[
  {
    "id": "WMO-H01",
    "question": "WMO-Q1",
    "hypothesis": "A defined sponsored service improves whole working-day completion compared with the best feasible conventional option.",
    "contrary": "The difference is smaller than the pre-agreed meaningful margin, or fallback burden/missed returns makes the comparison unfavorable.",
    "test": "Linked person-day and leg study with precommitted windows, concurrent or crossover comparison, and missingness sensitivity.",
    "consequence": "Narrow eligible uses, change operating hours/fallback, or retain the conventional option.",
    "status": "DESIGNED_NOT_RUN",
    "preregistration": "Proposed; freeze site-specific protocol before participant outcomes are seen",
    "metric_ids": [
      "M01",
      "M02"
    ],
    "comparator": "Best feasible conventional/current practice option on the same eligible population and period; site-specific definition must be frozen",
    "direction": "Higher M01 and M02 completion fractions by at least their frozen margins; unequal fallback is a treatment difference, not a hidden service effect.",
    "locally_frozen_margin": null,
    "margin_status": "REQUIRED_BEFORE_COLLECTION",
    "estimator": "Arm-specific rates/means and between-arm difference with allocation-appropriate person/site clustering; H06 team-level error rate",
    "multiplicity": "Before recruitment choose one confirmatory WMO hypothesis per site and one primary margin; H01 uses M01 and M02 as joint required outcomes. Other hypotheses/endpoints are exploratory unless a separate multiplicity plan and power analysis are frozen. No post-result switching.",
    "fallback_rule": "For H01 use the same funded fallback entitlement and access rules across arms when comparing the primary service mechanism. If fallback differs as part of an option, predeclare it as part of the treatment; report use, cost, funding, eligibility and equivalence by arm."
  },
  {
    "id": "WMO-H02",
    "question": "WMO-Q2",
    "hypothesis": "The service broadens practical access across the defined workforce.",
    "contrary": "Gain is concentrated among already well-served participants, or excluded strata face worse completion, cost or access. Non-equivalent fallback on the frozen access, cost, hours or booking dimensions is contrary evidence even if accepted.",
    "test": "Population-to-use funnel and stratified completion/affordability outcomes, including nonusers and practical-assistance testing.",
    "consequence": "Change coverage, eligibility, assistance, digital access or subsidy before expansion.",
    "status": "DESIGNED_NOT_RUN",
    "preregistration": "Proposed; freeze site-specific protocol before participant outcomes are seen",
    "metric_ids": [
      "M01",
      "M02",
      "M06",
      "M09"
    ],
    "comparator": "Best feasible conventional/current practice option on the same eligible population and period; site-specific definition must be frozen",
    "direction": "Improved access/completion in underserved strata with no predeclared stratum below its frozen noninferiority, affordability or equivalence boundary.",
    "locally_frozen_margin": null,
    "margin_status": "REQUIRED_BEFORE_COLLECTION",
    "estimator": "Arm-specific rates/means and between-arm difference with allocation-appropriate person/site clustering; H06 team-level error rate",
    "multiplicity": "Before recruitment choose one confirmatory WMO hypothesis per site and one primary margin; H01 uses M01 and M02 as joint required outcomes. Other hypotheses/endpoints are exploratory unless a separate multiplicity plan and power analysis are frozen. No post-result switching."
  },
  {
    "id": "WMO-H03",
    "question": "WMO-Q3",
    "hypothesis": "The service can operate with accepted, funded responsibilities and a viable recovery arrangement.",
    "contrary": "No party accepts critical work, cost/privacy disputes persist, or recovery cannot be delivered within the agreed boundary.",
    "test": "Signed responsibility schedule, walkthrough, task-time/cost log and disruptions exercised within safe pilot conditions.",
    "consequence": "Do not begin or expand exposure until the operating model changes.",
    "status": "DESIGNED_NOT_RUN",
    "preregistration": "Proposed; freeze site-specific protocol before participant outcomes are seen",
    "metric_ids": [
      "M04",
      "M05",
      "M07"
    ],
    "comparator": "Best feasible conventional/current practice option on the same eligible population and period; site-specific definition must be frozen",
    "direction": "All critical tasks accepted and funded; M04 suitable availability meets the frozen service boundary while M05/M07 cost and work remain within accepted budgets.",
    "locally_frozen_margin": null,
    "margin_status": "REQUIRED_BEFORE_COLLECTION",
    "estimator": "Arm-specific rates/means and between-arm difference with allocation-appropriate person/site clustering; H06 team-level error rate",
    "multiplicity": "Before recruitment choose one confirmatory WMO hypothesis per site and one primary margin; H01 uses M01 and M02 as joint required outcomes. Other hypotheses/endpoints are exploratory unless a separate multiplicity plan and power analysis are frozen. No post-result switching."
