{
  "claim": "The speedup plotted in R4T's own Figure 5 ranges from 8.1x to 16.2x and falls below 12x at five of the eight batch sizes measured. The paper's prose reports \"a consistent 12x-20x speedup\"; the 20x end does not appear anywhere in the figure.",
  "method": "Figure 5 ships as a matplotlib SVG (arxiv.org/html/2603.06397v1/query_fanout_efficiency.svg). Every marker is a <path transform=\"matrix(1,0,0,-1,tx,ty)\"> at the data point and every gridline is a horizontal <path> at a labelled tick, so ty calibrated against the six main-axes gridlines (0-50 s) recovers the plotted value. The calibration reproduces the paper's own two stated autoregressive numbers exactly -- 1.456 s at batch 8 against its \"approximately 1.46 seconds\", and 49.77 s at batch 1024 against its \"nearly 50 seconds\" -- and the figure's zoom inset, an independent set of axes, returns the same four values for batches 8-64.",
  "source": "https://arxiv.org/html/2603.06397v1",
  "captured": "2026-09-18",
  "note": "The prose's two diffusion numbers do not match its own figure: it reports 0.07 s at batch 8 where the figure plots 0.090 s, and 4.21 s at batch 1024 where the figure plots 3.93 s. 1.46/0.07 = 20.9x is where the headline 20x comes from; 1.456/0.090 = 16.2x is what the figure supports. No hardware, serving stack or token budget is stated for either series, and the retrieval calls the autoregressive path has to make are not separated out.",
  "columns": [
    { "key": "batch", "label": "batch size", "align": "right" },
    { "key": "ar", "label": "autoregressive (s)", "align": "right" },
    { "key": "diff", "label": "diffusion (s)", "align": "right" },
    { "key": "speedup", "label": "speedup", "align": "right" },
    { "key": "band", "label": "inside claimed 12x-20x?" }
  ],
  "rows": [
    { "batch": 8, "ar": 1.456, "diff": 0.09, "speedup": "16.18x", "band": "yes" },
    { "batch": 16, "ar": 1.518, "diff": 0.098, "speedup": "15.49x", "band": "yes" },
    { "batch": 32, "ar": 1.652, "diff": 0.157, "speedup": "10.52x", "band": "no — below" },
    { "batch": 64, "ar": 1.852, "diff": 0.23, "speedup": "8.05x", "band": "no — below" },
    { "batch": 128, "ar": 5.632, "diff": 0.527, "speedup": "10.69x", "band": "no — below" },
    { "batch": 256, "ar": 11.448, "diff": 1.091, "speedup": "10.49x", "band": "no — below" },
    { "batch": 512, "ar": 24.531, "diff": 2.141, "speedup": "11.46x", "band": "no — below" },
    { "batch": 1024, "ar": 49.766, "diff": 3.93, "speedup": "12.66x", "band": "yes" }
  ]
}