{"query":"Write Binary Rubrics","corpusVersion":"local","generatedAt":"2026-09-14T07:26:24.437Z","results":[{"blockId":"correctness.binary-rubrics#write-binary-rubrics","pageId":"correctness.binary-rubrics","title":"Write Binary Rubrics","pageTitle":"Write Binary Rubrics","url":"https://teammately.ai/docs/correctness-governance/binary-rubrics.md","humanUrl":"https://teammately.ai/docs/correctness-governance/binary-rubrics#write-binary-rubrics","markdownUrl":"https://teammately.ai/docs/correctness-governance/binary-rubrics.md","sectionId":"write-binary-rubrics","kind":"task","productArea":"correctness_governance","score":2439.4066909948688,"reasons":["search_match","title_match","display_title_match","term_match","prefix_or_fuzzy_match"],"markdown":"# Write Binary Rubrics\n\nWrite a rubric when a governed policy needs an observable pass-or-fail check for benchmark evaluation. A strong rubric identifies one behavior, the cases where it applies, and the evidence that distinguishes pass from fail."},{"blockId":"correctness.binary-rubrics#steps","pageId":"correctness.binary-rubrics","title":"Steps","pageTitle":"Write Binary Rubrics","url":"https://teammately.ai/docs/correctness-governance/binary-rubrics.md","humanUrl":"https://teammately.ai/docs/correctness-governance/binary-rubrics#steps","markdownUrl":"https://teammately.ai/docs/correctness-governance/binary-rubrics.md","sectionId":"steps","kind":"task","productArea":"correctness_governance","score":733.0511109869378,"reasons":["search_match","page_title_match","term_match","prefix_or_fuzzy_match"],"markdown":"## Steps\n\n1. State one behavior that can be inspected in the candidate response and visible case evidence.\n2. Name the policy or specialist judgment that authorizes the criterion.\n3. Define applicability before writing exceptions into the pass condition.\n4. Write explicit pass evidence and fail evidence. Avoid “good,” “appropriate,” or “high quality” without observable conditions.\n5. Link representative cases and test whether two informed reviewers would reach the same binary result.\n6. Split independent requirements into separate rubrics when each failure should be diagnosed separately.\n7. Inspect contribution provenance and approval state before relying on the rubric in benchmark interpretation."},{"blockId":"correctness.binary-rubrics#related-reference-pages","pageId":"correctness.binary-rubrics","title":"Related reference pages","pageTitle":"Write Binary Rubrics","url":"https://teammately.ai/docs/correctness-governance/binary-rubrics.md","humanUrl":"https://teammately.ai/docs/correctness-governance/binary-rubrics#related-reference-pages","markdownUrl":"https://teammately.ai/docs/correctness-governance/binary-rubrics.md","sectionId":"related-reference-pages","kind":"task","productArea":"correctness_governance","score":696.4339172719014,"reasons":["search_match","page_title_match","term_match"],"markdown":"## Related reference pages\n\n{% related-card-grid title=\"Related reference pages\" %}\n- [Policies and Rubrics](/docs/correctness-governance/policies-and-rubrics)\n- [Applicability Logic](/docs/object-model/applicability-logic)\n- [Rubrics](/docs/object-model/rubrics)\n{% /related-card-grid %}"},{"blockId":"correctness.binary-rubrics#related-troubleshooting-pages","pageId":"correctness.binary-rubrics","title":"Related troubleshooting pages","pageTitle":"Write Binary Rubrics","url":"https://teammately.ai/docs/correctness-governance/binary-rubrics.md","humanUrl":"https://teammately.ai/docs/correctness-governance/binary-rubrics#related-troubleshooting-pages","markdownUrl":"https://teammately.ai/docs/correctness-governance/binary-rubrics.md","sectionId":"related-troubleshooting-pages","kind":"task","productArea":"correctness_governance","score":694.6382968548734,"reasons":["search_match","page_title_match","term_match"],"markdown":"## Related troubleshooting pages\n\n{% related-card-grid title=\"Related troubleshooting pages\" %}\n- [Overlapping rubrics](/docs/troubleshooting/overlapping-rubrics)\n- [Weak applicability logic](/docs/troubleshooting/weak-applicability-logic)\n- [Low expert