Artul.ai Research LibraryStudy No. 55Hypotheses TestedUpdated 2026-08-28
Hypothesis Tested: Secure base, several live doors
By Artul.ai Research Group · n = 92 earnings calls · First published 2026-08-28
Some companies face pressure from multiple directions at once yet keep answering from a position of security — candid about problems, specific about numbers, and clearly working several live strategic doors rather than one. This study tested that "secure base, several live doors" pattern across Artul.ai's library, where an AI read 165,000 earnings-call transcripts with the same question battery. Of the 342 calls flagged in the base pattern, 92 matched this hypothesis, making it a fairly narrow slice of the corpus worth understanding.
The matched group reads distinctly calmer and more confident: stress scores of 1.79 versus 2.4 in the base, and confidence of 7.8 versus 7.32, with evasion lower at 2.45 versus 2.7. They raise guidance more often (33.7% vs 22.5%) and never withdrew it. Two overrepresented moments stand out: "Skeptic Reassured" appears in 94.6% of these calls (1.34x the base), and "Early Products Growing Fast" at 1.57x. Meanwhile, "The Question Left Hanging" is rare here — 21.7% versus 45.0% — suggesting few loose ends get left dangling.
These fields come from AI reads and are noisy; treat the profile numbers as directional. The return comparison (44 calls, median -0.093 vs -0.109 in the base) is descriptive history from a 22,449-call sample, not a trading signal — our own forward tests falsified directional prediction, and language models partially remember famous stocks' history, contaminating any backtest. The trend also shows the pattern peaking near 2015-2016 and fading since.
Matching Calls
92
26.9% of corpus
12m Excess vs SPY (median)
-9.3%
sample baseline -10.9%
Beat SPY
36%
baseline 38% · n=44
Behavior profile
| Meter | This group | All calls |
|---|
| Candor | 6.96/9 | 6.97/9 |
| Evasion | 2.45/9 | 2.70/9 |
| Specificity | 7.83/9 | 7.63/9 |
| Stress | 1.79/9 | 2.40/9 |
| Promotion | 5.23/9 | 5.06/9 |
| Confidence | 7.80/9 | 7.32/9 |
Guidance actions in this group
| Action | This group | All calls |
|---|
| raised | 33.7% | 22.5% |
| maintained | 51.1% | 51.8% |
| lowered | 9.8% | 12.6% |
| withdrawn | 0.0% | 1.2% |
What travels with it
| Signal | Lift | In group | Overall |
|---|
| Early Products Growing Fast | 1.57× | 56.5% | 36.0% |
| Skeptic Reassured | 1.34× | 94.6% | 70.8% |
| The Question Left Hanging | 0.48× | 21.7% | 45.0% |
| Results Worse Than Direction | 0.50× | 23.9% | 48.2% |
| Pricing Recovering | 0.60× | 10.9% | 18.1% |
| Volume About to Step Up | 0.67× | 17.4% | 26.0% |
| Underused Fixed Costs | 0.67× | 27.2% | 40.6% |
Share of calls by year
| Year | Share | |
|---|
| 2015 | 0.17% | |
| 2016 | 0.09% | |
| 2017 | 0.10% | |
| 2018 | 0.07% | |
| 2019 | 0.01% | |
| 2020 | 0.00% | |
| 2021 | 0.04% | |
| 2022 | 0.10% | |
| 2023 | 0.06% | |
| 2024 | 0.04% | |
| 2025 | 0.00% | |
Recent examples
| Ticker | Call | Date | Grade |
|---|
| WRBY | Q1 2024 | 2024-05-09 | A |
| LINC | Q1 2024 | 2024-05-06 | B+ |
| ROCK | Q1 2024 | 2024-05-01 | B+ |
| LTRX | Q3 2024 | 2024-04-29 | C |
| SNV | Q1 2024 | 2024-04-18 | B |
| NICE | Q4 2023 | 2024-02-22 | B+ |
| MET | Q4 2023 | 2024-02-01 | B+ |
| BRBR | Q4 2023 | 2023-11-21 | 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: Secure base, several live doors.” Artul.ai Earnings-Call Research Library, Study No. 55. https://artul.ai/research/hypothesis-secure-base-several-live-doors
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.