# The Implementation Lottery: Auditing Idea Reliability in Automated Research

arXiv: https://arxiv.org/abs/2607.26587 · HTML: https://mlsanity.com/paper/2607.26587/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 61 references that are in the map.
- First posted on arXiv 29 Jul 2026.

## Builds on (most cited first, 30 of 30)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [Deep Reinforcement Learning at the Edge of the Statistical Precipice](https://mlsanity.com/paper/2108.13264/) (2021)
- [Deep Reinforcement Learning that Matters](https://mlsanity.com/paper/1709.06560/) (2017)
- [OpenML: networked science in machine learning](https://mlsanity.com/paper/1407.7722/) (2014)
- [Underspecification Presents Challenges for Credibility in Modern Machine Learning](https://mlsanity.com/paper/2011.03395/) (2020)
- [Agent Laboratory: Using LLM Agents as Research Assistants](https://mlsanity.com/paper/2501.04227/) (2025)
- [The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search](https://mlsanity.com/paper/2504.08066/) (2025)
- [Accelerating scientific discovery with Co-Scientist](https://mlsanity.com/paper/2502.18864/) (2025)
- [Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers](https://mlsanity.com/paper/2409.04109/) (2024)
- [Accounting for Variance in Machine Learning Benchmarks](https://mlsanity.com/paper/2103.03098/) (2021)
- [OpenML Benchmarking Suites](https://mlsanity.com/paper/1708.03731/) (2017)
- [Towards End-to-End Automation of AI Research](https://mlsanity.com/paper/2606.15497/) (2026)
- [The Benchmark Lottery](https://mlsanity.com/paper/2107.07002/) (2021)
- [MLGym: A New Framework and Benchmark for Advancing AI Research Agents](https://mlsanity.com/paper/2502.14499/) (2025)
- [Measuring what Matters: Construct Validity in Large Language Model Benchmarks](https://mlsanity.com/paper/2511.04703/) (2025)
- [Towards a Science of AI Agent Reliability](https://mlsanity.com/paper/2602.16666/) (2026)
- [MLR-Bench: Evaluating AI Agents on Open-Ended Machine Learning Research](https://mlsanity.com/paper/2505.19955/) (2025)
- [The Ideation-Execution Gap: Execution Outcomes of LLM-Generated versus Human Research Ideas](https://mlsanity.com/paper/2506.20803/) (2025)
- [ResearchCodeBench: Benchmarking LLMs on Implementing Novel Machine Learning Research Code](https://mlsanity.com/paper/2506.02314/) (2025)
- [LMR-BENCH: Evaluating LLM Agent's Ability on Reproducing Language Modeling Research](https://mlsanity.com/paper/2506.17335/) (2025)
- [Towards Execution-Grounded Automated AI Research](https://mlsanity.com/paper/2601.14525/) (2026)
- [Dolphin: Moving Towards Closed-loop Auto-research through Thinking, Practice, and Feedback](https://mlsanity.com/paper/2501.03916/) (2025)
- [ResearchGym: Evaluating Language Model Agents on Real-World AI Research](https://mlsanity.com/paper/2602.15112/) (2026)
- [From Reproduction to Replication: Evaluating Research Agents with Progressive Code Masking](https://mlsanity.com/paper/2506.19724/) (2025)
- [Stochasticity in Agentic Evaluations: Quantifying Inconsistency with Intraclass Correlation](https://mlsanity.com/paper/2512.06710/) (2025)
- [Auto Research with Specialist Agents Develops Effective and Non-Trivial Training Recipes](https://mlsanity.com/paper/2605.05724/) (2026)
- [Many AI Analysts, One Dataset: Navigating the Agentic Data Science Multiverse](https://mlsanity.com/paper/2602.18710/) (2026)
- [Closed-loop Auto Research for Molecular Property Prediction: Discovering and Certifying Generalizable Improvements](https://mlsanity.com/paper/2606.22731/) (2026)
- [Auto Research for Materials: Auditable AI-Scientist Workflows with Held-Out Transfer](https://mlsanity.com/paper/2607.17100/) (2026)

## Built on by (most cited first, 5 of 5)

- [Scores Alone Do Not Prove Discovery: The Discovery Certification Protocol for Auditing AI Research Agents](https://mlsanity.com/paper/2609.09219/) (2026)
- [WhatWorkedBench: Benchmarking Experimental Understanding in AI Agents](https://mlsanity.com/paper/2609.27490/) (2026)
- [ControlScope: Workflow Revision and Reliability in LLM Agents](https://mlsanity.com/paper/2609.34313/) (2026)
- [Rules to Tools: Executable Checks for LLM Agents in Scientific Computing](https://mlsanity.com/paper/2610.00313/) (2026)
- [Re-executing Coding-Agent Evaluations: Unchanged Decisions and Unresolved Policy Risk](https://mlsanity.com/paper/2610.14460/) (2026)

## Abstract (arXiv)

Automated research agents use program scores to judge ideas. We call variation in this evidence across implementations the implementation lottery. We introduce an Idea Reliability Audit that freezes mechanism specifications, samples independent programs, and compares selected code with fresh implementations of its mechanism. Across 3,048 assignments on 31 tabular classification tasks, all four primary aggregation tests have Holm-adjusted p≥0.56. Under mean-of-five selection, the prespecified secondary intention-to-treat comparison gives selected-code premiums of 0.38 [0.08, 0.82] and 0.45 [0.05, 1.12] accuracy-equivalent points for Bounded and Agentic execution, respectively. Minimum task-deletion means are 0.20 and 0.14. Fidelity conditioning exposes concentration: the Agentic premium falls from 0.33 to 0.01 when one task is removed. Post-outcome analysis finds cross-split variation on 41 of 70 paired cards per process. Exploratory replay gives nearly equal Bounded point losses at four and twenty implementations; Agentic point losses decrease across the four evaluated budget rules. Under duration costs, one seed per program minimizes fitted common-design variance. The two-seed design becomes preferable when implementation-to-seed cost ratios exceed approximately 13 or 9.5 in the continuous-budget model. The audit distinguishes evidence for reusing a selected artifact from evidence for implementing its idea again.