{"database": "pub10", "table": "documents", "rows": [["brief: adjudicator.md", "# Adjudicator brief (pub-10 main run, v1.2, 27.10.2026)\n\nYou are the adjudicator (extraction-protocol.md \u00a72). An independent verifier has judged statements that two blind extraction runs produced. You rule on every item where the verifier did **not** simply confirm, and on every missed capability it proposed.\n\nWorking directory: `/home/bat/dev/phd`. For each application id you are given, read:\n- `data/business-apps/verification-prompt.md` \u2014 the rules both the verifier and you apply;\n- `data/business-apps/run/<id>/adjudication-input.json` \u2014 everything you rule on, prepared by script:\n  `items` (non-confirmed verdicts other than duplicates, with statement, excerpt, the verifier's correction and reason),\n  `duplicates` (each rejected statement next to the statement it duplicates),\n  `missed` (the verifier's proposed additions; `verbatimFound` says whether the script found the excerpt in the sources),\n  `confirmedStatements` (the surviving statements, to judge whether a missed item is already covered).\nOpen a source file (`data/business-apps/sources/<id>/<sourceFile>`) only when an excerpt's surrounding context is needed to decide; use `grep -n` around the excerpt rather than reading whole files. Do not read `candidates.json` or `verify.json`.\n\nRules for rulings:\n- For each verdict `corrected` or `rejected`: decide `final` = `confirmed`, `corrected` or `rejected`. If `corrected`, give the final `statement` (usually the verifier's correction). Give a one-sentence `reason`. Duplicates: confirm the rejection when the two statements describe the same capability; overturn it when they describe different capabilities.\n- For each missed item: `accepted` true or false with a `reason`. Accept only if it is a real capability, supported by its excerpt, not already covered by a surviving statement, and `verbatimFound` is true. Copy its `statement` (or your corrected statement) and `excerpt` into your output entry.\n- You may add a capability that **both** runs and the verifier missed, only if it is clearly advertised; give `foundBy: \"adjudicator\"`, a statement in one of the two forms and a verbatim excerpt.\n- If you genuinely cannot decide, put the item in `undecidable` with the question for the human owner. Use this sparingly.\n- Be consistent with these standing rulings: user-facing sign-in features are capabilities; testimonial-only evidence never counts; claims about an underlying platform are not capabilities of the app; marketing qualities are not capabilities.\n\nWrite `data/business-apps/run/<id>/adjudication.json` with the Write tool, exactly this shape:\n\n```json\n{\"appId\":\"F1-001\",\n \"rulings\":[{\"id\":\"F1-001-A003\",\"verifierVerdict\":\"rejected\",\"final\":\"rejected\",\"reason\":\"\u2026\"},\n            {\"id\":\"F1-001-B010\",\"verifierVerdict\":\"corrected\",\"final\":\"corrected\",\"statement\":\"The system \u2026\",\"reason\":\"\u2026\"}],\n \"missed\":[{\"statement\":\"The system \u2026\",\"excerpt\":\"<verbatim>\",\"accepted\":true,\"foundBy\":\"verifier\",\"reason\":\"\u2026\"}],\n \"duplicatesUpheld\":[\"F1-001-B004\"],\n \"undecidable\":[]}\n```\n\nDuplicates: most rejections are `duplicate of <id>` because two runs extracted the same capability. Check each pair; list every duplicate rejection you **uphold** in `\"duplicatesUpheld\":[\"<id>\", \u2026]` instead of writing a ruling for it. Write a ruling only for duplicates you overturn and for all other non-confirmed verdicts.\n\nEvery non-confirmed verdict must appear exactly once, either in `rulings` or in `duplicatesUpheld`. Do not include confirmed statements.\n\nFinal answer: one line per application, `<id> rulings=<n> overturned=<n> missed_accepted=<n>/<m> undecidable=<n>`. Nothing else.\n\n<!-- v1.2 (27.10.2026): reads the script-prepared adjudication-input.json instead of whole sources, to cut cost (protocol v1.5). -->\n"]], "columns": ["name", "text"], "primary_keys": ["name"], "primary_key_values": ["brief: adjudicator.md"], "units": {}, "query_ms": 1.705557107925415, "source": "Ahmed ElBatanony, Innopolis University", "license": "Not yet licensed \u2014 internal review only"}