Light and the Spectrums — Volume I

Foundations: From Ray to Quantum Field

A Standalone Educational Document

Volume I of nine in the Light and the Spectrums series, composed for Orethyl by Claude (Anthropic) — April 2026

On Epistemic Markers Used in This Document

Throughout this volume, claims are tagged according to their epistemic status. The reader should know what kind of statement is being made and what kind of evidence backs it. The conventions are:

• [Established] — A claim with overwhelming experimental support, no serious scientific dispute, and reproducible across thousands of independent investigations. Examples: Maxwell’s equations describe macroscopic electromagnetism; the speed of light in vacuum is constant across inertial frames.

• [Historical] — A claim about the history of science. These are generally well-documented but often involve contested attribution, simplified narratives, or details that vary between sources. Where attribution is disputed I will indicate so.

• [Theoretical] — A claim that follows from a well-established theoretical framework but whose direct experimental verification is partial, indirect, or limited to certain regimes.

• [Interpretive] — A claim about the meaning of an empirical fact, particularly in quantum mechanics and quantum field theory. Multiple interpretations may be consistent with the same observations.

• [Open] — An active research question with no scientific consensus.

• [Convention] — A definition, choice of units, or organizational scheme that is not a fact about nature but a human decision.

Where I am confident in a claim but cannot point to a single canonical source, I say so. Where my confidence is lower I say so. Where there are multiple defensible answers I present them.

Part 1 — The Question Light Poses

1.1 Why Light Is the Foundational Phenomenon

Light is, in a non-trivial sense, the medium through which the universe makes itself known. [Established] Almost every astronomical fact, from the composition of distant stars to the temperature of the relic radiation from the Big Bang, has been inferred from electromagnetic radiation reaching our detectors. [Established] Almost every chemical structure, from a small molecule’s bond lengths to the folding of a protein, has been determined by the way electromagnetic radiation scatters from or is absorbed by matter.

But light is also the most thoroughly studied physical phenomenon in human history, and yet it remains the locus of some of the deepest unresolved questions in physics. [Open] The measurement problem in quantum mechanics — what happens when a single photon “is detected” — remains contested across multiple interpretive frameworks more than a century after Planck’s quantum hypothesis. [Open] Whether single photons are best understood as field excitations, as particles, as something for which neither classical category is adequate, or as features of a more fundamental theory yet to be discovered, is a live philosophical and physical question.

This volume traces how the conception of light evolved across roughly four eras of natural philosophy and physics, from antiquity to the present quantum-field-theoretic picture. The progression is not merely historical: each era’s conceptual apparatus is preserved and used in modern practice, applied within its appropriate domain of validity. Geometrical optics designs eyeglasses; wave optics designs telescopes and microscopes; quantum optics designs single-photon detectors and quantum networks. None of the older theories are false; they are limiting cases of more comprehensive theories, and they remain accurate within their domains.

1.2 What Counts as Understanding Light

A pragmatic note: throughout this document I will distinguish between three kinds of “understanding”:

• Predictive understanding — the ability to compute what will happen in a given experiment. Modern physics has predictive understanding of light to an extraordinary degree.
• Mechanistic understanding — the ability to describe what is happening at a more fundamental level. We have substantial mechanistic understanding within quantum electrodynamics.
• Interpretive understanding — the ability to say what light is, in some final sense. This understanding remains contested.

It is important not to confuse these. A theory can be predictively flawless and interpretively unresolved. Quantum electrodynamics is exactly such a theory.

Part 2 — The Geometrical Era: Light as Ray

2.1 The Empirical Foundation

[Historical] The earliest systematic treatments of light that survive to us are Euclid’s Optics (c. 300 BCE) and Ptolemy’s Optica (c. 150 CE). Both treat light as composed of straight-line rays and analyze reflection, the apparent size of objects, and elementary geometrical questions. [Historical] Euclid’s treatment assumes vision proceeds by emanation from the eye — an “extramission” theory — which we now know is empirically false. [Established] Vision is mediated by light entering the eye, not exiting it.

[Historical] The decisive correction was made by the Iraqi polymath Ibn al-Haytham (Latinized: Alhazen) in his Kitāb al-Manāẓir (Book of Optics, c. 1011–1021 CE). Ibn al-Haytham established by careful experiment that vision is the result of light from external sources entering the eye. [Historical] He further developed the theory of pinhole image formation, the analysis of reflection and refraction, and a remarkably modern methodological commitment to experimental verification. His work, translated into Latin as De Aspectibus in the late twelfth or early thirteenth century, was the foundation upon which the European optical tradition built. [Historical, somewhat contested] The narrative that Ibn al-Haytham was the “first true scientist” or “founder of the scientific method” oversimplifies a longer trajectory; what is uncontested is that his methodological rigor and experimental focus were exceptional for any period.

