Research › Signal Combinations
Artul.ai Research LibraryStudy No. 23Signal CombinationsUpdated 2026-08-28

Dodged and Left Hanging: When Two Signals Appear Together

By Artul.ai Research Group · n = 3,629 earnings calls · First published 2026-08-28

Some earnings calls combine two red flags: executives dodge a question, and the analyst who asked it never gets a real answer. Across 165,182 earnings-call transcripts read by an AI, 3,629 calls — about 2.2% — show this "dodged and left hanging" pattern. For anyone who listens to calls for a living, it's worth knowing what tends to travel with it: rehearsed delivery, weak guidance, and a notable absence of reassured skeptics.

The profile is striking: evasion scores average 6.23 versus 2.7 baseline, while candor sits at 5.75 against 6.86. Guidance is withdrawn on 8.0% of these calls versus 2.7% overall, and raised on only 8.5% versus 21.1%. Co-occurrence tells the same story: "Calls That Resolve Doubts" appears on just 19.9% of these calls versus 79.5% baseline (a 0.25 ratio), and "Skeptic Reassured" on 17.0% versus 66.4%. The pattern has also faded over time, falling from 3.93% of calls in 2015 to 1.36% in 2025. Among 360 such calls with return data, the median move was -13.3% versus -7.2% baseline.

These AI-read fields are noisy, and the return comparison 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' histories, which contaminates any backtest. Treat this as a description of how language patterns cluster, not a forecast.

Matching Calls
3,629
2.2% of corpus
12m Excess vs SPY (median)
-13.3%
sample baseline -7.2%
Beat SPY
32%
baseline 39% · n=360

Behavior profile

MeterThis groupAll calls
Candor5.75/96.86/9
Evasion6.23/92.70/9
Specificity6.25/97.56/9
Stress4.13/92.43/9
Promotion5.18/95.05/9
Confidence6.47/97.21/9

Guidance actions in this group

ActionThis groupAll calls
raised8.5%21.1%
maintained38.6%48.8%
lowered11.9%11.6%
withdrawn8.0%2.7%

What travels with it

SignalLiftIn groupOverall
Scale-Dependent Advantage Claims2.65×29.4%11.1%
Calls That Read Rehearsed1.36×52.6%38.7%
Results Worse Than Direction1.32×67.6%51.1%
The Finished-Story Tell1.28×5.6%4.4%
Underused Fixed Costs1.27×52.8%41.6%
Calls That Resolve Doubts0.25×19.9%79.5%
Skeptic Reassured0.26×17.0%66.4%
Guidance Worth Underwriting0.41×29.1%71.5%
Confidence Proportionate to Evidence0.63×55.4%87.6%
Pricing Recovering0.66×14.1%21.5%

Share of calls by year

YearShare
20153.93%
20163.01%
20172.85%
20182.64%
20192.54%
20202.20%
20211.81%
20221.70%
20231.58%
20241.53%
20251.36%

Recent examples

TickerCallDateGrade
HYMTFQ2 20252025-07-24F
UNPQ2 20252025-07-24D
WFGQ2 20252025-07-24F
NESRFQ4 20252025-07-24F
TSLAQ2 20252025-07-23F
THCQ2 20252025-07-23C+
VICRQ2 20252025-07-22F
SARTFQ2 20252025-07-22D
Cite this study Artul.ai Research Group (2026). “Dodged and Left Hanging: When Two Signals Appear Together.” Artul.ai Earnings-Call Research Library, Study No. 23. https://artul.ai/research/dodged-and-left-hanging

Related studies

Small Base, Fast Growth, Huge Market: When Two SignaRaised Guidance That Even Skeptics Buy: When Two SigFounder-Led and Unusually Candid: When Two Signals ABacklog Building Into a Volume Step-Up: When Two SigFounder-Led and Promotional: When Two Signals AppearCFO Front and Center While Margins Fall: When Two Si
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.