Equity melt-up versus building recession risk
What changed
The headline signal — how confidence moved from the previous snapshot, and why.
Moved from 2.1.1 0.70 ± 0.08 to 0.66 ± 0.08 - mean step of -0.04 on the cumulative weekend-plus-Monday escalation pressing the recession-risk leg: Sunday Barakah attack, Trump "clock is ticking" framing, WTI follow-through to $107.98, 10Y to 4.61-4.63%, S&P futures down -0.58%, Polymarket 6% on "Up" open. Width held at 0.08; the Wed-Thu binary tells (FOMC minutes, NVDA, Walmart) are still the operative move-generators and post-print rerating is the operative direction. Beta(24, 12.4) encodes ~36 effective observations - up from ~33 reflecting weekend-plus-Monday additions. The 0.66 level sits closer to the recession-risk side of the named tell range; next material confidence move comes from the Wed-Thu binary cluster.
The thesis
The claim and where confidence stands now.
S&P 500 closed 7,408.50 on Friday May 15 (-1.24%) - retreating below 7,500 from Thursday's 7,501.24 record. Nasdaq Composite -1.54% to 26,225.14 from Thursday's 26,635.22 record; SPY 739.17 (-1.20%); VIX surged ~10% to ~19, still inside the 15-20 mid-zone and well below the 25 vol-expansion threshold. The named tell from the 1.0.13 step-up - muscle-through across three consecutive hot inflation prints - was tested by the Friday oil shock (WTI +4.5%, weekly +11%) plus tech wreck (NVDA -4.4%, AMD -5.7%, Intel -8%, Micron -6.6%) plus 10Y to 4.59% (fresh ~1-year high) and did not hold past the next session. The recession-risk leg pressed harder over the weekend and Monday morning: Sunday Barakah nuclear-plant attack, Trump "clock is ticking" Truth Social escalation, WTI to $107.98 (+2.43% Monday) / Brent through $110, 10Y to 4.61-4.63%, and S&P 500 futures down -0.58% with SPY pre-market -0.19% to $737.74. Polymarket pricing only 6% probability of an "Up" open Monday. CME FedWatch hike-by-December holds the Friday ~56% level with futures continuing to price zero 2026 cuts. CSCO printed a divergent +13.4% on its Q3 catalyst - a partial offset on the AI-spend side. Q1 2026 earnings season closed at 84% beat rate, 27.7% blended EPS growth (latest FactSet refresh), blended net margin 13.4% (highest since FactSet began tracking in 2009). Invalidation requires either a vol-expansion break (VIX > 25 with SPY breaking 50d MA for 5 trading days) or unimpeded melt-up confirmation (SPX > 7,300 with VIX < 15 for 5 trading days) - neither side has fired, but the weekend + Monday cumulatively walks back the melt-up confirmation side. Three binary tells land in the next 56 hours Wed May 20 - Thu May 21: FOMC minutes, NVDA Q1 FY2027, Walmart Q1 FY2027.
Drivers
The underlying macro forces this thesis expresses - the loading mean is how much each force drives the thesis, the stddev our confidence in the mapping.
Supporting evidence
Typed, citation-backed observations across time, grouped by strength. Hover a point for the claim.
What would invalidate this
The machine-evaluable conditions that would falsify the thesis.