{
 "figure": "long_context",
 "plotted": [
  {
   "length_bin": 1024,
   "items": 320,
   "controlled_pct": 57.81,
   "ci95_pct": [
    52.34,
    63.1
   ]
  },
  {
   "length_bin": 2048,
   "items": 320,
   "controlled_pct": 54.69,
   "ci95_pct": [
    49.21,
    60.05
   ]
  },
  {
   "length_bin": 4096,
   "items": 320,
   "controlled_pct": 58.13,
   "ci95_pct": [
    52.65,
    63.4
   ]
  },
  {
   "length_bin": 8192,
   "items": 320,
   "controlled_pct": 54.37,
   "ci95_pct": [
    48.9,
    59.75
   ]
  },
  {
   "length_bin": 12288,
   "items": 320,
   "controlled_pct": 54.37,
   "ci95_pct": [
    48.9,
    59.75
   ]
  },
  {
   "length_bin": 16384,
   "items": 320,
   "controlled_pct": 54.69,
   "ci95_pct": [
    49.21,
    60.05
   ]
  },
  {
   "length_bin": 24576,
   "items": 1280,
   "controlled_pct": 55.31,
   "ci95_pct": [
    52.58,
    58.02
   ]
  }
 ],
 "reference_controlled_2k_4k_pct": 56.41,
 "gap_24k_vs_ref_pts": -1.09,
 "spread_all_bins_pts": 3.75,
 "claim_25k_ok": true,
 "a_gap_ok": true,
 "b_deciles_ok": true,
 "c_controls_ok": true,
 "verified_length_bin": 4096,
 "caution": "verified_length_bin = 4096: the stricter every-bin (8K-16K) decile criterion fails in some deciles; the card may say 'preregistered 25K claim passed' but not 'verified at every length'",
 "controlled_24k_by_decile": {
  "0": 0.5234375,
  "1": 0.515625,
  "2": 0.546875,
  "3": 0.5390625,
  "4": 0.5546875,
  "5": 0.5546875,
  "6": 0.5703125,
  "7": 0.5625,
  "8": 0.5390625,
  "9": 0.625
 },
 "controls_pooled_by_length": {
  "1024": {
   "question_only": {
    "n": 320,
    "accuracy": 0.290625,
    "chance": 0.28003348214285717,
    "p_above_chance": 0.3511374281963401,
    "at_chance": true
   },
   "state_swap": {
    "n": 320,
    "accuracy": 0.315625,
    "chance": 0.28003348214285717,
    "p_above_chance": 0.07484199516389486,
    "at_chance": true
   }
  },
  "2048": {
   "question_only": {
    "n": 320,
    "accuracy": 0.2875,
    "chance": 0.28029017857142857,
    "p_above_chance": 0.40558180434986946,
    "at_chance": true
   },
   "state_swap": {
    "n": 320,
    "accuracy": 0.303125,
    "chance": 0.28029017857142857,
    "p_above_chance": 0.18406466252955953,
    "at_chance": true
   }
  },
  "4096": {
   "question_only": {
    "n": 320,
    "accuracy": 0.253125,
    "chance": 0.28010044642857146,
    "p_above_chance": 0.8864307901965104,
    "at_chance": true
   },
   "state_swap": {
    "n": 320,
    "accuracy": 0.29375,
    "chance": 0.28010044642857146,
    "p_above_chance": 0.304486548332512,
    "at_chance": true
   }
  },
  "8192": {
   "question_only": {
    "n": 320,
    "accuracy": 0.28125,
    "chance": 0.28131324404761904,
    "p_above_chance": 0.5273741085290076,
    "at_chance": true
   },
   "state_swap": {
    "n": 320,
    "accuracy": 0.284375,
    "chance": 0.28131324404761904,
    "p_above_chance": 0.4747527191420883,
    "at_chance": true
   }
  },
  "12288": {
   "question_only": {
    "n": 320,
    "accuracy": 0.278125,
    "chance": 0.2804017857142857,
    "p_above_chance": 0.5644923218252806,
    "at_chance": true
   },
   "state_swap": {
    "n": 320,
    "accuracy": 0.284375,
    "chance": 0.2804017857142857,
    "p_above_chance": 0.4593971620159274,
    "at_chance": true
   }
  },
  "16384": {
   "question_only": {
    "n": 320,
    "accuracy": 0.265625,
    "chance": 0.28533854166666667,
    "p_above_chance": 0.8139517721332229,
    "at_chance": true
   },
   "state_swap": {
    "n": 320,
    "accuracy": 0.28125,
    "chance": 0.28533854166666667,
    "p_above_chance": 0.5936977453471026,
    "at_chance": true
   }
  },
  "24576": {
   "question_only": {
    "n": 1280,
    "accuracy": 0.2890625,
    "chance": 0.2837481398809524,
    "p_above_chance": 0.33937799270227736,
    "at_chance": true
   },
   "state_swap": {
    "n": 1280,
    "accuracy": 0.28515625,
    "chance": 0.2837481398809524,
    "p_above_chance": 0.4658977510199284,
    "at_chance": true
   }
  }
 },
 "laya_budgets": {
  "laya_english": 512,
  "laya_multilingual": 1024,
  "laya_typed_decisions": 1024,
  "source": "third_party/laya/README.md lines 366-368 (defaults); models/laya-official/.../multilingual/rl_agent_config.json max_len 1024"
 },
 "v3_context_tokens": 25600,
 "sources": [
  "runs/macjev/received/own_evals/main/test.own/long_grid_plus.jsonl + runs/macjev/received/own_evals/main/temperatures.json via macjev.eval.aggregate.suite_metrics('long_grid_plus') (recomputed); matches runs/macjev/report_r2/scoreboard/scoreboard.json long_grid_plus",
  "chart_data.json#long_grid_plus.bins"
 ],
 "protocol_label": "v3 only (Laya cannot run >4K; not applicable). Controlled = real row correct AND question_only + state_swap controls pass; Wilson CI; 2K-4K reference; preregistered 2026-09-24, amended pre-data (+96 items per 24K decile, thresholds unchanged)",
 "footnote": "v3 only. Laya's default input budget is 512 tokens (English) / 1,024 (multilingual, typed) per the Laya README;\nlonger rows exceed Laya's default budgets, so Laya is not plotted. Suite long_grid_plus: preregistered 2026-09-24, amended pre-data\n(+96 items per 24K depth decile, thresholds unchanged); 320 items per bin, 1,280 at 24K. Controlled accuracy = real-state\nanswer correct AND its question-only and state-swap controls pass; both controls are at chance in every length bin.\n25K claim rule: |24K \u2212 2K\u20134K reference| \u2264 5 pts and every 24K evidence-depth decile within 10 pts of it.\nPlotted values: figures/long_context.json (bin-level controlled accuracy and CIs)."
}