{"provenance":"Entirely invented AI-authored demonstration; not a customer or the public X author ledger.","request":{"run_ledger_json":"{\"window\":{\"start\":\"2026-10-04T00:00:00Z\",\"end\":\"2026-10-05T00:00:00Z\"},\"runs\":[{\"run_id\":\"mail-0\",\"job_id\":\"mail-check\",\"started_at\":\"2026-10-04T00:00:00Z\",\"status\":\"completed\",\"model_called\":false,\"notified\":false,\"outcome\":\"no_change\",\"cost_usd\":\"0\"},{\"run_id\":\"mail-1\",\"job_id\":\"mail-check\",\"started_at\":\"2026-10-04T06:00:00Z\",\"status\":\"completed\",\"model_called\":false,\"notified\":false,\"outcome\":\"no_change\",\"cost_usd\":\"0\"},{\"run_id\":\"mail-2\",\"job_id\":\"mail-check\",\"started_at\":\"2026-10-04T12:00:00Z\",\"status\":\"completed\",\"model_called\":true,\"notified\":false,\"outcome\":\"no_change\",\"cost_usd\":\"0.05\"},{\"run_id\":\"mail-3\",\"job_id\":\"mail-check\",\"started_at\":\"2026-10-04T18:00:00Z\",\"status\":\"completed\",\"model_called\":true,\"notified\":false,\"outcome\":\"no_change\",\"cost_usd\":\"0.05\"},{\"run_id\":\"docs-1\",\"job_id\":\"docs-check\",\"started_at\":\"2026-10-04T06:00:00Z\",\"status\":\"failed\",\"model_called\":true,\"notified\":null,\"outcome\":\"unknown\",\"cost_usd\":\"0.2\"},{\"run_id\":\"docs-2\",\"job_id\":\"docs-check\",\"started_at\":\"2026-10-04T18:00:00Z\",\"status\":\"completed\",\"model_called\":true,\"notified\":true,\"outcome\":\"useful\",\"cost_usd\":\"0.25\"},{\"run_id\":\"artifact-1\",\"job_id\":\"artifact-check\",\"started_at\":\"2026-10-04T06:00:00Z\",\"status\":\"completed\",\"model_called\":true,\"notified\":false,\"outcome\":\"useful\",\"cost_usd\":\"0.09\"},{\"run_id\":\"artifact-2\",\"job_id\":\"artifact-check\",\"started_at\":\"2026-10-04T18:00:00Z\",\"status\":\"running\",\"model_called\":null,\"notified\":null,\"outcome\":\"unknown\",\"cost_usd\":null}]}","objectives":"Invented public example: mail-check flags actionable inbox changes; docs-check alerts changed public documentation; artifact-check verifies a selected local release artifact and writes a durable report. None is a customer ledger.","constraints":"No changes may be made. Mail latency target6hours, documentation12hours, artifact review12hours. Preserve reports even without a notification. Failed/running outcomes require resolution evidence before considering schedule changes."},"mechanics":{"schema":"tableproof-run-outcome-audit-1","window_utc":{"start":"2026-10-04T00:00:00+00:00","end_exclusive":"2026-10-05T00:00:00+00:00"},"supplied_runs":8,"excluded_outside_start_window":0,"summary":{"runs":8,"statuses":{"completed":6,"failed":1,"running":1},"completed_runs":6,"completed_notified":1,"completed_silent":5,"completed_notification_unknown":0,"completed_notification_rate_known_denominator":"0.166667","completed_outcomes":{"no_change":4,"useful":2},"model_called":5,"model_not_called":2,"model_call_unknown":1,"reported_cost_usd_known_subtotal":"0.640000","reported_cost_missing_runs":1,"cost_coverage_complete_for_supplied_runs":false},"jobs":{"artifact-check":{"runs":2,"statuses":{"completed":1,"running":1},"completed_runs":1,"completed_notified":0,"completed_silent":1,"completed_notification_unknown":0,"completed_notification_rate_known_denominator":"0.000000","completed_outcomes":{"useful":1},"model_called":1,"model_not_called":0,"model_call_unknown":1,"reported_cost_usd_known_subtotal":"0.090000","reported_cost_missing_runs":1,"cost_coverage_complete_for_supplied_runs":false},"docs-check":{"runs":2,"statuses":{"completed":1,"failed":1},"completed_runs":1,"completed_notified":1,"completed_silent":0,"completed_notification_unknown":0,"completed_notification_rate_known_denominator":"1.000000","completed_outcomes":{"useful":1},"model_called":2,"model_not_called":0,"model_call_unknown":0,"reported_cost_usd_known_subtotal":"0.450000","reported_cost_missing_runs":0,"cost_coverage_complete_for_supplied_runs":true},"mail-check":{"runs":4,"statuses":{"completed":4},"completed_runs":4,"completed_notified":0,"completed_silent":4,"completed_notification_unknown":0,"completed_notification_rate_known_denominator":"0.000000","completed_outcomes":{"no_change":4},"model_called":2,"model_not_called":2,"model_call_unknown":0,"reported_cost_usd_known_subtotal":"0.100000","reported_cost_missing_runs":0,"cost_coverage_complete_for_supplied_runs":true}},"limits":["Supplied records only; no scheduler, native Dots or historical completeness verification.","Run status, model calls, outcomes and costs are supplied labels, not independently verified facts.","A silent completed check can be valuable. Notifications do not prove usefulness or delivery.","Costs are caller-reported USD labels, not invoices, receipts, savings or earned revenue.","No schedule is changed; safe frequency reduction and missed-event risk are not established."]