{"campaign_id":"common-native-interrupted-20261011-ubuntu","candidate":{"build_sha256":"ebe8df863e511665b343b513d6e866559f7977e033e9ca2c792d37d4f92a22d2","channel":"experimental","identity_complete":true,"label":"Ubuntu private frame-peer-r9"},"comparison":null,"correction":null,"groups":[{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Ubuntu software VM","fixture_seed":1,"model":"Deterministic common native recipe","scenario":"Covered-frame refusal"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Ubuntu software VM","fixture_seed":2,"model":"Deterministic common native recipe","scenario":"Covered-frame refusal"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Ubuntu software VM","fixture_seed":3,"model":"Deterministic common native recipe","scenario":"Covered-frame refusal"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Ubuntu software VM","fixture_seed":1,"model":"Deterministic common native recipe","scenario":"Exact shadow Unicode"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Ubuntu software VM","fixture_seed":2,"model":"Deterministic common native recipe","scenario":"Exact shadow Unicode"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Ubuntu software VM","fixture_seed":3,"model":"Deterministic common native recipe","scenario":"Exact shadow Unicode"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Ubuntu software VM","fixture_seed":1,"model":"Deterministic common native recipe","scenario":"Frame and shadow controls"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Ubuntu software VM","fixture_seed":2,"model":"Deterministic common native recipe","scenario":"Frame and shadow controls"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Ubuntu software VM","fixture_seed":3,"model":"Deterministic common native recipe","scenario":"Frame and shadow controls"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Ubuntu software VM","fixture_seed":1,"model":"Deterministic common native recipe","scenario":"Hidden-frame negative check"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Ubuntu software VM","fixture_seed":2,"model":"Deterministic common native recipe","scenario":"Hidden-frame negative check"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Ubuntu software VM","fixture_seed":1,"model":"Deterministic common native recipe","scenario":"Modal frame"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Ubuntu software VM","fixture_seed":2,"model":"Deterministic common native recipe","scenario":"Modal frame"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Ubuntu software VM","fixture_seed":3,"model":"Deterministic common native recipe","scenario":"Modal frame"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Ubuntu software VM","fixture_seed":1,"model":"Deterministic common native recipe","scenario":"Native Unicode save and exact download"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Ubuntu software VM","fixture_seed":2,"model":"Deterministic common native recipe","scenario":"Native Unicode save and exact download"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Ubuntu software VM","fixture_seed":1,"model":"Deterministic common native recipe","scenario":"Nested cross-origin frame"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Ubuntu software VM","fixture_seed":2,"model":"Deterministic common native recipe","scenario":"Nested cross-origin frame"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Ubuntu software VM","fixture_seed":3,"model":"Deterministic common native recipe","scenario":"Nested cross-origin frame"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Ubuntu software VM","fixture_seed":1,"model":"Deterministic common native recipe","scenario":"Open-shadow modal"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Ubuntu software VM","fixture_seed":2,"model":"Deterministic common native recipe","scenario":"Open-shadow modal"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Ubuntu software VM","fixture_seed":3,"model":"Deterministic common native recipe","scenario":"Open-shadow modal"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Ubuntu software VM","fixture_seed":1,"model":"Deterministic common native recipe","scenario":"Padded-frame refusal"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Ubuntu software VM","fixture_seed":2,"model":"Deterministic common native recipe","scenario":"Padded-frame refusal"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Ubuntu software VM","fixture_seed":3,"model":"Deterministic common native recipe","scenario":"Padded-frame refusal"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Ubuntu software VM","fixture_seed":1,"model":"Deterministic common native recipe","scenario":"Redirect and srcdoc attribution"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Ubuntu software VM","fixture_seed":2,"model":"Deterministic common native recipe","scenario":"Redirect and srcdoc attribution"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Ubuntu software VM","fixture_seed":1,"model":"Deterministic common native recipe","scenario":"Replaced-frame refusal"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Ubuntu software VM","fixture_seed":2,"model":"Deterministic common native recipe","scenario":"Replaced-frame refusal"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Ubuntu software VM","fixture_seed":3,"model":"Deterministic common native recipe","scenario":"Replaced-frame refusal"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Ubuntu software VM","fixture_seed":1,"model":"Deterministic common native recipe","scenario":"Slotted modal button"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Ubuntu software VM","fixture_seed":2,"model":"Deterministic common native recipe","scenario":"Slotted modal button"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Ubuntu software VM","fixture_seed":1,"model":"Deterministic common native recipe","scenario":"Slotted modal frame"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Ubuntu software VM","fixture_seed":2,"model":"Deterministic common native recipe","scenario":"Slotted modal