Hypothesis Tested: Strong facts, held-back story

Some executives load their calls with hard specifics while keeping the narrative quiet — strong facts, held-back story. We tested this pattern across 165,000 earnings-call transcripts read by an AI, isolating 101 calls that fit it (about 22% of a 460-call matched base). For anyone who listens to earnings calls, it matters because it's a recognizable style: dense numbers, minimal storytelling, and the question is whether that restraint signals confidence or trouble.

The profile fits the label: specificity runs 7.79 versus 7.65 in the base, and confidence 7.67 versus 7.33, while stress is lower (2.2 vs 2.4). Guidance skews positive — 39.6% raised guidance versus 22% in the base, and only 1% lowered versus 12.8%. These calls are 1.58 times more likely to feature "Pricing Recovering" and 1.29 times more likely to leave a "Skeptic Reassured." But the pattern is fading: it peaked around 11% of calls in 2016 and 2022, then dropped to 2% in 2024 and zero in 2025.

These fields come from an AI reading transcripts, so they're noisy and imperfect. The return figures — median −6.7% across 51 calls versus −7.6% in the base — are 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, contaminating any backtest. Read this as a descriptive pattern, not an edge.

Behavior profile

Guidance actions in this group

What travels with it

Share of calls by year

Recent examples

This hypothesis has its own page with every matching company: see the full question.