SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2305.14874 · 2023

From Words to Wires: Generating Functioning Electronic Devices from Natural Language Descriptions

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 failures of our instrument; 0 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2305.14874.json · badge: /api/ran/2305.14874.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
cognitiveailab/words2wires canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
doPinoutGeneration Ran
ran; our contract draft was wrong, not the code
cognitiveailab/words2wires/GeneratePinouts.py
code served (permissive licence) · get_code("c9212c72cdf73f12")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned dict. The image it ran in was not recorded. If your copy returns the same type on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.nn as nn

class MockEngine:
    """Mock engine that simulates the getResponse method"""
    def getResponse(self, prompt, temperature, maxTokensOut):
        # Simulate a response with pinout information
        response = """
{
    "7479": {
        "description": "Dual D positive-edge triggered flip flop, asynchronous preset and clear",
        "pinout": ["#R1", "D1", "CLK1", "#PR1", "Q1", "#Q1", "VSS", "#Q2", "Q2", "#PR2", "CLK2", "D2", "#R2", "VDD"]
    }
}
"""
        success = True
        numTokensSent = 150
        numTokensReceived = 200
        return response, success, numTokensSent, numTokensReceived

# Create mock engine instance
mock_engine = MockEngine()

# Define ARGS dictionary with all parameters
ARGS = {
    'deviceName': '7479',
    'engine': mock_engine,
    'temperature': 0.0,
    'maxTokensOut': 1000
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
loadDeviceNames Ran
ran; our contract draft was wrong, not the code
cognitiveailab/words2wires/GeneratePinouts.py
code served (permissive licence) · get_code("93671ebf70ce7852")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import tempfile
import os

# Create a temporary file with device data in the expected format
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt')
temp_file.write("# This is a comment\n")
temp_file.write("Device1\tDescription of Device 1\tPinout A\n")
temp_file.write("Device2\tDescription of Device 2\tPinout B\n")
temp_file.write("\n")  # Empty line to test skipping
temp_file.write("Device3\tDescription of Device 3\tPinout C\n")
temp_file.close()

filename_in = temp_file.name

ARGS = {
    'filenameIn': filename_in
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
loadTaskDescriptions Ran
ran; our contract draft was wrong, not the code
cognitiveailab/words2wires/GenerateDevice.py
code served (permissive licence) · get_code("38c9f70040a00b54")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned list, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import tempfile
import os

# Create a temporary file with tab-separated task descriptions
temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt')
temp_filename = temp_file.name

# Write header and sample data
temp_file.write("task_id\ttask_name\tdescription\n")
temp_file.write("1\ttask_one\tFirst task description\n")
temp_file.write("2\ttask_two\tSecond task description\n")
temp_file.write("\n")  # Empty line to test skipping
temp_file.write("# This is a comment\n")  # Comment line to test skipping
temp_file.write("3\ttask_three\tThird task description\n")
temp_file.close()

ARGS = {
    "filenameIn": temp_filename
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type list, ndim 1, dtype family float — a list output has no array shape of its own; none is stated
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block

Also present in other papers' code

Of 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 3 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

In this work, we show that contemporary language models have a previously unknown skill -- the capacity for electronic circuit design from high-level textual descriptions, akin to code generation. We introduce two benchmarks: Pins100, assessing model knowledge of electrical components, and Micro25, evaluating a model's capability to design common microcontroller circuits and code in the Arduino ecosystem that involve input, output, sensors, motors, protocols, and logic -- with models such as GPT-4 and Claude-V1 achieving between 60% to 96% Pass@1 on generating full devices. We include six case studies of using language models as a design assistant for moderately complex devices, such as a radiation-powered random number generator, an emoji keyboard, a visible spectrometer, and several assistive devices, while offering a qualitative analysis performance, outlining evaluation challenges, and suggesting areas of development to improve complex circuit design and practical utility. With this work, we aim to spur research at the juncture of natural language processing and electronic design.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2305.14874")
get_code_for_paper("2305.14874")
have("2305.14874")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2305.14874.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2305.14874.svg)](https://syntology.ai/paper/2305.14874)

Connect an agent — have() is free.