Execution contract
Execute the competitive blueprint as governed research objects.
This contract converts competitor lessons into concrete dataset-import, Cell Browser, ModelRun, perturbation-network, prospective-benchmark and outcome-chain gates. It makes the next work executable without pretending that pathway deltas are already predicted.
Implemented work
The project now has execution gates, not only competitor lessons.
Execution units6
Network nodes15
Network edges18
DMD delta predictions0
Perturbation network contract
A real virtual-cell path is now represented as a locked, auditable network.
Runnable gates
Each unit has a current state, next action and acceptance gate.
| Unit | Axis | State | Next action | Acceptance gate |
|---|---|---|---|---|
V95-DATASET-IMPORT | Dataset import | EXECUTABLE_SPEC_READY | Register candidate DMD single-cell, single-nucleus and spatial datasets with donor, disease, state, perturbation and checksum fields before browsing. | At least two disease-relevant datasets have stable accessions, donor-level metadata, raw/processed SHA-256, license and prohibited-use fields. |
V95-CELL-BROWSER | Real Cell Browser | PLANNED_REQUIRES_DATA_IMPORT | Replace concept-only context cards with donor-filtered cell-state panels, expression lookup, pseudobulk differential tables and exportable selections. | Browser selections resolve to Dataset object IDs and never summarize disease effect without donor-aware aggregation. |
V95-MODELRUN | ModelRun adapter | LEDGER_RELEASED_NO_DMD_RUN | Use the frozen ModelRun ledger as the single execution-history source and require every future baseline or advanced model to append the same envelope. | Completed negative runs remain visible; model id, revision, container status, data release, split, seed, metrics, gate and missing provenance are explicit. |
V95-PERTURBATION-NETWORK | Perturbation delta network | CONTRACT_READY_DELTA_LOCKED | Bind candidate perturbations to pathway modules, cell-state transitions, functional readouts and the missing evidence edge that would unlock each delta. | Every edge declares observed, inferred, planned or locked state; layout seed is fixed and node position is not interpreted as biology. |
V95-PROSPECTIVE-BENCHMARK | Prospective benchmark | SPEC_READY_NO_HIDDEN_OUTCOMES | Freeze Study Card, Prediction Card and Outcome slots before laboratory outcomes are visible. | Timestamped prediction objects exist before outcome access, with null, toxic, failed-QC and abstained outcomes preserved. |
V95-OUTCOME-CHAIN | Outcome return path | OBJECT_SCHEMA_READY_NO_MEASURED_OUTCOME | Append measured outcomes to the same object chain that generated the study and prediction records. | Study -> Prediction -> Experiment -> Outcome IDs remain linked without regenerating downstream IDs from URL parameters. |
V95-* prefixes are immutable research-object identifiers retained for citation; they are not the current interface build.
Edge audit
Every edge says whether it supports a delta prediction.
| Edge | Relation | Evidence state | Supports delta prediction |
|---|---|---|---|
QUESTION -> GENE_ZNF133 | candidate_input | USER_SELECTABLE | No |
QUESTION -> GENE_MON1A | candidate_input | USER_SELECTABLE | No |
QUESTION -> GENE_GFOD2 | audit_input | USER_SELECTABLE | No |
GENE_ZNF133 -> DATASET_IMPORT | requires_matched_context | PLANNED | No |
GENE_MON1A -> DATASET_IMPORT | requires_matched_context | PLANNED | No |
GENE_GFOD2 -> DATASET_IMPORT | requires_external_audit | LOCKED_PENDING_IMPORT | No |
DATASET_IMPORT -> CELL_BROWSER | populates_browser | PLANNED | No |
CELL_BROWSER -> PATHWAY_MYOGENESIS | annotates_module | CONTEXT_ONLY | No |
CELL_BROWSER -> PATHWAY_FIBROSIS | annotates_module | CONTEXT_ONLY | No |
CELL_BROWSER -> PATHWAY_MITO | annotates_module | CONTEXT_ONLY | No |
PATHWAY_MYOGENESIS -> CELL_STATE | would_emit_cell_state_delta | LOCKED_NO_MATCHED_TRUTH | No |
PATHWAY_FIBROSIS -> CELL_STATE | would_emit_cell_state_delta | LOCKED_NO_MATCHED_TRUTH | No |
PATHWAY_MITO -> FUNCTION | would_emit_function_delta | LOCKED_NO_FUNCTIONAL_OUTCOME | No |
CELL_STATE -> MODELRUN | candidate_training_target | REQUIRES_OUTCOME | No |
FUNCTION -> MODELRUN | candidate_training_target | REQUIRES_OUTCOME | No |
MODELRUN -> PREDICTION_CARD | writes_prediction_object | SPEC_READY_EMPTY | No |
PREDICTION_CARD -> OUTCOME | prospective_comparison | LOCKED_NO_OUTCOME | No |
OUTCOME -> CLAIM_BOUNDARY | could_update_claim_boundary_after_validation | FUTURE_ONLY | No |