GENESISv0.1.0
development instance · real Pump.fun observations · no token · no real rewards
Ledger / Prediction #3788 · narrative · 1H

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

GENESIS said 47% → FADES CORRECT

What GENESIS knew, before

10 of 1068 launches in the last hour referenced "yumi" (8 distinct creators, rank #32). Last 15m momentum 1.01×.

Made2026-10-14 10:00 UTC
Resolves2026-10-14 11:00 UTC
Evidence cutoff2026-10-14 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": 0.1039720770839918,
      "momentum": 0.01223544675883835,
      "diversity": 0.06000000000000005
    },
    "rawProbability": 0.46909134272482256
  },
  "features": {
    "term": "yumi",
    "rank60": 32,
    "share15": 0.009943181818181818,
    "share60": 0.009822263797942002,
    "total15": 351,
    "total60": 1068,
    "momentum": 1.012310606060606,
    "diversity": 0.8,
    "launches15": 3,
    "launches60": 10,
    "contextMinutes": 60,
    "uniqueCreators60": 8
  },
  "extractor": "terms-v2",
  "selection": "random-eligible",
  "candidates": 111,
  "calibration": null,
  "methodology": "attention-v1",
  "termHistory": null,
  "contextCoverage": 0.9938175,
  "memoriesRecalled": 0,
  "priorWindowCoverage": 0.9938175
}
Expected
{
  "direction": "down",
  "magnitude": null,
  "magnitudeNote": "v0 does not model magnitude",
  "probabilityUp": 0.46909134272482256
}
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

Graded2026-10-14 11:03 UTC
StatusSCORED
OutcomeFADED
ClassificationCORRECT
Brier0.220
Log loss0.633
Graderjudge-v1
Outcome data
{
  "shareAfter": 0.0007564296520423601,
  "shareRatio": 0.11640211640211641,
  "totalAfter": 1322,
  "shareBefore": 0.009285051067780872,
  "totalBefore": 1077,
  "coverageAfter": 1,
  "launchesAfter": 1,
  "coverageBefore": 1,
  "launchesBefore": 10
}
Post-outcome analysis · judge-v1

Predicted 47% that "yumi" would gain share over 1H. Its share of launches moved 0.93% → 0.08% (-92%). CORRECT.

— The prior alone was right on "yumi" (1H). No signal pushed toward the outcome; the base assumption carried the prediction.

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

Integrity

Hash1a86594c9a2878fb8a50ed3a9f2c0c926c0615a7f5276dec7a42ae65a292d71f
Previous hashc128a480c946afe2389da0528e1420e1ace67354a2cf85cb8977a73da5255212