{"about":{"non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","site":"https://codewithpapers.app","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"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 (most first), then date (newest first), then slug; the archive holds no stars","population":"every paper the archive tags with this task (distinct papers; spam titles not listed). 'of' counts the papers listed; until 2026-09-25 it counted only the papers with a code link, and that number is of_with_code","page":1,"pages_in_order":5,"rows_per_page":100,"shown":100,"of":464,"of_with_code":192,"tagged_in_all":464,"counts":{"archive_papers_tagged":464,"with_a_code_link":192,"where_syntology_ran_a_sample":58,"not_listed_spam_title":0,"listed":464,"listed_where_code_ran":58,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":41,"every_run_a_failure_of_syntologys_instrument":17,"listed_with_a_run_with_no_instrument_failure":41,"listed_every_run_a_failure_of_syntologys_instrument":17,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"items":[{"url":"/paper/discovering-physical-concepts-with-neural","slug":"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":6,"n_constructed":0,"n_ran_checked":6,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":3,"n_no_contract":2,"n_pointer_only":3,"phrase":"6 ran (of which 0 constructed an object rather than computing a result; 6 with no instrument failure: 1 honoured, 3 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/discovering-physical-concepts-with-neural#ran","syntology_url":"https://syntology.ai/paper/1807.10300","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1807.10300"}},"official":{"repos":["eth-nn-physics/nn_physical_concepts"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/nnu-net-breaking-the-spell-on-successful","slug":"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","slug":"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","slug":"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":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 2 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/can-llms-generate-novel-research-ideas-a#ran","syntology_url":"https://syntology.ai/paper/2409.04109","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.04109"}},"official":{"repos":["NoviScl/AI-Researcher"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/automl-two-sample-test","slug":"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_constructed":0,"n_ran_checked":2,"n_instrument":8,"n_unverified":1,"n_honours":2,"n_violates":0,"n_no_contract":0,"n_pointer_only":2,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 2 honoured, 0 violated, 0 with no contract checked; 8 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/automl-two-sample-test#ran","syntology_url":"https://syntology.ai/paper/2206.08843","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2206.08843"}},"official":{"repos":["antoninschrab/fl-mmdagg","jmkuebler/auto-tst","jmkuebler/automl-tst-paper"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":1,"ran_from_kinds":["official","unlocated"]}}},{"url":"/paper/2506-08618","slug":"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":10,"n_constructed":0,"n_ran_checked":5,"n_instrument":5,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/2506-08618#ran","syntology_url":"https://syntology.ai/paper/2506.08618","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.08618"}},"official":{"repos":["sarinstein-yan/hsg-12m","sarinstein-yan/poly2graph"],"state":"official (archive's flag): 10 ran","n_ran":10,"n_constructed":0,"n_ran_no_instrument_failure":5,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/llamea-bo-a-large-language-model-evolutionary","slug":"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","slug":"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","slug":"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":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/hypobench-towards-systematic-and-principled#ran","syntology_url":"https://syntology.ai/paper/2504.11524","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.11524"}},"official":null}},{"url":"/paper/the-ai-scientist-v2-workshop-level-automated","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/the-ai-scientist-v2-workshop-level-automated#ran","syntology_url":"https://syntology.ai/paper/2504.08066","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2504.08066"}},"official":{"repos":["sakanaai/ai-scientist-iclr2025-workshop-experiment","sakanaai/ai-scientist-v2"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/2503-00096","slug":"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":9,"n_constructed":0,"n_ran_checked":9,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":9,"n_pointer_only":0,"phrase":"9 