{"submission_id":"c204a268-2c1d-48a1-bc5f-86ab739f2909","submission_revision_id":"a1825152-48ca-4045-a2d0-32739071bc2c","revision_version":5,"submission_status":"under_review","submitted_at":"2026-09-23T18:16:24.619909Z","submitter_name":"Yangjunfeng Zhu","submitter_email":"zhuyangjunfeng@gmail.com","task":{"status":"submitted","version":5,"extra_fields":{},"submitted_at":"2026-09-23T18:16:24.619909+00:00","industry_domain":"Sports Science and Exercise Physiology","task_short_name":"mader_metabolic_pipeline","operating_system":"Linux","task_description":"Build a reproducible pipeline for a synthetic five-state endurance model. This is an implementation task, not repair of an old program or a real-athlete diagnosis. Read model_contract.md and numerical_contract.md; use the paper for background. Write pipeline.py with three commands: profile fits VO2max and VLamax from the four fixed effort windows; tmax simulates the first exhaustion event and separately calculates the three-minute coach comparison; plan produces an actual-speed GPX pacing schedule that meets the stated lactate, glycogen, reserve and no-early-exhaustion limits. Deliver profile.json, tmax.json, plan.csv and plan.json alongside the code. Run all three public examples before submission. Hidden athletes and courses follow the same published rules. Do not hard-code the examples or present model predictions as validated training advice.","software_licensing":"Free/Open Source","evaluation_criteria":null,"verification_method":"Require runnable pipeline.py and all four outputs. Re-run each public command twice; require same-host determinism and compare submitted example outputs with the rerun using the published tight numeric tolerance. Check reported effort means against their fixed CSV windows, including the 180-second segment. On hidden synthetic athletes, check fitted VO2max/VLamax and vo2max_load; on hidden loads, check dynamic T-max, net blood-lactate rate, the separate coach-rate comparison and first-event labels. Independently replay every submitted plan over the full GPX terrain at each model step; enforce the four feasibility limits, distance/units/report consistency and the published time baselines. Reward is binary: the worst normalized profile/time/plan-time error must be at most 0.27 and all plans feasible. If private-file isolation cannot be enforced, report an infrastructure error, not a model failure.","software_and_version":"Python 3.12, NumPy 2.0.2","specific_requirements":null,"expected_completion_time":null},"files":[{"file_id":"995178a0-fb3d-4b3b-894a-18896cf453aa","filename":"mader_metabolic_pipeline_input_v3.zip","category":"input_materials","content_type":"application/zip","size_bytes":2017730},{"file_id":"bab8eee2-ee2b-4130-88bd-f3ced44da82b","filename":"mader_metabolic_pipeline_reference_eval_v3.zip","category":"reference_output","content_type":"application/zip","size_bytes":149814}],"deep_review":{"overall_verdict":"Strong Accept","review_text":"**Overall Verdict:** Strong Accept — The revision is complete, coherent, securely evaluable, and provides a reproducible end-to-end implementation task with objective acceptance criteria.\n\n**Completeness Check:**\n- Instruction: Complete — the task card, model contract, numerical contract, and coaching notes define all three commands, equations, units, numerical conventions, output schemas, and feasibility conditions.\n- Inputs: Complete — the input archive contains readable athlete cards, constraints, a valid 4,580-row CSV session, an 844-point GPX course, notes, and an unencrypted 17-page background paper.\n- Toolchain: Complete — Python 3.12 and NumPy 2.0.2 are legally obtainable, Linux-compatible, and sufficient; the reference implementation itself uses only Python’s standard library.\n- Reference output: Complete — runnable reference code, all four expected public artifacts, protected fixtures, frozen expected values, and replay modules are present.\n- Rubric: Complete — hard gates, determinism checks, numeric tolerances, hidden slices, feasibility replay, event-label checks, time baselines, and the binary 0.27 threshold are explicit and implemented consistently.\n\n**File and Task Reachability:**\nThe attachment classification is `reachable`, and the end-to-end task classification is `reachable`. Both `mader_metabolic_pipeline_input_v3.zip` and `mader_metabolic_pipeline_reference_eval_v3.zip` matched their declared sizes, were valid unencrypted ZIP files, passed integrity checks, and contained no traversal paths, links, device entries, or unsafe expansion. Every member was inspected, including the public contracts, notes, JSON cards, CSV, GPX, PDF, task card, provenance and README files; the reference pipeline and helper modules; evaluator, scoring, isolation, and reward code; protected specifications, expected values, fixtures, courses, and public output artifacts. The CSV effort means match the fixed windows, GPX distances and plan timing are internally consistent, JSON files parse, and the PDF contains no JavaScript or embedded files. No content was left unreviewed, and no material tooling limitation affected the assessment. Solver-visible inputs and evaluator-only references are separated, while the evaluator verifies that protected files cannot be read by candidate processes before execution. An ordinary contributor can implement the pipeline on one CPU machine, produce the required artifacts, and be evaluated objectively. License keys, accounts, tokens, and other credentials are not required from the contributor. Confidential, proprietary, or internal material may be evaluated as submitted evidence without requiring additional disclosure.\n\n**Special Screening:**\nNone\n\n**Recommended Changes:**\nThe revision already provides unusually precise public numerical contracts, realistic cross-stage implementation work, protected generalization cases, and independent full-course replay. No changes are required.","reviewed_at":"2026-09-23T18:28:26.230865Z"},"claim":null}