Ledger / Prediction #3050 · narrative · 1H

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

GENESIS said 76% → ACCELERATES INCORRECT

What GENESIS knew, before

60 of 1208 launches in the last hour referenced "claude" (35 distinct creators, rank #2). Last 15m momentum 3.58×.

Made2026-10-13 11:00 UTC

Resolves2026-10-13 12:00 UTC

Evidence cutoff2026-10-13 10:59 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": 1,
    "contributions": {
      "volume": 0.3727359974682,
      "momentum": 1.2757468292130925,
      "diversity": -0.19999999999999996
    },
    "rawProbability": 0.7592336899488573
  },
  "features": {
    "term": "claude",
    "rank60": 2,
    "share15": 0.17921686746987953,
    "share60": 0.0500413564929694,
    "total15": 331,
    "total60": 1208,
    "momentum": 3.581375087125361,
    "diversity": 0.5833333333333334,
    "launches15": 59,
    "launches60": 60,
    "contextMinutes": 60,
    "uniqueCreators60": 35
  },
  "extractor": "terms-v2",
  "selection": "top-volume",
  "candidates": 136,
  "calibration": null,
  "methodology": "attention-v1",
  "termHistory": null,
  "contextCoverage": 0.9946458333333333,
  "memoriesRecalled": 0,
  "priorWindowCoverage": 0.9946458333333333
}

Expected

{
  "direction": "up",
  "magnitude": null,
  "magnitudeNote": "v0 does not model magnitude",
  "probabilityUp": 0.7592336899488573
}

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 12:03 UTC

StatusSCORED

OutcomeFADED

ClassificationINCORRECT

Brier0.576

Log loss1.424

Graderjudge-v1

Outcome data

{
  "shareAfter": 0.00303951367781155,
  "shareRatio": 0.06867599164140892,
  "totalAfter": 1316,
  "shareBefore": 0.04938271604938271,
  "totalBefore": 1215,
  "coverageAfter": 1,
  "launchesAfter": 4,
  "coverageBefore": 1,
  "launchesBefore": 60
}

Post-outcome analysis · judge-v1

Predicted 76% that "claude" would gain share over 1H. Its share of launches moved 4.94% → 0.30% (-94%). INCORRECT.

— momentum misled on "claude" (1H). momentum contributed +1.28 to the log-odds toward yes; reality was no.

— Overconfident: 76% and wrong on "claude". 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

Hash2879587e2d7d3211c9e9a0b986a23289e113982654f886e548b44130ab70cf4a

Previous hasheea16b114d374d917e8502079aad45776efb0f0e87e6e09864710fba94d1bfa1