\(
\def\cuberoot#1{\sqrt[3]{#1}}
\def\fourthroot#1{\sqrt[4]{#1}}
\def\abspartial#1#2#3#4{\left|\,{\partial(#1,#2)\over\partial(#3,#4)}\,\right|}
\def\absdeltal#1#2#3#4{\left|\,{\d(#1,#2)\over\d(#3,#4)}\,\right|}
\def\dispop#1#2{\disfrac{\partial #1}{\partial #2}}
\def\definedas{\equiv}
\def\bb{{\bf b}}
\def\bB{{\bf B}}
\def\bsigma{\boldsymbol{\sigma}}
\def\bx{{\bf x}}
\def\bu{{\bf u}}
\def\Re{{\rm Re\hskip1pt}}
\def\Reals{{\mathbb R\hskip1pt}}
\def\Integers{{\mathbb Z\hskip1pt}}
\def\Im{{\rm Im\hskip1pt}}
\def\P{\mbox{P}}
\def\half{{\textstyle{1\over 2}}}
\def\third{{\textstyle{1\over3}}}
\def\fourth{{\textstyle{1\over 4}}}
\def\fifth{{\scriptstyle{1\over 5}}}
\def\sixth{{\textstyle{1\over 6}}}
\def\oA{\rlap{$A$}\kern2pt\overline{\phantom{\dis{}I}}\kern.5pt}
\def\obA{\rlap{$A$}\kern2pt\overline{\phantom{\dis{}I}}\kern.5pt}
\def\obX{\rlap{$X$}\kern2pt\overline{\phantom{\dis{}I}}\kern.5pt}
\def\obY{\rlap{$Y$}\kern2pt\overline{\phantom{\dis{}I}}\kern.5pt}
\def\obZ{\rlap{$Z$}\kern2pt\overline{\phantom{\dis{}I}}\kern.5pt}
\def\obc{\rlap{$c$}\kern2pt\overline{\phantom{\dis{}I}}\kern.5pt}
\def\obd{\rlap{$d$}\kern2pt\overline{\phantom{\dis{}I}}\kern.5pt}
\def\obk{\rlap{$k$}\kern2pt\overline{\phantom{\dis{}I}}\kern.5pt}
\def\oba{\rlap{$a$}\kern2pt\overline{\phantom{\dis{}I}}\kern.5pt}
\def\obb{\rlap{$b$}\kern1pt\overline{\phantom{\dis{}t}}\kern.5pt}
\def\obw{\rlap{$w$}\kern1pt\overline{\phantom{\dis{}t}}\kern.5pt}
\def\obz{\overline{z}}\kern.5pt}
\newcommand{\bx}{\boldsymbol{x}}
\newcommand{\by}{\boldsymbol{y}}
\newcommand{\br}{\boldsymbol{r}}
\renewcommand{\bk}{\boldsymbol{k}}
\def\cuberoot#1{\sqrt[3]{#1}}
\def\fourthroot#1{\sqrt[4]{#1}}
\def\fifthroot#1{\sqrt[5]{#1}}
\def\eighthroot#1{\sqrt[8]{#1}}
\def\twelfthroot#1{\sqrt[12]{#1}}
\def\dis{\displaystyle}
%\def\definedas{\equiv}
\def\bq{{\bf q}}
\def\bp{{\bf p}}
\def\abs#1{\left|\,#1\,\right|}
\def\disfrac#1#2{{\displaystyle #1\over\displaystyle #2}}
\renewcommand{\ba}{\boldsymbol{a}}
\renewcommand{\bb}{\boldsymbol{b}}
\newcommand{\bc}{\boldsymbol{c}}
\newcommand{\bh}{\boldsymbol{h}}
\newcommand{\bA}{\boldsymbol{A}}
\newcommand{\bB}{\boldsymbol{B}}
\newcommand{\bC}{\boldsymbol{C}}
\newcommand{\definedas}{\equiv}
\newcommand{\half}{\frac{1}{2}}
\newcommand{\bsigma}{\boldsymbol \sigma}
\newcommand{\abs}[1]{\left|\,#1\,\right|}
\newcommand{\Rectangle}{\sqsubset\!\sqsupset}
\newcommand{\rectangle}{{%
\ooalign{$\sqsubset\mkern3mu$\cr$\mkern3mu\sqsupset$\cr}%
}}
\)
The Arrow of Time in Unitary systems
Patrick Reany
8 August 2025
Patrick:
Since quantum systems are driven by unitary operators, how does the system know which way is positive time? In other words, why doesn't the system spontaneously reverse itself (go backwards in time)?
