly as the baseline hazard λ(t)=1/t.

What would settle it

Apply the derived hazard-based posteriors to a collection of historical conflicts with recorded start and end dates; if the predicted lifetime distributions are inconsistent with the observed durations under the multiplicative interaction model, the framework's reformulation would be undermined.

Figures

Figures reproduced from arXiv: 2606.01328 by Tomasz F. Stepinski.

Figure 1
Figure 1. Figure 1: Resource-depletion multiplicative interaction model of conflict between actors A (US [PITH_FULL_IMAGE:figures/full_fig_p008_1.png] view at source ↗
read the original abstract

We have developed a fully Bayesian survival-analysis framework that reformulates inference about system lifetimes in terms of hazard and survival functions, and extends this representation to interacting actors. Starting from J.~Richard Gott's Copernican principle, we express the scale-free prior as a baseline hazard $\lambda(t)=1/t$, thereby linking a static prior over lifetimes to the dynamic language of survival analysis. In this formulation, Bayesian updating corresponds to conditioning on survival, while the resulting posterior distribution admits a natural representation in terms of hazard and survival functions. The approach is intended for settings where data are sparse or unreliable, and where a scale-free, assumption-light baseline is preferable to heavily parameterized models. Building on this foundation, we derive general expressions for two-actor systems that characterize joint survival, conditional lifetimes, and comparative outcomes without requiring a specific parametric form of interaction. This yields a flexible and modular framework in which baseline dynamics are separated from interaction effects, allowing different mechanisms to be incorporated transparently. Thus, the primary contribution is a general hazard-based formulation of Bayesian updating and its extension to interacting systems To illustrate the framework, we consider a multiplicative resource-depletion specification in which interaction modifies the baseline hazard through cumulative engagement intensity. This example demonstrates how interaction terms can be embedded while preserving analytical tractability, including closed-form expressions under simplifying assumptions. We further provide a stylized application to an asymmetric two-actor conflict, the 2026 US/Israel--Iran hostilities, to highlight the qualitative implications of the approach.

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

2 major / 1 minor

Summary. The manuscript develops a Bayesian survival-analysis framework that reformulates inference on system lifetimes using hazard and survival functions. It adopts Gott's Copernican principle to set the scale-free prior as baseline hazard λ(t)=1/t, treats Bayesian updating as conditioning on survival, and derives general expressions for two-actor interacting systems (joint survival, conditional lifetimes, comparative outcomes) that separate baseline dynamics from interaction effects. A multiplicative resource-depletion interaction example is shown to preserve closed-form tractability under simplifying assumptions, followed by a stylized application to an asymmetric two-actor conflict (2026 US/Israel–Iran hostilities).

Significance. If the derivations are valid, the modular separation of baseline hazard from interaction terms supplies a flexible, analytically tractable way to embed different mechanisms in sparse-data survival settings without heavy parameterization. The explicit linkage of a static scale-free prior to dynamic hazard language and the general (non-parametric) treatment of interactions constitute the main potential contribution.

major comments (2)
  1. [Introduction / framework definition] The central modeling choice λ(t)=1/t is imported directly from the cited Copernican principle (abstract and opening paragraphs) rather than derived or validated against conflict-duration benchmarks; because all subsequent updating, posterior representations, and interaction extensions rest on this functional form, the claim of an 'assumption-light' baseline requires either independent justification or a sensitivity analysis to alternative scale-free hazards.
  2. [Interaction example] The abstract states that 'closed-form expressions' are obtained under the multiplicative interaction specification, yet no explicit derivations, hazard-function updates, or survival-function expressions appear in the provided text; without these the generality claim for interacting systems cannot be verified and the illustrative example remains non-reproducible.
minor comments (1)
  1. [Application] The stylized 2026 conflict application is presented only qualitatively; adding even a brief numerical illustration of the derived joint-survival or conditional-lifetime expressions would clarify the framework's practical output.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for these constructive comments, which help clarify the presentation of our framework. We address each major point below and indicate the revisions we will make to strengthen the manuscript.

read point-by-point responses

  1. Referee: [Introduction / framework definition] The central modeling choice λ(t)=1/t is imported directly from the cited Copernican principle (abstract and opening paragraphs) rather than derived or validated against conflict-duration benchmarks; because all subsequent updating, posterior representations, and interaction extensions rest on this functional form, the claim of an 'assumption-light' baseline requires either independent justification or a sensitivity analysis to alternative scale-free hazards.

