{
 "_method": "Looked at a 1024-px contact sheet of all ten (selection/review/contact-1024.jpg), then one 768-px 1:1 crop of each at canvas (1664,640) beside the same rectangle of the category's real held-out reference field (selection/review/crop-NN.jpg), plus extra 1:1 spot checks at other canvas positions where a field looked uniform or a region looked odd. Written by a machine reviewer, not a pathologist; these are engineering observations about shapes and artefacts, not diagnoses.",
 "notes": {
  "1": "Groups of epithelial cells with pale granular cytoplasm and dark, mostly ovoid nuclei that in places form a single row along the edge of a cell group; small irregular clear spaces between the groups read as pit lumina rather than as open gland lumina. Between the groups a dense scatter of small round dark nuclei reads as inflamed lamina propria (stromal nuclear density 6229/mm2 against a real held-out 4588 - the only final that is above real on that axis). No surface epithelium in the crop; a wide pale lumen exists elsewhere on the canvas at (2475,0) and that is where the overlay put its rods. Spot-checked at (600,1300) and (3200,300): glands with granular pale cytoplasm, and a lymphocyte-rich field with small clear spaces. No tiling, no repeated motif, no seam (window-boundary column ratio 0.977 against an off-boundary null of 1.000). Against the real crop: the real field has one broad columnar band with a clean basal nuclear row, red cells in vessels and much finer fibrillar stroma; this one is more crowded and its epithelium is less polarised.",
  "2": "Long parallel gland profiles running down the crop with foamy vacuolated pale cytoplasm and a border row of dark nuclei, a scatter of small dark nuclei between them, and a few red cells. The vacuolation is coarser and more regular than the real crop's mucin - a soap-bubble texture rather than mucin droplets. Spot-checked at (400,300) and (2600,300): parallel glands, and a lumen with adjacent epithelium and a dense infiltrate. A large open pale surface space in the lower right is where the overlay placed its rods. No seam (1.020 vs null 1.016), no tiling.",
  "3": "Crowded epithelial cells with pale vacuolated cytoplasm and roughly one row of ovoid nuclei per group, a prominent cluster of red cells in the centre of the crop (a capillary or small haemorrhage), and small clear lumina at the lower edge. The stromal scatter is present but sparser than in images 01-02 (1637/mm2 against a real 4588), so the infiltrate that defines the category is thin. No seam (1.004 vs null 1.035) even though this canvas was assembled from many separate real donor fields.",
  "4": "Gland profiles with an open lumen at centre-right, cells with pale vacuolated cytoplasm and large ovoid nuclei carrying a visible nuclear membrane and pale chromatin, basally placed around each gland. The nuclei are larger and more vesicular than the real crop's. No goblet cell with a crisp single apical mucin vacuole is identifiable - the vacuolation is diffuse cytoplasmic, so the field reads as metaplastic-looking glandular tissue rather than as unambiguous intestinal metaplasia. No seams, no tiling.",
  "5": "Two or three gland cross-sections with a clear lumen, a wall about one cell thick with basally placed round-to-oval nuclei, and pale cytoplasm; a band of eosinophilic stroma crosses the middle of the crop; a small orange-brown clump at the left edge is either pigment or a red-cell aggregate. Reads clearly as glandular tissue rather than as sheets of cells. Same vesicular-nucleus criticism as image 04.",
  "6": "Glandular clusters with pale cytoplasm and about one row of nuclei per cluster, and between them a dense scatter of small dark round nuclei. The lower half of the crop has larger pale vacuolated cells with clearer nuclei. Both a glandular component and an inflammatory component are present in the same field, which is what the mixed category asks for. The overlay placed rods in a gland lumen at (443,348). No seam (0.987 vs null 1.033).",
