WLP: Wet-Lab Protocol -- AI-to-Automation Instruction Schema v0

Status of This Memo

This Internet-Draft is submitted in full conformance with the provisions of BCP 78 and BCP 79.¶

Internet-Drafts are working documents of the Internet Engineering Task Force (IETF). Note that other groups may also distribute working documents as Internet-Drafts. The list of current Internet-Drafts is at https://datatracker.ietf.org/drafts/current/.¶

Internet-Drafts are draft documents valid for a maximum of six months and may be updated, replaced, or obsoleted by other documents at any time. It is inappropriate to use Internet-Drafts as reference material or to cite them other than as "work in progress."¶

This Internet-Draft will expire on 20 November 2026.¶

Copyright Notice

Copyright (c) 2026 IETF Trust and the persons identified as the document authors. All rights reserved.¶

This document is subject to BCP 78 and the IETF Trust's Legal Provisions Relating to IETF Documents (https://trustee.ietf.org/license-info) in effect on the date of publication of this document. Please review these documents carefully, as they describe your rights and restrictions with respect to this document.¶

Table of Contents

1. Introduction

WLP closes the loop between AI hypothesis generation and physical experimental execution without human translation. Each WLP-instruction carries a PACR provenance link and a lambda (energy) budget, enabling full cost accounting and falsifiability tracing.¶

Key design principles: (1) AI-to-Machine direct translation -- WLP- instructions are machine-executable; (2) PACR traceable -- every instruction has a pacr_record_id provenance link; (3) lambda budget constrained -- platforms MUST reject over-budget instructions; (4) Conformance verifiable -- any platform can run the Conformance Suite.¶

2. WLP-instruction Schema v0.1

{
  "wlp_version": "0.1",
  "instruction_id": "WLP-{gene}-{yyyymmdd}-{seq}",
  "target": {
    "gene": "FOXO3",
    "itt_l_id": "ITT-L-001",
    "h_itt_v2": 0.72
  },
  "intervention": {
    "type": "crispr_knockdown | compound | overexpression | sirna | small_molecule",
    "reagent": "sgRNA-FOXO3-001",
    "dose": {"value": 10, "unit": "nM | uM | mg/kg"},
    "window": {"start_day": 0, "end_day": 14}
  },
  "readout": {
    "primary": "S_T_delta",
    "secondary": ["lifespan_extension_pct", "healthspan_marker"],
    "model": "C_elegans | mouse | organoid | cell_line",
    "timepoint_days": [7, 14, 30]
  },
  "expected": {
    "S_T_delta": 0.05,
    "confidence": 0.65,
    "basis": "superlearner_dqn_v2"
  },
  "constraints": {
    "lambda_budget_j": 500,
    "max_duration_days": 30,
    "min_replicates": 3
  },
  "provenance": {
    "generated_by": "II:superlearner-meta-v1",
    "pacr_record_id": "pacr-discovery-v3:line-XXXXXX",
    "wlp_conformance": "v0.1"
  }
}

3. WLP-outcome Schema

{
  "instruction_id": "WLP-FOXO3-20260519-001",
  "executed_by": "wet-lab-node-001",
  "execution_date": "2026-05-26",
  "result": {
    "S_T_delta_observed": 0.048,
    "S_T_delta_expected": 0.050,
    "prediction_accuracy": 0.96,
    "replicates": 3,
    "p_value": 0.023
  },
  "lambda_actual_j": 420,
  "falsification_triggered": false,
  "notes": ""
}

4. AgentCard Extension

Wet-lab nodes MUST declare capability via AgentCard extension fields:¶

{
  "execution_capability": ["crispr-screen", "organoid-assay",
                            "model-organism", "compound-screen"],
  "wlp_version": "0.1",
  "throughput": {
    "assays_per_week": 10,
    "lambda_capacity_j_per_week": 5000
  }
}

5. Conformance Requirements

An implementation is conformant if it passes all 5 tests. Reference test vectors are in crates/wlp-conformance/src/lib.rs.¶

6. Execution Flow

Superlearner DQN
  -> generate WLP-instruction
  -> write to ~/.eon/bus/wlp-queue.jsonl
        |
        v
wlp_dispatcher.py
  -> match wet-lab-node AgentCard (execution_capability filter)
  -> send WLP-instruction to node
        |
        v
Automated wet-lab platform
  -> execute experiment
  -> return WLP-outcome.json
        |
        v
wlp_outcome_bridge.py
  -> convert to PACR record (domain="wet_lab")
  -> write to ~/.eon/pacr-wet-lab-v1.jsonl

7. Lambda Throughput Ratio

lambda_throughput_ratio = PACR_virtual_hypotheses / WLP_executed_instructions

Target (Day 90): filtered hypotheses (H_ITT_v2 >= 0.5) / WLP count >= 1000x

8. IANA Considerations

This document has no IANA actions.¶

9. Security Considerations

WLP-instructions carry lambda budgets that MUST be enforced by execution platforms to prevent resource exhaustion. PACR provenance links MUST be validated before execution.¶

Author's Address