GENESISv0.1.0
development instance · real Pump.fun observations · no token · no real rewards
Ledger / Prediction #3354 · narrative · 1H

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

GENESIS said 49% → FADES CORRECT

What GENESIS knew, before

67 of 2540 launches in the last hour referenced "taku" (34 distinct creators, rank #3). Last 15m momentum 1.19×.

Made2026-10-13 20:30 UTC
Resolves2026-10-13 21:30 UTC
Evidence cutoff2026-10-13 20:30 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": 0.3892882060435298,
      "momentum": 0.17434427029410254,
      "diversity": -0.29104477611940294
    },
    "rawProbability": 0.4931473541585421
  },
  "features": {
    "term": "taku",
    "rank60": 3,
    "share15": 0.03162393162393162,
    "share60": 0.026564344746162927,
    "total15": 584,
    "total60": 2540,
    "momentum": 1.1904653371320038,
    "diversity": 0.5074626865671642,
    "launches15": 18,
    "launches60": 67,
    "contextMinutes": 60,
    "uniqueCreators60": 34
  },
  "extractor": "terms-v2",
  "selection": "top-volume",
  "candidates": 319,
  "calibration": null,
  "methodology": "attention-v1",
  "termHistory": null,
  "contextCoverage": 0.9990919444444445,
  "memoriesRecalled": 0,
  "priorWindowCoverage": 0.9990919444444445
}
Expected
{
  "direction": "down",
  "magnitude": null,
  "magnitudeNote": "v0 does not model magnitude",
  "probabilityUp": 0.4931473541585421
}
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 21:34 UTC
StatusSCORED
OutcomeFADED
ClassificationCORRECT
Brier0.243
Log loss0.679
Graderjudge-v1
Outcome data
{
  "shareAfter": 0.001849796522382538,
  "shareRatio": 0.07656969099276792,
  "totalAfter": 2703,
  "shareBefore": 0.02637795275590551,
  "totalBefore": 2540,
  "coverageAfter": 1,
  "launchesAfter": 5,
  "coverageBefore": 1,
  "launchesBefore": 67
}
Post-outcome analysis · judge-v1

Predicted 49% that "taku" would gain share over 1H. Its share of launches moved 2.64% → 0.18% (-93%). CORRECT.

— diversity pointed the right way on "taku" (1H). diversity contributed -0.29 to the log-odds and the outcome agreed.

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

Integrity

Hash47e29a3ee48587530e6345a09d9ef0fd48ae653647ec3e85bcbffb562d3f9c67
Previous hash20f1ae14ed3089495c61fa8bdb3d5656a5f993125d83cb5f1913b51977bf0946