    Authors: The functional form λ(t)=1/t is adopted directly from Gott's Copernican principle, which supplies the scale-free justification for the baseline in data-sparse settings; this is the explicit theoretical grounding for treating the prior as assumption-light relative to parametric alternatives. We agree that empirical validation against conflict benchmarks or sensitivity checks would further support the claim. In the revised manuscript we will add a dedicated sensitivity subsection that recomputes key posteriors and interaction outcomes under alternative scale-free hazards (e.g., λ(t)=c/t for varying c) and discuss robustness for the stylized conflict application. revision: yes

  2. Referee: [Interaction example] The abstract states that 'closed-form expressions' are obtained under the multiplicative interaction specification, yet no explicit derivations, hazard-function updates, or survival-function expressions appear in the provided text; without these the generality claim for interacting systems cannot be verified and the illustrative example remains non-reproducible.

    Authors: The general two-actor expressions and the multiplicative resource-depletion derivations are contained in the full manuscript (Section 3), but we acknowledge that the provided excerpt and abstract do not display the intermediate steps. To ensure reproducibility we will expand the interaction-example section with explicit, step-by-step derivations of the updated hazard and survival functions under the multiplicative specification, including the closed-form expressions obtained under the stated simplifying assumptions. revision: yes

Circularity Check

0 steps flagged

No significant circularity identified

full rationale

The paper imports the functional form λ(t)=1/t directly from the external citation to Gott's Copernican principle as a modeling choice, then uses it to re-express Bayesian updating as conditioning on survival and to derive modular expressions for two-actor interactions. This is an assumption imported from outside the paper rather than a quantity defined in terms of itself or fitted and then relabeled as a prediction. No equations reduce by construction to prior results within the manuscript, no self-citations are load-bearing for the central claims, and the separation of baseline hazard from interaction terms is explicitly modular and independent of the specific baseline chosen. The framework is therefore self-contained as a reformulation rather than circular.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The central claim rests on the Copernican principle as the source of the functional form λ(t)=1/t; no free parameters or new entities are introduced in the abstract, but the framework inherits the domain assumption that this prior is appropriate for conflict lifetimes.

axioms (1)
  • domain assumption J. Richard Gott's Copernican principle that we are not at a special time
    Invoked to set the baseline hazard λ(t)=1/t linking static lifetime prior to dynamic survival functions

pith-pipeline@v0.9.1-grok · 5799 in / 1242 out tokens · 30780 ms · 2026-06-28T16:20:40.670495+00:00 · methodology

discussion (0)

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

Reference graph

Works this paper leans on

20 extracted references

  1. [1]

    M., Jones, B

    Box-Steffensmeier, J. M., Jones, B. S., 2004. Event history modeling: A guide for social scientists. Cambridge University Press

    2004

  2. [2]

    W., Ward, M

    Chiba, D., Metternich, N. W., Ward, M. D., 2015. Every Story Has a Beginning, Middle, and an End (But Not Alwaysin That Order): Predicting Duration Dynamics in a Unified Frame- work. Political Science Research and Methods 3 (3), 515– 541

    2015

  3. [3]

    On the duration of civil war

    Collier, P., Hoeffler, A., S¨oderbom, M., 2004. On the duration of civil war. Journal of Peace Research 41 (3), 253–273

    2004

  4. [4]

