AI review — page 8

claude-opus-4-8 · prompt v7 · 2026-09-04T15:08:30+00:00 · applied: yes · changed: yes

Screenshot sent to the model (reading-order tags burned on)

Instructions (system prompt)

The screenshot has annotations burned onto it that are NOT part of the document:
- a small red numbered tag at the top-left corner of each item, showing that item's position in the OCR-determined reading order (the same order the items appear in the json data);
- a red-and-white dotted outline around each item, showing the area the OCR detected for that content block.
Use the tags and outlines to see the detected reading order and item boundaries directly on the page, and judge that sequence against how a human would naturally read it. Ignore the annotations when checking text fidelity — they overlay the content, they are not content.

For the given screenshot of a PDF's page and the attached json data, I want you to perform the following tasks in order...

Review the reading order set out in the json data and compare to what a natural reading order for that of a human would be by looking at the screenshot. Decide on any changes and re-arrange the items for the most logical reading order.
Look at all text for each item and correct any extraction errors like missing words, spelling mistakes etc.
Look at each item in the JSON and ensure that the OCR process has identified the item as the correct type: text, list item etc.
Look for any text that duplicates: if two items next to each other contain the exact same text but the text only appears once on the screenshot, one of them is an extraction error — keep the item whose box matches where the text is visible and flag the other for removal.
Make amendments as you proceed through the items and list of instructions.
Reading Order Advice: If there is columns with headings and text, I wouldnt expect the reading order to jump from one heading straight to another if there is text associated with that heading.

Return format: Give me the json data back only, with the amendments you make.

Mechanical notes (so your answer can be applied automatically):
- Each item has an `id` — keep every item and its `id` exactly as given; never invent, drop or duplicate ids. Re-arranging means changing the position of items (and their nesting) in the arrays.
- Never move text (or a type) from one item to another: each item's coordinates travel with its id, so to change reading order you must move the whole item object, and text amendments must be in-place corrections of that item's own text.
- To flag a duplicate item, keep it in the array and add `"remove": "duplicate"` to it — never just delete it (deleted items are restored automatically).
- ids are opaque labels, not sequence numbers: never renumber them. After a removal or re-arrangement, every remaining item keeps the exact id it came with, even if the ids no longer look sequential.
- Text may contain `[pN.M…]` placeholders marking where an inline formula belongs — treat them as part of the text and leave them exactly where they are.
- `box` is [left, top, right, bottom] as percentages of the page from the top-left corner; return it unchanged.
- Respond with raw JSON only: no code fences, no commentary, same shape as the input (`{"items": [...]}`).

User message (json data sent)

Page 8 json data:

{"items":[{"id":"p8.1","type":"text","box":[12,11,88,15],"text":"This also highlights how lottery participation increases engagement among older age groups."},{"id":"p8.2","type":"heading","box":[12,19,48,21],"text":"2.2 Popular Gambling Activities"},{"id":"p8.3","type":"text","box":[12,21,67,23],"text":"The most common forms of gambling in Great Britain remain:"},{"id":"p8.4","type":"list","box":[15,24,74,32],"text":"","children":[{"id":"p8.4.1","type":"list_item","box":[15,24,66,26],"text":"• National Lottery draws (highest participation product)"},{"id":"p8.4.2","type":"list_item","box":[15,27,38,29],"text":"Other charity lotteries"},{"id":"p8.4.3","type":"list_item","box":[15,30,74,32],"text":"- Instant-win games and betting products as secondary activities"}]},{"id":"p8.5","type":"text","box":[12,33,76,34],"text":"These patterns remain consistent across GSGB's rolling wave releases."},{"id":"p8.6","type":"heading","box":[12,38,45,40],"text":"2.3 Motivations for Gambling"},{"id":"p8.7","type":"text","box":[12,41,73,43],"text":"The most common reasons for adults to participate in gambling are:"},{"id":"p8.8","type":"list","box":[15,44,60,52],"text":"","children":[{"id":"p8.8.1","type":"list_item","box":[15,44,60,46],"text":"- the chance of winning big money (85 percent),"},{"id":"p8.8.2","type":"list_item","box":[15,46,52,48],"text":"• because gambling is fun (72 percent),"},{"id":"p8.8.3","type":"list_item","box":[15,48,44,50],"text":"• to make money (57 percent)"},{"id":"p8.8.4","type":"list_item","box":[15,50,51,52],"text":"• because it was exciting (56 percent)."}]},{"id":"p8.9","type":"text","box":[12,53,88,56],"text":"This is consistent with the previous year and reflect the emotionally driven aspects of gambling behaviour."},{"id":"p8.10","type":"heading","box":[12,60,55,62],"text":"2.4 Gambling-Related Risks and Harm"},{"id":"p8.11","type":"heading","box":[12,63,72,65],"text":"2.4.1 Problem Gambling Severity Index (PGSI) Scores"},{"id":"p8.12","type":"text","box":[12,67,87,77],"text":"The Problem Gambling Severity Index (PGSI) is used to measure both behavioural symptoms of gambling disorder and certain adverse consequences from gambling. The PGSI consists of 9 items that are rated on a 4 point-scale. The PGSI categories represent a continuum of risk, ranging from those experiencing no adverse consequences or behavioural symptoms of disorder to those experiencing both."},{"id":"p8.13","type":"text","box":[12,78,59,80],"text":"Using the Problem Gambling Severity Index (PGSI):"},{"id":"p8.14","type":"text","box":[12,80,84,85],"text":"2.7% of adults score 8+, placing them in the high-risk/problem gambling category\nHigher-risk groups include:"},{"id":"p8.15","type":"list","box":[15,86,35,90],"text":"","children":[{"id":"p8.15.1","type":"list_item","box":[15,86,22,88],"text":"• Men"},{"id":"p8.15.2","type":"list_item","box":[15,88,35,90],"text":"• Adults aged 18–34"}]},{"id":"p8.16","type":"footer","box":[49,93,51,94],"text":"7"}]}