GENESISv0.1.0
development instance · real Pump.fun observations · no token · no real rewards
Ledger / Prediction #1089 · narrative · 24H

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

GENESIS said 41% → FADES INCORRECT

What GENESIS knew, before

52 of 2404 launches in the last hour referenced "trump" (37 distinct creators, rank #10). Last 15m momentum 0.65×.

Made2026-10-10 21:30 UTC
Resolves2026-10-11 21:30 UTC
Evidence cutoff2026-10-10 21:29 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": 0.351270870922099,
      "momentum": -0.43159339837375116,
      "diversity": -0.04615384615384612
    },
    "rawProbability": 0.41017591886307
  },
  "features": {
    "term": "trump",
    "rank60": 10,
    "share15": 0.014177693761814745,
    "share60": 0.02182952182952183,
    "total15": 528,
    "total60": 2404,
    "momentum": 0.6494733999459897,
    "diversity": 0.7115384615384616,
    "launches15": 7,
    "launches60": 52,
    "contextMinutes": 60,
    "uniqueCreators60": 37
  },
  "extractor": "terms-v2",
  "selection": "top-volume",
  "candidates": 360,
  "calibration": null,
  "methodology": "attention-v1",
  "termHistory": null,
  "contextCoverage": 0.9927038888888889,
  "memoriesRecalled": 0,
  "priorWindowCoverage": 0.9996959953703703
}
Expected
{
  "direction": "down",
  "magnitude": null,
  "magnitudeNote": "v0 does not model magnitude",
  "probabilityUp": 0.41017591886307
}
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 21:33 UTC
StatusSCORED
OutcomeACCELERATED
ClassificationINCORRECT
Brier0.348
Log loss0.891
Graderjudge-v1
Outcome data
{
  "shareAfter": 0.008216945996275605,
  "shareRatio": 1.6874905574162786,
  "totalAfter": 42960,
  "shareBefore": 0.004866031435784673,
  "totalBefore": 49116,
  "coverageAfter": 1,
  "launchesAfter": 353,
  "coverageBefore": 1,
  "launchesBefore": 239
}
Post-outcome analysis · judge-v1

Predicted 41% that "trump" would gain share over 24H. Its share of launches moved 0.49% → 0.82% (+69%). INCORRECT.

— momentum misled on "trump" (24H). momentum contributed -0.43 to the log-odds toward no; reality was yes.

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

Integrity

Hash9aca1916508760a57cb85fbe5ec2960c8b0bc5282b8c577e605cc8a8061d28c6
Previous hash5eae7a36a15a65698e0382e1c65a5d49dc5fde0fb1d0af2fdd7b784b29c5bd94