{
  "schema": "open-scaffold.proof-comparison.v1",
  "comparison_id": "codex-token-efficient-resume-2026-06-16",
  "title": "Codex cold-resume token efficiency: raw artifacts vs Open Scaffold capsule",
  "question": "For a bounded paused-work resume decision, does an Open Scaffold compact resume capsule let Codex preserve decision quality while using at least 2x fewer reported total tokens than a naked raw-artifact prompt?",
  "arms": {
    "control": {
      "id": "naked-codex-raw-paused-session",
      "label": "Naked Codex over raw paused-session artifacts",
      "runtime": "codex-cli exec / gpt-5.5"
    },
    "scaffolded": {
      "id": "open-scaffold-resume-capsule-codex",
      "label": "Open Scaffold resume capsule + Codex",
      "runtime": "codex-cli exec / gpt-5.5"
    }
  },
  "metrics": [
    {
      "id": "quality.decision_score_median",
      "label": "Median human-facing decision quality score",
      "category": "quality",
      "unit": "points / 6",
      "direction": "higher",
      "control": 6,
      "scaffolded": 6,
      "source_refs": [
        "receipts/aggregate.json",
        "receipts/control-r1.json",
        "receipts/control-r2.json",
        "receipts/control-r3.json",
        "receipts/scaffolded-r1.json",
        "receipts/scaffolded-r2.json",
        "receipts/scaffolded-r3.json"
      ],
      "notes": "Six deterministic reader-usability checks cover plain action, explanatory reasons, unambiguous resume pointer, clear acceptance/remaining-work status, complete next fields plus at least one traceable evidence ref, and a plain no-approval boundary."
    },
    {
      "id": "usage.codex_reported_total_tokens_median",
      "label": "Median Codex-reported total tokens",
      "category": "tokens",
      "unit": "tokens",
      "direction": "lower",
      "control": 137327,
      "scaffolded": 31715,
      "minimum_ratio": 2,
      "source_refs": [
        "receipts/aggregate.json",
        "receipts/control-r1.json",
        "receipts/control-r2.json",
        "receipts/control-r3.json",
        "receipts/scaffolded-r1.json",
        "receipts/scaffolded-r2.json",
        "receipts/scaffolded-r3.json"
      ],
      "notes": "Derived from Codex CLI input_tokens + output_tokens in turn.completed usage for three read-only replicates per arm."
    },
    {
      "id": "usage.prompt_payload_bytes",
      "label": "Prompt payload bytes given to Codex",
      "category": "tokens",
      "unit": "bytes",
      "direction": "lower",
      "control": 419233,
      "scaffolded": 1557,
      "minimum_ratio": 2,
      "source_refs": [
        "prompts/control-naked-raw-prompt.txt",
        "prompts/scaffolded-resume-capsule-prompt.md",
        "receipts/aggregate.json"
      ],
      "notes": "Direct prompt payload size, not an inferred model-token count."
    },
    {
      "id": "speed.wall_seconds_median",
      "label": "Median wall-clock seconds for Codex response",
      "category": "speed",
      "unit": "seconds",
      "direction": "lower",
      "control": 33.533,
      "scaffolded": 26.894,
      "source_refs": [
        "receipts/aggregate.json",
        "receipts/control-r1.json",
        "receipts/control-r2.json",
        "receipts/control-r3.json",
        "receipts/scaffolded-r1.json",
        "receipts/scaffolded-r2.json",
        "receipts/scaffolded-r3.json"
      ],
      "notes": "Wall time includes local Codex CLI startup/plugin overhead on the measured machine."
    },
    {
      "id": "evolution.compiled_record_available",
      "label": "Compiled Open Scaffold resume record available",
      "category": "evolution",
      "unit": "present",
      "direction": "higher",
      "control": 0,
      "scaffolded": 1,
      "source_refs": [
        "prompts/scaffolded-resume-capsule-prompt.md",
        "generate-fixture.mjs",
        "receipts/aggregate.json"
      ],
      "notes": "This is the mechanism difference: raw artifacts vs a compiled Open Scaffold resume capsule. It is not a claim that the model became smarter."
    }
  ],
  "evidence_battery": [
    {
      "id": "codex-2x-cold-resume-replicates",
      "kind": "cold_resume_fixture",
      "status": "demonstrated",
      "required_for_pass": true,
      "claim": "3 read-only Codex replicates per arm preserved decision quality at 6/6 while reducing median Codex-reported total tokens by 4.330033x.",
      "boundary": "One paused-work cold-resume decision on codex-cli exec / gpt-5.5; not a universal workload, model, or production-readiness claim.",
      "source_refs": [
        "receipts/aggregate.json",
        "receipts/control-r1.json",
        "receipts/control-r2.json",
        "receipts/control-r3.json",
        "receipts/scaffolded-r1.json",
        "receipts/scaffolded-r2.json",
        "receipts/scaffolded-r3.json"
      ]
    },
    {
      "id": "cold-resume-packet-contract",
      "kind": "cold_resume_packet",
      "status": "demonstrated",
      "required_for_pass": true,
      "claim": "The scaffolded arm uses a compact packet with explicit plan, objective, action, resume pointer, acceptance summary, reasons, next fields, evidence refs, and authority boundary.",
      "boundary": "Packet-field contract for this fixture only; it does not define a universal resume schema or claim human-reviewer replication.",
      "source_refs": [
        "prompts/scaffolded-resume-capsule-prompt.md",
        "generate-fixture.mjs",
        "receipts/aggregate.json"
      ]
    },
    {
      "id": "human-reviewer-replication",
      "kind": "human_reviewer_replication",
      "status": "not_demonstrated",
      "required_for_pass": false,
      "claim": "No blind human-reviewer replication is claimed for this Codex 2x fixture.",
      "boundary": "The shipped quality score is deterministic and human-facing; a real human-reader replication needs separate preregistration, answer keys, blinded packets, and receipts.",
      "source_refs": [
        "evidence/human-reviewer-replication-boundary.md",
        "receipts/aggregate.json"
      ]
    },
    {
      "id": "controlled-ablations",
      "kind": "controlled_ablation",
      "status": "mixed_not_proven",
      "required_for_pass": false,
      "claim": "No minimal-checklist, packet-only, or alternate-packet ablation is claimed by this fixture.",
      "boundary": "Ablations are disclosure-only here and cannot support broad dominance; future ablation claims must ship their own committed receipts.",
      "source_refs": [
        "evidence/controlled-ablations-boundary.md",
        "receipts/aggregate.json"
      ]
    }
  ],
  "required_evidence": [
    "codex-2x-cold-resume-replicates",
    "cold-resume-packet-contract"
  ],
  "caveats": [
    "Bounded fixture proof only: one paused-work cold-resume decision, not all AI work or all repositories.",
    "Codex CLI did not emit total_tokens directly in this environment; receipts record input/output splits and derive total as input_tokens + output_tokens.",
    "The raw control prompt is intentionally a long paused-session artifact stream; the scaffolded arm is the compact packet compiled from those facts.",
    "The quality score is deterministic and human-facing, but it is still a rubric over committed answers rather than a blind human-reader study.",
    "Open Scaffold did not approve closeout, merge, publish, release, deployment, or compliance."
  ]
}