Copilot:
This is a beautifully subtle question, Patrick---and it touches the heart of quantum dynamics, time symmetry, and the role of measurement. Let's unpack it.
Why Don't Quantum Systems Spontaneously Reverse Time?
Quantum systems evolve according to the Schrodinger equation, which is time-reversible. That is, if you know the state at time $𝑡_0$, you can evolve it forward or backward using a unitary operator: $$ |\psi(t)\rangle = U(t, t_0) |\psi(t_0)\rangle $$ where $𝑈(t,t_0)$ is unitary and invertible:
\begin{equation}
U(t_0, t) = U(t, t_0)^\dagger
\end{equation}
So in principle, nothing prevents a quantum system from evolving backward in time. But in practice, it doesn't. Why?
The Arrow of Time Emerges from Measurement and Decoherence
Unitary evolution is symmetric: Between measurements, quantum systems evolve in a way that doesn't distinguish past from future. The equations are time-symmetric.
Measurement breaks symmetry: When a quantum system is measured, its wavefunction collapses irreversibly. This collapse introduces an arrow of time---not from the Schrodinger equation, but from the Born rule and decoherence.
Decoherence is irreversible: Interaction with the environment causes quantum systems to lose coherence. This process is effectively irreversible and gives rise to classical behavior.
Thermodynamic arrow: Entropy increases over time. Even though microscopic laws are reversible, macroscopic systems overwhelmingly evolve toward higher entropy states.
So How Does the System "Know" Which Way Is Forward?
It doesn't---until you measure it or couple it to an environment. The unitary evolution itself is blind to time direction. But once you introduce:
- Initial conditions (preparation of a state)
- Measurement outcomes (collapse)
- Environmental interactions (decoherence)
…then the system acquires a temporal asymmetry.
Patrick:
In the many-worlds interpretation of QM, there is no collapse of the wave function; therefore there is no safeguard against 'time going backwards' in such a situation.
Copilot:
You're absolutely right, Patrick---and your observation cuts to the core of the tension between unitary evolution and the arrow of time in the many-worlds interpretation (MWI) of quantum mechanics.
In Many-Worlds, There Is No Collapse
In MWI:
- The wavefunction evolves unitarily and deterministically according to the Schrodinger equation.
- All possible outcomes of quantum measurements actually occur, each in a separate branch of the universal wavefunction.
- There is no collapse, no randomness injected by measurement, and no irreversible projection.
So yes---nothing in the formalism prevents time from running backward. The equations are time-symmetric, and the evolution is reversible.
Then Why Don't We See Time Reversals?
This is where things get subtle. Even in MWI, the appearance of time's arrow comes from:
- Initial conditions: The universe starts in a low-entropy state. As branches proliferate, entropy increases.
- Decoherence: As systems interact with their environments, interference between branches becomes negligible. This gives rise to classical-like behavior and an emergent arrow of time.
- Observer memory: Each observer in a branch has a memory that records events in one direction. Reversed evolution would erase memory, which is not observed.
So while the formalism allows time reversal, the structure of branching and decoherence makes it effectively impossible to observe.
Afterword: Copilot has listed only decoherence as common to both the MWI and non-MWI of time-asymmetry explanations. (I cannot accept the 'initial condition of the state' and the 'initial condition of the universe' as equivalent statements.)