Ledger / Prediction #2569 · narrative · 1H

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

GENESIS said 79% → ACCELERATES INCORRECT

What GENESIS knew, before

93 of 2872 launches in the last hour referenced "bullshit" (55 distinct creators, rank #1). Last 15m momentum 3.86×.

Made2026-10-12 20:00 UTC

Resolves2026-10-12 21:00 UTC

Evidence cutoff2026-10-12 20:00 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": 0.43847423710787337,
      "momentum": 1.3510710241461978,
      "diversity": -0.19032258064516125
    },
    "rawProbability": 0.7857041323954506
  },
  "features": {
    "term": "bullshit",
    "rank60": 1,
    "share15": 0.1256720430107527,
    "share60": 0.03254437869822485,
    "total15": 743,
    "total60": 2872,
    "momentum": 3.8615591397849465,
    "diversity": 0.5913978494623656,
    "launches15": 93,
    "launches60": 93,
    "contextMinutes": 60,
    "uniqueCreators60": 55
  },
  "extractor": "terms-v2",
  "selection": "top-volume",
  "candidates": 356,
  "calibration": null,
  "methodology": "attention-v1",
  "termHistory": null,
  "contextCoverage": 0.9993741666666667,
  "memoriesRecalled": 0,
  "priorWindowCoverage": 0.9993741666666667
}

Expected

{
  "direction": "up",
  "magnitude": null,
  "magnitudeNote": "v0 does not model magnitude",
  "probabilityUp": 0.7857041323954506
}

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

Graded2026-10-12 21:03 UTC

StatusSCORED

OutcomeFADED

ClassificationINCORRECT

Brier0.617

Log loss1.540

Graderjudge-v1

Outcome data

{
  "shareAfter": 0.0016233766233766235,
  "shareRatio": 0.05502415182236478,
  "totalAfter": 3080,
  "shareBefore": 0.032280458174245054,
  "totalBefore": 2881,
  "coverageAfter": 1,
  "launchesAfter": 5,
  "coverageBefore": 1,
  "launchesBefore": 93
}

Post-outcome analysis · judge-v1

Predicted 79% that "bullshit" would gain share over 1H. Its share of launches moved 3.23% → 0.16% (-95%). INCORRECT.

— momentum misled on "bullshit" (1H). momentum contributed +1.35 to the log-odds toward yes; reality was no.

— Overconfident: 79% and wrong on "bullshit". 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

Hash7174e3cd01cde0a4cd2c721c731b46f1386c64881136ac195e248f49af6faaef

Previous hashdc3d2e14180ee16a9258a070de03141eba2a41fe9136ee30308338ead0af681a