frame"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":0,"planned":1,"safe_refusal":0,"unknown":1},"dimension":"cohort","environment":"Ubuntu software VM","fixture_seed":1,"model":"Deterministic common native recipe","scenario":"Synthetic form"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":0,"planned":1,"safe_refusal":0,"unknown":1},"dimension":"cohort","environment":"Ubuntu software VM","fixture_seed":2,"model":"Deterministic common native recipe","scenario":"Synthetic form"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":0,"planned":1,"safe_refusal":0,"unknown":1},"dimension":"cohort","environment":"Ubuntu software VM","fixture_seed":3,"model":"Deterministic common native recipe","scenario":"Synthetic form"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Ubuntu software VM","fixture_seed":1,"model":"Deterministic common native recipe","scenario":"Transformed-frame refusal"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Ubuntu software VM","fixture_seed":2,"model":"Deterministic common native recipe","scenario":"Transformed-frame refusal"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":0,"not_run":0,"passed":1,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Ubuntu software VM","fixture_seed":3,"model":"Deterministic common native recipe","scenario":"Transformed-frame refusal"},{"counts":{"attempted":0,"blocked":0,"failed":0,"not_run":20,"passed":0,"planned":20,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Not run","model":"Not run","scenario":"Planned but not run"}],"kind":"benchmark","limitations":["Scripted system diagnostic, not fresh-agent productivity or model ranking.","Shared-host software VM versus physical Dell: timings are descriptive, not an operating-system causal comparison.","Initial fullscreen is required by this recipe. Ordinary-window and F11-resize Chrome geometry failures remain outside positive qualification.","Mousepad0.7.0 versions match; distribution binaries and compositor backends differ.","Ubuntu form submission can be held by its effect approval policy. Held attempts remain unknown, with no submission replay or bypass. Omarchy policy differs.","Up to four samples per scenario; scenario p95 is withheld.","The first common campaign stopped after81 attempted slots when Dell reached its metadata cap;39 slots were not run. Databases were privately backed up and integrity checked, then the supported limit was raised from100MiB to256MiB without deleting receipts. Confirmation is a new cohort with the identical recipe and reader; it does not rewrite that interruption.","Omarchy native editor failures can retain its released legacy adapter session refusals before typing; these are not replayed or repaired during the frozen cohort.","The shared operator bridge executable was not independently hashed in each original attempt. The target, reader, browser, viewport and copied recipe identities are checked per attempt.","Native Chrome and GNOME Text Editor accessibility trees, signed-in profiles, physical Ubuntu GPUs, multi-output and fractional scaling are not qualified.","Calibration failures and changed recipes are retained separately; original benchmark campaigns remain immutable.","Full screenshots, credentials, profiles and video are not published."],"measured_at":{"end":"2026-10-11T05:57:13.452009+00:00","start":"2026-10-11T05:41:12.149810+00:00"},"methodology":"Four balanced rounds of fifteen workflows on each environment use the same frozen native MCP recipe, trusted synthetic fixture and reader source, Chrome155.0.8059.39,1280x800 scale1 and initial fullscreen. Exact file bytes, trusted fixture events, independent cleanup and before/after software identities verify outcomes. Every attempted slot is retained without replay. Per-call receipts and host resource observations remain private.","metrics":[{"denominator":40,"name":"Verified task completion","numerator":37,"population":"scripted attempts","sample_count":40,"statistic":"ratio","unit":"fraction","value":0.925},{"denominator":null,"name":"Attempt duration","numerator":null,"population":"scripted: Attempt summaries with duration_ms measured","sample_count":40,"statistic":"mean","unit":"ms","value":15650.275},{"denominator":null,"name":"Tool calls","numerator":null,"population":"scripted: Attempt summaries with tool_calls measured","sample_count":40,"statistic":"mean","unit":"count","value":13.625},{"denominator":null,"name":"Model tokens","numerator":null,"population":"scripted: Attempt summaries with tokens measured","sample_count":0,"statistic":"mean","unit":"count","value":null},{"denominator":null,"name":"Measured model cost","numerator":null,"population":"scripted: Attempt summaries with cost_usd measured","sample_count":0,"statistic":"mean","unit":"USD","value":null}],"provenance":{"snapshot_sha256":"e3ff5069f25bad505caaa107de0ce81ba505637ba7c948d4dec8379e7c5e2fdd","source_sha256":null,"source_url":null,"type":"warehouse_snapshot"},"qualification":{"classification":"diagnostic","completed_cells":0,"eligible_for_comparison":false,"mode_counts":[{"counts":{"attempted":40,"blocked":0,"failed":0,"not_run":0,"passed":37,"planned":40,"safe_refusal":0,"unknown":3},"mode":"scripted"},{"counts":{"attempted":0,"blocked":0,"failed":0,"not_run":20,"passed":0,"planned":20,"safe_refusal":0,"unknown":0},"mode":"unclassified"}],"planned_cells":0,"reasons":["An observed attempt is outside the frozen matrix.","Diagnostic evidence is not an accepted comparison baseline.","Exactly one frozen campaign manifest is required.","The frozen matrix has missing, duplicate or unplanned attempts; valid failures remain counted.","The planned machine, workflow, mode and seed matrix is unavailable."]},"revision":1,"schema_version":"1.0","sealed_at":"2026-10-11T05:59:17.532508+00:00","suite":{"label":"Matched fullscreen browser and exact native file workflows","version":"common-fullscreen-v1"},"title":"Ubuntu interrupted common native diagnostic","totals":{"attempted":40,"blocked":0,"failed":0,"not_run":20,"passed":37,"planned":60,"safe_refusal":0,"unknown":3}}