{"url":"/task/scientific-discovery","name":"scientific discovery","slug":"scientific-discovery","description_markdown":null,"categories":[{"name":"Miscellaneous","url":"/area/miscellaneous"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"derived"},"counts":{"papers_tagged":464,"papers_with_code":192,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":0,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":192,"tagged_in_all":464,"items":[{"url":"/paper/discovering-physical-concepts-with-neural","title":"Discovering physical concepts with neural networks","date":"2018-07-26","arxiv_id":"1807.10300","repositories_listed":7,"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":3}},{"url":"/paper/nnu-net-breaking-the-spell-on-successful","title":"Automated Design of Deep Learning Methods for Biomedical Image Segmentation","date":"2019-04-17","arxiv_id":"1904.08128","repositories_listed":6,"syntology":null},{"url":"/paper/structure-discovery-in-nonparametric","title":"Structure Discovery in Nonparametric Regression through Compositional Kernel Search","date":"2013-02-20","arxiv_id":"1302.4922","repositories_listed":5,"syntology":null},{"url":"/paper/can-llms-generate-novel-research-ideas-a","title":"Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers","date":"2024-09-06","arxiv_id":"2409.04109","repositories_listed":3,"syntology":{"n":5,"n_ran":0,"n_unverified":5,"n_pointer_only":0}},{"url":"/paper/automl-two-sample-test","title":"AutoML Two-Sample Test","date":"2022-06-17","arxiv_id":"2206.08843","repositories_listed":3,"syntology":{"n":11,"n_ran":10,"n_unverified":1,"n_pointer_only":2}},{"url":"/paper/2506-08618","title":"HSG-12M: A Large-Scale Spatial Multigraph Dataset","date":"2025-06-10","arxiv_id":"2506.08618","repositories_listed":2,"syntology":{"n":14,"n_ran":6,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/llamea-bo-a-large-language-model-evolutionary","title":"LLaMEA-BO: A Large Language Model Evolutionary Algorithm for Automatically Generating Bayesian Optimization Algorithms","date":"2025-05-27","arxiv_id":"2505.21034","repositories_listed":2,"syntology":null},{"url":"/paper/ai-driven-automation-can-become-the","title":"AI-Driven Automation Can Become the Foundation of Next-Era Science of Science Research","date":"2025-05-17","arxiv_id":"2505.12039","repositories_listed":2,"syntology":null},{"url":"/paper/hypobench-towards-systematic-and-principled","title":"HypoBench: Towards Systematic and Principled Benchmarking for Hypothesis Generation","date":"2025-04-15","arxiv_id":"2504.11524","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":0}},{"url":"/paper/the-ai-scientist-v2-workshop-level-automated","title":"The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Search","date":"2025-04-10","arxiv_id":"2504.08066","repositories_listed":2,"syntology":{"n":3,"n_ran":1,"n_unverified":2,"n_pointer_only":3}},{"url":"/paper/2503-00096","title":"BixBench: a Comprehensive Benchmark for LLM-based Agents in Computational Biology","date":"2025-02-28","arxiv_id":"2503.00096","repositories_listed":2,"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/agent-laboratory-using-llm-agents-as-research","title":"Agent Laboratory: Using LLM Agents as Research Assistants","date":"2025-01-08","arxiv_id":"2501.04227","repositories_listed":2,"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/two-heads-are-better-than-one-a-multi-agent","title":"Many Heads Are Better Than One: Improved Scientific Idea Generation by A LLM-Based Multi-Agent System","date":"2024-10-12","arxiv_id":"2410.09403","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/sciagents-automating-scientific-discovery","title":"SciAgents: Automating scientific discovery through multi-agent intelligent graph