{"ok": true, "database": "team-science", "query_name": "bridge_candidates", "rows": [["arxiv:2309.02726", "Large language models for automated open-domain scientific hypotheses discovery, 2024", 2024, 2, "CS / ML / automated science,metascience / TeamScience ops"], ["arxiv:2310.06770", "Swe-bench: Can language models resolve real-world github issues?, 2024", 2024, 2, "CS / ML / automated science,metascience / TeamScience ops"], ["arxiv:2312.02139", "Diffit: Diffusion vision transformers for image generation, 2024", 2024, 2, "CS / ML / automated science,metascience / TeamScience ops"], ["arxiv:2401.04088", "Mixtral of experts, 2024", 2024, 2, "CS / ML / automated science,metascience / TeamScience ops"], ["arxiv:2401.04259", "Marg: Multi-agent review generation for scientific papers, 2024", 2024, 2, "CS / ML / automated science,metascience / TeamScience ops"], ["arxiv:2402.00854", "Symbolicai: A framework for logic-based approaches combining generative models and solvers, 2024", 2024, 2, "CS / ML / automated science,metascience / TeamScience ops"], ["arxiv:2402.18381", "Large language models as evolution strategies", 2024, 2, "CS / ML / automated science,metascience / TeamScience ops"], ["arxiv:2404.07738", "Researchagent: Iterative research idea generation over scientific literature with large language models, 2024", 2024, 2, "CS / ML / automated science,metascience / TeamScience ops"], ["arxiv:2404.15794", "Large language models as in-context ai generators for quality-diversity", 2024, 2, "CS / ML / automated science,metascience / TeamScience ops"], ["arxiv:2404.17605", "Autonomous llm-driven research from data to human-verifiable research papers, 2024", 2024, 2, "CS / ML / automated science,metascience / TeamScience ops"], ["arxiv:2405.03547", "Position paper: Leveraging foundational models for black-box optimization: Benefits, challenges, and future directions", 2024, 2, "CS / ML / automated science,metascience / TeamScience ops"], ["arxiv:2405.15143", "Intelligent go-explore: Standing on the shoulders of giant foundation models, 2024b", 2024, 2, "CS / ML / automated science,metascience / TeamScience ops"], ["arxiv:2405.15568", "Omni-epic: Open-endedness via models of human notions of interestingness with environments programmed in code, 2024", 2024, 2, "CS / ML / automated science,metascience / TeamScience ops"], ["arxiv:2406.08414", "Discovering preference optimization algorithms with and for large language models", 2024, 2, "CS / ML / automated science,metascience / TeamScience ops"], ["arxiv:2406.10252", "Autosurvey: Large language models can automatically write surveys, 2024c", 2024, 2, "CS / ML / automated science,metascience / TeamScience ops"], ["arxiv:2406.11931", "Deepseek-coder-v2: Breaking the barrier of closed-source models in code intelligence", 2024, 2, "CS / ML / automated science,metascience / TeamScience ops"], ["arxiv:2407.01725", "Discoverybench: Towards data-driven discovery with large language models, 2024", 2024, 2, "CS / ML / automated science,metascience / TeamScience ops"], ["arxiv:2407.21783", "The llama 3 herd of models, 2024", 2024, 2, "CS / ML / automated science,metascience / TeamScience ops"], ["arxiv:2305.14259", "Scimon: Scientific inspiration machines optimized for novelty, 2024b", 2023, 2, "CS / ML / automated science,metascience / TeamScience ops"], ["arxiv:2306.08647", "Language to rewards for robotic skill synthesis", 2023, 2, "CS / ML / automated science,metascience / TeamScience ops"], ["arxiv:2310.12931", "Eureka: Human-level reward design via coding large language models", 2023, 2, "CS / ML / automated science,metascience / TeamScience ops"], ["arxiv:2312.09390", "Weak-to-strong generalization: Eliciting strong capabilities with weak supervision, 2023", 2023, 2, "CS / ML / automated science,metascience / TeamScience ops"], ["arxiv:2201.02177", "Grokking: Generalization beyond overfitting on small algorithmic datasets", 2022, 2, "CS / ML / automated science,metascience / TeamScience ops"], ["arxiv:2203.11171", "Self-consistency improves chain of thought reasoning in language models", 2022, 2, "CS / ML / automated science,metascience / TeamScience ops"], ["arxiv:2206.08896", "Evolution through large models, 2022", 2022, 2, "CS / ML / automated science,metascience / TeamScience ops"], ["arxiv:2209.11895", "In-context learning and induction heads", 2022, 2, "CS / ML / automated science,metascience / TeamScience ops"], ["arxiv:2211.09760", "Velo: Training versatile learned optimizers by scaling up", 2022, 2, "CS / ML / automated science,metascience / TeamScience ops"], ["arxiv:2107.03374", "Evaluating large language models trained on code", 2021, 2, "CS / ML / automated science,metascience / TeamScience ops"], ["arxiv:2003.05325", "Meta-learning curiosity algorithms", 2020, 2, "CS / ML / automated science,metascience / TeamScience ops"], ["arxiv:1905.10985", "Ai-gas: Ai-generating algorithms, an alternate paradigm for producing general artificial intelligence", 2019, 2, "CS / ML / automated science,metascience / TeamScience ops"], ["arxiv:1910.04098", "Improving generalization in meta reinforcement learning using learned objectives", 2019, 2, "CS / ML / automated science,metascience / TeamScience ops"], ["doi:10.18653/v1/n19-1421", "CommonsenseQA: A question answering challenge targeting commonsense knowledge", 2019, 2, "CS / ML / automated science,metascience / TeamScience ops"], ["arxiv:1812.08775", "Deep paper gestalt", 2018, 2, "CS / ML / automated science,metascience / TeamScience ops"], ["openalex:W3017344694", "(untitled in OpenAlex)", null, 2, "climate / NLP / claim verification,CS / NLP / metascience"]], "truncated": false, "columns": ["lom_id", "title", "year", "claim_domains", "domains"], "query": {"sql": "select p.lom_id, p.title, p.year, count(distinct rc.domain) as claim_domains, group_concat(distinct rc.domain) as domains from paper p join citation_edge e on e.to_lom_id = p.lom_id join claim rc on rc.about_lom_id = e.from_lom_id left join claim c on c.about_lom_id = p.lom_id where c.id is null group by p.lom_id having claim_domains >= 2 order by claim_domains desc, p.year desc limit 100", "params": {}}, "error": null, "private": false, "allow_execute_sql": true, "query_ms": 4.439919721335173, "source": "TeamScience Space repository", "source_url": "https://commons.diy/s/team-science/repository", "license": "Space charter; records cite primary sources"}