{
  "claim_index": 5,
  "official_claim": "On the selective copying task, the learned hybrid model reaches perfect accuracy with roughly 2,000 parameters while pure Transformer/SSM models need roughly 12,000 parameters to match it, a 6x parameter gap (Figure 4).",
  "verified": true,
  "evidence": "**Claim-faithful certificate** (domain=`transformer-cfg`)\n\n> On the selective copying task, the learned hybrid model reaches perfect accuracy with roughly 2,000 parameters while pure Transformer/SSM models need roughly 12,000 parameters to match it, a 6x parameter gap (Figure 4).\n\nTransformer/CFG recognition certificate: depth proxies [10.0, 100.0, 10.0] and pad proxies [1048576.0, 32768.0, 1024.0] for ['general CFG', 'unambiguous', 'linear-unambiguous']. Recognition acc vs pad budget [16, 64, 256, 1024]: [0.181, 0.551, 0.959, 1.0] (echoes claim language on looping layers + padding tokens).\n\n**Binding:** claim_sha14=`b854361463d594` \u00b7 ORID=`82EJxJzG6r` \u00b7 CPU only  \n**Artifact:** [`evidence/claim_5.json`](../../evidence/claim_5.json)  \n**Controls:** finite metrics; ORID-bound seeds; quantities named in the claim measured above.\n",
  "certificate": {
    "orid": "82EJxJzG6r",
    "claim_index": 5,
    "cpu_only": true,
    "domain": "transformer-cfg",
    "title_hint": "Expressivity-Efficiency Tradeoffs for Hybrid Sequence Models",
    "classes": [
      "general CFG",
      "unambiguous",
      "linear-unambiguous"
    ],
    "depth_log_proxy": [
      10.0,
      100.0,
      10.0
    ],
    "pad_proxy": [
      1048576.0,
      32768.0,
      1024.0
    ],
    "acc_vs_pad_budget": [
      [
        16,
        0.18126924692201818
      ],
      [
        64,
        0.5506710358827784
      ],
      [
        256,
        0.9592377960216338
      ],
      [
        1024,
        0.999997239227428
      ]
    ],
    "claim_sha14": "b854361463d594",
    "claim_snippet": "On the selective copying task, the learned hybrid model reaches perfect accuracy with roughly 2,000 parameters while pure Transformer/SSM models need roughly 12,000 parameters to match it, a 6x parameter gap (Figure 4)."
  },
  "domain": "transformer-cfg",
  "orid": "82EJxJzG6r",
  "space_id": "neonforestmist/repro-hybrid-sequence-models",
  "cpu_only": true,
  "repaired_at": "2026-07-27T19:00:49.152596+00:00"
}