Ledger / Prediction #3724 · narrative · 1H

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

GENESIS said 14% → FADES INCORRECT

What GENESIS knew, before

6 of 1262 launches in the last hour referenced "trench" (3 distinct creators, rank #120). Last 15m momentum 0.29×.

Made2026-10-14 08:00 UTC

Resolves2026-10-14 09:00 UTC

Evidence cutoff2026-10-14 07:59 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": 0.027348233519093188,
      "momentum": -1.237834766936112,
      "diversity": -0.3
    },
    "rawProbability": 0.14057933405119738
  },
  "features": {
    "term": "trench",
    "rank60": 120,
    "share15": 0.0014925373134328358,
    "share60": 0.005146476642913698,
    "total15": 334,
    "total60": 1262,
    "momentum": 0.2900114810562572,
    "diversity": 0.5,
    "launches15": 0,
    "launches60": 6,
    "contextMinutes": 60,
    "uniqueCreators60": 3
  },
  "extractor": "terms-v2",
  "selection": "random-eligible",
  "candidates": 132,
  "calibration": null,
  "methodology": "attention-v1",
  "termHistory": null,
  "contextCoverage": 0.9980002777777778,
  "memoriesRecalled": 0,
  "priorWindowCoverage": 0.9980002777777778
}

Expected

{
  "direction": "down",
  "magnitude": null,
  "magnitudeNote": "v0 does not model magnitude",
  "probabilityUp": 0.14057933405119738
}

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 09:03 UTC

StatusSCORED

OutcomeACCELERATED

ClassificationINCORRECT

Brier0.739

Log loss1.962

Graderjudge-v1

Outcome data

{
  "shareAfter": 0.005994005994005994,
  "shareRatio": 1.2634730538922156,
  "totalAfter": 1001,
  "shareBefore": 0.0047430830039525695,
  "totalBefore": 1265,
  "coverageAfter": 1,
  "launchesAfter": 6,
  "coverageBefore": 1,
  "launchesBefore": 6
}

Post-outcome analysis · judge-v1

Predicted 14% that "trench" would gain share over 1H. Its share of launches moved 0.47% → 0.60% (+26%). INCORRECT.

— momentum misled on "trench" (1H). momentum contributed -1.24 to the log-odds toward no; reality was yes.

— Overconfident: 86% and wrong on "trench". 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

Hash6b8abb332c57a9a64372f5970a15ed7dc3aa756630d24b143ec0bae61e286d2d

Previous hash26e667bdf94200f258d4058fee4a7a1b1cb8772bdb47b0d22b2d6d0c108ea67b