agreement](/docs/troubleshooting/low-expert-agreement)\n{% /related-card-grid %}"},{"blockId":"correctness.binary-rubrics#prerequisites","pageId":"correctness.binary-rubrics","title":"Prerequisites","pageTitle":"Write Binary Rubrics","url":"https://teammately.ai/docs/correctness-governance/binary-rubrics.md","humanUrl":"https://teammately.ai/docs/correctness-governance/binary-rubrics#prerequisites","markdownUrl":"https://teammately.ai/docs/correctness-governance/binary-rubrics.md","sectionId":"prerequisites","kind":"task","productArea":"correctness_governance","score":691.2603195073814,"reasons":["search_match","page_title_match","term_match"],"markdown":"## Prerequisites\n\n- A policy or expert-grounded correctness statement.\n- Representative passing, failing, and boundary cases.\n- Clear applicability for the behavior being checked.\n- Access to Correctness Governance → Rubrics."},{"blockId":"correctness.binary-rubrics#source-confidence","pageId":"correctness.binary-rubrics","title":"Source confidence","pageTitle":"Write Binary Rubrics","url":"https://teammately.ai/docs/correctness-governance/binary-rubrics.md","humanUrl":"https://teammately.ai/docs/correctness-governance/binary-rubrics#source-confidence","markdownUrl":"https://teammately.ai/docs/correctness-governance/binary-rubrics.md","sectionId":"source-confidence","kind":"task","productArea":"correctness_governance","score":682.4050757122687,"reasons":["search_match","page_title_match","term_match","prefix_or_fuzzy_match"],"markdown":"## Source confidence\n\nCode-backed: the active Correctness Governance rubric list and detail surfaces support rubric inspection, relationships, and lifecycle context. The drafting guidance is constrained to those verified artifact boundaries."},{"blockId":"correctness.binary-rubrics#common-failure-modes","pageId":"correctness.binary-rubrics","title":"Common failure modes","pageTitle":"Write Binary Rubrics","url":"https://teammately.ai/docs/correctness-governance/binary-rubrics.md","humanUrl":"https://teammately.ai/docs/correctness-governance/binary-rubrics#common-failure-modes","markdownUrl":"https://teammately.ai/docs/correctness-governance/binary-rubrics.md","sectionId":"common-failure-modes","kind":"task","productArea":"correctness_governance","score":682.393697563342,"reasons":["search_match","page_title_match","term_match","prefix_or_fuzzy_match"],"markdown":"## Common failure modes\n\n- Combining several behaviors into one criterion.\n- Restating the policy without defining observable evidence.\n- Encoding applicability only as exceptions inside the rubric.\n- Using a suggested or contributed draft as if it were already governed.\n- Changing rubric wording and comparing Runs without checking the benchmark version boundary.\n\n{% example-demo title=\"Example: grounding rubric\" %}\nPolicy: material claims must use the controlling source or state uncertainty. Rubric: pass only when every material claim is supported by the current controlling source, or the response explicitly says the available sources do not resolve the claim. Unsupported blending of current and superseded sources fails.\n{% /example-demo %}"},{"blockId":"correctness.binary-rubrics#object-and-state-changes","pageId":"correctness.binary-rubrics","title":"Object and state changes","pageTitle":"Write Binary Rubrics","url":"https://teammately.ai/docs/correctness-governance/binary-rubrics.md","humanUrl":"https://teammately.ai/docs/correctness-governance/binary-rubrics#object-and-state-changes","markdownUrl":"https://teammately.ai/docs/correctness-governance/binary-rubrics.md","sectionId":"object-and-state-changes","kind":"task","productArea":"correctness_governance","score":682.0992223843464,"reasons":["search_match","page_title_match","term_match","prefix_or_fuzzy_match"],"markdown":"## Object and state changes\n\nThis task creates or updates a project-level rubric and can change its wording, policy relationship, linked cases, evaluation use, activity, and approval context. Linking a case does not add it to a benchmark dataset. Editing a rubric does not alter historical Run evidence that used an earlier benchmark boundary."}]}