GENESISv0.1.0
development instance · real Pump.fun observations · no token · no real rewards
Ledger / Prediction #390 · narrative · 6H

Will "save" take a larger share of new Pump.fun launches in the next 6H than in the previous 6H?

GENESIS said 44% → FADES INCORRECT

What GENESIS knew, before

98 of 2625 launches in the last hour referenced "save" (4 distinct creators, rank #4). Last 15m momentum 1.62×.

Made2026-10-09 23:00 UTC
Resolves2026-10-10 05:00 UTC
Evidence cutoff2026-10-09 22:59 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": 0.7,
    "contributions": {
      "volume": 0.4463294349354708,
      "momentum": 0.48248881570209157,
      "diversity": -0.8510204081632652
    },
    "rawProbability": 0.4389211878703642
  },
  "features": {
    "term": "save",
    "rank60": 4,
    "share15": 0.06076923076923077,
    "share60": 0.03750952018278751,
    "total15": 649,
    "total60": 2625,
    "momentum": 1.6201015228426394,
    "diversity": 0.04081632653061224,
    "launches15": 39,
    "launches60": 98,
    "contextMinutes": 60,
    "uniqueCreators60": 4
  },
  "extractor": "terms-v2",
  "selection": "top-volume",
  "candidates": 408,
  "calibration": null,
  "methodology": "attention-v1",
  "termHistory": null,
  "contextCoverage": 0.9946447222222222,
  "memoriesRecalled": 0,
  "priorWindowCoverage": 0.9991074537037037
}
Expected
{
  "direction": "down",
  "magnitude": null,
  "magnitudeNote": "v0 does not model magnitude",
  "probabilityUp": 0.4389211878703642
}
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 05:03 UTC
StatusSCORED
OutcomeACCELERATED
ClassificationINCORRECT
Brier0.315
Log loss0.823
Graderjudge-v1
Outcome data
{
  "shareAfter": 0.02066115702479339,
  "shareRatio": 2.8895290845038764,
  "totalAfter": 13068,
  "shareBefore": 0.007131384516543527,
  "totalBefore": 15565,
  "coverageAfter": 1,
  "launchesAfter": 270,
  "coverageBefore": 1,
  "launchesBefore": 111
}
Post-outcome analysis · judge-v1

Predicted 44% that "save" would gain share over 6H. Its share of launches moved 0.71% → 2.07% (+190%). INCORRECT.

— diversity misled on "save" (6H). diversity contributed -0.85 to the log-odds toward no; reality was yes.

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

Integrity

Hash3e70b20298eb48ccfd34f22ccc80fe49504a26dbaa31400df30d04c1b3c541f6
Previous hashcb27bf5b384c92316769fd51a395839635b848f0b42920c0de890775e48b265e