GENESISv0.1.0
development instance · real Pump.fun observations · no token · no real rewards
Ledger / Prediction #3044 · narrative · 24H

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

GENESIS said 20% → FADES INCORRECT

What GENESIS knew, before

10 of 1026 launches in the last hour referenced "donated" (3 distinct creators, rank #26). Last 15m momentum 0.17×.

Made2026-10-13 10:30 UTC
Resolves2026-10-14 10:30 UTC
Evidence cutoff2026-10-13 10:29 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": 0.1039720770839918,
      "momentum": -1.7937049951335464,
      "diversity": -0.54
    },
    "rawProbability": 0.19546762253030886
  },
  "features": {
    "term": "donated",
    "rank60": 26,
    "share15": 0.0017006802721088435,
    "share60": 0.010223953261927946,
    "total15": 293,
    "total60": 1026,
    "momentum": 0.16634272756721735,
    "diversity": 0.3,
    "launches15": 0,
    "launches60": 10,
    "contextMinutes": 60,
    "uniqueCreators60": 3
  },
  "extractor": "terms-v2",
  "selection": "random-eligible",
  "candidates": 106,
  "calibration": null,
  "methodology": "attention-v1",
  "termHistory": null,
  "contextCoverage": 0.9974333333333333,
  "memoriesRecalled": 0,
  "priorWindowCoverage": 0.9998930555555555
}
Expected
{
  "direction": "down",
  "magnitude": null,
  "magnitudeNote": "v0 does not model magnitude",
  "probabilityUp": 0.19546762253030886
}
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 10:33 UTC
StatusSCORED
OutcomeACCELERATED
ClassificationINCORRECT
Brier0.647
Log loss1.632
Graderjudge-v1
Outcome data
{
  "shareAfter": 0.0004585893790699807,
  "shareRatio": 1.7663476486368745,
  "totalAfter": 43612,
  "shareBefore": 0.0002554713446308439,
  "totalBefore": 46972,
  "coverageAfter": 1,
  "launchesAfter": 20,
  "coverageBefore": 1,
  "launchesBefore": 12
}
Post-outcome analysis · judge-v1

Predicted 20% that "donated" would gain share over 24H. Its share of launches moved 0.03% → 0.05% (+80%). INCORRECT.

— momentum misled on "donated" (24H). momentum contributed -1.79 to the log-odds toward no; reality was yes.

— Overconfident: 80% and wrong on "donated". Confidence this high should be wrong about 1 time in 4 or less; track this bucket.

2 memory records written (sealed: written while memory was short-context only).

Integrity

Hash4bf2f7bb3fa7f4ed7582ed97c0c9d394e60067c66dd36497671136501e882901
Previous hash0367876c108bfd7dad00afb72df517e934807a12b2bccc4fe1967a306799b5e4