GENESISv0.1.0
development instance · real Pump.fun observations · no token · no real rewards
Ledger / Prediction #716 · narrative · 1H

Will "friendly" take a larger share of new Pump.fun launches in the next 1H than in the previous 1H?

GENESIS said 40% → FADES INCORRECT

What GENESIS knew, before

14 of 1547 launches in the last hour referenced "friendly" (5 distinct creators, rank #49). Last 15m momentum 1.25×.

Made2026-10-10 10:00 UTC
Resolves2026-10-10 11:00 UTC
Evidence cutoff2026-10-10 09:59 UTC
Data sourcespumpfun.launch_feed
GENESIS version0.1.0
Enginenarrative-heuristic-v0
Scoring methodshare-direction-v1
Active capabilities6
Evidence (exact record)
{
  "model": {
    "bias": -0.3,
    "version": "narrative-heuristic-v0",
    "horizonScale": 1,
    "contributions": {
      "volume": 0.1544429125771737,
      "momentum": 0.22140446721163357,
      "diversity": -0.4714285714285714
    },
    "rawProbability": 0.40237446752581424
  },
  "features": {
    "term": "friendly",
    "rank60": 49,
    "share15": 0.011688311688311689,
    "share60": 0.009366925064599484,
    "total15": 384,
    "total60": 1547,
    "momentum": 1.2478280340349306,
    "diversity": 0.35714285714285715,
    "launches15": 4,
    "launches60": 14,
    "contextMinutes": 60,
    "uniqueCreators60": 5
  },
  "extractor": "terms-v2",
  "selection": "random-eligible",
  "candidates": 213,
  "calibration": null,
  "methodology": "attention-v1",
  "termHistory": null,
  "contextCoverage": 0.9943466666666667,
  "memoriesRecalled": 0,
  "priorWindowCoverage": 0.9943466666666667
}
Expected
{
  "direction": "down",
  "magnitude": null,
  "magnitudeNote": "v0 does not model magnitude",
  "probabilityUp": 0.40237446752581424
}
Engine narrative-heuristic-v0

P(term's share of new Pump.fun launches is higher in the next H than in the previous H). Hand-set logistic heuristic over 60 minutes of launch observations: short-term momentum, creator diversity, volume. Slight mean-reversion prior because candidates are selected while already popular.

What happened, after

Graded2026-10-10 11:03 UTC
StatusSCORED
OutcomeACCELERATED
ClassificationINCORRECT
Brier0.357
Log loss0.910
Graderjudge-v1
Outcome data
{
  "shareAfter": 0.012437810945273632,
  "shareRatio": 1.3672231628126272,
  "totalAfter": 1608,
  "shareBefore": 0.0090032154340836,
  "totalBefore": 1555,
  "coverageAfter": 1,
  "launchesAfter": 20,
  "coverageBefore": 1,
  "launchesBefore": 14
}
Post-outcome analysis · judge-v1

Predicted 40% that "friendly" would gain share over 1H. Its share of launches moved 0.90% → 1.24% (+38%). INCORRECT.

— diversity misled on "friendly" (1H). diversity contributed -0.47 to the log-odds toward no; reality was yes.

1 memory record written (sealed: written while memory was short-context only).

Integrity

Hash878fb44aea3d3a30a8f67e08611210f44444aa1b8be44a473a52e00b0f99d7c5
Previous hash14f0dfbfef83b5e204fbad1928a4bb67d3e8480c9bdb57df9ab88dfcbedaab9d