Pump.fun Graduation Regime Windows: Survival Analysis of 832,941 Token Launches and the Social-Presence Effect

Abstract

We present a Kaplan-Meier and Cox proportional-hazards survival analysis of 832,941 Solana pump.fun token launches with 24-hour graduation outcomes, observed continuously between 2026-05-08 and 2026-06-10. The pooled graduation rate is 0.198% (Wilson 95% CI [0.189%, 0.208%]), a 3.18x decline from the 0.63% rate reported by Marino et al. (2026) for September-October 2025. After excluding a four-day tracker warm-up and the partial last day, the steady-state rate is 0.207% (Wilson 95% CI [0.198%, 0.218%]). We formalise the windowed comparison as the Graduation Regime Windows (GRW) framework, name our 34-day window the RED-PUMP-2026-v1 regime, and release the 860,213-launch dataset under CC-BY-4.0 on Zenodo at concept DOI 10.5281/zenodo.20633486. Social-channel presence exerts a large effect: launches advertising Telegram graduate at 1.485% versus 0.166% without (8.94x lift, log-rank p < 1e-300); Cox hazard ratio for Telegram is 5.40 (95% CI [4.73, 6.17], p = 6.6e-138). Launches advertising all three social channels graduate at 1.919% versus 0.110% for launches with none (17.4x lift). Initial market-cap above the 30 SOL platform default, a proxy for creator self-buying, raises the hazard ratio to 4.51; the top quartile (mcap > 31 SOL) graduates at 0.634%, matching the 2025 pooled rate. The cross-regime decline is substantially attributable to a shift toward zero-self-buy tokens rather than a fall in success rate among self-buy launches. Cox concordance is 0.858.