Artul.ai Research LibraryStudy No. 77Signal CombinationsUpdated 2026-08-28
Rehearsed and Vague: When Two Signals Appear Together
By Artul.ai Research Group · n = 378 earnings calls · First published 2026-08-28
When an executive leans on rehearsed talking points while staying vague on substance, the combination is easy to miss in real time but stands out when measured at scale. Across 165,182 earnings-call transcripts read by an AI, 378 calls — about 0.2% — matched this pattern of high scripted delivery paired with low informational content. Anyone who follows calls closely knows the type; this study sizes it and shows what else tends to travel with it.
The profile shows confidence (4.65 to 7.21) running well above candor (3.61 to 6.86), a gap that fits the rehearsed-and-vague label. Co-occurrence is striking: "The Question Left Hanging" appears on 100% of these calls versus 48% of the base, a 2.09 lift, and "Scale-Dependent Advantage Claims" shows a 1.72 lift. Meanwhile, "Calls That Resolve Doubts" and "Guidance Worth Underwriting" are entirely absent. The trend is the sharpest signal: the pattern was rare for a decade, then jumped to 0.6% of calls in 2024 and 4.41% in 2025.
These fields come from AI reading of transcripts and are noisy; the 2024–2025 spike may partly reflect how the model reads modern call language rather than a real behavioral shift. Return figures here are descriptive history from a 22,449-call sample, not a trading signal — our own forward tests failed to confirm directional prediction, and language models partially remember famous stocks' histories, contaminating any backtest. Treat this as a description of a pattern, not an edge.
Matching Calls
378
0.2% of corpus
Behavior profile
| Meter | This group | All calls |
|---|
| Candor | 3.61/9 | 6.86/9 |
| Evasion | 0.30/9 | 2.70/9 |
| Specificity | 1.42/9 | 7.56/9 |
| Stress | 1.38/9 | 2.43/9 |
| Promotion | 2.51/9 | 5.05/9 |
| Confidence | 4.65/9 | 7.21/9 |
Guidance actions in this group
| Action | This group | All calls |
|---|
| raised | 0.0% | 21.1% |
| maintained | 0.8% | 48.8% |
| lowered | 0.3% | 11.6% |
| withdrawn | 0.0% | 2.7% |
What travels with it
| Signal | Lift | In group | Overall |
|---|
| The Question Left Hanging | 2.09× | 100.0% | 48.0% |
| Scale-Dependent Advantage Claims | 1.72× | 19.0% | 11.1% |
| Calls That Resolve Doubts | 0.00× | 0.0% | 79.5% |
| Guidance Worth Underwriting | 0.00× | 0.0% | 71.5% |
| Skeptic Reassured | 0.00× | 0.0% | 66.4% |
| Pricing Recovering | 0.02× | 0.5% | 21.5% |
| Deferred Revenue Growing | 0.03× | 0.3% | 8.9% |
Share of calls by year
| Year | Share | |
|---|
| 2015 | 0.00% | |
| 2016 | 0.01% | |
| 2017 | 0.01% | |
| 2018 | 0.01% | |
| 2019 | 0.00% | |
| 2020 | 0.00% | |
| 2021 | 0.00% | |
| 2022 | 0.01% | |
| 2023 | 0.01% | |
| 2024 | 0.60% | |
| 2025 | 4.41% | |
Recent examples
| Ticker | Call | Date | Grade |
|---|
| CRDOF | Q1 2025 | 2025-05-29 | F |
| REX | Q1 2025 | 2025-05-28 | F |
| TPTA | Q1 2025 | 2025-05-22 | F |
| WB | Q1 2025 | 2025-05-21 | F |
| WRD | Q1 2025 | 2025-05-21 | F |
| MDWD | Q1 2025 | 2025-05-21 | D |
| BIOX | Q3 2025 | 2025-05-21 | D |
| XPEV | Q1 2025 | 2025-05-21 | F |
Cite this study
Artul.ai Research Group (2026). “Rehearsed and Vague: When Two Signals Appear Together.” Artul.ai Earnings-Call Research Library, Study No. 77. https://artul.ai/research/rehearsed-and-vague
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.