Research base
Every peer-reviewed study RealSmile cites, mapped to the page that uses it. If a claim on RealSmile is not supported by a study in this list, treat it as opinion, not evidence.
Maintained by Randy, founder of RealSmile. Last verified 2026-05-23.
How to read this page
- Each row is one published study. Authors, year, and venue come straight from the paper.
- The Applied on column lists the RealSmile pages that use that study in body copy. Click through to see the citation in context.
- Reference ranges (averages, percentile distributions) live at /research. The long-form bibliographic write-up of 12 selected studies is at /research/citations.
First Impressions: Making Up Your Mind After a 100-Ms Exposure to a Face
Willis & Todorov (2006) · Psychological Science
Observers form attractiveness, trustworthiness, competence, and aggressiveness judgments from a face in roughly 100 milliseconds. Longer exposures increase confidence in the initial verdict rather than changing it.
Misleading First Impressions
Todorov & Porter (2014) · Psychological Science
Face impressions are formed in as little as 33 milliseconds and are stable across longer exposures. Lighting and pose changes shift the impression by more than the underlying structure does.
Applied on
Symmetry, Sexual Dimorphism in Facial Proportions and Male Facial Attractiveness
Penton-Voak et al. (2001) · Proceedings of the Royal Society B
Jawline definition and lower-face masculinity are reliable predictors of perceived attractiveness in male faces. The effect is independent of symmetry.
The Evolutionary Psychology of Facial Beauty
Rhodes (2006) · Annual Review of Psychology
Meta-analysis identifies three structural predictors of facial attractiveness: symmetry, averageness, and sexual dimorphism. Averageness is often the largest single contributor.
Applied on
Human (Homo sapiens) Facial Attractiveness and Sexual Selection: The Role of Symmetry and Averageness
Grammer & Thornhill (1994) · Journal of Comparative Psychology
Bilateral facial symmetry is rated as more attractive across cultures and is associated with perceived dominance via the facial width-to-height ratio.
Applied on
Facial Action Coding System (FACS)
Ekman & Friesen (1978) · Consulting Psychologists Press
A Duchenne (genuine) smile combines Action Unit 6, orbicularis oculi engagement around the eye, with Action Unit 12, zygomatic major lip-corner pull. Posed smiles use only AU12.
Applied on
Beauty and the Labor Market
Hamermesh & Biddle (1994) · American Economic Review
Workers rated above average in physical appearance earn roughly 5 percent more, and those rated below average earn roughly 9 percent less, controlling for education and experience.
Applied on
Attractive Faces Are Only Average
Langlois & Roggman (1990) · Psychological Science
Composite (averaged) faces are consistently rated more attractive than the individual faces from which they were built. Averageness, not rarity, drives attractiveness.
In Your Face: Facial Metrics Predict Aggressive Behaviour in the Laboratory and in Varsity and Professional Hockey Players
Carre & McCormick (2008) · Proceedings of the Royal Society B
Facial width-to-height ratio above 2.0 is associated with perceived dominance and aggressive behavior in men.
Applied on
The Look of a Winner
Todorov & Olivola (2008) · Scientific American Mind
Snap judgments of competence from a single face photo predict real political election outcomes above chance. The effect generalizes to hiring and partner-selection contexts.
Applied on
Evidence from Meta-Analyses of the Facial Width-to-Height Ratio as an Evolved Cue of Threat
Geniole et al. (2015) · PLOS ONE
Meta-analysis confirms FWHR signals perceived threat and dominance, but the effect on perceived attractiveness is small and context-dependent.
The Face, Beauty, and Symmetry: Perceiving Asymmetry in Beautiful Faces
Zaidel & Cohen (2005) · International Journal of Neuroscience
Lighting direction shifts perceived facial symmetry by up to 23 percent independent of the underlying structure.
Applied on
Anthropometry of the Head and Face
Farkas (1994) · Raven Press, New York
Established the normative anthropometric ranges still used in modern facial-analysis tooling: average canthal tilt, gonial angle, facial thirds, and bizygomatic-to-midface ratios.
SCUT-FBP5500: A Diverse Benchmark Dataset for Multi-Paradigm Facial Beauty Prediction
Liang, Lin, Jin, Xie & Li (2018) · ICPR (arXiv:1801.06345)
5,500 face photos each rated for attractiveness by 60 human raters — the standard academic benchmark for facial beauty prediction. We use it to validate our own scoring: our Impression Percentile model reaches cross-validated r ≈ 0.80 against the averaged human ratings (see "Our own validation" below).
Our own validation · published 2026-07-02
We tested our scoring against 5,500 human-rated faces. Here is exactly what we found.
Method. We ran our production pipeline — the same 68-point landmark detector every scan uses — against the SCUT-FBP5500 academic benchmark (Liang et al., 2018): 5,500 face photos, each independently rated for attractiveness by 60 human raters. We compared our scores to the averaged human ratings using 5-fold cross-validation, so every reported number is measured on faces the model never saw during fitting.
