Artul.ai Research LibraryStudy No. 60Hypotheses TestedUpdated 2026-08-28
Hypothesis Tested: The feared thing keeps not happening
By Artul.ai Research Group · n = 93 earnings calls · First published 2026-08-28
On earnings calls, management often names a fear — a churn risk, a cost headwind, a regulatory question — and then, quarter after quarter, the feared thing keeps not happening. We tested this pattern across 165,000 AI-read transcripts: 994 calls matched, and in 93 of them (9.4%) the pattern was strong enough to flag. The question is whether naming a fear that never materializes is candor, or a rehearsed way to look transparent.
The profile suggests neither evasion nor stress: candor (6.96 vs 6.93) and evasion (2.68 vs 2.67) are flat, but confidence runs higher (7.65 vs 7.36). Guidance tells a better story — 36.6% raised guidance versus a 23.4% base rate, with only 8.6% lowering it. The clearest co-occurrence is "Deferred Revenue Growing" at 1.86x the base rate (16.1% vs 8.7%), while "Calls That Read Rehearsed" appears less often (25.8% vs 38.8%).
These fields come from an AI reading transcripts and are noisy at the margins. The return comparison (51 flagged calls, median -6.5% vs -6.9% baseline) is descriptive history from a 22,449-call sample, not a trading signal — our own forward tests falsified directional prediction. Language models also partially remember famous stocks' histories, which contaminates any backtest of this kind.
Matching Calls
93
9.4% of corpus
12m Excess vs SPY (median)
-6.5%
sample baseline -6.9%
Beat SPY
39%
baseline 41% · n=51
Behavior profile
| Meter | This group | All calls |
|---|
| Candor | 6.96/9 | 6.93/9 |
| Evasion | 2.68/9 | 2.67/9 |
| Specificity | 7.78/9 | 7.65/9 |
| Stress | 2.40/9 | 2.36/9 |
| Promotion | 5.20/9 | 5.07/9 |
| Confidence | 7.65/9 | 7.36/9 |
Guidance actions in this group
| Action | This group | All calls |
|---|
| raised | 36.6% | 23.4% |
| maintained | 50.5% | 51.8% |
| lowered | 8.6% | 12.7% |
| withdrawn | 1.1% | 1.1% |
What travels with it
| Signal | Lift | In group | Overall |
|---|
| Deferred Revenue Growing | 1.86× | 16.1% | 8.7% |
| The Hidden Segment | 1.29× | 28.0% | 21.7% |
| Scale-Dependent Advantage Claims | 0.53× | 4.3% | 8.0% |
| Calls That Read Rehearsed | 0.66× | 25.8% | 38.8% |
Share of calls by year
| Year | Share | |
|---|
| 2015 | 0.03% | |
| 2016 | 0.06% | |
| 2017 | 0.06% | |
| 2018 | 0.07% | |
| 2019 | 0.00% | |
| 2020 | 0.00% | |
| 2021 | 0.06% | |
| 2022 | 0.14% | |
| 2023 | 0.11% | |
| 2024 | 0.02% | |
| 2025 | 0.00% | |
Recent examples
| Ticker | Call | Date | Grade |
|---|
| AVTR | Q2 2024 | 2024-07-26 | C+ |
| IFS | Q1 2024 | 2024-05-14 | C+ |
| AZEK | Q2 2024 | 2024-05-08 | B+ |
| GL | Q1 2024 | 2024-04-23 | F |
| MNKD | Q4 2023 | 2024-02-27 | C |
| NICE | Q4 2023 | 2024-02-22 | B+ |
| TYGO | Q4 2023 | 2024-02-14 | F |
| MET | Q4 2023 | 2024-02-01 | B+ |
This hypothesis has its own page with every matching company: see the full question.
Cite this study
Artul.ai Research Group (2026). “Hypothesis Tested: The feared thing keeps not happening.” Artul.ai Earnings-Call Research Library, Study No. 60. https://artul.ai/research/hypothesis-the-feared-thing-keeps-not-happening
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.