Artul.ai Research LibraryStudy No. 25Signal CombinationsUpdated 2026-08-28
Evasive and Under Stress: When Two Signals Appear Together
By Artul.ai Research Group · n = 657 earnings calls · First published 2026-08-28
When an AI read 165,182 earnings-call transcripts and scored each one, it found 657 calls—about 0.4% of the corpus—where high evasion and high stress appear together. That combination matters because each signal alone is common and easy to dismiss; together they mark calls where management is both deflecting questions and showing visible strain, which is when the deflection is hardest to read as routine caution.
These calls look different on almost every dimension: evasion of 6.55 versus 2.7 baseline, stress of 6.41 versus 2.43, and confidence of 5.5 versus 7.21. Guidance tells the story—14% withdrew guidance versus 2.7% baseline, and 19.5% lowered it versus 11.6%. Only 3.4% raised guidance against 21.1% overall. Nearly all of these calls (100%) contain "The Question Left Hanging," versus 48% baseline. Post-call returns were worse: median −13.0% versus −7.2% baseline, with 28.9% beating versus 39.5%. The pattern has also faded over time, from 0.78 in 2015 to 0.18 in 2025.
These fields are AI-generated and noisy, and the return comparison is descriptive history from a 22,449-call sample—not a trading signal. Our own forward tests failed to confirm directional prediction from these signals. Language models also partially remember famous stocks' histories, which contaminates any backtest of language-based patterns.
Matching Calls
657
0.4% of corpus
12m Excess vs SPY (median)
-13.0%
sample baseline -7.2%
Beat SPY
29%
baseline 39% · n=45
Behavior profile
| Meter | This group | All calls |
|---|
| Candor | 5.49/9 | 6.86/9 |
| Evasion | 6.55/9 | 2.70/9 |
| Specificity | 6.03/9 | 7.56/9 |
| Stress | 6.41/9 | 2.43/9 |
| Promotion | 4.88/9 | 5.05/9 |
| Confidence | 5.50/9 | 7.21/9 |
Guidance actions in this group
| Action | This group | All calls |
|---|
| raised | 4.0% | 21.1% |
| maintained | 27.1% | 48.8% |
| lowered | 19.5% | 11.6% |
| withdrawn | 14.0% | 2.7% |
What travels with it
| Signal | Lift | In group | Overall |
|---|
| Scale-Dependent Advantage Claims | 4.00× | 44.3% | 11.1% |
| The Question Left Hanging | 2.09× | 100.0% | 48.0% |
| The Finished-Story Tell | 1.98× | 8.7% | 4.4% |
| Underused Fixed Costs | 1.67× | 69.4% | 41.6% |
| Results Worse Than Direction | 1.57× | 80.2% | 51.1% |
| Skeptic Reassured | 0.00× | 0.2% | 66.4% |
| Calls That Resolve Doubts | 0.01× | 0.8% | 79.5% |
| Guidance Worth Underwriting | 0.10× | 6.8% | 71.5% |
| Confidence Proportionate to Evidence | 0.21× | 18.1% | 87.6% |
| Pricing Recovering | 0.55× | 11.9% | 21.5% |
Share of calls by year
| Year | Share | |
|---|
| 2015 | 0.78% | |
| 2016 | 0.70% | |
| 2017 | 0.59% | |
| 2018 | 0.51% | |
| 2019 | 0.40% | |
| 2020 | 0.27% | |
| 2021 | 0.28% | |
| 2022 | 0.34% | |
| 2023 | 0.30% | |
| 2024 | 0.27% | |
| 2025 | 0.18% | |
Recent examples
| Ticker | Call | Date | Grade |
|---|
| PRPH | Q1 2025 | 2025-05-20 | F |
| LAZR | Q1 2025 | 2025-05-14 | F |
| SKM | Q1 2025 | 2025-05-12 | F |
| PMMAF | Q1 2025 | 2025-05-10 | F |
| CLQDF | Q1 2025 | 2025-05-09 | F |
| HAIN | Q3 2025 | 2025-05-07 | F |
| DSNY | Q2 2025 | 2025-04-14 | F |
| REKR | Q4 2024 | 2025-03-31 | F |
Cite this study
Artul.ai Research Group (2026). “Evasive and Under Stress: When Two Signals Appear Together.” Artul.ai Earnings-Call Research Library, Study No. 25. https://artul.ai/research/evasive-and-under-stress
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.