SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2003.05562 · NeurIPS · 2020

Learning Compositional Rules via Neural Program Synthesis

Joshua Tenenbaum, Maxwell Nye, Armando Solar-Lezama, Mit Brenden, M Lake, Nyu Facebook

arXiv · PDF · Open in the Atlas

Code that ran

4 of 5 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (1 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 3 failures of our instrument; 1 no recorded run), measured 2026-11-21; 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/2003.05562.json · badge: /api/ran/2003.05562.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
mtensor/rulesynthesis canonical (classifier label)
classifier basis: classifier_2025
4 ran · 1 no recorded run
FunctionStatusWhere it lives
PositionalEncoder Ran
ran on a synthesized input · constructed an object; no result was computed
mtensor/rulesynthesis/batched_synth_net.py
pointer only (licence: NONE) · get_code("4de24e46c8209aaf")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mtensor/rulesynthesis when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

asMinutes Ran
ran; our contract draft was wrong, not the code
mtensor/rulesynthesis/train_metanet_attn.py
pointer only (licence: NONE) · get_code("324537dd7c7ee111")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mtensor/rulesynthesis when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

make_hashable Ran
ran; our contract draft was wrong, not the code
mtensor/rulesynthesis/train_metanet_attn.py
pointer only (licence: NONE) · get_code("39b0d55da5e13f32")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mtensor/rulesynthesis when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

timeSince Ran
ran; our contract draft was wrong, not the code
mtensor/rulesynthesis/train_metanet_attn.py
pointer only (licence: NONE) · get_code("c0a5b7ee10788222")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mtensor/rulesynthesis when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

BatchedRuleSynthEncoderRNN Not yet run
unverified (harvested, no recorded run)
mtensor/rulesynthesis/batched_synth_net.py
pointer only (licence: NONE) · get_code("018a3d57a65e2241")
How it ran

The body of this sample is withheld: GitHub detected no licence in this paper's repository, mtensor/rulesynthesis when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. No invocation recorded.

Also present in other papers' code

Of 5 samples lifted from this paper's linked repositories, 5 carry a function identity and 0 do not. Of the 5 distinct functions with an identity, 2 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 2 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.

FunctionAlso present inEarliest-datedOthers named
timeSince 4 other papers
4 later
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2202.13330 (2022-02)
DialFRED: Dialogue-Enabled Agents for Embodied Instruction Following
2305.07766 (2023-05)
NL2TL: Transforming Natural Languages to Temporal Logics using Large Language Models
and 1 more not named here
asMinutes 3 other papers
3 later
2006.11239 (2020-06)
Denoising Diffusion Probabilistic Models
2202.13330 (2022-02)
DialFRED: Dialogue-Enabled Agents for Embodied Instruction Following
2305.07766 (2023-05)
NL2TL: Transforming Natural Languages to Temporal Logics using Large Language Models

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 2026-11-21.

Repositories linked to this paper

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

Abstract

Many aspects of human reasoning, including language, require learning rules from very little data. Humans can do this, often learning systematic rules from very few examples, and combining these rules to form compositional rule-based systems. Current neural architectures, on the other hand, often fail to generalize in a compositional manner, especially when evaluated in ways that vary systematically from training. In this work, we present a neuro-symbolic model which learns entire rule systems from a small set of examples. Instead of directly predicting outputs from inputs, we train our model to induce the explicit system of rules governing a set of previously seen examples, drawing upon techniques from the neural program synthesis literature. Our rule-synthesis approach outperforms neural meta-learning techniques in three domains: an artificial instruction-learning domain used to evaluate human learning, the SCAN challenge datasets, and learning rule-based translations of number words into integers for a wide range of human languages.

For agents

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

get_harvested_code_for_paper("2003.05562")
get_code_for_paper("2003.05562")
have("2003.05562")

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

curl https://syntology.ai/api/ran/2003.05562.json

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

[![Syntology run record](https://syntology.ai/api/ran/2003.05562.svg)](https://syntology.ai/paper/2003.05562)

Connect an agent — have() is free.