  },
  {
    "id": "WMO-H04",
    "question": "WMO-Q4",
    "hypothesis": "A passenger hub adds enough benefit over coordinated pickup and conventional interchange to justify its space and recurring cost.",
    "contrary": "Extra walking/waiting, staffing, rights or cost offsets the benefit, or simple coordination performs as well.",
    "test": "Same-population option comparison including route-to-door access, peak passenger demand and accepted assistance.",
    "consequence": "Use the smaller reversible intervention or a different interchange pattern.",
    "status": "DESIGNED_NOT_RUN",
    "preregistration": "Proposed; freeze site-specific protocol before participant outcomes are seen",
    "metric_ids": [
      "M01",
      "M02",
      "M05",
      "M07"
    ],
    "comparator": "Best feasible conventional/current practice option on the same eligible population and period; site-specific definition must be frozen",
    "direction": "Additional completion or reduced burden versus coordinated pickup/current travel must meet the frozen benefit margin after incremental space and cost are reported.",
    "locally_frozen_margin": null,
    "margin_status": "REQUIRED_BEFORE_COLLECTION",
    "estimator": "Arm-specific rates/means and between-arm difference with allocation-appropriate person/site clustering; H06 team-level error rate",
    "multiplicity": "Before recruitment choose one confirmatory WMO hypothesis per site and one primary margin; H01 uses M01 and M02 as joint required outcomes. Other hypotheses/endpoints are exploratory unless a separate multiplicity plan and power analysis are frozen. No post-result switching."
  },
  {
    "id": "WMO-H05",
    "question": "WMO-Q5",
    "hypothesis": "The chosen option meets its explicit resource/environmental objective within the defined system boundary.",
    "contrary": "Empty/rebound travel, mode substitution, energy or displaced facilities erase the benefit, or data cannot support the claim.",
    "test": "Measure actual displaced modes, occupied/empty distance, occupancy, energy and relevant facilities; report separate accounts.",
    "consequence": "Withdraw the environmental claim, change service design, or select another option.",
    "status": "DESIGNED_NOT_RUN",
    "preregistration": "Proposed; freeze site-specific protocol before participant outcomes are seen",
    "metric_ids": [
      "M08"
    ],
    "comparator": "Best feasible conventional/current practice option on the same eligible population and period; site-specific definition must be frozen",
    "direction": "Lower specifically frozen M08 resource component per equivalent completed person-day or passenger-distance; no aggregate environmental benefit inferred from unmeasured components.",
    "locally_frozen_margin": null,
    "margin_status": "REQUIRED_BEFORE_COLLECTION",
    "estimator": "Arm-specific rates/means and between-arm difference with allocation-appropriate person/site clustering; H06 team-level error rate",
    "multiplicity": "Before recruitment choose one confirmatory WMO hypothesis per site and one primary margin; H01 uses M01 and M02 as joint required outcomes. Other hypotheses/endpoints are exploratory unless a separate multiplicity plan and power analysis are frozen. No post-result switching."
  },
  {
    "id": "WMO-H06",
    "question": "WMO-Q6",
    "hypothesis": "Real occupier and delivery teams make better documented decisions with the guide/toolkit than with current practice.",
    "contrary": "Unsupported commitments persist, error rates do not improve, or the tools increase burden without decision benefit.",
    "test": "Counterbalanced practitioner decision tasks scored blind against a frozen rubric; assess accuracy, bounded claims, actionability, time and dissent.",
    "consequence": "Revise chapters/instruments before calling them practitioner-tested.",
    "status": "DESIGNED_NOT_RUN",
    "preregistration": "Proposed; freeze site-specific protocol before participant outcomes are seen",
    "metric_ids": [
      "H06 critical decision error rate"
    ],
    "comparator": "Best feasible conventional/current practice option on the same eligible population and period; site-specific definition must be frozen",
    "direction": "Lower team-level critical decision-error rate by the frozen meaningful margin; report burden/time as secondary.",
    "locally_frozen_margin": null,
    "margin_status": "REQUIRED_BEFORE_COLLECTION",
    "estimator": "Arm-specific rates/means and between-arm difference with allocation-appropriate person/site clustering; H06 team-level error rate",
    "multiplicity": "Before recruitment choose one confirmatory WMO hypothesis per site and one primary margin; H01 uses M01 and M02 as joint required outcomes. Other hypotheses/endpoints are exploratory unless a separate multiplicity plan and power analysis are frozen. No post-result switching.",
    "prospective_design": {
      "design": "Prospective between-team randomized allocation or balanced case sets, analyzed at team level. Do not mix team learning with material effect.",
      "case_author": "UNASSIGNED_REQUIRED_INDEPENDENT_OF_TOOLKIT_PRODUCTION",
      "rubric_author": "UNASSIGNED_REQUIRED_INDEPENDENT_OF_TOOLKIT_PRODUCTION",
      "primary": "critical decision error rate using external task consequences, not toolkit vocabulary; local meaningful margin must be frozen",
      "raters": "At least two raters blind to tool allocation and case provenance; name them and freeze training, weighted kappa or another outcome-appropriate reliability statistic, threshold and adjudication rule before scoring.",
      "status": "NOT_READY_FOR_EXECUTION_UNTIL_APPOINTMENTS_AND_FREEZE"
    }
  }
]