Less Is More on the Earnings Call: A Profile of Low-Complexity Talk
This study examines earnings calls scoring 2 or lower on Artul.ai's 0-9 complexity meter: 861 calls, roughly 0.52% of the 165,182-call corpus spanning 1990-2026. Low-complexity calls read as unusually candid (7.09 vs 6.86) and less evasive (2.19 vs 2.70), with less promotion language (4.45 vs 5.05). Guidance is maintained less often (37.3% vs 48.8%) and withdrawn more often (4.2% vs 2.7%). Phrases overused in this segment include 'Volume About to Step Up' (0.46x, appearing in 13.2% of these calls vs 28.5% expected) and 'Early Products Growing Fast' (0.5x). The annual share of such calls rose to 0.77 per call in 2025 from 0.55 in 2024. Among 99 calls with measured outcomes, the median return was -0.85% versus -7.16% for the base set, and 48.5% beat versus 39.5%.
- Only 861 of 165,182 calls (0.52%) score 2 or lower on the complexity meter, with a 95% interval of 0.49% to 0.56%.
- Low-complexity calls are more candid (7.09 vs 6.86), less evasive (2.19 vs 2.70), and show less promotion language (4.45 vs 5.05) than the corpus.
- Guidance is withdrawn on 4.2% of these calls versus 2.7% corpus-wide, and maintained on 37.3% versus 48.8%.
- The median post-call return in a 99-call sample was -0.85% versus -7.16% for the 22,449-call base, with 48.5% beating versus 39.5%.
1Introduction
Anyone who reads earnings calls for a living learns to distrust smoothness. Yet a tiny slice of transcripts, about 0.52% of the corpus, reads strikingly simple: calls scoring 2 or lower on a 0-9 complexity meter. These calls describe themselves as candid, low on promotion-speak, and occasionally the venue for withdrawn guidance. Whether simplicity signals confidence, fatigue, or something else is an open question, but the segment is distinctive enough to deserve description. This study profiles these 861 calls from 1990-2026: their language profile, guidance behavior, characteristic phrases, prevalence over time, and measured outcomes.
2Data & methodology
The corpus comprises 165,182 earnings-call transcripts published between 1990 and 2026, 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 scoring 2 or lower on the 0–9 complexity meter (n = 861; 0.5% of the reference set, 95% Wilson interval 0.5%–0.6%). Baseline figures use all scored calls. 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 language deltas sketch a plain-spoken register: candor runs 7.09 vs 6.86 corpus-wide, evasion 2.19 vs 2.70, stress 2.15 vs 2.43, and promotion 4.45 vs 5.05. Guidance patterns diverge too: calls are maintained less often (37.3% vs 48.8%) and withdrawn more often (4.2% vs 2.7%), with raised guidance roughly equal (21.1% vs 21.1%). The underused-phrase list includes 'Volume About to Step Up' at 0.46x lift (13.2% of these calls vs 28.5% expected) and 'Early Products Growing Fast' at 0.5x (19.2% vs 38.5%). Prevalence has drifted upward, from 0.55 per call in 2024 to 0.77 in 2025. In the 99-call outcome sample, the median return was -0.85% vs -7.16% for the base.
| Meter | Study group | Baseline | Δ |
|---|---|---|---|
| Candor | 7.09 | 6.86 | +0.23 |
| Evasion | 2.19 | 2.70 | -0.51 |
| Specificity | 7.63 | 7.56 | +0.07 |
| Stress | 2.15 | 2.43 | -0.28 |
| Promotion | 4.45 | 5.05 | -0.60 |
| Confidence | 7.17 | 7.21 | -0.04 |
| Action | Study group | Baseline |
|---|---|---|
| Raised | 21.1% | 21.1% |
| Maintained | 37.3% | 48.8% |
| Lowered | 9.6% | 11.6% |
| Withdrawn | 4.2% | 2.7% |
| Signal | Lift | In group | Baseline |
|---|---|---|---|
| The Hidden Segment | 0.26× | 5.5% | 21.1% |
| Scale-Dependent Advantage Claims | 0.27× | 3.0% | 11.1% |
| Volume About to Step Up | 0.46× | 13.2% | 28.5% |
| Early Products Growing Fast | 0.50× | 19.2% | 38.5% |
| The Finished-Story Tell | 0.61× | 2.7% | 4.4% |
| Statistic | Study group | Returns sample |
|---|---|---|
| Median excess return | -0.9% | -7.2% |
| Interquartile range | -20.4% to +24.1% | — |
| Share beating SPY | 48.5% (95% CI 39%–58%) | 39.5% |
| Observations | 99 | 22,449 |
| Ticker | Quarter | Call date | Call grade |
|---|---|---|---|
| VRSN | Q2 2025 | 2025-07-24 | A |
| WTBA | Q2 2025 | 2025-07-24 | B+ |
| ORLY | Q2 2025 | 2025-07-24 | B+ |
| ACU | Q2 2025 | 2025-07-23 | A |
| CPAC | Q2 2025 | 2025-07-23 | B |
| SMPL | Q3 2025 | 2025-07-10 | C |
| SWBI | Q4 2025 | 2025-06-18 | D |
| CANADA | Q1 2026 | 2025-06-18 | D |
4Discussion
A careful reader should treat this as a description of a distinctive segment, not a verdict on it. Low-complexity calls genuinely differ in tone: they read as more candid, less promotional, and less evasive than average, and they withdraw guidance more often. The outcome sample is small, 99 calls, and its mean return (5.60%) sits far above its median (-0.85%), indicating heavy skew rather than a reliable pattern. Nothing here establishes that simplicity causes better outcomes, predicts beats, or offers a trading edge; the association could reflect the kinds of companies that happen to speak plainly.
5Limitations
The complexity and language scores come from AI-read fields and are noisy at the call level. The outcome sample, 99 calls against a 22,449-call base, is skewed toward liquid names, so the -0.85% vs -7.16% median comparison should not be generalized. Artul's own forward tests falsified directional prediction from these features: nothing here implies future returns. Additionally, LLMs partially remember famous stocks' histories, which contaminates any backtest built on these annotations. The share estimate carries sampling uncertainty (0.49%-0.56%), and the 2025 figure reflects only 6,012 calls. See the full methodology, including the C1 pattern’s forward-test failure and the LLM-memorization finding.