{"campaign_id":"native-interaction-20261010-round04","candidate":{"build_sha256":"514e2b2bb169e1e60737d3a6c688266faffbb549556c6a1f5ebc4d5fd7fa1058","channel":"released","identity_complete":true,"label":"ibara 0.2.1-1 on Omarchy"},"comparison":null,"correction":null,"groups":[{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":1,"not_run":0,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Omarchy representative desktop","fixture_seed":0,"model":"Deterministic native recipe","scenario":"Frame and shadow controls"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":1,"not_run":0,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Omarchy representative desktop","fixture_seed":1,"model":"Deterministic native recipe","scenario":"Frame and shadow controls"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":1,"not_run":0,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Omarchy representative desktop","fixture_seed":2,"model":"Deterministic native recipe","scenario":"Frame and shadow controls"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":1,"not_run":0,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Omarchy representative desktop","fixture_seed":3,"model":"Deterministic native recipe","scenario":"Frame and shadow controls"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":1,"not_run":0,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Omarchy representative desktop","fixture_seed":4,"model":"Deterministic native recipe","scenario":"Frame and shadow controls"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":1,"not_run":0,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Omarchy representative desktop","fixture_seed":5,"model":"Deterministic native recipe","scenario":"Frame and shadow controls"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":1,"not_run":0,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Omarchy representative desktop","fixture_seed":6,"model":"Deterministic native recipe","scenario":"Frame and shadow controls"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":1,"not_run":0,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Omarchy representative desktop","fixture_seed":7,"model":"Deterministic native recipe","scenario":"Frame and shadow controls"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":1,"not_run":0,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Omarchy representative desktop","fixture_seed":8,"model":"Deterministic native recipe","scenario":"Frame and shadow controls"},{"benchmark_mode":"scripted","counts":{"attempted":1,"blocked":0,"failed":1,"not_run":0,"passed":0,"planned":1,"safe_refusal":0,"unknown":0},"dimension":"cohort","environment":"Omarchy representative desktop","fixture_seed":9,"model":"Deterministic native recipe","scenario":"Frame and shadow controls"},{"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":"Omarchy representative desktop","fixture_seed":0,"model":"Deterministic native recipe","scenario":"Long Unicode save and reopen"},{"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":"Omarchy representative desktop","fixture_seed":1,"model":"Deterministic native recipe","scenario":"Long Unicode save and reopen"},{"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":"Omarchy representative desktop","fixture_seed":2,"model":"Deterministic native recipe","scenario":"Long Unicode save and reopen"},{"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":"Omarchy representative desktop","fixture_seed":3,"model":"Deterministic native recipe","scenario":"Long Unicode save and reopen"},{"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":"Omarchy representative desktop","fixture_seed":4,"model":"Deterministic native recipe","scenario":"Long Unicode save and reopen"},{"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":"Omarchy representative desktop","fixture_seed":5,"model":"Deterministic native recipe","scenario":"Long Unicode save and reopen"},{"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":"Omarchy representative desktop","fixture_seed":6,"model":"Deterministic native recipe","scenario":"Long Unicode save and reopen"},{"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":"Omarchy representative desktop","fixture_seed":7,"model":"Deterministic native recipe","scenario":"Long Unicode save and reopen"},{"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":"Omarchy representative desktop","fixture_seed":8,"model":"Deterministic native recipe","scenario":"Long Unicode save and reopen"},{"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":"Omarchy representative desktop","fixture_seed":9,"model":"Deterministic native recipe","scenario":"Long Unicode save and reopen"},{"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":"Omarchy representative desktop","fixture_seed":0,"model":"Deterministic native recipe","scenario":"Nested scrolling"},{"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":"Omarchy representative desktop","fixture_seed":1,"model":"Deterministic