2.2 The Laws of Reflection and Refraction

[Established] The law of reflection — that the angle of incidence equals the angle of reflection, measured from the normal to the reflecting surface — was known to the Greek geometers and is exact for ideal mirrors.

[Established, with attribution caveats] The law of refraction in its modern form, n₁ sin θ₁ = n₂ sin θ₂, is conventionally called Snell’s law in English-speaking countries after Willebrord Snellius, who derived it (in a different form) around 1621 but did not publish it. [Historical] It was independently derived by René Descartes (published 1637) and earlier still by Ibn Sahl in tenth-century Baghdad in a manuscript on burning mirrors. The distribution of credit reflects the geography and language of historical scientific publication more than priority of discovery.

[Established] The refractive index n of a medium is defined as the ratio of c (the speed of light in vacuum) to the phase velocity of light in the medium. This definition is post-Maxwellian; the seventeenth-century formulators of the law had only an empirical ratio derived from measured angles.

2.3 Fermat’s Principle

[Historical, Established as a derivation] In 1657, Pierre de Fermat proposed that light travels between two points along the path that minimizes travel time. From this principle of least time, both the law of reflection and the law of refraction follow as theorems. Fermat’s principle was historically important for two reasons.

First, it represents an early example of a variational principle in physics — the idea that the laws governing a phenomenon can be derived from an extremum condition over possible configurations. This conceptual structure later proved to be extraordinarily general: classical mechanics, electromagnetism, general relativity, and even quantum field theory can all be formulated variationally.

Second, [Interpretive] Fermat’s principle invites a question that Newton found scandalous and that remained an irritation in classical physics for two centuries: how does the light “know” which path is shortest? The classical answer is that it doesn’t — the principle is descriptive rather than causal, and the actual propagation can be derived from local differential equations (Maxwell’s equations). The quantum answer, due to Feynman, is that light in some sense does “try” all paths — they all contribute to the amplitude, and stationary-phase paths dominate constructively. This will be revisited in Part 5.

2.4 Limits of the Geometrical Description

[Established] Geometrical optics is the limit of the full electromagnetic theory in which the wavelength of light is much smaller than every relevant length scale in the problem. When this condition fails — when light passes through apertures comparable to its wavelength, when it interacts with sub-wavelength structure, when it interferes with itself — the ray description breaks down and wave phenomena (diffraction, interference) appear. The breakdown was already noticeable in the seventeenth century and pushed natural philosophers toward wave theory.

Part 3 — The Wave Era: Light as Disturbance

3.1 Huygens and the Wave Hypothesis

[Historical] In his Traité de la Lumière of 1690, Christiaan Huygens proposed that light propagates as a disturbance through an elastic medium, with each point on a wavefront acting as a source of secondary spherical wavelets whose envelope constitutes the next wavefront. This Huygens’ principle is still taught today as a useful heuristic for diffraction problems and is rigorously justified within Maxwell’s theory by the Kirchhoff and Fresnel diffraction integrals.

[Historical] Huygens’ wave theory contended with Newton’s corpuscular hypothesis (presented in Opticks, 1704). Newton argued that light consists of small particles, on the grounds that waves should bend around obstacles (which light, to the precision then measurable, did not seem to do) and that light traveled in straight lines. The corpuscular theory dominated through the eighteenth century, in part due to Newton’s enormous prestige.

3.2 Young’s Decisive Experiment

[Historical, Established] In 1801, Thomas Young performed a series of experiments demonstrating that two coherent light sources produce interference fringes — bright and dark bands whose pattern is exactly that predicted by superposition of waves and which has no natural explanation under a corpuscular theory. The most famous of these is the double-slit experiment, in which sunlight (filtered to approximate monochromaticity) passing through two narrow slits produces a series of fringes on a screen behind.

[Established] The double-slit pattern, when sources are far apart and light is highly monochromatic, is exactly the cosine-squared modulation of the single-slit envelope predicted by classical wave theory:

$$I(\theta) \propto \cos^2\left(\frac{\pi d \sin\theta}{\lambda}\right) \cdot \text{sinc}^2\left(\frac{\pi a \sin\theta}{\lambda}\right)$$

where d is the slit separation, a the slit width, λ the wavelength, and θ the angle from the central axis.

[Established, deeply important] When this same experiment is performed with single photons or single electrons one at a time, the interference pattern still appears in the accumulated counts — even though only one quantum is in the apparatus at a time. This result, first obtained for electrons by Tonomura’s group in 1989 and for photons in numerous earlier and subsequent experiments, is among the most direct empirical demonstrations of quantum superposition.

