Research › Hypotheses Tested
Artul.ai Research LibraryStudy No. 53Hypotheses TestedUpdated 2026-08-28

Dress for the Market Cap You Want: Calls Running Ahead of Their Numbers

By Artul.ai Research Group · n = 88 earnings calls · First published 2026-08-28
Abstract

This study examines earnings calls that answered YES to the hypothesis 'Running the company for a size the numbers don't show yet' — companies acting like they are bigger than current results imply. Of 497 calls analyzed from 2015–2024, 88 calls (a 17.7% share, 95% CI 14.6%–21.3%) fit the pattern. These calls skew promotional: promotion scores run 5.51 vs 5.10 and confidence 7.70 vs 7.33, while stress is lower at 2.10 vs 2.39. Guidance is raised on 29.5% of calls vs 21.7% for the base. The strongest over-expression is 'Volume About to Step Up' at a 2.11x lift. Post-call returns for the 27-call traded sample show a median of -0.267% vs -0.105% for the base.

Key findings
  • 88 of 497 calls (17.7%, CI 14.6%–21.3%) fit the 'running for a size the numbers don't show yet' pattern.
  • Promotion scores run 5.51 vs 5.10 and confidence 7.70 vs 7.33 for the base, while stress is lower at 2.10 vs 2.39.
  • 'Volume About to Step Up' appears 2.11x more often than in the base corpus (53.4% vs 25.4%), and 'Early Products Growing Fast' shows a 1.32x lift.
  • The 27-call returns sample shows a median post-call return of -0.267% versus -0.105% for the 197-call base, with 33.3% beating the base beat rate of 38.1%.

1Introduction

Some management teams talk like their company has already doubled: they discuss capacity ahead of demand, product lines ahead of revenue, and headcount plans ahead of results. If you follow earnings calls, this 'running for a size the numbers don't show yet' posture is easy to hear and hard to quantify — it sits at the intersection of ambition, promotion, and candor. Whether it is a rare posture, how its tone profile differs from typical calls, and how often its guidance moves up rather than down are open questions. This study examines 88 such calls drawn from a 497-call corpus spanning 2015–2024, measuring their language profile, guidance behavior, associated themes, and post-call outcomes.

2Data & methodology

The corpus comprises 497 earnings-call transcripts published between 2015 and 2024, each scored independently by a large language model on an identical 37-field battery: seven categorical business verdicts, eight 0–9 behavioral meters, and twenty yes/no judgments. The study group is defined as calls that answered YES to the research hypothesis "Running the company for a size the numbers don't show yet" (n = 88; 17.7% of the reference set, 95% Wilson interval 14.6%–21.3%). Baseline figures use the set of calls on which this question was tested. Market outcomes join a fixed sample of 22,449 calls with twelve-month total returns in excess of SPY, measured from the first close after each call; this sample skews toward liquid U.S. names and is reported as descriptive history only.

3Results

The tone profile is the headline: these calls are more promotional (5.51 vs 5.10) and more confident (7.70 vs 7.33) than the base, while stress is lower (2.10 vs 2.39) and evasion slightly lower (2.55 vs 2.71) — conviction without visible strain. Candor is essentially flat (6.88 vs 6.92). Guidance behavior leans positive: 29.5% of these calls raised guidance vs 21.7% in the base, and none withdrew it. Theme lifts reinforce the growth posture: 'Volume About to Step Up' appears at 2.11x the base rate and 'Early Products Growing Fast' at 1.32x. The trend peaked in 2022 at a 0.12 share before easing to 0.05 in 2024. Despite the confident framing, the 27-call traded sample shows a median return of -0.267% vs -0.105% for the base.

Table 1. Mean behavioral scores (0–9 scale), study group versus baseline
MeterStudy groupBaselineΔ
Candor6.886.92-0.04
Evasion2.552.71-0.16
Specificity7.737.65+0.08
Stress2.102.39-0.29
Promotion5.515.10+0.41
Confidence7.707.33+0.37
Table 2. Guidance actions, study group versus baseline
ActionStudy groupBaseline
Raised29.5%21.7%
Maintained51.1%53.1%
Lowered10.2%13.3%
Withdrawn0.0%1.0%
Table 3. Co-occurring battery signals ranked by lift (group prevalence ÷ baseline prevalence)
SignalLiftIn groupBaseline
Volume About to Step Up2.11×53.4%25.4%
Early Products Growing Fast1.32×51.1%38.6%
When the CFO Dominates0.39×5.7%14.5%
Calls That Read Rehearsed0.61×24.4%40.3%
20150.06%
20160.03%
20170.05%
20180.07%
20190.00%
20200.00%
20210.10%
20220.12%
20230.07%
20240.05%
20250.00%
Figure 1. Share of all analyzed calls matching the study definition, by year.
Table 4. Twelve-month excess total returns versus SPY (descriptive history, not a signal)
StatisticStudy groupReturns sample
Median excess return-26.7%-10.5%
Interquartile range-50.8% to +4.4%
Share beating SPY33.3% (95% CI 19%–52%)38.1%
Observations27197
Table 5. Most recent calls matching the study definition
TickerQuarterCall dateCall grade
NOAHQ1 20242024-05-30D
WRBYQ1 20242024-05-09A
ECPGQ1 20242024-05-08B
LINCQ1 20242024-05-06B+
AESQ1 20242024-05-03C+
WECQ1 20242024-05-01A
ROCKQ1 20242024-05-01B+
KOPNQ4 20232024-03-14C+

4Discussion

A careful reader should conclude that this posture is measurable and reasonably common — 17.7% of calls, with wide uncertainty (14.6%–21.3%). It is safe to say these calls sound more confident and more promotional, and that their guidance leans toward raises. What should not be concluded: that the posture causes outcomes, predicts returns, or signals either overreach or hidden strength. The returns comparison (median -0.267% vs -0.105%) is descriptive of a small 27-call sample and cannot support any trading claim. Treat this as a taxonomy of a recognizable management style, not a signal.

5Limitations

The behavioral fields are AI-read from transcripts and are inherently noisy, so small tone deltas like the -0.04 candor gap should not be over-weighted. The returns sample covers only 27 calls and the broader test universe spans 22,449 calls skewed toward liquid names, so results may not generalize. Our own forward tests falsified directional prediction, and LLMs partially remember famous stocks' history, contaminating any backtest. The 17.7% share carries a wide confidence interval. All findings here are descriptive associations within one corpus, not evidence of causation or predictive power. See the full methodology, including the C1 pattern’s forward-test failure and the LLM-memorization finding.

Companion page: every company matching this hypothesis is listed at the question’s own page.

Cite this study Artul.ai Research Group (2026). “Dress for the Market Cap You Want: Calls Running Ahead of Their Numbers.” Artul.ai Earnings-Call Research Library, Study No. 53. https://artul.ai/research/hypothesis-running-the-company-for-a-size-the-numbers-don-t-show-yet

Related studies

The Numbers Are Fine; Everything Else Is Pending: FlRoom to Run and Nowhere to Hide: Calls With UncontesLight at the End of the Tunnel Is Often a Train: RecDon't Stick to the Script: Earnings Calls Where AnswHave Your Cake and Expand the Base Too: Repeat GrowtPressed Harder, Answered Straight: A Profile of 183
Not investment advice. Artul.ai publishes AI-generated earnings-call quality grades and expected-volatility estimates — never buy or sell recommendations. We tested over 1,600 predictive hypotheses against 165,000 transcripts; the honest result, including what failed, is documented in our methodology.