native recipe","scenario":"Nested scrolling"},{"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":"Omarchy representative desktop","fixture_seed":2,"model":"Deterministic native recipe","scenario":"Nested scrolling"},{"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":"Omarchy representative desktop","fixture_seed":3,"model":"Deterministic native recipe","scenario":"Nested scrolling"},{"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":"Omarchy representative desktop","fixture_seed":4,"model":"Deterministic native recipe","scenario":"Nested scrolling"},{"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":"Omarchy representative desktop","fixture_seed":5,"model":"Deterministic native recipe","scenario":"Nested scrolling"},{"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":"Omarchy representative desktop","fixture_seed":6,"model":"Deterministic native recipe","scenario":"Nested scrolling"},{"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":"Omarchy representative desktop","fixture_seed":7,"model":"Deterministic native recipe","scenario":"Nested scrolling"},{"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":"Omarchy representative desktop","fixture_seed":8,"model":"Deterministic native recipe","scenario":"Nested scrolling"},{"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":"Omarchy representative desktop","fixture_seed":9,"model":"Deterministic native recipe","scenario":"Nested scrolling"},{"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":"Omarchy representative desktop","fixture_seed":0,"model":"Deterministic native recipe","scenario":"Repeated native observations"},{"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":"Omarchy representative desktop","fixture_seed":1,"model":"Deterministic native recipe","scenario":"Repeated native observations"},{"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":"Omarchy representative desktop","fixture_seed":2,"model":"Deterministic native recipe","scenario":"Repeated native observations"},{"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":"Omarchy representative desktop","fixture_seed":3,"model":"Deterministic native recipe","scenario":"Repeated native observations"},{"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":"Omarchy representative desktop","fixture_seed":4,"model":"Deterministic native recipe","scenario":"Repeated native observations"},{"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":"Omarchy representative desktop","fixture_seed":5,"model":"Deterministic native recipe","scenario":"Repeated native observations"},{"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":"Omarchy representative desktop","fixture_seed":6,"model":"Deterministic native recipe","scenario":"Repeated native observations"},{"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":"Omarchy representative desktop","fixture_seed":7,"model":"Deterministic native recipe","scenario":"Repeated native observations"},{"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":"Omarchy representative desktop","fixture_seed":8,"model":"Deterministic native recipe","scenario":"Repeated native observations"},{"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":"Omarchy representative desktop","fixture_seed":9,"model":"Deterministic native recipe","scenario":"Repeated native observations"},{"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":"Omarchy representative desktop","fixture_seed":0,"model":"Deterministic native recipe","scenario":"Short Unicode save and reopen"},{"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":"Omarchy representative desktop","fixture_seed":1,"model":"Deterministic native recipe","scenario":"Short Unicode save and reopen"},{"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":"Omarchy representative desktop","fixture_seed":2,"model":"Deterministic native recipe","scenario":"Short Unicode save and reopen"},{"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":"Omarchy representative desktop","fixture_seed":3,"model":"Deterministic native recipe","scenario":"Short Unicode save and reopen"},{"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":"Omarchy representative desktop","fixture_seed":4,"model":"Deterministic native recipe","scenario":"Short Unicode save and reopen"},{"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":"Omarchy representative desktop","fixture_seed":5,"model":"Deterministic native recipe","scenario":"Short Unicode save and reopen"},{"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":"Omarchy representative desktop","fixture_seed":6,"model":"Deterministic native recipe","scenario":"Short Unicode save and reopen"},{"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":"Omarchy representative desktop","fixture_seed":7,"model":"Deterministic native recipe","scenario":"Short Unicode save and reopen"},{"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":"Omarchy representative desktop","fixture_seed":8,"model":"Deterministic