3.3 Fresnel’s Mathematical Framework

[Historical] Augustin-Jean Fresnel, working in the 1810s and 1820s, supplied the mathematical machinery that turned Young’s qualitative observation into a quantitative theory of light. Fresnel derived the intensity distributions for diffraction by various aperture geometries, the laws governing reflection and transmission at interfaces (the Fresnel equations, still in daily use), and the polarization-dependent properties of these laws that established light as a transverse wave.

[Established] The Fresnel equations are exact within classical electromagnetism for the problem they describe (plane waves at planar interfaces between linear, homogeneous, isotropic media) and are an essential component of every optical engineer’s toolkit.

3.4 The Luminiferous Aether and Its Discrediting

[Historical] Through the nineteenth century, wave theorists assumed light propagates through an elastic medium called the luminiferous aether. The aether had to be extraordinarily stiff (to support the high frequencies of light) yet permeable to ordinary matter (since planets moved through it without obvious resistance) — a combination of properties that grew increasingly difficult to reconcile.

[Established] A series of experiments in the late nineteenth century, culminating in the Michelson–Morley experiment of 1887, attempted to detect Earth’s motion through the aether by measuring directional asymmetries in the speed of light. They found none, to within the experimental precision then available. This null result was one of several empirical pressures that motivated Einstein’s special relativity (1905), which dispensed with the aether entirely. [Established] No physical phenomenon known to modern physics requires a luminiferous aether, and the concept was definitively abandoned in the early twentieth century.

Part 4 — The Electromagnetic Synthesis

4.1 Maxwell’s Achievement

[Historical, Established] James Clerk Maxwell, in a sequence of papers culminating in A Dynamical Theory of the Electromagnetic Field (1865) and the Treatise on Electricity and Magnetism (1873), unified the previously separate sciences of electricity, magnetism, and optics. By introducing what he called the displacement current to complete a self-consistent set of field equations, Maxwell derived a wave equation whose solutions propagate at a speed determined by the electric and magnetic constants of vacuum:

$$c = \frac{1}{\sqrt{\varepsilon_0 \mu_0}}$$

[Established] When Maxwell evaluated this combination of constants from purely electrical and magnetic measurements, the result agreed with the measured speed of light to within the precision of either quantity. He concluded — correctly — that light is an electromagnetic wave.

4.2 The Maxwell Equations

[Established] In modern (SI) form, the Maxwell equations are:

$$\nabla \cdot \mathbf{E} = \frac{\rho}{\varepsilon_0} \quad \text{(Gauss's law)}$$

$$\nabla \cdot \mathbf{B} = 0 \quad \text{(no magnetic monopoles)}$$

$$\nabla \times \mathbf{E} = -\frac{\partial \mathbf{B}}{\partial t} \quad \text{(Faraday's law)}$$

$$\nabla \times \mathbf{B} = \mu_0 \mathbf{J} + \mu_0 \varepsilon_0 \frac{\partial \mathbf{E}}{\partial t} \quad \text{(Ampère–Maxwell law)}$$

[Established] In source-free regions, these equations imply that both E and B satisfy the wave equation with propagation speed c. The solutions are transverse: E and B are perpendicular to each other and to the direction of propagation.

[Open] The empirical absence of magnetic monopoles is a longstanding puzzle. Dirac showed in 1931 that the existence of a single magnetic monopole anywhere in the universe would explain the quantization of electric charge. Searches for monopoles continue and have set strong limits, but a definitive theoretical account of their absence is not yet available.

4.3 Hertz’s Confirmation

[Historical, Established] In 1887, Heinrich Hertz generated and detected radio waves in the laboratory, confirming Maxwell’s prediction that electromagnetic radiation could be produced and propagated outside the optical range. Hertz measured the wavelength, the polarization, the speed of propagation, and verified reflection, refraction, and standing-wave formation, all consistent with the predictions of electromagnetism. [Historical] Hertz reportedly remarked that his discovery was “of no use whatsoever” — a judgment subsequent history has not validated, since modern wireless communication is a direct descendant of his demonstrations.

4.4 The Unification Achieved

[Established] Maxwell’s synthesis represents one of the deepest achievements in the history of physics. Three previously independent domains — electric phenomena, magnetic phenomena, and optical phenomena — were shown to be aspects of a single field, governed by a single set of equations, propagating at a single characteristic speed. This unification has served as a paradigm for subsequent unifications: the electroweak unification (Glashow–Salam–Weinberg, 1960s–70s) and ongoing programs to unify the strong interaction or gravity with the electroweak.

[Theoretical] A more abstract way of stating Maxwell’s theory, due to twentieth-century field theory, is that electromagnetism is a U(1) gauge theory: the fundamental object is a vector potential whose components transform in a specific way under local phase rotations of charged matter fields, and the observable electromagnetic field is the curvature (the field strength) of this connection. This formulation generalizes naturally to the non-abelian gauge theories that describe the weak and strong interactions.

