GENESISv0.1.0
development instance · real Pump.fun observations · no token · no real rewards
Ledger / Prediction #2908 · narrative · 1H

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

GENESIS said 48% → FADES CORRECT

What GENESIS knew, before

7 of 1224 launches in the last hour referenced "meet" (4 distinct creators, rank #89). Last 15m momentum 1.46×.

Made2026-10-13 06:30 UTC
Resolves2026-10-13 07:30 UTC
Evidence cutoff2026-10-13 06:29 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": 0.050470835493181924,
      "momentum": 0.3808720524893521,
      "diversity": -0.21428571428571433
    },
    "rawProbability": 0.4792761728810547
  },
  "features": {
    "term": "meet",
    "rank60": 89,
    "share15": 0.008960573476702509,
    "share60": 0.006122448979591836,
    "total15": 278,
    "total60": 1224,
    "momentum": 1.4635603345280765,
    "diversity": 0.5714285714285714,
    "launches15": 2,
    "launches60": 7,
    "contextMinutes": 60,
    "uniqueCreators60": 4
  },
  "extractor": "terms-v2",
  "selection": "random-eligible",
  "candidates": 125,
  "calibration": null,
  "methodology": "attention-v1",
  "termHistory": null,
  "contextCoverage": 0.9963066666666667,
  "memoriesRecalled": 0,
  "priorWindowCoverage": 0.9963066666666667
}
Expected
{
  "direction": "down",
  "magnitude": null,
  "magnitudeNote": "v0 does not model magnitude",
  "probabilityUp": 0.4792761728810547
}
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

Graded2026-10-13 07:33 UTC
StatusSCORED
OutcomeFADED
ClassificationCORRECT
Brier0.230
Log loss0.653
Graderjudge-v1
Outcome data
{
  "shareAfter": 0.0035842293906810036,
  "shareRatio": 0.6585496866606984,
  "totalAfter": 1116,
  "shareBefore": 0.005714285714285714,
  "totalBefore": 1225,
  "coverageAfter": 1,
  "launchesAfter": 4,
  "coverageBefore": 1,
  "launchesBefore": 7
}
Post-outcome analysis · judge-v1

Predicted 48% that "meet" would gain share over 1H. Its share of launches moved 0.57% → 0.36% (-37%). CORRECT.

— diversity pointed the right way on "meet" (1H). diversity contributed -0.21 to the log-odds and the outcome agreed.

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

Integrity

Hashf99976de16a8f667688314b778069fd62ebf3d634c72e5418aebf28761fd3b9a
Previous hash6968af6e3b27726343d6b56468899de9a0013e1a865845d0c6d75f30457b5a6c