{"claim":{"id":"90af7194-9c39-4d48-949d-90addaf6dc97","submission_id":"5854cf7b-d435-40f4-a3db-4da13073d702","submission_revision_id":"82510949-37a5-4484-a540-4389aa2e13ef","builder":"builder-01","status":"active","claimed_at":"2026-10-15T15:08:05.275662Z","delivered_at":null,"ended_at":null,"delivery_note":null,"end_reason":null},"task":{"submission_id":"5854cf7b-d435-40f4-a3db-4da13073d702","submission_revision_id":"82510949-37a5-4484-a540-4389aa2e13ef","revision_version":3,"submission_status":"under_review","submitted_at":"2026-08-18T06:03:49.706291Z","submitter_name":"Dongrong Yang","submitter_email":"hlthrevolution21@gmail.com","task":{"status":"submitted","version":3,"extra_fields":{"difficulty_self_test":{"model":"sonnet 5","harness":"claude code","estimated_score":"<1%"}},"submitted_at":"2026-08-18T06:03:49.706291+00:00","industry_domain":"Medical Physics — Proton Therapy Radiobiology","task_short_name":"variable_proton_rbe_model_1","operating_system":"Linux","task_description":"Objective: Act as a radiation-biology / medical-physics researcher and derive an executable variable proton relative biological effectiveness (RBE) model from noisy in-vitro clonogenic cell-survival experiments. The model must generalize to unseen cell lines and proton conditions outside the training tissue-sensitivity and LET ranges.\n\nStarting state: The input bundle contains train_survival.csv (dose-response measurements with uncertainties), train_experiments.csv (experiment-level photon LQ parameters, alpha/beta and LETd), example_query.csv (the exact prediction schema), and complete instructions. Data are synthetic, reproducibly generated, and calibrated to published aggregate properties of proton cell-survival data; no restricted PIDE records are redistributed.\n\nInstructions and rules:\n1. Analyze survival using SF(D)=exp(-alpha*D-beta*D^2).\n2. Choose and fit a biophysically meaningful global model relating proton alpha_p and beta_p to photon alpha_x, beta_x, tissue alpha/beta and LETd.\n3. Handle uncertainty and alpha-beta degeneracy; validate extrapolation rather than only fitting individual curves.\n4. Create predict_rbe.py, executable as: python predict_rbe.py --input experiments.csv --output predictions.csv.\n5. Output exactly exp_id,alpha_p,beta_p, one row per query.\n6. Predictions must be finite, positive, physically plausible, and use only staged offline data.\n7. The evaluator will independently run the submitted program on hidden cell lines and hidden extrapolated conditions.\n\nExpected deliverable: the executable prediction program plus any local parameter/model files it requires.","software_licensing":"Free/Open Source","evaluation_criteria":null,"verification_method":"The evaluator must independently execute the submitted predict_rbe.py on hidden query experiments; agent-reported metrics are never trusted. All conditions are required:\n\n1. Output/schema gate: predictions.csv contains exp_id, alpha_p and beta_p, exactly one finite positive prediction per hidden query.\n2. Physics gate: RBE_max=alpha_p/alpha_x is at least 1 within tolerance, and RBE at 2 Gy is within [0.95, 3.0].\n3. RBE@50% survival mean absolute error <= 0.11.\n4. RBE@10% survival mean absolute error <= 0.08.\n5. Log-surviving-fraction RMSE over the measurable survival window <= 0.18.\n6. Both RBE errors must be <=60% of the corresponding clinical constant-RBE=1.1 baseline errors.\n\nHidden test cell lines do not occur in training; their alpha/beta values lie outside the training range and LETd includes values above the training maximum. The uploaded reference/evaluation bundle contains the self-contained grader, hidden query/ground-truth assets, reference solution, reproducible generation documentation, and calibration evidence. The expert reference passes 7/7 checks; constant RBE, fixed tissue-exponent models and generic regressors fail.","software_and_version":"Python 3.11; NumPy 1.26.4; pandas 2.2.2; SciPy 1.13.0","specific_requirements":null,"expected_completion_time":null},"files":[{"file_id":"389ab026-d787-40fb-8800-bba62ed873b7","filename":"proton-rbe-input-materials.zip","category":"input_materials","content_type":"application/zip","size_bytes":46555},{"file_id":"9df52d94-b336-46ab-b5af-c07110763cc9","filename":"proton-rbe-reference-evaluation.zip","category":"reference_output","content_type":"application/zip","size_bytes":61218}],"deep_review":{"overall_verdict":"Accept","review_text":"**Overall Verdict:** Accept — The task is complete, professionally scoped, self-contained, and objectively evaluable, with only minor nonblocking data and verifier inconsistencies.