{
  "title": "Engram Hypotheses",
  "description": "Candidate, AI-surfaced hypotheses: grounded, sourced, cross-model verified.",
  "site": "https://engram-hypotheses.vercel.app",
  "count": 1,
  "hypotheses": [
    {
      "slug": "ann-snn-conversion-temporal-alignment",
      "url": "https://engram-hypotheses.vercel.app/h/ann-snn-conversion-temporal-alignment/",
      "headline": "The accuracy lost converting a network to spikes may be a clock problem, not a hard limit",
      "idea": "The latency and accuracy gap introduced when an artificial neural network is converted to a spiking neural network may track a single quantity, how well spike-train firing rates are temporally aligned across layers, rather than being an irreducible cost of spiking, suggesting the gap is a synchronization artifact, not a fundamental limit.",
      "prediction": "If the gap is alignment-driven, then explicitly phase-aligning per-layer spike windows during conversion should recover converted-SNN accuracy toward the source ANN with fewer timesteps, and the residual error should correlate with a measurable cross-layer timing-jitter metric.",
      "a": "ANN-to-SNN conversion",
      "b": "temporal alignment",
      "via": "firing rate",
      "topic": "neuromorphic computing",
      "date": "2026-06-04",
      "testable": true,
      "verdict": "kept",
      "sources": [
        "https://openalex.org/W2964081807",
        "https://openalex.org/W2787136860"
      ]
    }
  ]
}