GENESISv0.1.0
development instance · real Pump.fun observations · no token · no real rewards
Ledger / Prediction #1027 · narrative · 24H

Will "hello" take a larger share of new Pump.fun launches in the next 24H than in the previous 24H?

GENESIS said 46% → FADES CORRECT

What GENESIS knew, before

49 of 2567 launches in the last hour referenced "hello" (3 distinct creators, rank #17). Last 15m momentum 2.06×.

Made2026-10-10 19:30 UTC
Resolves2026-10-11 19:30 UTC
Evidence cutoff2026-10-10 19:29 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": 0.5,
    "contributions": {
      "volume": 0.34235735785147897,
      "momentum": 0.7245589904789177,
      "diversity": -0.826530612244898
    },
    "rawProbability": 0.4551689365925382
  },
  "features": {
    "term": "hello",
    "rank60": 17,
    "share15": 0.039781591263650544,
    "share60": 0.019275700934579438,
    "total15": 640,
    "total60": 2567,
    "momentum": 2.063820734647568,
    "diversity": 0.061224489795918366,
    "launches15": 25,
    "launches60": 49,
    "contextMinutes": 60,
    "uniqueCreators60": 3
  },
  "extractor": "terms-v2",
  "selection": "top-volume",
  "candidates": 412,
  "calibration": null,
  "methodology": "attention-v1",
  "termHistory": null,
  "contextCoverage": 0.9960297222222222,
  "memoriesRecalled": 0,
  "priorWindowCoverage": 0.9998345717592593
}
Expected
{
  "direction": "down",
  "magnitude": null,
  "magnitudeNote": "v0 does not model magnitude",
  "probabilityUp": 0.4551689365925382
}
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

Graded2026-10-11 19:33 UTC
StatusSCORED
OutcomeFADED
ClassificationCORRECT
Brier0.207
Log loss0.607
Graderjudge-v1
Outcome data
{
  "shareAfter": 0.0023033513762524475,
  "shareRatio": 0.8684164202225038,
  "totalAfter": 43415,
  "shareBefore": 0.0026554771750587854,
  "totalBefore": 49332,
  "coverageAfter": 1,
  "launchesAfter": 100,
  "coverageBefore": 1,
  "launchesBefore": 131
}
Post-outcome analysis · judge-v1

Predicted 46% that "hello" would gain share over 24H. Its share of launches moved 0.27% → 0.23% (-13%). CORRECT.

— diversity pointed the right way on "hello" (24H). diversity contributed -0.83 to the log-odds and the outcome agreed.

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

Integrity

Hash3ddfcbf47bcd969e1559315d98ff350b69f1befa1f324a2075d016b52d660dc1
Previous hash51703df56e4a6559ad7005e6b6ff3fc7deb940ebaa6c1ad08076b6cd122091bc