},"report":"# Scheduled-run evidence review — invented eight-run sample\n\nThis is an AI-authored demonstration using invented records and constraints. It is not the X author's ledger, a customer's data, native Dots testing, a measured saving or a production intervention.\n\n## What the supplied evidence supports\n\nThe start-inclusive / end-exclusive UTC window covers October 4, 2026. Eight distinct runs across three jobs were supplied: six completed, one failed and one still marked running. Completed records contain one notification and five silent results, so the known completed-run notification fraction is 1/6 (16.6667%). That fraction is not a usefulness score: artifact-1 is labeled useful despite no notification. Two completed records are labeled useful and four no_change. The source of those labels and actual notification delivery are unverified.\n\nFive supplied runs say a model was called, two say it was not, and one is unknown. The exact known caller-reported USD subtotal is 0.640000 across seven cost-bearing records. The eighth cost is missing. It would be incorrect to claim the total cost was $0.64, that silence wasted it, or that it can safely be eliminated. No invoice, model price, billed-token record or scheduling-completeness evidence is supplied.\n\n## Three conditional investigations\n\n1. **Mail change detection before model invocation.** mail-0 and mail-1 completed without model calls; mail-2 and mail-3 called a model and reported no_change, with 0.100000 total reported cost. This supports investigating their invocation reasons, not removing the calls. Obtain input hashes, model-call reasons and whether the no-model runs checked equivalent content. A shadow-only comparison could test a deterministic unchanged-input gate while preserving the supplied six-hour latency target and current schedule. Stop the experiment on any missed actionable change, mismatched comparison scope or inability to retain the existing path. No cost-saving prediction is justified yet.\n\n2. **Resolve documentation failure evidence.** docs-1 failed at 06:00 UTC with unknown notification and outcome; docs-2 completed at 18:00 and was labeled useful/notified. The later success does not prove the earlier failure harmless or that notification timing met the twelve-hour target. Obtain the actual error category, completion/delivery times, retry evidence and affected input version. An owner-run replay against public synthetic documentation can test failure escalation without retrying a real side effect. Keep the schedule; do not classify the failed run as a duplicate or cut it from a success-rate denominator.\n\n3. **Preserve useful silent artifacts and reconcile running state.** artifact-1 is useful/silent; artifact-2 remains running. Check the durable report reference and its integrity, then obtain a terminal state, elapsed duration and expected timeout for artifact-2. Test that an owner can recover the report without a notification and that a synthetic stale-running record escalates according to an explicit timeout. The record contains a start timestamp only; it cannot prove artifact-2 is currently stuck, completed, or within the twelve-hour target. Do not add notifications to every success merely to inflate notification rate.\n\n## Decision\n\nNo schedule change is justified by these eight records alone. The next decision gate is evidence collection for the three investigations above, especially runtime completion/delivery timestamps and source-completeness checks. The supplied constraints prohibit intervention, and none was performed. Recompute the summary from the companion synthetic input using the original offline audit; its arithmetic is reproducible, while these recommendations remain conditional AI-authored reasoning.\n"}