capability_id	lane	current_state	current_model_ids	current_model_run_ids	can_answer_now	cannot_answer_yet	required_dataset_to_unlock	required_outcome_to_unlock	next_decision	handoff_route	evidence_objects
CAP-MODEL-SAME-ASSAY-RESPONSE	Same-assay response baseline	Available as a bounded technical comparator	NMDVCELL-RIDGE-SAFE-2.3	MRUN-RIDGE-SAFE-2.3-G0-REPEATED-FOLD	Whether the released HepG2 CRISPRi ridge baseline improves mean response error within its own processed assay context.; Which permanent controls a future perturbation model must beat before it earns a stronger local claim.	DMD muscle response, pathway reversal, patient response or treatment simulation.; Directionally reliable biology outside the same processed HepG2 task.	A compatible same-assay holdout for continued technical benchmarking.; A harmonized external cell-level perturbation outcome before any transfer claim.	Task-bound response vectors with the same frozen feature space, split rule and leakage controls.; For DMD relevance, matched disease-context perturbation outcomes must be registered separately.	Retain as the permanent comparator every new architecture must clear.	/resource/model-run/mrun-ridge-safe-2-3-g0-repeated-fold/	/resource/model-run/mrun-ridge-safe-2-3-g0-repeated-fold/; /resource/api/v1.1/model-runs/mrun-ridge-safe-2-3-g0-repeated-fold.json; /resource/models/nmdvcell-ridge-safe-2-3/; /resource/dataset/nmdvcell-hepg2-crispri/
CAP-MODEL-EXTERNAL-TRANSFER-COMPARATOR	External transfer and advanced comparators	Executed evidence shows where complex models did not advance	NMDVCELL-TRANSFER-DIAGNOSTIC-1.0	MRUN-TRANSFER-DIAGNOSTIC-1.0-G1; MRUN-GEARS-0.1.2-FIVE-SEED-20260713; MRUN-SCGPT-0.2.5-FIVE-SEED-20260714; MRUN-TXPERT-CONFIG-GAT-SEED-20260712; MRUN-MORPH-DEPMAP25Q3-VALIDATION-20260722	Which frozen advanced-comparator runs failed, stopped or remained negative against the released baselines.; Which provenance, seed and feature-coverage gaps prevent a model-family reputation from becoming local evidence.	General superiority of GEARS, scGPT, TxPert, MORPH or any watched external model inside NMD-VCell.; A valid DMD or muscle-context transfer claim from aggregate HepG2-only evidence.	Harmonized cell-level perturbation outcomes with exact gene-feature alignment and reusable adapters.; External holdouts with preregistered task, split, baseline stack and failure-preserving ModelRun receipts.	Prospective transfer outcomes returned under the same evaluator and permanent baseline policy.; Feature-coverage, seed, code, container and data-digest receipts that make reruns auditable.	Use these runs as a value-producing negative-control library, then bind any new comparator to a fresh frozen task.	/resource/benchmarks/	/resource/benchmarks/; /resource/api/v1.1/model_run_registry.json; /resource/model-run/mrun-transfer-diagnostic-1-0-g1/; /resource/model-run/mrun-gears-0-1-2-five-seed-20260713/; /resource/model-run/mrun-scgpt-0-2-5-five-seed-20260714/; /resource/model-run/mrun-txpert-config-gat-seed-20260712/; /resource/model-run/mrun-morph-depmap25q3-validation-20260722/
CAP-MODEL-DMD-PERTURBATION-RESPONSE	DMD perturbation response	Ready as an evaluation contract; awaiting disease-context truth	NMDVCELL-DMD-TRANSITION-FUTURE; NMDVCELL-GENE-CHEMICAL-BRIDGE-FUTURE		Which exact evidence object is missing before NMD-VCell can train or release a disease-conditioned response model.; How a candidate should move from Evidence Card to Study Card to registered Prediction and returned Outcome.	Candidate-conditioned DMD molecular response, myogenic functional effect, toxicity or calibrated uncertainty.; Gene-to-drug translation in DMD without matched genetic and chemical perturbation screens.	Matched DMD and control myogenic perturbation dataset with donor, state, time, perturbation modality and target-engagement fields.; For the gene–chemical bridge, paired genetic and compound screens in the same relevant muscle-state space.	Replicated molecular plus fusion or viability endpoint returned through Study → Prediction → Outcome objects.; Donor- and context-disjoint holdouts with calibration, abstention and toxicity-miss audits.	Convert the strongest candidate handoffs into a small registered DMD outcome pilot instead of emitting a premature prediction.	/resource/dmd-outcome-pilot/	/resource/models/nmdvcell-dmd-transition-future/; /resource/models/nmdvcell-gene-chemical-bridge-future/; /resource/dmd-outcome-pilot/; /resource/study-card/ZNF133.html; /resource/study-card/MON1A.html
CAP-MODEL-PATIENT-FUNCTIONAL-GENERALIZATION	Patient and functional generalization	Research roadmap with governance requirements	NMDVCELL-PATIENT-TRAJECTORY-FUTURE		What patient-linked validation, privacy and prospective evaluation would require before trajectory modeling becomes meaningful.; Which current artifacts can prepare the path: dataset registry, outcome pilot, distribution contract and ModelRun ledger.	Patient-specific progression, individual treatment response, clinical decision support or therapeutic utility.; Functional recovery claims without longitudinal patient-linked outcomes and independent clinical governance.	Longitudinal patient-linked cell-state, intervention and phenotype datasets with auditable consent and privacy boundaries.; Site-, donor- and time-disjoint cohorts connected to molecular and functional readouts.	Prospective functional outcomes that can test calibration, safety, subgroup performance and clinical utility.; A governance-approved endpoint definition before any patient-facing interpretation is exposed.	Keep this lane as the north-star validation program while near-term work focuses on DMD perturbation truth.	/resource/research-program/	/resource/models/nmdvcell-patient-trajectory-future/; /resource/research-program/; /resource/trajectory/; /resource/distribution-modeling/