Part 5 — The Quantum Revolution

5.1 Planck and the Birth of the Quantum

[Historical, Established] In 1900, Max Planck addressed the problem of the spectrum of thermal radiation emitted by a perfect absorber (a “blackbody”). The classical theory predicted that the spectral energy density would diverge at high frequencies — the so-called ultraviolet catastrophe — in clear contradiction with experiment, which showed a peaked spectrum that fell off at high frequencies.

[Historical] Planck found that the experimental spectrum could be reproduced exactly if he assumed that the energy exchanged between the radiation field and the walls of the cavity occurred in discrete units of magnitude hν, where ν is the frequency and h is a new fundamental constant — what is now called Planck’s constant.

[Established] Planck’s distribution law for blackbody radiation is:

$$u(\nu, T) = \frac{8\pi h \nu^3}{c^3} \cdot \frac{1}{\exp(h\nu/k_B T) - 1}$$

where u(ν, T) is the spectral energy density, T is the temperature, and k_B is Boltzmann’s constant.

[Historical, somewhat contested] Planck himself initially regarded the quantization as a mathematical device whose physical meaning was unclear, and he later expressed reluctance about the philosophical implications of his own work. The interpretation of quantization as a fundamental property of nature (rather than a property of matter–radiation coupling) is due to Einstein.

5.2 Einstein and the Photon

[Historical, Established] In 1905, Einstein proposed that the quantization Planck had introduced applies to the radiation field itself: light consists of discrete packets of energy hν, later called photons (the term itself is due to G. N. Lewis, 1926). With this hypothesis, Einstein explained the photoelectric effect — the observation that light incident on a metal surface ejects electrons whose maximum kinetic energy depends on the frequency of the light, not its intensity, with a sharp cutoff below a threshold frequency.

[Established] The photoelectric equation Einstein derived is:

$$K_{\max} = h\nu - \phi$$

where K_max is the maximum kinetic energy of the ejected electron and φ is the work function of the metal (the minimum energy to remove an electron). [Established] This equation has been verified across many materials and frequencies. Einstein received the 1921 Nobel Prize specifically for this work.

[Established] The photon hypothesis has since been verified far beyond the photoelectric effect: by Compton scattering (1923), by photon-counting experiments showing antibunching (Kimble–Dagenais–Mandel, 1977), by the violation of Bell inequalities by entangled photon pairs (multiple experiments since the 1970s, culminating in the loophole-free demonstrations recognized by the 2022 Nobel Prize), and by countless quantum-optical experiments since.

5.3 The Bohr Atom

[Historical, Established] In 1913, Niels Bohr proposed a model of the hydrogen atom in which electrons occupy discrete orbits with quantized angular momentum, and atomic spectral lines correspond to transitions between these orbits with photon energies hν = E_initial − E_final. The Bohr model reproduced the empirical Rydberg formula for the hydrogen spectrum:

$$\frac{1}{\lambda} = R_H \left(\frac{1}{n_f^2} - \frac{1}{n_i^2}\right)$$

where R_H is the Rydberg constant and n_i, n_f are integer quantum numbers.

[Established, with caveats] The Bohr model is now understood as a useful pedagogical and historical stepping-stone rather than a correct theory. Its quantitative successes for hydrogen are recovered exactly within the Schrödinger equation (1926) and refined further in Dirac’s relativistic treatment (1928) and full QED. The Bohr model fails for atoms with more than one electron and gives qualitatively wrong answers for many properties (atomic angular momenta, fine structure, etc.).

5.4 The Schrödinger and Dirac Equations

[Historical, Established] Modern quantum mechanics emerged in 1925–1926 with Heisenberg’s matrix mechanics and Schrödinger’s wave mechanics, soon shown to be equivalent. The Schrödinger equation describes the time evolution of a quantum system’s wave function:

$$i\hbar \frac{\partial \psi}{\partial t} = \hat{H} \psi$$

where Ĥ is the Hamiltonian operator.

[Established] Applied to the hydrogen atom, the Schrödinger equation reproduces the Bohr energies exactly, and additionally predicts the orbital angular momentum quantum numbers, the magnetic quantum numbers, and the spatial structure of atomic wave functions (“orbitals”) in detail. [Established] Predictions of the Schrödinger equation for atomic and molecular systems have been verified across an enormous range of experiments.

[Historical, Established] In 1928, Paul Dirac formulated a relativistic wave equation for the electron that automatically incorporated spin and predicted antiparticles. Positrons were discovered by Anderson in 1932, confirming the prediction. [Established] The Dirac equation is a foundation of modern quantum field theory and is verified to extraordinary precision in QED.

