]> Aevum Network

kwailapt@gmail.com https://github.com/kwailapt/EON

Applications Individual Submission longevity wet-lab automation PACR hypothesis-execution This document specifies WLP v0, the Wet-Lab Protocol for translating AI hypotheses (PACR records) into machine-executable wet-lab instructions. WLP is the longevity-research analogue of SCP (Science Context Protocol) from the photoresist automation domain. The protocol is royalty-free (Apache-2.0). Reference implementations in Rust (crates/wlp-conformance) and Python (agentcard_adapters.wlp_conformance) are provided.

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.

WLP-instruction Schema v0.1

WLP-outcome Schema

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

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

Test	Acceptance Criterion
schema_valid	WLP-instruction has all 8 required top-level fields
pacr_traceable	provenance.pacr_record_id is non-empty
lambda_bounded	lambda_actual_j <= lambda_budget_j
outcome_parseable	WLP-outcome has all 5 required fields
s_t_delta_range	S_T_delta_observed in [-1.0, 1.0]

Execution Flow 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 ]]>

Lambda Throughput Ratio = 0.5) / WLP count >= 1000x ]]>

IANA Considerations This document has no IANA actions.

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.