Files
Marius CiepluchandClaude Opus 4.8 9a3250f6c5 fix(corpus): advisory-pair repo-overlap -- remove real pilot leaks, skip vendored trees
test_no_pair_repeats_a_repository_the_benchmarks_already_name failed: advisory-fix
catalog repos also appeared elsewhere under benchmarks/. Root cause split two ways:

1. Genuine leak: 16 catalog repos are also subjects in benchmarks/search/private/
   pilot.json (a real private pilot population). Removed those 16 pairs from the
   three catalogs and their verification.json rows (totals recomputed, catalog ==
   verification preserved).
2. Spurious: the overlap scan greped ~49k vendored files under
   benchmarks/search/private/runs/*/checkout/node_modules/, so any catalog repo a
   vendored dependency's README names collided. Added a narrow vendored-tree skip
   (node_modules/vendor) to the scan rather than deleting labelled pairs over a
   dependency mention.

Implemented from Codex's first pass (gpt-6.1-sol), then gated and corrected: Codex
removed 20 pairs; 4 of those (backstage/backstage, koajs/koa, beaugunderson/
ip-address, cakephp/cakephp) were driven only by vendored/non-population mentions
and are kept. Also excluded advisory-fixes-spread.json (catalog-derived report)
and research-2026-09-26.md (selection write-up) as non-population.

tests/test_advisory_fix_pairs.py + tests/test_learn_labels.py: 53 passed.