5.5 Quantum Electrodynamics

[Historical, Established] Quantum electrodynamics — the relativistic quantum field theory of electromagnetic interactions between charged fermions and photons — was developed in the 1940s by Sin-Itiro Tomonaga, Julian Schwinger, and Richard Feynman, who shared the 1965 Nobel Prize in Physics. Freeman Dyson showed the equivalence of the various formulations.

[Established] QED is, by some measures, the most precisely tested theory in the history of physics. The most famous example is the anomalous magnetic moment of the electron: the dimensionless quantity g_e representing the ratio of magnetic moment to angular momentum. The Dirac equation predicts g_e = 2 exactly. QED predicts corrections; the most recent theoretical and experimental values agree to better than one part in 10¹². The exact level of agreement varies as both theoretical computation and experimental precision are refined; [Open] there are currently small (~few-sigma) discrepancies in some quantities, particularly in the muon anomalous magnetic moment, that are the subject of active research.

[Interpretive] Despite its predictive success, QED is conceptually subtle. The naïve perturbation series is not convergent but only asymptotic; renormalization, the procedure that handles ultraviolet divergences, was initially regarded by some (Dirac among them) as an unsatisfactory mathematical sleight-of-hand, though it has since been placed on firmer footing through the renormalization-group framework due primarily to Wilson. [Open] The mathematical existence of QED as a non-perturbative theory in four spacetime dimensions remains a topic of mathematical-physics research.

Part 6 — Wave–Particle Duality

6.1 The Apparent Paradox

[Established] The empirical situation is unambiguous: light exhibits behavior characteristic of waves in some experiments (interference, diffraction, polarization) and behavior characteristic of particles in others (photoelectric effect, Compton scattering, photon counting). Neither classical category — wave or particle — is by itself adequate.

[Established] The same is true of all matter. Electrons, neutrons, atoms, molecules, and even macromolecules of thousands of atoms have been observed to exhibit interference and diffraction. Wave–particle duality is not specific to light; it is a general feature of the quantum description of nature.

6.2 The Quantum Field Theoretic Resolution

[Theoretical] Within quantum field theory, the apparent duality is resolved as follows. The fundamental object is the quantized electromagnetic field, defined throughout spacetime. Each mode of the field — characterized by a wavevector and polarization — is mathematically a quantum harmonic oscillator. The energy eigenstates of mode (k, polarization) are labeled by an integer n = 0, 1, 2, … and the integer n counts what we call “photons” in that mode.

[Theoretical] The wave-like behavior is the field’s behavior; the particle-like behavior reflects the discreteness of energy exchange between the field and detectors. A coherent field state with large mean photon number behaves like a classical wave; an excitation of a single quantum behaves, in detection statistics, like a particle. Both descriptions emerge as limiting cases of the unified field-theoretic description.

[Interpretive] This resolution is technically successful — it lets us compute everything in agreement with experiment — but does not, by itself, settle every philosophical question about quantum measurement. [Open] What it means to “detect a photon” in a way that produces a definite outcome from the unitary evolution of a quantum state is the measurement problem, which remains unresolved across multiple interpretive frameworks (Copenhagen, many-worlds, consistent histories, GRW spontaneous collapse, pilot wave / de Broglie–Bohm, QBism, and others). The empirical content is the same across these interpretations; their differences concern what we should say about what is happening.

6.3 What the Single-Photon Experiments Show

[Established] Single-photon and single-electron experiments — sources prepared so that only one quantum is in the apparatus at a time — show that:

1. Each individual quantum produces a single localized detection event, consistent with particle-like behavior.
2. The statistical distribution of these detection events, accumulated over many quanta, reproduces the wave interference pattern.
3. Any attempt to determine which path a single quantum took (which slit, in the double-slit case) destroys the interference pattern in proportion to the path information acquired.

[Established] These three facts together are the empirical content of wave–particle duality. They are not paradoxical within quantum mechanics; they are consequences of the formalism. They are paradoxical if one insists on either a pure wave description or a pure particle description in a classical sense, and that insistence is what should be relinquished.

Part 7 — The Speed of Light

7.1 Historical Measurement

[Historical, Established] That light has a finite speed was demonstrated in 1676 by the Danish astronomer Ole Rømer, who observed that the timing of eclipses of Jupiter’s moon Io varied with Earth’s distance from Jupiter. Rømer correctly attributed this variation to the time required for light to traverse the additional distance and obtained a value for c approximately 25% lower than the modern value. [Historical] James Bradley refined the measurement in 1729 using stellar aberration.