\n\n**Completeness Check:**\n- Instruction: Complete — The objective, LQ survival model, modeling expectations, executable interface, offline constraint, output schema, and extrapolation requirement are clear.\n- Inputs: Complete — The three documented CSV inputs are readable and usable, containing 203 training experiment identifiers, 42 cell lines, and 1,456 survival measurements with positive uncertainties and no missing fields. One identifier represents two nearly identical LET conditions because 17.58 and 17.59 were both rounded to `17.6`; this is nonblocking for the intended global pointwise fit.\n- Toolchain: Complete — The pinned Python scientific stack is open source, CPU-compatible, and adequately provisioned by the supplied Linux container definition.\n- Reference output: Complete — A reference prediction program, packaging wrapper, 68 held-out queries, 436 ground-truth survival rows, calibration notes, and the independent evaluator are supplied. The referenced dataset-generation source programs are not included, so the generation and baseline claims cannot be reproduced from first principles, but this is not required for task completion or fixed-data evaluation.\n- Rubric: Complete — Seven executable checks cover required predictions, finite positive parameters, physical plausibility, RBE errors at two survival levels, log-survival error, and improvement over the clinical baseline. The verifier is slightly looser than the written contract because it permits extra columns, extra or duplicate rows, and uses `0.95` as the RBE-max tolerance.\n\n**File and Task Reachability:**\nThe attachment classification is `reachable`, and the task classification is `reachable`. Both `proton-rbe-input-materials.zip` and `proton-rbe-reference-evaluation.zip` were inspected: they are readable, unencrypted ZIP archives matching their manifested sizes, with 7 and 14 safe text, CSV, Python, shell, JSON, TOML, and container-definition entries respectively. All attached content was reviewed; submitted programs were inspected statically and not executed. Training and held-out cell lines are disjoint, held-out alpha/beta and LET ranges genuinely extrapolate beyond training, and query metadata agrees with every ground-truth row. Solver-visible training assets are separated from reference solutions and evaluator-only truth. The end-to-end path is viable on one ordinary CPU machine: fit from staged survival data, write the required prediction program, run it on hidden query rows, and evaluate its output against supplied truth with deterministic numerical thresholds. 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 scientific workflow, reference method, hidden extrapolation design, and independent scoring path are valid. No material changes are required. Optional hardening would assign unique experiment identifiers to the two rounded LET conditions, enforce the exact output columns and row cardinality in the verifier, align the RBE-max tolerance with the written requirement, and include the referenced generation sources if full provenance reproduction is intended.","reviewed_at":"2026-08-18T17:29:57.902868Z"},"claim":{"id":"90af7194-9c39-4d48-949d-90addaf6dc97","submission_id":"5854cf7b-d435-40f4-a3db-4da13073d702","submission_revision_id":"82510949-37a5-4484-a540-4389aa2e13ef","builder":"builder-01","status":"active","claimed_at":"2026-10-15T15:08:05.275662Z","delivered_at":null,"ended_at":null,"delivery_note":null,"end_reason":null}},"revision_is_current":true}