Co-Authored-By: Claude Opus 4.8 <[email protected]>
2026-10-12 15:22:55 +02:00

477 lines
9.8 KiB
JSON

{
"pairs": [
{
"name": "prefect-token-validation-e216171",
"ok": true,
"bytes_read": 3697
},
{
"name": "arcadedb-getdatabasegroupsconfiguration-04110c0",
"ok": true,
"bytes_read": 3896
},
{
"name": "langflow-get-flow-by-id-or-endpoint-name-2c9f498",
"ok": true,
"bytes_read": 3948
},
{
"name": "grav-plugin-api-update-26f529c",
"ok": true,
"bytes_read": 5598
},
{
"name": "google-maps-mcp-main-00d8725",
"ok": true,
"bytes_read": 3371
},
{
"name": "camofox-mcp-createmcphttpapp-599f56e",
"ok": true,
"bytes_read": 5587
},
{
"name": "spring-graphql-isoverridefor-63a89ed",
"ok": true,
"bytes_read": 2045
},
{
"name": "jenkins-dofilltimezonenameitems-0586de4",
"ok": true,
"bytes_read": 2093
},
{
"name": "netlicensing-mcp-dispatch-fbbb1d5",
"ok": true,
"bytes_read": 2610
},
{
"name": "starlette-admin-validate-where-af05b45",
"ok": true,
"bytes_read": 2061
},
{
"name": "next-auth-initauth-d008b9b",
"ok": true,
"bytes_read": 8193
},
{
"name": "deepseek-mcp-server-starthttptransport-dab07ed",
"ok": true,
"bytes_read": 2394
},
{
"name": "network-ai-routerequest-a59c13a",
"ok": true,
"bytes_read": 5945
},
{
"name": "device-builder-parse-args-9e294f7",
"ok": true,
"bytes_read": 15243
},
{
"name": "typespec-start-30d6f65",
"ok": true,
"bytes_read": 2109
},
{
"name": "tomcat-findsecurityconstraints-8bafd79",
"ok": true,
"bytes_read": 18199
},
{
"name": "vm2-makebuiltinsfromlegacyoptions-b0f5066",
"ok": true,
"bytes_read": 3539
},
{
"name": "inlong-filtersensitive-ebcd6d3",
"ok": true,
"bytes_read": 6474
},
{
"name": "h2o-3-validatejdbcurl-0298ee3",
"ok": true,
"bytes_read": 4919
},
{
"name": "skops-load-model-29d61ea",
"ok": true,
"bytes_read": 1847
},
{
"name": "picklescan-list-globals-58983e1",
"ok": true,
"bytes_read": 6975
},
{
"name": "sglang-deserialize-49afb3d",
"ok": true,
"bytes_read": 4334
},
{
"name": "pdfminer-six-load-data-b808ee0",
"ok": true,
"bytes_read": 2399
},
{
"name": "reverb-handle-9ec26f8",
"ok": true,
"bytes_read": 3342
},
{
"name": "transformers-is-kernel-a7f8e7f",
"ok": true,
"bytes_read": 1921
},
{
"name": "opentelemetry-java-instrumentation-read-9cf4fba",
"ok": true,
"bytes_read": 2075
},
{
"name": "keras-from-config-55888d3",
"ok": true,
"bytes_read": 3154
},
{
"name": "airflow-handle-event-submit-a1ab065",
"ok": true,
"bytes_read": 4828
},
{
"name": "sequelize-partialescape-5deadd2",
"ok": true,
"bytes_read": 6826
},
{
"name": "electerm-mv-aa77881",
"ok": true,
"bytes_read": 1258
},
{
"name": "systeminformation-checklinuxdchpinterfaces-bbfddde",
"ok": true,
"bytes_read": 2208
},
{
"name": "prompty-buildagent-c27402d",
"ok": true,
"bytes_read": 3198
},
{
"name": "datamodel-code-generator-get-field-extras-17fc235",
"ok": true,
"bytes_read": 2471
},
{
"name": "spring-data-mongodb-bindablevaluefor-24d5afc",
"ok": true,
"bytes_read": 9895
},
{
"name": "spring-ai-emitlucenestring-2b20cfc",
"ok": true,
"bytes_read": 4037
},
{
"name": "aws-cdk-write-baa9e1d",
"ok": true,
"bytes_read": 1461
},
{
"name": "danger-js-localgetfileatsha-087a729",
"ok": true,
"bytes_read": 1724
},
{
"name": "argos-javascript-gitfetch-8355f3a",
"ok": true,
"bytes_read": 1319
},
{
"name": "cakephp-transformfunctionexpression-138f2f6",
"ok": true,
"bytes_read": 6754
},
{
"name": "orval-getroutepath-8ef1bfd",
"ok": true,
"bytes_read": 2607
},
{
"name": "velocity-js-isblockedpathkey-f8e47a6",
"ok": true,
"bytes_read": 1539
},
{
"name": "jsonata-evaluategroupexpression-4b217d5",
"ok": true,
"bytes_read": 7399
},
{
"name": "nuxt-getislandcontext-5b60017",
"ok": true,
"bytes_read": 6805
},
{
"name": "mermaid-addnamespace-12d472c",
"ok": true,
"bytes_read": 9722
},
{
"name": "php-codesniffer-getblamecontent-7a3a6bb",
"ok": true,
"bytes_read": 2040
},
{
"name": "xmldom-serializetostring-1cde3e3",
