# Alien Coding

arXiv: https://arxiv.org/abs/2301.11479 · HTML: https://mlsanity.com/paper/2301.11479/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- Builds on 13 of its 87 references that are in the map.
- First posted on arXiv 27 Jan 2023.

## Builds on (most cited first, 13 of 13)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [Hindsight Experience Replay](https://mlsanity.com/paper/1707.01495/) (2017)
- [Attention-Based Models for Speech Recognition](https://mlsanity.com/paper/1506.07503/) (2015)
- [Reinforcement Learning of Theorem Proving](https://mlsanity.com/paper/1805.07563/) (2018)
- [Deep Symbolic Regression for Recurrent Sequences](https://mlsanity.com/paper/2201.04600/) (2022)
- [First Experiments with Neural Translation of Informal to Formal Mathematics](https://mlsanity.com/paper/1805.06502/) (2018)
- [First Neural Conjecturing Datasets and Experiments](https://mlsanity.com/paper/2005.14664/) (2020)
- [Hammering Mizar by Learning Clause Guidance](https://mlsanity.com/paper/1904.01677/) (2019)
- [ATPboost: Learning Premise Selection in Binary Setting with ATP Feedback](https://mlsanity.com/paper/1802.03375/) (2018)
- [Can Neural Networks Learn Symbolic Rewriting?](https://mlsanity.com/paper/1911.04873/) (2019)
- [Learning Program Synthesis for Integer Sequences from Scratch](https://mlsanity.com/paper/2202.11908/) (2022)
- [Machine Learning Meets The Herbrand Universe](https://mlsanity.com/paper/2210.03590/) (2022)

## Built on by (most cited first, 9 of 9)

- [130k Lines of Formal Topology in Two Weeks: Simple and Cheap Autoformalization for Everyone?](https://mlsanity.com/paper/2601.03298/) (2026)
- [Learning Guided Automated Reasoning: A Brief Survey](https://mlsanity.com/paper/2403.04017/) (2024)
- [MizAR 60 for Mizar 50](https://mlsanity.com/paper/2303.06686/) (2023)
- [Learning Conjecturing from Scratch](https://mlsanity.com/paper/2503.01389/) (2025)
- [IntSeqBERT: Learning Arithmetic Structure in OEIS via Modulo-Spectrum Embeddings](https://mlsanity.com/paper/2603.05556/) (2026)
- [On the Complexity of Computing G"odel Numbers](https://mlsanity.com/paper/2302.04213/) (2023)
- [Artifical intelligence and inherent mathematical difficulty](https://mlsanity.com/paper/2408.03345/) (2024)
- [DecompRL: Solving Harder Problems by Learning Modular Code Generation](https://mlsanity.com/paper/2607.02390/) (2026)
- [Where Induction Runs Out: Description-Length Difficulty and the Memorisation Gap in Integer-Sequence Benchmarks](https://mlsanity.com/paper/2608.29411/) (2026)

## Abstract (arXiv)

We introduce a self-learning algorithm for synthesizing programs for OEIS sequences. The algorithm starts from scratch initially generating programs at random. Then it runs many iterations of a self-learning loop that interleaves (i) training neural machine translation to learn the correspondence between sequences and the programs discovered so far, and (ii) proposing many new programs for each OEIS sequence by the trained neural machine translator. The algorithm discovers on its own programs for more than 78000 OEIS sequences, sometimes developing unusual programming methods. We analyze its behavior and the invented programs in several experiments.