native recipe","scenario":"Short Unicode save and reopen"},{"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":"Omarchy representative desktop","fixture_seed":9,"model":"Deterministic native recipe","scenario":"Short Unicode save and reopen"},{"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":"Omarchy representative desktop","fixture_seed":0,"model":"Deterministic native recipe","scenario":"Synthetic browser 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":"Omarchy representative desktop","fixture_seed":1,"model":"Deterministic native recipe","scenario":"Synthetic browser 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":"Omarchy representative desktop","fixture_seed":2,"model":"Deterministic native recipe","scenario":"Synthetic browser 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":"Omarchy representative desktop","fixture_seed":3,"model":"Deterministic native recipe","scenario":"Synthetic browser 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":"Omarchy representative desktop","fixture_seed":4,"model":"Deterministic native recipe","scenario":"Synthetic browser 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":"Omarchy representative desktop","fixture_seed":5,"model":"Deterministic native recipe","scenario":"Synthetic browser 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":"Omarchy representative desktop","fixture_seed":6,"model":"Deterministic native recipe","scenario":"Synthetic browser 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":"Omarchy representative desktop","fixture_seed":7,"model":"Deterministic native recipe","scenario":"Synthetic browser 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":"Omarchy representative desktop","fixture_seed":8,"model":"Deterministic native recipe","scenario":"Synthetic browser 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":"Omarchy representative desktop","fixture_seed":9,"model":"Deterministic native recipe","scenario":"Synthetic browser form"}],"kind":"benchmark","limitations":["Scripted system benchmark; no fresh-agent productivity or model ranking claim.","One Omarchy computer and a fixed bridge route; these results do not qualify Ubuntu performance.","Timings include bridge transport, expectation settlement and returned observations; they are not pure target input latency.","Frame and shadow controls are intentionally probed; unsupported outcomes remain in the denominator.","Exact file bytes and trusted fixture events independently verify output; observation cases independently witness the owned native window, not correctness of every captured pixel.","Continuous video, physical takeover and stream frame-age measurements are absent.","All original receipts remain private; public output contains sanitized aggregate results.","Long-text expectations ended before saving; absent saved-output evidence remains unknown.","A disposable VM began provisioning on the collector host during this round; this round is descriptive and not a controlled product performance comparison."],"measured_at":{"end":"2026-10-10T22:53:17.627867+00:00","start":"2026-10-10T22:39:34.706252+00:00"},"methodology":"Ten repetitions per workflow on one fixed desktop through the public MCP route. Each attempt retains native receipts, host-monotonic tool timings, independent saved-file or trusted synthetic-fixture witnesses and fresh cleanup observations. Failures and unknown effects are retained. Per-attempt metadata is sealed and imported in a batch; no continuous video. Single and checked-batch variants are reported separately where present.","metrics":[{"denominator":60,"name":"Verified task completion","numerator":0,"population":"scripted attempts","sample_count":60,"statistic":"ratio","unit":"fraction","value":0.0},{"denominator":null,"name":"Attempt duration","numerator":null,"population":"scripted: Attempt summaries with duration_ms measured","sample_count":60,"statistic":"mean","unit":"ms","value":9978.017734081368},{"denominator":null,"name":"Tool calls","numerator":null,"population":"scripted: Attempt summaries with tool_calls measured","sample_count":60,"statistic":"mean","unit":"count","value":16.666666666666668},{"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":"02fb0b4a182c6df7776edca7fd5e01bbd18dc81d814efba453108fa3c3f291cb","source_sha256":null,"source_url":null,"type":"warehouse_snapshot"},"qualification":{"classification":"diagnostic","completed_cells":0,"eligible_for_comparison":false,"mode_counts":[{"counts":{"attempted":60,"blocked":0,"failed":10,"not_run":0,"passed":0,"planned":60,"safe_refusal":0,"unknown":50},"mode":"scripted"}],"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":"2026-10-10T22:56:33.653481+00:00","suite":{"label":"Native interaction and exact-output workflows","version":"v1"},"title":"Native interaction benchmark, round 4","totals":{"attempted":60,"blocked":0,"failed":10,"not_run":0,"passed":0,"planned":60,"safe_refusal":0,"unknown":50}}