  "7": "Glandular tissue with an inflammatory component. At 1024-px field scale the canvas has gland profiles with open lumina and columnar borders across the upper right and left, a broad pale mucus channel at the top centre with a columnar palisade along its left wall, a second pale channel at the bottom centre, and a red-cell (haemorrhagic) mass at the lower left. At 1:1 at (1664,640) the crop is solid cellular tissue: epithelial groups with pale vacuolated cytoplasm and dark ovoid nuclei, thin eosinophilic strands carrying spindle nuclei, small capillaries with red cells, and a scatter of small dark nuclei between the groups - a glandular and an inflammatory component in the same field, which is what the mixed category asks for. Unlike the a5 bag-diverse canvas this replaced, the field is not uniformly dense: (300,300) has a slit-like lumen and a dense nuclear cluster, (3100,1100) has pale vacuolated groups with clear spaces and a strong eosinophilic band, and the mosaic construction over 11 real fields shows as that variation. There is no clean columnar palisade in the (1664,640) crop itself and the nuclear membranes are softer than the real reference's, which carries crisp palisades and speckled chromatin. Detail 20.5 against a real mixed 22.8; infiltrate thin at 1603/mm2 against a real 3528. No seam, no tiling (boundary ratio 1.020 vs null 1.025).",
  "8": "The best-organised of the three normals and the only final with a real mucosal surface: an eosinophilic surface strand with empty slide above it at (200,120), a columnar band below it at (900,200), and beneath that gland profiles with clean lumina, one row of basal nuclei each, and capillaries carrying red cells at (2600,1400). At the standard crop position the field is a mass of pale foveolar-type cells with a gland lumen at the right and a row of dark nuclei down its wall. Stromal nuclear density 4520/mm2, the closest to real of the ten. No seam (1.012 vs null 1.035), no tiling. Its pale upper-left region is empty background above the tissue, not a mucus wash.",
  "9": "A uniform field of polygonal cells with fine granular pink cytoplasm, one small round dark nucleus each, and small round clear holes; plausible as oxyntic mucosa cut transversely. Checked at 1:1 at (300,300), (1664,640) and (3100,1100) - the same everywhere. That uniformity is the criticism: the whole canvas carries one texture, with no gland outlines, no stromal bands and no surface, so at field scale it reads as an even scatter of cells rather than as tissue with architecture. It is not a lattice and not a tiling: the cell outlines are irregular and the spacing is not periodic (boundary ratio 0.983 vs null 1.012).",
  "10": "Cohesive polygonal cells with granular pink-violet cytoplasm and one round-to-ovoid dark nucleus each, separated by thin eosinophilic strands carrying spindle nuclei, with frequent clusters of red cells reading as capillaries and very many small round clear holes spread evenly over the whole canvas. Those holes are the ring measurement: 0.985 of ring-detected objects have a lumen, above the real held-out normal ceiling of 0.976, and at 1:1 they are small intercellular openings rather than gland lumina with a bordering epithelial row - the over-production of openings that filter (2)'s upper bound exists to catch. Nuclear chromatin is speckled and the nuclear membranes are the crispest in the package (mean absolute Laplacian 23.7, the highest of the ten and the only one of the ten above its own category's real held-out median of 22.8), and stromal nuclear density is 5511/mm2, the highest of the three normals and 1300 above the real held-out normal median of 4211 - on this measure it overshoots, where the gastritis and mixed images all fall far short of their own categories' real levels. Checked at 1:1 at (300,300), (1664,640) and (3100,1100): the same texture everywhere - like image 09, the whole canvas carries one texture, with no gland outlines, no surface and no distinct lamina propria band. The cells are cohesive, so this is not the dissociated-cell failure that the three v2 normal_s14 canvases were rejected for on sight (section 4). Against the real held-out normal crop the difference is architecture, not detail: the real field has a red-cell-packed capillary, gland profiles with a basal nuclear row and definite gland walls. This canvas is also less architectural than the image it replaced - cartoon lumen IoU 0.269 against that image's 0.622 - so what the swap buys in envelope distance (7.12 -> 3.27) and detail (17.8 -> 23.7) it pays for in how much of the procedural drawing's layout survives. No seam (boundary ratio 0.938 vs null 1.001, the lowest of the ten and below the real gastritis field's 0.948; a seam would read above 1, not below)."