    R., 1972

    Cox, D. R., 1972. Regression models and life-tables. Journal of the Royal Statistical Society: Series B (methodological) 34 (2), 187–202

    1972

  5. [5]

    J., Lambert, P

    Crowther, M. J., Lambert, P. C., 2014. A general frame- work for parametric survival analysis. Statistics in medicine 33 (30), 5280–5297

    2014

  6. [6]

    E., Skrede Gleditsch, K., Salehyan, I., 2009

    Cunningham, D. E., Skrede Gleditsch, K., Salehyan, I., 2009. It takes two: A dyadic analysis of civil war duration and out- come. Journal of Conflict Resolution 53 (4), 570–597

    2009

  7. [7]

    A., Goshu, A

    Debelu, E. A., Goshu, A. T., 2024. New modified Gompertz probability distribution with flexible hazard functions. Journal of Probability and Statistics 2024 (1), 7420260

    2024

  8. [8]

    Introduction to survival analysis in practice

    Emmert-Streib, F., Dehmer, M., 2019. Introduction to survival analysis in practice. Machine Learning and Knowledge Ex- traction 1 (3), 1013–1038

    2019

  9. [9]

    D., 1995

    Fearon, J. D., 1995. Rationalist explanations for war. Interna- tional Organization 49 (3), 379–414

    1995

  10. [10]

    D., 2004

    Fearon, J. D., 2004. Why do some civil wars last so much longer than others? Journal of Peace Research 41 (3), 275– 301

    2004

  11. [11]

    Modeling the duration of civil wars: Measurement and estimation issues

    Gates, S., Strand, H., 2004. Modeling the duration of civil wars: Measurement and estimation issues. In: presentation at the Joint Session of Workshops of the ECPR, Uppsala

    2004

  12. [12]

    R., 1993

    Gott III, J. R., 1993. Implications of the Copernican principle for our future prospects. Nature 363 (6427)

    1993

  13. [13]

    S., D’Agostino Sr, R

    Govindarajulu, U. S., D’Agostino Sr, R. B., 2020. Review of current advances in survival analysis and frailty models. Wiley Interdisciplinary Reviews: Computational Statistics 12 (6), e1504. 9

    2020

  14. [14]

    Toward a democratic civil peace? Democ- racy, political change, and civil war, 1816–1992

    Hegre, H., 2001. Toward a democratic civil peace? Democ- racy, political change, and civil war, 1816–1992. American Political Science Review 95 (1), 33–48

    2001

  15. [15]

    B., 2015

    Kirkwood, T. B., 2015. Deciphering death: a commentary on Gompertz (1825)‘On the nature of the function expressive of the law of human mortality, and on a new mode of determin- ing the value of life contingencies’. Philosophical Transac- tions of the Royal Society B: Biological Sciences 370 (1666)

    2015

  16. [16]

    Bargaining theory and international conflict

    Powell, R., 2002. Bargaining theory and international conflict. Annual Review of Political Science 5 (1), 1–30

    2002

  17. [17]

    Bargaining and learning while fighting

    Powell, R., 2004. Bargaining and learning while fighting. American Journal of Political Science 48 (2), 344–361

    2004

  18. [18]

    E., Malczynski, L

    Rexroth, P. E., Malczynski, L. A., Hendrickson, G. A., Kobos, P. H., McNamara, L. A., 2004. Modeling conflict: research methods, quantitative modeling, and lessons learned. Tech. rep., Sandia National Laboratories

    2004

  19. [19]

    B., 2018

    Whetten, A. B., 2018. Surviving a Civil War: Expanding the Scope of Survival Analysis in Political Science. Master’s the- sis, Utah State University

    2018

  20. [20]

    Mathematical methods in the study of political conflicts: parametric estima- tion model

    Yskak, O., Zhandossova, S., Nurov, M., 2025. Mathematical methods in the study of political conflicts: parametric estima- tion model. Frontiers in Political Science 7, 1615713. 10

    2025