ran (of which 0 constructed an object rather than computing a result; 9 with no instrument failure: 0 honoured, 0 violated, 9 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/2503-00096#ran","syntology_url":"https://syntology.ai/paper/2503.00096","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.00096"}},"official":{"repos":["Future-House/BixBench","Future-House/data-analysis-crow"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":9,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/agent-laboratory-using-llm-agents-as-research","slug":"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":5,"n_constructed":0,"n_ran_checked":5,"n_instrument":0,"n_unverified":4,"n_honours":0,"n_violates":0,"n_no_contract":5,"n_pointer_only":0,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 5 with no instrument failure: 0 honoured, 0 violated, 5 with no contract checked; 0 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/agent-laboratory-using-llm-agents-as-research#ran","syntology_url":"https://syntology.ai/paper/2501.04227","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2501.04227"}},"official":null}},{"url":"/paper/two-heads-are-better-than-one-a-multi-agent","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/two-heads-are-better-than-one-a-multi-agent#ran","syntology_url":"https://syntology.ai/paper/2410.09403","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.09403"}},"official":{"repos":["open-sciencelab/social_science","open-sciencelab/virtual-scientists"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/sciagents-automating-scientific-discovery","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/sciagents-automating-scientific-discovery#ran","syntology_url":"https://syntology.ai/paper/2409.05556","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2409.05556"}},"official":{"repos":["lamm-mit/SciAgentsDiscovery"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/the-ai-scientist-towards-fully-automated-open","slug":"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_constructed":0,"n_ran_checked":7,"n_instrument":3,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":6,"n_pointer_only":9,"phrase":"10 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 1 honoured, 0 violated, 6 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/the-ai-scientist-towards-fully-automated-open#ran","syntology_url":"https://syntology.ai/paper/2408.06292","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.06292"}},"official":{"repos":["sakanaai/ai-scientist"],"state":"official (archive's flag): 9 ran","n_ran":9,"n_constructed":0,"n_ran_no_instrument_failure":6,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/llm-sr-scientific-equation-discovery-via","slug":"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","slug":"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","slug":"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_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":5,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/deep-generative-symbolic-regression#ran","syntology_url":"https://syntology.ai/paper/2401.00282","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2401.00282"}},"official":{"repos":["samholt/deepgenerativesymbolicregression","vanderschaarlab/deepgenerativesymbolicregression"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/a-transformer-model-for-symbolic-regression","slug":"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","slug":"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_constructed":0,"n_ran_checked":2,"n_instrument":3,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":7,"phrase":"5 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/sum-of-parts-models-faithful-attributions-for#ran","syntology_url":"https://syntology.ai/paper/2310.16316","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2310.16316"}},"official":{"repos":["brachiolab/sop","debugml/sop"],"state":"official (archive's flag): 5 ran","n_ran":5,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/multi-fidelity-active-learning-with-gflownets","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/multi-fidelity-active-learning-with-gflownets#ran","syntology_url":"https://syntology.ai/paper/2306.11715","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.11715"}},"official":{"repos":["nikita-0209/mf-al-gfn"],"state":"official: no sample here; runs from other or unrecorded