kind,id,label,extra
paper,arxiv:2608.13940,AI Research Preference Models,
cites,arxiv:1711.09846,Population based training of neural networks,arxiv:2608.13940 reference list (arXiv HTML bibliography)
cites,arxiv:2301.04104,Mastering diverse domains through world models,arxiv:2608.13940 reference list (arXiv HTML bibliography)
cites,arxiv:2408.06292,The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery,Foster et al. 2026 Related Work / References: Lu et al. (2024) The AI Scientist arXiv:2408.06292
cites,arxiv:2502.13138,Aide: Ai-driven exploration in the space of code,arxiv:2608.13940 reference list (arXiv HTML bibliography)
cites,arxiv:2510.02387,Cwm: An open-weights llm for research on code generation with world models,arxiv:2608.13940 reference list (arXiv HTML bibliography)
cites,arxiv:2601.03267,Openai gpt-5 system card,arxiv:2608.13940 reference list (arXiv HTML bibliography)
cites,arxiv:2601.05930,Can We Predict Before Executing Machine Learning Agents?,Foster et al. 2026 References: Zheng et al. (2026) Can we predict before executing machine learning agents? arXiv:2601.05930
cites,arxiv:2602.02660,MARS: modular agent with reflective search for automated ai research,arxiv:2608.13940 reference list (arXiv HTML bibliography)
cites,arxiv:2602.06855,AIRS-Bench: a Suite of Tasks for Frontier AI Research Science Agents,arxiv:2608.13940 reference list (arXiv HTML bibliography)
cites,arxiv:2603.17863,DiscoGen: Procedural Generation of Algorithm Discovery Tasks in Machine Learning,Foster et al. 2026 References: Goldie et al. (2026) DiscoGen arXiv:2603.17863
claim,ts-claim-c3-ai-scientist-s2-novelty,The AI Scientist’s idea-generation filter discards ideas that are too similar to existing literature by querying the Semantic Scholar API (plus web access); novelty is therefore a retrieved-paper simi,proposed
claim,ts-claim-z1-listwise-collapse-global-discrimination,The drop of Accuracy@1 from 61.3% (N=2) to 31.1% (N=5) in Table 3 indicates that the LLM judge lacks global discrimination capability beyond binary interactions.,contradicted
claim,ts-claim-s1-novelty-not-significance,"A claim can be graph-novel vs TeamScience JSONL and still be insignificant if it would not change a #177 rule, a cheapest test, or the next ingest walk.",proposed