[Historical, Established] Terrestrial measurements followed in the nineteenth century. Hippolyte Fizeau in 1849 used a rotating toothed wheel to chop a light beam reflected from a distant mirror; by counting the rotations needed to “miss” the returning pulse, he obtained c to about one percent. Léon Foucault improved the method using a rotating mirror (1862). Albert Michelson, beginning in the 1880s, refined these techniques over decades and in 1926 obtained c = 299,796 km/s, well within 0.001% of the modern value.

7.2 The Constancy of c

[Established] Special relativity, due to Einstein in 1905, asserts that the speed of light in vacuum is the same in all inertial reference frames. This is not a feature of light specifically; it is a feature of the geometry of spacetime. Any massless particle propagates at c; any massive particle propagates at less than c; no signal can be transmitted faster than c.

[Established] The constancy of c has been verified across an enormous range of experiments and to astonishing precision. Modern tests include comparisons of the propagation speed of high-energy gamma rays from astrophysical sources with that of low-energy photons, comparisons of the propagation speed of photons with that of gravitational waves (verified to within roughly one part in 10¹⁵ by the 2017 observation of GW170817 and its electromagnetic counterpart GRB 170817A), and direct laboratory tests of Lorentz invariance.

7.3 The 1983 and 2019 SI Redefinitions

[Convention] Until 1983, the meter was defined in terms of a physical artifact (originally a platinum-iridium bar; from 1960 in terms of the wavelength of a krypton-86 emission line), and c was a measured quantity. [Convention] In 1983, the 17th General Conference on Weights and Measures redefined the meter as the distance light travels in vacuum in 1/299,792,458 of a second. From that moment, c has been defined to be exactly 299,792,458 m/s by international convention; what is measured is the meter.

[Convention] In 2019, a more comprehensive revision of the SI base units came into effect. The kilogram, ampere, kelvin, and mole were redefined in terms of fixed numerical values of fundamental physical constants (Planck’s constant h, the elementary charge e, the Boltzmann constant k_B, and the Avogadro constant N_A respectively). [Established] Since this revision, all seven SI base units are defined in terms of seven defining constants, of which c and h are the most relevant to optics. The numerical values are exact by definition:

• c = 299,792,458 m/s
• h = 6.62607015 × 10⁻³⁴ J·s

7.4 Phase, Group, Signal, and Front Velocities

[Established] In a dispersive medium, a propagating wave is characterized by several distinct velocities, and these can differ from each other and from c.

• The phase velocity v_p = ω/k is the speed at which a surface of constant phase moves. In media where n(ω) > 1 it is less than c, but in some frequency ranges n < 1 and the phase velocity formally exceeds c. [Established] This does not violate causality: phase velocity does not transport information.

• The group velocity v_g = dω/dk is the speed at which the envelope of a wave packet moves. In normal dispersion v_g < c; in regions of anomalous dispersion (typically near absorption lines) v_g can formally exceed c or even become negative. [Established] Again, this does not violate causality: in the anomalous regime the wave packet is severely distorted, and the group velocity ceases to track the position of any localized signal.

• The signal velocity is the speed at which the leading detectable disturbance propagates. [Established] It does not exceed c in any medium.

• The front velocity is the speed at which the foremost edge of any disturbance propagates — the edge ahead of which the field is identically zero. [Established] Sommerfeld and Brillouin proved in 1914 that the front velocity is exactly c in any causal medium.

[Established] Reports of “faster-than-light” propagation, which appear periodically in popular science, invariably refer to phase or group velocity in special regimes and never to signal or front velocity. No experiment has ever transmitted information faster than c, and special relativity prohibits this absolutely.

Part 8 — The Fundamental Relations

8.1 Wave Relation

[Established] For a monochromatic wave in vacuum, the wavelength λ, frequency ν, and speed c are related by:

$$c = \lambda \nu$$

[Established] In a medium of refractive index n, the wavelength and phase velocity are reduced by a factor of n while the frequency is unchanged, so that v_p = λ_medium ν = c/n.

8.2 Planck–Einstein Relation

[Established] The energy of a single photon is related to its frequency by:

$$E = h\nu = \hbar\omega = \frac{hc}{\lambda}$$

where ℏ = h/2π is the reduced Planck’s constant and ω = 2πν is the angular frequency.

[Established] Numerical values useful in optical work:

• A photon of wavelength 500 nm (visible green) has energy approximately 2.48 eV.
• A photon of wavelength 1 μm (near-infrared) has energy approximately 1.24 eV.
• A photon of wavelength 1 mm (far-infrared / microwave) has energy approximately 1.24 meV.
• A photon of wavelength 1 nm (soft X-ray) has energy approximately 1240 eV.

The convenient mnemonic E(eV) ≈ 1240 / λ(nm) follows from substituting hc in eV·nm units.