repositories","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["named_in_paper"]}}},{"url":"/paper/automated-gadget-discovery-in-science","slug":"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/explaining-patterns-in-data-with-language","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/explaining-patterns-in-data-with-language#ran","syntology_url":"https://syntology.ai/paper/2210.01848","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.01848"}},"official":{"repos":["csinva/imodelsX"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/selection-by-prediction-with-conformal-p","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":3,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/selection-by-prediction-with-conformal-p#ran","syntology_url":"https://syntology.ai/paper/2210.01408","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2210.01408"}},"official":{"repos":["ying531/selcf_paper"],"state":"community repositories only","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed"]}}},{"url":"/paper/quantitative-probing-validating-causal-models","slug":"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","slug":"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_constructed":0,"n_ran_checked":0,"n_instrument":3,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":4,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/3d-transformer-molecular-representation-with#ran","syntology_url":"https://syntology.ai/paper/2110.01191","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.01191"}},"official":{"repos":["smiles724/3d-transformer","smiles724/molformer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/neural-symbolic-regression-that-scales","slug":"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_constructed":4,"n_ran_checked":4,"n_instrument":0,"n_unverified":3,"n_honours":0,"n_violates":0,"n_no_contract":4,"n_pointer_only":0,"phrase":"4 ran (of which 4 constructed an object rather than computing a result; 4 with no instrument failure: 0 honoured, 0 violated, 4 with no contract checked; 0 where Syntology's instrument failed) · 3 unverified; every one of the 4 samples that ran constructed an object rather than computing a result","sample_list":"/paper/neural-symbolic-regression-that-scales#ran","syntology_url":"https://syntology.ai/paper/2106.06427","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.06427"}},"official":{"repos":["SymposiumOrganization/NeuralSymbolicRegressionThatScales"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":["listed"]}}},{"url":"/paper/data-driven-discovery-of-physical-laws-with","slug":"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":2,"n_constructed":0,"n_ran_checked":2,"n_instrument":0,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 2 with no instrument failure: 0 honoured, 0 violated, 2 with no contract checked; 0 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/data-driven-discovery-of-physical-laws-with#ran","syntology_url":"https://syntology.ai/paper/2105.00266","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2105.00266"}},"official":{"repos":["NBoulle/greenlearning"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":2,"n_unverified":7,"ran_from_kinds":["official"]}}},{"url":"/paper/differentiable-learning-under-triage","slug":"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","slug":"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},{"url":"/paper/transformation-importance-with-applications","slug":"transformation-importance-with-applications","title":"Transformation Importance with Applications to Cosmology","date":"2020-03-04","arxiv_id":"2003.01926","repositories_listed":2,"syntology":{"n":3,"n_ran":3,"n_constructed":1,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 ran (of which 1 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/transformation-importance-with-applications#ran","syntology_url":"https://syntology.ai/paper/2003.01926","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2003.01926"}},"official":{"repos":["csinva/transformation-importance"],"state":"official (archive's flag): 2 ran","n_ran":2,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["listed","official"]}}},{"url":"/paper/physics-guided-neural-networks-pgnn-an","slug":"physics-guided-neural-networks-pgnn-an","title":"Physics-guided Neural Networks (PGNN): An Application in Lake Temperature Modeling","date":"2017-10-31","arxiv_id":"1710.11431","repositories_listed":2,"syntology":null},{"url":"/paper/open-source-planning-control-system-with","slug":"open-source-planning-control-system-with","title":"Open Source Planning & Control System with Language Agents for Autonomous Scientific Discovery","date":"2025-07-09","arxiv_id":"2507.07257","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/open-source-planning-control-system-with#ran","syntology_url":"https://syntology.ai/paper/2507.07257","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2507.07257"}},"official":{"repos":["cmbagents/cmbagent"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["community","official"]}}},{"url":"/paper/structsense-a-task-agnostic-agentic-framework","slug":"structsense-a-task-agnostic-agentic-framework","title":"STRUCTSENSE: A Task-Agnostic Agentic Framework for Structured Information Extraction with Human-In-The-Loop Evaluation and Benchmarking","date":"2025-07-04","arxiv_id":"2507.03674","repositories_listed":1,"syntology":null},{"url":"/paper/from-reproduction-to-replication-evaluating","slug":"from-reproduction-to-replication-evaluating","title":"From Reproduction to Replication: Evaluating Research Agents with Progressive Code Masking","date":"2025-06-24","arxiv_id":"2506.19724","repositories_listed":1,"syntology":null},{"url":"/paper/lmr-bench-evaluating-llm-agent-s-ability-on","slug":"lmr-bench-evaluating-llm-agent-s-ability-on","title":"LMR-BENCH: Evaluating LLM Agent's Ability on Reproducing Language Modeling Research","date":"2025-06-19","arxiv_id":"2506.17335","repositories_listed":1,"syntology":{"n":6,"n_ran":4,"n_constructed":0,"n_ran_checked":1,"n_instrument":3,"n_unverified":2,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":6,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 3 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/lmr-bench-evaluating-llm-agent-s-ability-on#ran","syntology_url":"https://syntology.ai/paper/2506.17335","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.17335"}},"official":{"repos":["du-nlp-lab/lmr-bench"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/climatechat-designing-data-and-methods-for","slug":"climatechat-designing-data-and-methods-for","title":"ClimateChat: Designing Data and Methods for Instruction Tuning LLMs to Answer Climate Change Queries","date":"2025-06-12","arxiv_id":"2506.13796","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":1,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/climatechat-designing-data-and-methods-for#ran","syntology_url":"https://syntology.ai/paper/2506.13796","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2506.13796"}},"official":{"repos":["thu-esis/jiuzhou"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/aline-joint-amortization-for-bayesian","slug":"aline-joint-amortization-for-bayesian","title":"ALINE: Joint Amortization for Bayesian Inference and Active Data Acquisition","date":"2025-06-08","arxiv_id":"2506.07259","repositories_listed":1,"syntology":null},{"url":"/paper/2506-04553","slug":"2506-04553","title":"Unsupervised Machine Learning for Scientific Discovery: Workflow and Best Practices","date":"2025-06-05","arxiv_id":"2506.04553","repositories_listed":1,"syntology":null},{"url":"/paper/matter-of-fact-a-benchmark-for-verifying-the","slug":"matter-of-fact-a-benchmark-for-verifying-the","title":"Matter-of-Fact: A Benchmark for Verifying the Feasibility of Literature-Supported Claims in Materials Science","date":"2025-06-04","arxiv_id":"2506.04410","repositories_listed":1,"syntology":null},{"url":"/paper/bioreason-incentivizing-multimodal-biological","slug":"bioreason-incentivizing-multimodal-biological","title":"BioReason: Incentivizing Multimodal Biological Reasoning within a DNA-LLM Model","date":"2025-05-29","arxiv_id":"2505.23579","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_constructed":0,"n_ran_checked":8,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":8,"n_pointer_only":0,"phrase":"8 ran (of which 0 constructed an object rather than computing a result; 8 with no instrument failure: 0 honoured, 0 violated, 8 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/bioreason-incentivizing-multimodal-biological#ran","syntology_url":"https://syntology.ai/paper/2505.23579","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.23579"}},"official":{"repos":["bowang-lab/bioreason"],"state":"official (archive's flag): 8 ran","n_ran":8,"n_constructed":0,"n_ran_no_instrument_failure":8,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/safescientist-toward-risk-aware-scientific","slug":"safescientist-toward-risk-aware-scientific","title":"SafeScientist: Toward Risk-Aware Scientific Discoveries by LLM Agents","date":"2025-05-29","arxiv_id":"2505.23559","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/safescientist-toward-risk-aware-scientific#ran","syntology_url":"https://syntology.ai/paper/2505.23559","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.23559"}},"official":{"repos":["ulab-uiuc/safescientist"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/mlr-bench-evaluating-ai-agents-on-open-ended","slug":"mlr-bench-evaluating-ai-agents-on-open-ended","title":"MLR-Bench: Evaluating AI Agents on Open-Ended Machine Learning Research","date":"2025-05-26","arxiv_id":"2505.19955","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_constructed":0,"n_ran_checked":0,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"0 ran · 1 