reasoning","date":"2024-09-09","arxiv_id":"2409.05556","repositories_listed":2,"syntology":{"n":2,"n_ran":2,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/the-ai-scientist-towards-fully-automated-open","title":"The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery","date":"2024-08-12","arxiv_id":"2408.06292","repositories_listed":2,"syntology":{"n":11,"n_ran":10,"n_unverified":1,"n_pointer_only":9}},{"url":"/paper/llm-sr-scientific-equation-discovery-via","title":"LLM-SR: Scientific Equation Discovery via Programming with Large Language Models","date":"2024-04-29","arxiv_id":"2404.18400","repositories_listed":2,"syntology":null},{"url":"/paper/autonomous-llm-driven-research-from-data-to","title":"Autonomous LLM-driven research from data to human-verifiable research papers","date":"2024-04-24","arxiv_id":"2404.17605","repositories_listed":2,"syntology":null},{"url":"/paper/deep-generative-symbolic-regression","title":"Deep Generative Symbolic Regression","date":"2023-12-30","arxiv_id":"2401.00282","repositories_listed":2,"syntology":{"n":5,"n_ran":3,"n_unverified":2,"n_pointer_only":5}},{"url":"/paper/a-transformer-model-for-symbolic-regression","title":"A Transformer Model for Symbolic Regression towards Scientific Discovery","date":"2023-12-07","arxiv_id":"2312.04070","repositories_listed":2,"syntology":null},{"url":"/paper/sum-of-parts-models-faithful-attributions-for","title":"Sum-of-Parts: Faithful Attributions for Groups of Features","date":"2023-10-25","arxiv_id":"2310.16316","repositories_listed":2,"syntology":{"n":7,"n_ran":5,"n_unverified":2,"n_pointer_only":7}},{"url":"/paper/multi-fidelity-active-learning-with-gflownets","title":"Multi-Fidelity Active Learning with GFlowNets","date":"2023-06-20","arxiv_id":"2306.11715","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/automated-gadget-discovery-in-science","title":"Automated Gadget Discovery in Science","date":"2022-12-24","arxiv_id":"2212.12743","repositories_listed":2,"syntology":null},{"url":"/paper/selection-by-prediction-with-conformal-p","title":"Selection by Prediction with Conformal p-values","date":"2022-10-04","arxiv_id":"2210.01408","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_unverified":0,"n_pointer_only":3}},{"url":"/paper/explaining-patterns-in-data-with-language","title":"Explaining Patterns in Data with Language Models via Interpretable Autoprompting","date":"2022-10-04","arxiv_id":"2210.01848","repositories_listed":2,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/quantitative-probing-validating-causal-models","title":"Quantitative probing: Validating causal models using quantitative domain knowledge","date":"2022-09-07","arxiv_id":"2209.03013","repositories_listed":2,"syntology":null},{"url":"/paper/3d-transformer-molecular-representation-with","title":"Molformer: Motif-based Transformer on 3D Heterogeneous Molecular Graphs","date":"2021-10-04","arxiv_id":"2110.01191","repositories_listed":2,"syntology":{"n":4,"n_ran":3,"n_unverified":1,"n_pointer_only":4}},{"url":"/paper/neural-symbolic-regression-that-scales","title":"Neural Symbolic Regression that Scales","date":"2021-06-11","arxiv_id":"2106.06427","repositories_listed":2,"syntology":{"n":7,"n_ran":4,"n_unverified":3,"n_pointer_only":0}},{"url":"/paper/data-driven-discovery-of-physical-laws-with","title":"Data-driven discovery of Green's functions with human-understandable deep learning","date":"2021-05-01","arxiv_id":"2105.00266","repositories_listed":2,"syntology":{"n":9,"n_ran":0,"n_unverified":9,"n_pointer_only":0}},{"url":"/paper/differentiable-learning-under-triage","title":"Differentiable Learning Under Triage","date":"2021-03-16","arxiv_id":"2103.08902","repositories_listed":2,"syntology":null},{"url":"/paper/using-deep-networks-for-scientific-discovery","title":"Using Deep Networks for Scientific Discovery in Physiological Signals","date":"2020-08-25","arxiv_id":"2008.10936","repositories_listed":2,"syntology":null}],"syntology_records":19,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}