Ledger / Prediction #2378 · narrative · 1H

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

GENESIS said 75% → ACCELERATES INCORRECT

What GENESIS knew, before

55 of 2297 launches in the last hour referenced "shadow" (22 distinct creators, rank #7). Last 15m momentum 4.39×.

Made2026-10-12 14:00 UTC

Resolves2026-10-12 15:00 UTC

Evidence cutoff2026-10-12 13:59 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": 0.35968429091975557,
      "momentum": 1.4783027740876589,
      "diversity": -0.42
    },
    "rawProbability": 0.753615146810697
  },
  "features": {
    "term": "shadow",
    "rank60": 7,
    "share15": 0.10591603053435114,
    "share60": 0.024151436031331592,
    "total15": 523,
    "total60": 2297,
    "momentum": 4.385496183206107,
    "diversity": 0.4,
    "launches15": 55,
    "launches60": 55,
    "contextMinutes": 60,
    "uniqueCreators60": 22
  },
  "extractor": "terms-v2",
  "selection": "top-volume",
  "candidates": 290,
  "calibration": null,
  "methodology": "attention-v1",
  "termHistory": null,
  "contextCoverage": 0.9948661111111111,
  "memoriesRecalled": 0,
  "priorWindowCoverage": 0.9948661111111111
}

Expected

{
  "direction": "up",
  "magnitude": null,
  "magnitudeNote": "v0 does not model magnitude",
  "probabilityUp": 0.753615146810697
}

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 15:03 UTC

StatusSCORED

OutcomeFADED

ClassificationINCORRECT

Brier0.568

Log loss1.401

Graderjudge-v1

Outcome data

{
  "shareAfter": 0.002277904328018223,
  "shareRatio": 0.10231635810383438,
  "totalAfter": 2634,
  "shareBefore": 0.023902651021295088,
  "totalBefore": 2301,
  "coverageAfter": 1,
  "launchesAfter": 6,
  "coverageBefore": 1,
  "launchesBefore": 55
}

Post-outcome analysis · judge-v1

Predicted 75% that "shadow" would gain share over 1H. Its share of launches moved 2.39% → 0.23% (-90%). INCORRECT.

— momentum misled on "shadow" (1H). momentum contributed +1.48 to the log-odds toward yes; reality was no.

— Overconfident: 75% and wrong on "shadow". 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

Hashdbd50b8a5e52a80f0537be08b4757f552437e1e209277b83e1c81249536d5c3d

Previous hash328105f2c8b02d32848432c22a05db5423b7df0ac1468751c94271a4ceb50c30