unverified","sample_list":"/paper/mlr-bench-evaluating-ai-agents-on-open-ended#ran","syntology_url":"https://syntology.ai/paper/2505.19955","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.19955"}},"official":{"repos":["chchenhui/mlrbench"],"state":"official: harvested, nothing ran","n_ran":0,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":1,"ran_from_kinds":[]}}},{"url":"/paper/ai-researcher-autonomous-scientific","slug":"ai-researcher-autonomous-scientific","title":"AI-Researcher: Autonomous Scientific Innovation","date":"2025-05-24","arxiv_id":"2505.18705","repositories_listed":1,"syntology":null},{"url":"/paper/biomedsql-text-to-sql-for-scientific","slug":"biomedsql-text-to-sql-for-scientific","title":"BiomedSQL: Text-to-SQL for Scientific Reasoning on Biomedical Knowledge Bases","date":"2025-05-23","arxiv_id":"2505.20321","repositories_listed":1,"syntology":null},{"url":"/paper/moose-chem3-toward-experiment-guided","slug":"moose-chem3-toward-experiment-guided","title":"MOOSE-Chem3: Toward Experiment-Guided Hypothesis Ranking via Simulated Experimental Feedback","date":"2025-05-23","arxiv_id":"2505.17873","repositories_listed":1,"syntology":null},{"url":"/paper/piflow-principle-aware-scientific-discovery","slug":"piflow-principle-aware-scientific-discovery","title":"PiFlow: Principle-aware Scientific Discovery with Multi-Agent Collaboration","date":"2025-05-21","arxiv_id":"2505.15047","repositories_listed":1,"syntology":null},{"url":"/paper/mm-agent-llm-as-agents-for-real-world","slug":"mm-agent-llm-as-agents-for-real-world","title":"MM-Agent: LLM as Agents for Real-world Mathematical Modeling Problem","date":"2025-05-20","arxiv_id":"2505.14148","repositories_listed":1,"syntology":null},{"url":"/paper/toward-reliable-biomedical-hypothesis","slug":"toward-reliable-biomedical-hypothesis","title":"Toward Reliable Biomedical Hypothesis Generation: Evaluating Truthfulness and Hallucination in Large Language Models","date":"2025-05-20","arxiv_id":"2505.14599","repositories_listed":1,"syntology":null},{"url":"/paper/from-automation-to-autonomy-a-survey-on-large","slug":"from-automation-to-autonomy-a-survey-on-large","title":"From Automation to Autonomy: A Survey on Large Language Models in Scientific Discovery","date":"2025-05-19","arxiv_id":"2505.13259","repositories_listed":1,"syntology":null},{"url":"/paper/robin-a-multi-agent-system-for-automating","slug":"robin-a-multi-agent-system-for-automating","title":"Robin: A multi-agent system for automating scientific discovery","date":"2025-05-19","arxiv_id":"2505.13400","repositories_listed":1,"syntology":null},{"url":"/paper/interfeat-an-automated-pipeline-for-finding","slug":"interfeat-an-automated-pipeline-for-finding","title":"InterFeat: An Automated Pipeline for Finding Interesting Hypotheses in Structured Biomedical Data","date":"2025-05-18","arxiv_id":"2505.13534","repositories_listed":1,"syntology":null},{"url":"/paper/when-ai-co-scientists-fail-spot-a-benchmark","slug":"when-ai-co-scientists-fail-spot-a-benchmark","title":"When AI Co-Scientists Fail: SPOT-a Benchmark for Automated Verification of Scientific Research","date":"2025-05-17","arxiv_id":"2505.11855","repositories_listed":1,"syntology":null},{"url":"/paper/benchmarking-ai-scientists-in-omics-data","slug":"benchmarking-ai-scientists-in-omics-data","title":"Benchmarking AI scientists in omics data-driven biological research","date":"2025-05-13","arxiv_id":"2505.08341","repositories_listed":1,"syntology":null},{"url":"/paper/iris-interactive-research-ideation-system-for","slug":"iris-interactive-research-ideation-system-for","title":"IRIS: Interactive Research Ideation System for Accelerating Scientific Discovery","date":"2025-04-23","arxiv_id":"2504.16728","repositories_listed":1,"syntology":null},{"url":"/paper/the-ai-cosmologist-i-an-agentic-system-for","slug":"the-ai-cosmologist-i-an-agentic-system-for","title":"The AI Cosmologist I: An Agentic System for Automated Data Analysis","date":"2025-04-04","arxiv_id":"2504.03424","repositories_listed":1,"syntology":null},{"url":"/paper/how-deep-do-large-language-models-internalize","slug":"how-deep-do-large-language-models-internalize","title":"How Deep Do Large Language Models Internalize Scientific Literature and Citation Practices?","date":"2025-04-03","arxiv_id":"2504.02767","repositories_listed":1,"syntology":null},{"url":"/paper/ai-newton-a-concept-driven-physical-law","slug":"ai-newton-a-concept-driven-physical-law","title":"AI-Newton: A Concept-Driven Physical Law Discovery System without Prior Physical Knowledge","date":"2025-04-02","arxiv_id":"2504.01538","repositories_listed":1,"syntology":null},{"url":"/paper/detecting-localized-density-anomalies-in","slug":"detecting-localized-density-anomalies-in","title":"Detecting Localized Density Anomalies in Multivariate Data via Coin-Flip