"ok": true,
"bytes_read": 23297
},
{
"name": "trix-fromjson-9c0a993",
"ok": true,
"bytes_read": 1295
},
{
"name": "oauthlib-prepare-token-revocation-request-c888359",
"ok": true,
"bytes_read": 4800
},
{
"name": "suneditor-submitsrc-9d43a5e",
"ok": true,
"bytes_read": 2319
},
{
"name": "mathlive-atomtomathml-5fe1c46",
"ok": true,
"bytes_read": 32529
},
{
"name": "genql-comment-2dbc80f",
"ok": true,
"bytes_read": 1633
},
{
"name": "angular-visitelementlike-417a407",
"ok": true,
"bytes_read": 8480
},
{
"name": "cyberchef-objtotable-85db3be",
"ok": true,
"bytes_read": 2556
},
{
"name": "mdc-isanchorlinkallowed-61d636c",
"ok": true,
"bytes_read": 1795
},
{
"name": "node-xhtml-purifier-node-21d461a",
"ok": true,
"bytes_read": 7486
},
{
"name": "orpc-init-daabded",
"ok": true,
"bytes_read": 6240
},
{
"name": "mkdocs-material-mountsearchsuggest-52fb6be",
"ok": true,
"bytes_read": 4493
},
{
"name": "jodit-isremovablenode-49a31f4",
"ok": true,
"bytes_read": 3921
},
{
"name": "prowler-transform-6db407e",
"ok": true,
"bytes_read": 5481
},
{
"name": "commonmark-parseattributes-dfcdf45",
"ok": true,
"bytes_read": 6437
},
{
"name": "svgo-fn-3db3ef3",
"ok": true,
"bytes_read": 6895
},
{
"name": "tiptap-mergeattributes-01d7af8",
"ok": true,
"bytes_read": 3690
},
{
"name": "nogginlessdom-matchfilesnapshot-785e6ac",
"ok": true,
"bytes_read": 3023
},
{
"name": "gradio-preprocess-97d541f",
"ok": true,
"bytes_read": 2581
},
{
"name": "gemini-bridge-resolve-path-8f3b85a",
"ok": true,
"bytes_read": 2006
},
{
"name": "libreoffice-convert-convertwithoptions-b78f17d",
"ok": true,
"bytes_read": 8912
},
{
"name": "atomic-agents-stack-do-get-ec474f4",
"ok": true,
"bytes_read": 3493
},
{
"name": "browse-mcp-downloadurl-5352a4a",
"ok": true,
"bytes_read": 5302
},
{
"name": "langchain-nvidia-url-to-b64-string-b483c7c",
"ok": true,
"bytes_read": 2318
},
{
"name": "redocly-cli-iteratepathitems-5041204",
"ok": true,
"bytes_read": 4412
},
{
"name": "pip-filename-10dfb6b",
"ok": true,
"bytes_read": 1419
},
{
"name": "lib-get-db-path-d665042",
"ok": true,
"bytes_read": 3879
},
{
"name": "blender-mcp-download-polyhaven-asset-30a3308",
"ok": true,
"bytes_read": 35668
},
{
"name": "datasets-set-feature-f989ef9",
"ok": true,
"bytes_read": 4882
},
{
"name": "postcss-loadfile-7beca13",
"ok": true,
"bytes_read": 1712
},
{
"name": "vitest-configureserver-51edf2b",
"ok": true,
"bytes_read": 3287
},
{
"name": "next-js-getfilepath-968b9fc",
"ok": true,
"bytes_read": 2462
},
{
"name": "composer-install-53b8bb4",
"ok": true,
"bytes_read": 4127
},
{
"name": "vue-cli-mayproxy-72ba750",
"ok": true,
"bytes_read": 1203
},
{
"name": "h3-redirectback-459a1c6",
"ok": true,
"bytes_read": 2750
},
{
"name": "rembg-s-command-07ad0d4",
"ok": true,
"bytes_read": 21204
},
{
"name": "http-server-getpreviousurl-2008fb6",
"ok": true,
"bytes_read": 4395
},
{
"name": "authlib-get-authorization-grant-3be0846",
"ok": true,
"bytes_read": 2631
},
{
"name": "java-client-overrideserverurl-2b9cd44",
"ok": true,
"bytes_read": 1382
},
{
"name": "n8n-mcp-validatewebhookurl-9639f75",
"ok": true,
"bytes_read": 13458
},
{
"name": "ufo-withoutbase-5cd9e67",
"ok": true,
"bytes_read": 2154
},
{
"name": "symfony-dogenerate-4b63c3a",
"ok": true,
"bytes_read": 16981
},
{
"name": "php-weasyprint-isoptionurl-9582dcf",
"ok": true,
"bytes_read": 1090
},
{
"name": "compliance-trestle-check-metadata-endpoints-d107cd1",
"ok": true,
"bytes_read": 2412
},
{
"name": "vllm-preprocess-audio-54503ec",
"ok": true,
"bytes_read": 4629
},
{
"name": "phpspreadsheet-webservice-7ef7b25",
"ok": true,
"bytes_read": 4441
},
{
"name": "frontmcp-dofetch-077201e",
"ok": true,
"bytes_read": 3737
},
{
"name": "ip-address-islinklocal-d03e960",
"ok": true,
"bytes_read": 1489
},
{
"name": "pyjwt-fetch-data-0a795b8",
"ok": true,
"bytes_read": 3385
}
],
"verified": 94,
"bytes_read": 504230
}