Research › Hypotheses Tested
Artul.ai Research LibraryStudy No. 54Hypotheses TestedUpdated 2026-08-28

Second Front, Funded and Fueled: Who Says Yes on the Earnings Call

By Artul.ai Research Group · n = 153 earnings calls · First published 2026-08-28
Abstract

We examine 153 earnings calls (2015-2024) that answered YES to the research hypothesis 'Second demand front open and funded' out of a 494-call base, a 0.3097 share. These calls show a modest promotion-language lift (5.41 vs 5.11) and slightly higher confidence (7.39 vs 7.33), with candor, evasion, and specificity essentially flat. Guidance mixes are similar to the base, though withdrawn guidance is 0.0 vs 0.0101. Returns for the 57-call returns subset show a median of -0.130174 versus -0.108449 for the 196-call base, and a 0.3333 beat rate versus 0.3724. The 'Early Products Growing Fast' theme appears 1.61x more often.

Key findings
  • 153 of 494 calls (0.3097, 95% CI 0.2705 to 0.3518) answered YES to 'Second demand front open and funded'.
  • Promotion language scored 5.41 vs 5.11 in the base and confidence 7.39 vs 7.33, while candor (6.86 vs 6.91) and evasion (2.70 vs 2.71) were nearly unchanged.
  • Guidance was withdrawn on 0.0 of YES calls vs 0.0101 of base calls, with 0.2026 raising vs 0.2186.
  • Median subsequent return for the 57-call subset was -0.130174 vs -0.108449 for the 196-call base, with a 0.3333 beat rate vs 0.3724.

1Introduction

When management declares that a second demand front is open and funded, it is one of the boldest claims an earnings call can make: a new engine of growth, already capitalized. Analysts hear such framing as either genuine optionality or rehearsed storytelling, and the difference matters for how a call ages. Yet the claim is rarely studied as a discrete signal across a large corpus. This study examines 153 calls from 2015 through 2024 that answered YES to that hypothesis, comparing their language profiles, guidance behavior, recurring themes, and subsequent outcomes against the remaining base.

2Data & methodology

The corpus comprises 494 earnings-call transcripts published between 2015 and 2024, each scored independently by a large language model on an identical 37-field battery: seven categorical business verdicts, eight 0–9 behavioral meters, and twenty yes/no judgments. The study group is defined as calls that answered YES to the research hypothesis "Second demand front open and funded" (n = 153; 31.0% of the reference set, 95% Wilson interval 27.1%–35.2%). Baseline figures use the set of calls on which this question was tested. Market outcomes join a fixed sample of 22,449 calls with twelve-month total returns in excess of SPY, measured from the first close after each call; this sample skews toward liquid U.S. names and is reported as descriptive history only.

3Results

The language deltas are small but directional: promotion rises 0.3 (5.41 vs 5.11) and confidence 0.06 (7.39 vs 7.33), while candor, evasion, specificity, and stress all tick down slightly, suggesting a slightly more upbeat but not less transparent register. Theme analysis shows 'Early Products Growing Fast' at 1.61x lift, 'The Hidden Segment' at 1.68x, and 'A Tiny Fraction of the Market' at 1.42x, with no underrepresented themes. The trend is episodic: prevalence hits 0.17 in 2022 and 0.16 in 2023 after near-zero years in 2019 and 2020, then falls back to 0.09 in 2024. Returns in the 57-call subset trail the base on median and beat rate.

Table 1. Mean behavioral scores (0–9 scale), study group versus baseline
MeterStudy groupBaselineΔ
Candor6.866.91-0.06
Evasion2.702.71-0.02
Specificity7.637.65-0.02
Stress2.372.40-0.03
Promotion5.415.11+0.30
Confidence7.397.33+0.06
Table 2. Guidance actions, study group versus baseline
ActionStudy groupBaseline
Raised20.3%21.9%
Maintained54.9%53.2%
Lowered14.4%13.0%
Withdrawn0.0%1.0%
Table 3. Co-occurring battery signals ranked by lift (group prevalence ÷ baseline prevalence)
SignalLiftIn groupBaseline
The Hidden Segment1.68×39.9%23.7%
Early Products Growing Fast1.61×62.7%38.9%
A Tiny Fraction of the Market1.42×43.8%30.8%
20150.09%
20160.09%
20170.13%
20180.07%
20190.01%
20200.00%
20210.14%
20220.17%
20230.16%
20240.09%
20250.00%
Figure 1. Share of all analyzed calls matching the study definition, by year.
Table 4. Twelve-month excess total returns versus SPY (descriptive history, not a signal)
StatisticStudy groupReturns sample
Median excess return-13.0%-10.8%
Interquartile range-33.4% to +6.6%
Share beating SPY33.3% (95% CI 22%–46%)37.2%
Observations57196
Table 5. Most recent calls matching the study definition
TickerQuarterCall dateCall grade
ASOQ1 20242024-06-11C+
CRGOQ1 20242024-05-20C+
RCELQ1 20242024-05-14F
FWONKQ1 20242024-05-08C+
LINCQ1 20242024-05-06B+
NCQ1 20242024-05-05C+
AESQ1 20242024-05-03C+
ROCKQ1 20242024-05-01B+

4Discussion

A careful reader should conclude that calls affirming a funded second demand front sound modestly more promotional and confident, lean on growth-themed language, and in this sample show slightly weaker subsequent returns than the base. None of these differences establishes that the claim itself causes anything, or that YES calls predict outcomes. The prevalence trend shows the claim clusters in certain years, likely reflecting market conditions. Treat these as descriptive patterns about how such calls read and what accompanied them, not as a standalone signal for decisions.

5Limitations

Language fields are AI-read and inherently noisy, so small deltas may be measurement error. The returns comparison covers only 57 of these calls against a 196-call base, drawn from a universe of 22,449 calls skewed toward liquid names, limiting generalizability. Our own forward tests falsified directional prediction, so no edge should be inferred. Additionally, LLMs partially remember famous stocks' histories, which can contaminate any backtest of call-language signals against later price action. See the full methodology, including the C1 pattern’s forward-test failure and the LLM-memorization finding.

Companion page: every company matching this hypothesis is listed at the question’s own page.

Cite this study Artul.ai Research Group (2026). “Second Front, Funded and Fueled: Who Says Yes on the Earnings Call.” Artul.ai Earnings-Call Research Library, Study No. 54. https://artul.ai/research/hypothesis-second-demand-front-open-and-funded

Related studies

The Numbers Are Fine; Everything Else Is Pending: FlRoom to Run and Nowhere to Hide: Calls With UncontesLight at the End of the Tunnel Is Often a Train: RecDon't Stick to the Script: Earnings Calls Where AnswHave Your Cake and Expand the Base Too: Repeat GrowtPressed Harder, Answered Straight: A Profile of 183
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.