8.3 Photon Momentum

[Established] A photon carries momentum p = E/c = h/λ. The fact that light carries momentum is a prediction of Maxwell’s electromagnetism and was demonstrated experimentally by Lebedev (1900) and by Nichols and Hull (1901) using radiation pressure. [Established] Compton scattering (1923) — the scattering of X-rays from electrons — showed that photon momentum exchange follows the relativistic kinematics of a massless particle, providing decisive evidence for the photon hypothesis.

[Established] Photon momentum underlies a wide range of modern technology and physics: optical tweezers (Ashkin, 1970, 2018 Nobel Prize), laser cooling of atoms (1997 Nobel Prize), radiation pressure on solar sails, the (small but non-zero) braking effect of starlight on small bodies in the solar system, and the optomechanical interactions that allow gram-scale mechanical oscillators to be cooled to their quantum ground states.

8.4 Photon Spin and Polarization

[Established] Photons are massless spin-1 bosons. A massive spin-1 particle would have three polarization states; a massless spin-1 particle has two, corresponding to the two transverse polarizations. The “missing” longitudinal mode is removed by gauge invariance.

[Established] The two physical polarization states can be described in various bases: linear (horizontal/vertical, or any rotation thereof), circular (left/right), or elliptical. [Established] Circularly polarized photons carry angular momentum ±ℏ per photon along the propagation direction, which has been demonstrated experimentally by mechanical torque measurements and which underlies optical-spin-injection techniques in modern semiconductor physics.

Part 9 — Synthesis: What We Know and What We Don’t

9.1 The Established Domain

[Established] Within domains where it has been tested — which include essentially every optical experiment from radio frequencies through hard X-rays, and a great deal of the gamma-ray range — quantum electrodynamics provides predictively flawless descriptions of light and its interactions with charged matter. The classical theory of Maxwell is a limit of QED valid when the photon occupation numbers are large; geometrical optics is a further limit valid when wavelengths are small compared to relevant length scales. None of these theories has ever been falsified within its domain of validity.

[Established] The basic physical character of light — as the propagating excitations of a quantized electromagnetic field, with discrete energy quanta of magnitude hν and momentum h/λ, propagating in vacuum at the universal constant speed c — is not in scientific dispute.

9.2 The Interpretive Domain

[Interpretive] What it means for a photon to be detected, what happens when a quantum field “collapses” into a localized event, and what relationship the formalism of quantum mechanics bears to the underlying physical reality, remain matters on which thoughtful physicists and philosophers disagree. [Open] No experimental result is currently capable of distinguishing among the principal interpretations, although work in this direction continues — particularly through tests of Bell-type inequalities under increasingly stringent loophole closures, tests of the Leggett–Garg inequality for macroscopic realism, and proposed tabletop tests of quantum behavior of gravity that may eventually constrain interpretations.

9.3 The Open Frontier

The principal open questions in the foundations of light, as of the present writing, include the following, all of which I tag [Open]:

• The mathematical existence of QED as a non-perturbative quantum field theory in four spacetime dimensions.
• The relationship between electromagnetism and gravity, particularly whether photons can be entangled via gravitational interactions in detectable laboratory experiments.
• The nature of the measurement process and the apparent emergence of classical outcomes from unitary quantum dynamics.
• Whether there exist additional, very weakly coupled fields (axions, dark photons, hidden photons) that could mix with the electromagnetic field at low levels.
• The high-energy limit of QED. The theory exhibits a “Landau pole” — a formal divergence at extremely high energies — that signals either a breakdown or, more likely, an incorporation into a more comprehensive theory at energies far beyond any current accelerator.

These are not loose ends of an otherwise complete edifice; they are doors into the next epoch of physics, and progress on any of them will likely revise our understanding of light alongside everything else.

9.4 A Closing Reflection

The single most important thing to understand about the foundations of light is that all the historical theories are still in use. Every working physicist switches between them depending on the problem at hand. A telecommunications engineer designing a fiber link uses geometrical optics for the gross design, wave optics for the modal structure of the fiber, and quantum optics only when noise approaches the shot-noise floor. An astronomer determining the composition of a stellar atmosphere uses absorption line analysis grounded in quantum mechanics, but uses classical refraction to design the spectrograph. The progression of theories is not a sequence in which each new theory replaces and falsifies its predecessor; it is a sequence in which each new theory contains its predecessors as limiting cases and clarifies the conditions under which they are accurate.

This is what makes light a particularly good case study in how scientific knowledge accumulates. The geometrical-optics knowledge of Ibn al-Haytham and Snell is not obsolete; it is contained in Maxwell’s electromagnetism, which is contained in QED. Each layer is preserved, refined, and bounded.

The foundations are deep, and they remain solid. The remaining mysteries of light lie not in foundations but in extensions: foundations to gravity, foundations to information, foundations to the conditions under which classical reality emerges from quantum substrate. To these we will return in subsequent volumes.

