{ "ok": true, "packet": { "packet_id": "freight-routeops-proof-packet-v1", "vertical_id": "freight-field-routing", "case_id": "freight-routeops-mini-v1", "generated_from": [ "eval-results/routeops-eval.json", "npm run eval:routeops", "npm run eval:routeops:baselines:required with live Cloudflare OR-Tools/PyVRP/VROOM rows" ], "claim_boundary": "This proof packet is paid-pilot evidence, not OR-Tools/PyVRP/VROOM solver-superiority evidence until all pinned open-solver baselines pass.", "evidence_readiness": { "status": "complete", "score_pct": 100, "checks_passed": 6, "checks_total": 6, "summary": "Freight RouteOps proof packet is 100% complete for the declared evidence-pack scope.", "checks": [ { "id": "baseline_rows_complete", "label": "Baseline rows complete", "pass": true, "evidence": "Dispatcher, feasible heuristic, and Catalyst-Q candidate rows are present." }, { "id": "hard_constraints_pass", "label": "Hard constraints pass", "pass": true, "evidence": "Catalyst-Q candidate has zero capacity violation, zero lateness, and no vehicle overage on the proof fixture." }, { "id": "route_stability_pass", "label": "Route stability gate passes", "pass": true, "evidence": "Urgent-order/storm replan stays under the minimal-change threshold." }, { "id": "roi_deltas_present", "label": "ROI deltas present", "pass": true, "evidence": "Distance, objective, lateness, capacity, and emissions proxy deltas are computable from packet baselines." }, { "id": "csv_intake_ready", "label": "CSV intake ready", "pass": true, "evidence": "Orders and vehicles templates include time windows, capacity, and driver-hour fields." }, { "id": "external_baseline_gate_tracked", "label": "External solver gate tracked", "pass": true, "evidence": "OR-Tools, PyVRP, and VROOM are tracked as the separate public solver-superiority gate." } ] }, "buyer_readout": [ "Catalyst-Q clears the synthetic freight hard constraints: all stops served, zero lateness, zero capacity violation, and no vehicle overage.", "Against the feasible nearest-neighbor baseline, Catalyst-Q reduces the objective by 42.206%, distance by 13.498 units, and emissions proxy by 12.418 kg CO2e.", "Against the dispatcher baseline, Catalyst-Q removes 152.549 lateness minutes and 3 units of capacity violation in the disruption case.", "Route stability remains controlled through the urgent-order/storm minimal-change replan gate." ], "baselines": [ { "id": "dispatcher_baseline", "label": "Dispatcher baseline before urgent pickup and storm disruption", "metrics": { "distance": 332.934, "duration": 744.227, "capacity_violation": 3, "lateness_minutes": 152.549, "route_changes_from_baseline": 0, "vehicle_count": 3, "vehicle_overage": 0, "emissions_proxy_kg_co2e": 306.299, "objective": 2236.821 } }, { "id": "nearest_neighbor_baseline", "label": "Nearest-neighbor feasible heuristic baseline", "metrics": { "distance": 301.602, "duration": 801.91, "capacity_violation": 0, "lateness_minutes": 0, "route_changes_from_baseline": 9, "vehicle_count": 4, "vehicle_overage": 1, "emissions_proxy_kg_co2e": 277.474, "objective": 648.002 } }, { "id": "catalyst_routeops_v0", "label": "Catalyst-Q RouteOps candidate", "metrics": { "distance": 288.104, "duration": 679.612, "capacity_violation": 0, "lateness_minutes": 0, "route_changes_from_baseline": 4, "vehicle_count": 3, "vehicle_overage": 0, "emissions_proxy_kg_co2e": 265.056, "objective": 374.504 } } ], "deltas": { "vs_nearest_neighbor": { "distance_saved": 13.498, "distance_improvement_pct": 4.475, "objective_improvement_pct": 42.206, "emissions_proxy_kg_co2e_saved": 12.418, "vehicle_count_reduction": 1, "lateness_minutes_removed": 0, "capacity_violation_removed": 0 }, "vs_dispatcher": { "distance_saved": 44.83, "objective_improvement_pct": 83.257, "emissions_proxy_kg_co2e_saved": 41.243, "lateness_minutes_removed": 152.549, "capacity_violation_removed": 3 } }, "route_stability": { "minimal_change_replan": { "scenario_id": "urgent-order-storm-minimal-change", "route_changes_from_baseline": 2.5, "max_allowed_route_changes": 6, "pass": true }, "acceptance": [ "all_stops_served", "no_capacity_violation", "no_lateness", "minimal_change_replan", "objective_not_regressed_more_than_10pct" ] }, "open_solver_evidence": { "required_solvers": [ { "id": "ortools", "name": "Google OR-Tools", "status": "remote_available", "evidence": "Live in the Cloudflare benchmark container and returning feasible RouteOps comparison rows." }, { "id": "pyvrp", "name": "PyVRP", "status": "remote_available", "evidence": "Live in the Cloudflare benchmark container and returning feasible RouteOps comparison rows." }, { "id": "vroom", "name": "VROOM", "status": "remote_available", "evidence": "Pinned VROOM CLI is live in the Cloudflare benchmark container and returning feasible RouteOps comparison rows." } ], "claim_gate": { "id": "freight-open-solver-superiority", "passed": false, "reason": "OR-Tools, PyVRP, and VROOM comparison rows are now live; use the best feasible open-solver route as the ensemble seed and keep solver-superiority language gated until Catalyst-Q beats, matches, or explains gaps across pinned public benchmark suites." }, "runbook": { "local_no_docker": "npm run eval:routeops && npm run smoke:local", "remote_without_docker": "gh workflow run deploy-benchmark-container.yml --ref main, then npm run smoke:production", "promotion_command": "npm run eval:routeops:baselines:required" } }, "pricing_offer": { "paid_pilot": { "price": "$15,000-$35,000 for 4-6 weeks", "includes": [ "CSV/order intake setup", "baseline replay and shadow mode", "weekly Freight proof packet", "dispatcher approval workflow", "Browser Run evidence for portal and handoff moments" ] }, "conversion": { "price": "$2,500-$7,500/month + usage + verified savings kicker", "usage_meter": "optimized stops, replans, Browser Run evidence minutes, and Catalyst-Q shots", "kicker": "3%-8% of verified savings above the signed baseline after the base platform fee" }, "acceptance_metric": "mileage, lateness, capacity, route stability, fuel/emissions proxy, and dispatcher acceptance against baseline" } }, "templates": { "orders": "order_id,x,y,demand,ready,due,service,priority\nclinic-a,44,66,3,40,210,10,3\nclinic-b,39,71,4,45,230,10,2\npharmacy-north,31,62,2,60,260,8,2\nlab-east,70,61,4,25,210,11,3\nhospital-east,75,47,5,80,280,12,3\nurgent-pickup,55,72,2,20,160,8,5", "vehicles": "vehicle_id,capacity,shift_start,shift_end,driver_hours\ntruck-1,15,0,480,8\ntruck-2,15,0,480,8" }, "links": { "page": "https://catalyst-q.strategic-innovations.ai/freight/proof", "workbench": "https://catalyst-q.strategic-innovations.ai/app?agent=freight-field-routing", "evals": "https://catalyst-q.strategic-innovations.ai/evals" } }