 },
 "overlay_notes": {
  "1": "Cluster at (2635,125), 6 rods of the 90 placed. At 2x, faint grey-violet curved rods 10-18 px long lie inside a pale pit lumen and along its epithelial rim, in the orientation the renderer intends (roughly parallel to the nearest dark surface). They read as an overlay rather than as objects in the mucus: every rod has the same colour and edge softness and none is partly obscured by mucus or out of focus.",
  "2": "Cluster at (3008,1943), 6 rods of 90. The rods sit in a wide open pale space beside a thin strand of epithelium. Several are far from any epithelial border - the renderer's band is measured to the nearest sub-228-brightness pixel, which here is a faint mucus wisp, so they read as free-floating in mucus rather than as surface-adherent.",
  "3": "Cluster at (545,1865), 6 rods of 78 placed (12 short of the 90 requested; the canvas has one large lumen component of 36187 px). At 2x, a gland lumen bordered by dark basal nuclei is filled with rods. The density inside this single lumen is high - visually more organisms per lumen than the other three.",
  "6": "Cluster at (603,508), 6 rods of 42 placed (48 short of 90; one large lumen component of 26121 px). Rods lie inside a gland lumen directly against the columnar epithelial border - the most convincing placement of the four, because the border is a clean palisade and the rods follow it.",
  "7": "Cluster at (1948,108), one of six anchors; 36 rods of the 90 requested were placed, all of them inside the canvas's single accepted bright component (21283 px, just over the renderer's 20000-px minimum), so all 36 sit in one 300x230-px region of the top centre and the rest of the canvas carries none. At 2x before and after (selection/review/overlay-2x-07.jpg) the before crop is a pale mucus channel bordered on the left by an eosinophilic epithelial strand with dark nuclei and on the right by a faint bluish mucus wisp; the after crop has about twenty curved rods scattered through it. A few lie within a few pixels of the left epithelial border, but most are in mid-channel, 20-40 px from any tissue - the same criticism as image 02, because the renderer measures its 2-14 px band to the nearest sub-228 brightness pixel and here that is the faint mucus wisp, not the epithelium. So they read as free in mucus rather than as surface-adherent. As in the other four, every rod has the same colour and edge softness, none is partly obscured or out of focus, and the thickness does not vary the way real bacilli do at 0.25 um/px: this reads as an overlay, and it is disclosed as one."
 },
 "_swaps_note": "SUBMIT-FIX, 9 September 2026: images 07 and 10 were replaced after review, so their notes below describe the new canvases and were written the same way - a 768-px 1:1 crop at (1664,640) beside the real held-out reference crop (selection/review/crop-07.jpg, crop-10.jpg), a 1024-px full view (selection/review/full-07.jpg, full-10.jpg) and 512-px 1:1 spot checks at (300,300), (1664,640) and (3100,1100) (selection/review/spotcheck-07.jpg, spotcheck-10.jpg). The notes for 01-06, 08 and 09 are unchanged from SUBMIT-SELECT.",
 "selection_notes": {
  "7": "SUBMIT-FIX swap. This image replaces `a5 bag-diverse mixed_s15_across` (D 3.01), which placed 0 organisms because its largest bright connected component was 9284 px against the organism renderer's 20000-px minimum, leaving one of the two mixed images with none. The replacement is the next mixed survivor with a usable surface, `a5 match-si3 mixed_s15_oblique` (survivor rank 7 of 12 by envelope D, one 21283-px component), at a cost of 0.49 in envelope D (3.01 -> 3.50) and 0.058 in copy margin (0.168 -> 0.110), and a gain of a more conservative token provenance (mosaic over 11 real fields, own-source 0.25, against bag over 24 fields, own-source 0.625). No filter was relaxed for this swap: the replacement passes all five hard filters and is inside the mixed band. The decision it rests on is that a mixed image must carry the procedural H. pylori overlay to represent its category, which outranks 0.49 of envelope distance; the cost is that the ten are no longer ranked strictly by D within the mixed category. Recorded in SELECTION.md, 'Two swaps made after review'.",
  "10": "SUBMIT-FIX swap, and the package's one relaxed filter. This image replaces `f3 B_si3_donor normal_s13_across` (D 7.12), which was admitted only by relaxing filter (1), the envelope band, by 2.78. The replacement `f3 B_si3_donor normal_s14_across` is inside the normal band at D 3.27 and fails only filter (2)'s upper ring bound, at ring 0.985 against a ceiling of 0.976 - the maximum of the four real held-out normal fields - so it overshoots that ceiling by 0.009. The decision is that a 0.009 overshoot of a four-field maximum is a weaker reason to exclude an image than a D of 7.12 is to include one. Relaxing only the ring ceiling (the floor of 0.671 is left in place) admits exactly two normal images, this one at D 3.27 and `f3 B_fromnoise normal_s14_across` at D 3.68, both seed s14; the D order and filter (4) then pick this one uniquely. Filter (4) still holds: the three normals are cartoon seeds s12 (08), s11 (09) and s14 (10). Filter (5) holds: pairwise SSIM of the three normals is under 0.75. What the swap costs is architecture - cartoon lumen IoU 0.269 against the replaced image's 0.622 - and it is the ring over-production that the eye check describes. Recorded in SELECTION.md, 'Two swaps made after review'."
 }
}