Selected Bibliography for Volume I

Primary Historical Sources

• Ibn al-Haytham. Kitāb al-Manāẓir (Book of Optics). c. 1011–1021 CE. Modern critical translations include the multi-volume edition by A. I. Sabra (1983–2002).
• Newton, I. Opticks. London, 1704. Dover reprint, 1979.
• Huygens, C. Traité de la Lumière. Leiden, 1690.
• Maxwell, J. C. “A Dynamical Theory of the Electromagnetic Field.” Philosophical Transactions of the Royal Society of London 155, 459–512 (1865).
• Maxwell, J. C. A Treatise on Electricity and Magnetism. Oxford, 1873. Dover reprint of 3rd ed., 1954.
• Planck, M. “Über das Gesetz der Energieverteilung im Normalspektrum.” Annalen der Physik 4, 553–563 (1901).
• Einstein, A. “Über einen die Erzeugung und Verwandlung des Lichtes betreffenden heuristischen Gesichtspunkt.” Annalen der Physik 17, 132–148 (1905).
• Einstein, A. “Zur Elektrodynamik bewegter Körper.” Annalen der Physik 17, 891–921 (1905). [Special relativity.]

Modern Textbook References

• Born, M. and Wolf, E. Principles of Optics. 7th ed. Cambridge University Press, 1999. The canonical reference for classical optics.
• Jackson, J. D. Classical Electrodynamics. 3rd ed. Wiley, 1998. The standard graduate-level treatment of classical electromagnetism.
• Loudon, R. The Quantum Theory of Light. 3rd ed. Oxford University Press, 2000.
• Mandel, L. and Wolf, E. Optical Coherence and Quantum Optics. Cambridge University Press, 1995.
• Peskin, M. E. and Schroeder, D. V. An Introduction to Quantum Field Theory. Westview, 1995. Standard QED reference.
• Weinberg, S. The Quantum Theory of Fields, Vol. I. Cambridge University Press, 1995. More foundational treatment.

History of Physics

• Whittaker, E. A History of the Theories of Aether and Electricity. 2 volumes. Tomash/AIP, 1987 (reprint of original 1951 edition).
• Pais, A. “Subtle is the Lord”: The Science and the Life of Albert Einstein. Oxford University Press, 1982.
• Mehra, J. and Rechenberg, H. The Historical Development of Quantum Theory. 6 volumes. Springer, 1982–2001.
• Sabra, A. I. Theories of Light from Descartes to Newton. 2nd ed. Cambridge University Press, 1981.

Foundations and Interpretation

• Bell, J. S. Speakable and Unspeakable in Quantum Mechanics. 2nd ed. Cambridge University Press, 2004.
• Wheeler, J. A. and Zurek, W. H. (eds.). Quantum Theory and Measurement. Princeton University Press, 1983.
• Auletta, G. Foundations and Interpretation of Quantum Mechanics. World Scientific, 2000.

Specific Topics

• Aspect, A., Grangier, P., and Roger, G. “Experimental Tests of Realistic Local Theories via Bell’s Theorem.” Physical Review Letters 47, 460 (1981). Foundational Bell-test experiment recognized by the 2022 Nobel Prize.
• Tonomura, A., et al. “Demonstration of single-electron buildup of an interference pattern.” American Journal of Physics 57, 117 (1989).
• BIPM. The International System of Units (SI), 9th edition (2019). The official document defining the SI base units.

Notes on Sources and Confidence

The historical narrative in this volume relies on a combination of primary sources and standard secondary literature in the history of physics. Where I have made specific factual claims about dates, attributions, and content of historical work, I have drawn on the standard references listed above. [Confidence high] for the broad outlines of the history; [Confidence moderate] for specific dates and attributions, where minor variations between sources are common; [Confidence high] for all physics claims tagged [Established].

Where I have stated values of fundamental constants or numerical results, I have given values consistent with the post-2019 SI definitions. Numerical precision claims for QED and similar matters reflect the situation as of my knowledge cutoff; the precision of these tests improves continuously and current values may exceed those cited. For the most current numerical values, the reader is directed to the CODATA recommended values (most recent: CODATA 2022, published 2024) and to the Particle Data Group’s Review of Particle Physics.

Where I have stated something as [Open], I have done so on the basis of substantial scientific judgment but acknowledge that the boundary between “open” and “settled” can shift quickly. A claim presented here as open in 2026 may be resolved in coming years; conversely, claims presented as established may be refined in unexpected ways. Science is, in the end, provisional all the way down.

End of Volume I — Foundations.

Volume II (forthcoming): The Electromagnetic Spectrum — Radio through Gamma.