Finding 1 — our original geometry composite failed, and we say so. The 17-metric weighted average we previously used as the overall score showed no positive correlation with human attractiveness ratings (r ≈ −0.33). The individual measurements are real geometry; the blended composite simply does not predict how people rate a face. That is why the report now presents the 17 metrics as measurements — not as an attractiveness verdict.
Finding 2 — the replacement passes. Our Impression Percentile model, built on a 128-dimension facial appearance representation, reaches a cross-validated correlation of r ≈ 0.80 with the averaged 60-rater human judgments (n = 1,566 benchmark faces; consistent across male and female subsets). For reference, published deep-learning models on this benchmark reach r ≈ 0.85–0.90, and simple geometric-feature models reach r ≈ 0.55–0.65.
July 2026 update — v2. A second-generation kernel model, validated the same way, reaches a 5-fold cross-validated correlation of r ≈ 0.836 (percentiles calibrated on out-of-fold predictions). v2 is served to Pro subscribers; v1 (r ≈ 0.80) remains the model in the one-time report.
Scope and limits. The validation covers the Impression Percentile only. It measures agreement with how people rate photos on this benchmark — not dating outcomes, not real-world results, and the benchmark skews toward controlled, front-facing photos. Your number moves with lighting, angle, and expression, which is exactly why the report treats it as photo feedback rather than a verdict on your face.
To our knowledge, no other consumer face-rating tool publishes any validation of its scoring against human ratings. If a competitor publishes theirs, we will link it here.
Read the full Face Score validation write-up — method, per-subset results, and where the number stops applying.
Original data · Photo Variance · published 2026-07-14
Same face, different photo: how much does the photo move the score?
Among people who scored two or more photos of themselves, the median gap between their highest and lowest Impression Percentile was 7 points, and 9 of the 27 saw a gap of 20 points or more. Same face, different photo. For a third of repeat scanners, photo choice moved the number more than most facial differences between two strangers would.
What we measured. Every RealSmile scan computes a validated Impression Percentile (0 to 99), a model of how a panel of human raters would place the photo, cross-validated at r ≈ 0.80 against averaged 60-rater judgments (see the validation section above). Since 2026-07-08 the percentile is saved with each scan, so for anyone who scanned more than one photo we can measure how far the same person's number moves between photos. Spread = highest minus lowest percentile across that person's distinct scored photos. Repeat saves of the identical photo are deduplicated first, so the spread compares genuinely different photos.
| Statistic (window: Jul 8 to Jul 14, 2026) | Value |
|---|---|
| Scans with a saved percentile | 126 |
| People with 2+ scored photos | 27 (95 consecutive photo pairs) |
| Median within-person spread | 7 percentile points |
| Spread of 10+ points | 12 of 27 people |
| Spread of 20+ points | 9 of 27 people |
| 75th-percentile spread | 33 points |
| Consecutive photo pairs that moved 10+ points | 23 of 95 |
| Scanners (all-time) who scanned more than once | 38 of 73 |
“In RealSmile's first week of saved percentile data, the median repeat scanner's score moved 7 percentile points between photos of the same face, and a third of repeat scanners saw swings of 20 points or more. The photo you choose is a first-impression variable in its own right.”
Why this matters. It is a production-data echo of the published lab findings above: Todorov & Porter (2014) showed lighting and pose shift face impressions more than underlying structure, and Zaidel & Cohen (2005) found lighting direction alone shifts perceived symmetry by up to 23 percent. Our users reproduce the direction of that effect on their own photos, with a validated score attached.
Honest limitations. This is a small, early sample: 126 scored scans and 27 repeat scanners from the first week the percentile was stored. RealSmile users are self-selected (skewed young, male, and appearance-focused), not a population sample. People who scan several photos may deliberately vary lighting and angle, which would widen spreads versus casual retakes. Same-day re-saves keep the best score of the day, which can only shrink, never inflate, the reported spreads. None of this measures attractiveness of faces; it measures how much one person's photo-level score varies. We will re-publish these numbers as the sample grows and will not delete this early version.
Cite this as: RealSmile Photo Variance aggregate (July 2026), realsmile.online/research-base#photo-variance. Attribution: “RealSmile production data, n = 126 scans / 27 repeat scanners, July 8 to 14, 2026.” Aggregates only; no row-level data is published or shared.
Why this page exists
The face-perception literature is well-established but spread across psychology, anthropology, and economics journals. A single lookup that maps each study to the RealSmile page that uses it makes the citation chain checkable in one click. The studies above are the load-bearing references for the 17-metric audit, the dating-photo audit, the LinkedIn headshot audit, and the four long-tail measurement guides.
For the original-data companion to this index, see the State of Looksmaxxing 2026 data report, which publishes RealSmile's aggregated face-scan distributions alongside the published-research baselines listed above.