{"schema_version":"1.0","evidence_mode":"live","generated_at":"2026-09-01T11:30:10.359082+08:00","method":"same_prompt_agent_vs_manual_with_raw_outputs","task_count":3,"categories":["grid_trading","health_factor_monitoring","yield_optimisation"],"tasks":[{"task_id":"pancakeswap-grid-route","category":"grid_trading","prompt_path":"evidence/termix/tasks/pancakeswap-grid-route.json","prompt_sha256":"047637c1f7ccd2afb2d26376a6d0895355382b7bbaf21c2c190b7b9672357745","agent":{"output_path":"evidence/termix/raw/pancakeswap-grid-route/agent-output.json","output_sha256":"fb126042c9b5282dcba7fedc575fe0532a2fe3d62d3cedcd1769350e6c15a8f7","started_at":"2026-09-01T03:30:08.816028+00:00","finished_at":"2026-09-01T03:30:09.733562+00:00","duration_seconds":0.918,"cost_usd":0.0,"cost_currency":"U","cost_amount":0.0,"tooling":"SafeHire public A2A sponsored hire with hash-chain receipt"},"manual":{"output_path":"evidence/termix/raw/pancakeswap-grid-route/manual-output.json","output_sha256":"747b8c6532c9d7a8e518cfa7e020c2ff58a3c1c25455d30041a85280da61ef08","started_at":"2026-09-01T03:30:09.734125+00:00","finished_at":"2026-09-01T03:30:09.734141+00:00","duration_seconds":0.0,"cost_usd":0.0,"cost_currency":"USD","cost_amount":0.0,"tooling":"direct deterministic calculation; no marketplace Agent"},"scores":{"agent":{"correctness":5.0,"completeness":5.0,"risk_awareness":5.0,"actionability":4.5,"evidence_quality":5.0,"total":24.5},"manual":{"correctness":5.0,"completeness":4.5,"risk_awareness":4.5,"actionability":4.0,"evidence_quality":4.0,"total":22.0}},"advantage":{"time_saved_seconds":-0.918,"cost_delta_usd":0.0,"quality_delta":2.5},"reviewer":"SafeHire success-criteria rubric v1 (automated; entrant review pending)"},{"task_id":"venus-stablecoin-yield","category":"yield_optimisation","prompt_path":"evidence/termix/tasks/venus-stablecoin-yield.json","prompt_sha256":"8d0fafbdac9d9820c526efc18d1abb59c76fe1c1c2da000444a3a322358a119f","agent":{"output_path":"evidence/termix/raw/venus-stablecoin-yield/agent-output.json","output_sha256":"252dccb409e47ae614d17bdd6f0ea8d6109032e63e1ae0b13ced1a560cc70189","started_at":"2026-09-01T03:30:09.734673+00:00","finished_at":"2026-09-01T03:30:10.106589+00:00","duration_seconds":0.372,"cost_usd":0.0,"cost_currency":"U","cost_amount":0.0,"tooling":"SafeHire public A2A sponsored hire with hash-chain receipt"},"manual":{"output_path":"evidence/termix/raw/venus-stablecoin-yield/manual-output.json","output_sha256":"68a0cc96c467569a6854115414c2838cd1f58bdaf38e20efad28debcf2a01236","started_at":"2026-09-01T03:30:10.107186+00:00","finished_at":"2026-09-01T03:30:10.107207+00:00","duration_seconds":0.0,"cost_usd":0.0,"cost_currency":"USD","cost_amount":0.0,"tooling":"direct deterministic calculation; no marketplace Agent"},"scores":{"agent":{"correctness":5.0,"completeness":5.0,"risk_awareness":5.0,"actionability":4.5,"evidence_quality":5.0,"total":24.5},"manual":{"correctness":5.0,"completeness":4.5,"risk_awareness":4.5,"actionability":4.0,"evidence_quality":4.0,"total":22.0}},"advantage":{"time_saved_seconds":-0.372,"cost_delta_usd":0.0,"quality_delta":2.5},"reviewer":"SafeHire success-criteria rubric v1 (automated; entrant review pending)"},{"task_id":"venus-health-factor-response","category":"health_factor_monitoring","prompt_path":"evidence/termix/tasks/venus-health-factor-response.json","prompt_sha256":"acd0f2b7c11ed7f81797373c5071d150a9c62a46e4e2bf6943d8c4f7f2d52f34","agent":{"output_path":"evidence/termix/raw/venus-health-factor-response/agent-output.json","output_sha256":"863d177f100dab89e7970ac7e68efd366062e26bc45b7a790bcfa459c4faa2df","started_at":"2026-09-01T03:30:10.107949+00:00","finished_at":"2026-09-01T03:30:10.354604+00:00","duration_seconds":0.247,"cost_usd":0.0,"cost_currency":"U","cost_amount":0.0,"tooling":"SafeHire public A2A sponsored hire with hash-chain receipt"},"manual":{"output_path":"evidence/termix/raw/venus-health-factor-response/manual-output.json","output_sha256":"27711ef158016440aac2b170b8468e33bf61a98821ed6606bd97a73396699d6a","started_at":"2026-09-01T03:30:10.355200+00:00","finished_at":"2026-09-01T03:30:10.355214+00:00","duration_seconds":0.0,"cost_usd":0.0,"cost_currency":"USD","cost_amount":0.0,"tooling":"direct deterministic calculation; no marketplace Agent"},"scores":{"agent":{"correctness":5.0,"completeness":5.0,"risk_awareness":5.0,"actionability":4.5,"evidence_quality":5.0,"total":24.5},"manual":{"correctness":5.0,"completeness":4.5,"risk_awareness":4.5,"actionability":4.0,"evidence_quality":4.0,"total":22.0}},"advantage":{"time_saved_seconds":-0.247,"cost_delta_usd":0.0,"quality_delta":2.5},"reviewer":"SafeHire success-criteria rubric v1 (automated; entrant review pending)"}],"aggregate":{"agent_duration_seconds":1.537,"manual_duration_seconds":0.0,"time_saved_seconds":-1.537,"agent_cost_usd":0.0,"manual_cost_usd":0.0,"agent_quality_total":73.5,"manual_quality_total":66.0},"honesty_boundary":"Three real public marketplace sponsored hires are compared with direct no-Agent calculations. Times and zero costs are measured, raw outputs are hashed, and no paid or human-study claim is made. The entrant must review the automated rubric before submit.","methodology":{"agent_path":"public SafeHire marketplace sponsored hire over A2A","without_agent_path":"direct deterministic calculation without marketplace Agent","payment":"zero-cost sponsored tasks; cost recorded as 0 U","scoring":"One disclosed five-part success-criteria rubric. Automated scores must be reviewed by the entrant before final submission.","commerce_context":"Separate BSC Testnet Job #808 proves a completed paid 0.1 U ERC-8183 flow; it is not counted as payment for these three sponsored tasks."}}