{
  "paper": {
    "num": 19,
    "title": "When Engagement Is Not Enough: What Should AI Optimize in Gamified Education?",
    "authors": "Takuji Takemoto",
    "affiliation": "University of Fukui"
  },
  "inputs": {
    "weights E/L/B/P": "0.25 / 0.25 / 0.25 / 0.25",
    "retention (assumed)": 0.5,
    "affect\u2013learning corr.": 0.0,
    "engagement scale top": 7.0,
    "n Case 1": 49,
    "n Case 2": 37,
    "seed": 3,
    "data": "synthetic, calibrated to the paper"
  },
  "tiles": [
    {
      "label": "Winner under your weights",
      "value": "Gamified",
      "sub": "in 55% of 4,000 bootstrap resamples (Case 1, composite +0.017)",
      "tone": "accent"
    },
    {
      "label": "Decision flips at",
      "value": "51% on L",
      "sub": "you put 50% on learning vs engagement; 50% of your weight is on outcomes Case 1 never measured",
      "tone": "neutral"
    },
    {
      "label": "Engagement as a proxy",
      "value": "43%",
      "sub": "of the top-third knowledge gainers found by watching engagement (chance 33%; 23% of learners hit the ceiling)",
      "tone": "warn"
    },
    {
      "label": "Same game, two verdicts",
      "value": "3.68 vs 0.03",
      "sub": "Case 2 standardized effect: engagement vs behavioural intention",
      "tone": "neutral"
    }
  ],
  "figures": [
    {
      "path": "fig_case1_effects.png",
      "title": "Case 1: which condition is 'better' depends on the outcome",
      "caption": "Grey = the paper's d_z and 95% CI. Coloured = this run's synthetic learners (generated so the sample d_z match exactly) with bootstrap CIs. Blue = engagement-type outcomes (E), orange = learning (L)."
    },
    {
      "path": "fig_flip.png",
      "title": "Where does the decision flip?",
      "caption": "Probability that the gamified condition comes out ahead as the weight moves from engagement to learning. The star is your weighting (B and P weights dropped: Case 1 did not measure them)."
    },
    {
      "path": "fig_proxy.png",
      "title": "Case 2: can an AI find who learned by watching engagement?",
      "caption": "Left: one synthetic cohort, engagement vs perceived-knowledge gain (note the pile-up at the scale top). Right: share of the top-third gainers that a system ranking learners by engagement would pick, by how strongly engagement tracks gains (300 synthetic cohorts per point)."
    },
    {
      "path": "fig_case2_classes.png",
      "title": "Case 2: one intervention, four 'success' numbers",
      "caption": "Standardized effects from the paper's reported numbers. Persistence is not measured yet (T2 ongoing): the hatched bar is your retention assumption times the learning effect."
    }
  ],
  "compare": [
    {
      "metric": "Case 1 d_z: Interest",
      "paper": "0.64 [0.35, 0.92]",
      "yours": "0.64 [0.34, 1.05]",
      "note": "synthetic, n = 49"
    },
    {
      "metric": "Case 1 d_z: Enjoyment of interaction",
      "paper": "0.61 [0.32, 0.89]",
      "yours": "0.61 [0.33, 0.94]",
      "note": "synthetic, n = 49"
    },
    {
      "metric": "Case 1 d_z: Overall enjoyment",
      "paper": "0.50 [0.21, 0.78]",
      "yours": "0.50 [0.22, 0.82]",
      "note": "synthetic, n = 49"
    },
    {
      "metric": "Case 1 d_z: Acquisition of new expressions",
      "paper": "-0.55 [-0.84, -0.27]",
      "yours": "-0.55 [-0.90, -0.28]",
      "note": "synthetic, n = 49"
    },
    {
      "metric": "Case 2 knowledge T0 \u2192 T1 (d_z)",
      "paper": "4.37 \u2192 5.45 (d_z = 1.53)",
      "yours": "4.37 \u2192 5.44 (d_z = 1.53)",
      "note": "calibrated"
    },
    {
      "metric": "Case 2 competence T0 \u2192 T1 (d_z)",
      "paper": "4.07 \u2192 5.49 (d_z = 1.99)",
      "yours": "4.07 \u2192 5.48 (d_z = 1.99)",
      "note": "calibrated"
    },
    {
      "metric": "Case 2 intention T0 \u2192 T1 (d_z)",
      "paper": "5.97 \u2192 6.00 (d_z = 0.03)",
      "yours": "5.97 \u2192 6.00 (d_z = 0.03)",
      "note": "calibrated"
    },
    {
      "metric": "r(engagement, gain): knowledge / intention / competence",
      "paper": "r \u2248 .24 / .26 / .05",
      "yours": "0.17 / 0.24 / -0.01",
      "note": "one synthetic cohort, engagement scale 1\u20137"
    },
    {
      "metric": "Persistence (T2)",
      "paper": "T2 is ongoing; at present, persistence cannot yet be established",
      "yours": "assumed retention 0.5",
      "note": "your assumption, not data"
    }
  ],
  "runbook": {
    "name": "smash-19-engagement-not-enough",
    "url": ""
  }
}