Statistics","date":"2025-03-31","arxiv_id":"2503.23927","repositories_listed":1,"syntology":null},{"url":"/paper/agentrxiv-towards-collaborative-autonomous","slug":"agentrxiv-towards-collaborative-autonomous","title":"AgentRxiv: Towards Collaborative Autonomous Research","date":"2025-03-23","arxiv_id":"2503.18102","repositories_listed":1,"syntology":{"n":9,"n_ran":2,"n_constructed":0,"n_ran_checked":1,"n_instrument":1,"n_unverified":7,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 1 where Syntology's instrument failed) · 7 unverified","sample_list":"/paper/agentrxiv-towards-collaborative-autonomous#ran","syntology_url":"https://syntology.ai/paper/2503.18102","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.18102"}},"official":null}},{"url":"/paper/offline-model-based-optimization","slug":"offline-model-based-optimization","title":"Offline Model-Based Optimization: Comprehensive Review","date":"2025-03-21","arxiv_id":"2503.17286","repositories_listed":1,"syntology":null},{"url":"/paper/microvqa-a-multimodal-reasoning-benchmark-for","slug":"microvqa-a-multimodal-reasoning-benchmark-for","title":"MicroVQA: A Multimodal Reasoning Benchmark for Microscopy-Based Scientific Research","date":"2025-03-17","arxiv_id":"2503.13399","repositories_listed":1,"syntology":null},{"url":"/paper/can-language-models-falsify-evaluating","slug":"can-language-models-falsify-evaluating","title":"Can Language Models Falsify? Evaluating Algorithmic Reasoning with Counterexample Creation","date":"2025-02-26","arxiv_id":"2502.19414","repositories_listed":1,"syntology":null},{"url":"/paper/protein-large-language-models-a-comprehensive","slug":"protein-large-language-models-a-comprehensive","title":"Protein Large Language Models: A Comprehensive Survey","date":"2025-02-21","arxiv_id":"2502.17504","repositories_listed":1,"syntology":null},{"url":"/paper/inductionbench-llms-fail-in-the-simplest","slug":"inductionbench-llms-fail-in-the-simplest","title":"InductionBench: LLMs Fail in the Simplest Complexity Class","date":"2025-02-20","arxiv_id":"2502.15823","repositories_listed":1,"syntology":{"n":4,"n_ran":3,"n_constructed":0,"n_ran_checked":3,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 0 honoured, 0 violated, 3 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/inductionbench-llms-fail-in-the-simplest#ran","syntology_url":"https://syntology.ai/paper/2502.15823","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.15823"}},"official":{"repos":["wenyueh/inductive_reasoning_benchmark"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/agentic-deep-graph-reasoning-yields-self","slug":"agentic-deep-graph-reasoning-yields-self","title":"Agentic Deep Graph Reasoning Yields Self-Organizing Knowledge Networks","date":"2025-02-18","arxiv_id":"2502.13025","repositories_listed":1,"syntology":null},{"url":"/paper/k-paths-reasoning-over-graph-paths-for-drug","slug":"k-paths-reasoning-over-graph-paths-for-drug","title":"K-Paths: Reasoning over Graph Paths for Drug Repurposing and Drug Interaction Prediction","date":"2025-02-18","arxiv_id":"2502.13344","repositories_listed":1,"syntology":null},{"url":"/paper/diffms-diffusion-generation-of-molecules","slug":"diffms-diffusion-generation-of-molecules","title":"DiffMS: Diffusion Generation of Molecules Conditioned on Mass Spectra","date":"2025-02-13","arxiv_id":"2502.09571","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/diffms-diffusion-generation-of-molecules#ran","syntology_url":"https://syntology.ai/paper/2502.09571","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2502.09571"}},"official":{"repos":["coleygroup/diffms"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/physics-guided-foundation-model-for","slug":"physics-guided-foundation-model-for","title":"Physics-Guided Foundation Model for Scientific Discovery: An Application to Aquatic Science","date":"2025-02-10","arxiv_id":"2502.06084","repositories_listed":1,"syntology":null},{"url":"/paper/transforming-science-with-large-language","slug":"transforming-science-with-large-language","title":"Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluation","date":"2025-02-07","arxiv_id":"2502.05151","repositories_listed":1,"syntology":null},{"url":"/paper/safety-at-scale-a-comprehensive-survey-of","slug":"safety-at-scale-a-comprehensive-survey-of","title":"Safety at Scale: A Comprehensive Survey of Large Model Safety","date":"2025-02-02","arxiv_id":"2502.05206","repositories_listed":1,"syntology":null},{"url":"/paper/ocsu-optical-chemical-structure-understanding","slug":"ocsu-optical-chemical-structure-understanding","title":"OCSU: Optical Chemical Structure Understanding for Molecule-centric Scientific Discovery","date":"2025-01-26","arxiv_id":"2501.15415","repositories_listed":1,"syntology":null},{"url":"/paper/in-situ-graph-reasoning-and-knowledge","slug":"in-situ-graph-reasoning-and-knowledge","title":"In-situ graph reasoning and knowledge expansion using Graph-PReFLexOR","date":"2025-01-14","arxiv_id":"2501.08120","repositories_listed":1,"syntology":null},{"url":"/paper/boxinggym-benchmarking-progress-in-automated","slug":"boxinggym-benchmarking-progress-in-automated","title":"BoxingGym: Benchmarking Progress in Automated Experimental Design and Model Discovery","date":"2025-01-02","arxiv_id":"2501.01540","repositories_listed":1,"syntology":null},{"url":"/paper/dropmicrofluidagents-dmfas-autonomous-droplet","slug":"dropmicrofluidagents-dmfas-autonomous-droplet","title":"DropMicroFluidAgents (DMFAs): Autonomous Droplet Microfluidic Research Framework Through Large Language Model Agents","date":"2024-12-30","arxiv_id":"2501.14772","repositories_listed":1,"syntology":null},{"url":"/paper/from-generalist-to-specialist-a-survey-of","slug":"from-generalist-to-specialist-a-survey-of","title":"From Generalist to Specialist: A Survey of Large Language Models for Chemistry","date":"2024-12-28","arxiv_id":"2412.19994","repositories_listed":1,"syntology":null},{"url":"/paper/llm4ad-a-platform-for-algorithm-design-with","slug":"llm4ad-a-platform-for-algorithm-design-with","title":"LLM4AD: A Platform for Algorithm Design with Large Language Model","date":"2024-12-23","arxiv_id":"2412.17287","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-discovery-of-formulas-for","slug":"unsupervised-discovery-of-formulas-for","title":"Unsupervised Discovery of Formulas for Mathematical Constants","date":"2024-12-22","arxiv_id":"2412.16818","repositories_listed":1,"syntology":null},{"url":"/paper/bridging-ai-and-science-implications-from-a","slug":"bridging-ai-and-science-implications-from-a","title":"Bridging AI and Science: Implications from a Large-Scale Literature Analysis of AI4Science","date":"2024-11-27","arxiv_id":"2412.09628","repositories_listed":1,"syntology":null},{"url":"/paper/aigs-generating-science-from-ai-powered","slug":"aigs-generating-science-from-ai-powered","title":"AIGS: Generating Science from AI-Powered Automated Falsification","date":"2024-11-17","arxiv_id":"2411.11910","repositories_listed":1,"syntology":null},{"url":"/paper/ideabench-benchmarking-large-language-models","slug":"ideabench-benchmarking-large-language-models","title":"IdeaBench: Benchmarking Large Language Models for Research Idea Generation","date":"2024-10-31","arxiv_id":"2411.02429","repositories_listed":1,"syntology":null},{"url":"/paper/aiscivision-a-framework-for-specializing","slug":"aiscivision-a-framework-for-specializing","title":"AiSciVision: A Framework for Specializing Large Multimodal Models in Scientific Image Classification","date":"2024-10-28","arxiv_id":"2410.21480","repositories_listed":1,"syntology":null},{"url":"/paper/from-tokens-to-materials-leveraging-language","slug":"from-tokens-to-materials-leveraging-language","title":"From Tokens to Materials: Leveraging Language Models for Scientific Discovery","date":"2024-10-21","arxiv_id":"2410.16165","repositories_listed":1,"syntology":null},{"url":"/paper/improving-parallel-program-performance","slug":"improving-parallel-program-performance","title":"Improving Parallel Program Performance with LLM Optimizers via Agent-System Interfaces","date":"2024-10-21","arxiv_id":"2410.15625","repositories_listed":1,"syntology":null},{"url":"/paper/geometry-aware-generative-autoencoders-for","slug":"geometry-aware-generative-autoencoders-for","title":"Geometry-Aware Generative Autoencoders for Warped Riemannian Metric Learning and Generative Modeling on Data Manifolds","date":"2024-10-16","arxiv_id":"2410.12779","repositories_listed":1,"syntology":null},{"url":"/paper/moose-chem-large-language-models-for","slug":"moose-chem-large-language-models-for","title":"MOOSE-Chem: Large Language Models for Rediscovering Unseen Chemistry Scientific Hypotheses","date":"2024-10-09","arxiv_id":"2410.07076","repositories_listed":1,"syntology":{"n":8,"n_ran":4,"n_constructed":0,"n_ran_checked":3,"n_instrument":1,"n_unverified":4,"n_honours":1,"n_violates":0,"n_no_contract":2,"n_pointer_only":0,"phrase":"4 ran (of which 0 constructed an object rather than computing a result; 3 with no instrument failure: 1 honoured, 0 violated, 2 with no contract checked; 1 where Syntology's instrument failed) · 4 unverified","sample_list":"/paper/moose-chem-large-language-models-for#ran","syntology_url":"https://syntology.ai/paper/2410.07076","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.07076"}},"official":{"repos":["ZonglinY/MOOSE-Chem"],"state":"official (archive's flag): 4 ran","n_ran":4,"n_constructed":0,"n_ran_no_instrument_failure":3,"n_unverified":4,"ran_from_kinds":["official"]}}},{"url":"/paper/o1-replication-journey-a-strategic-progress","slug":"o1-replication-journey-a-strategic-progress","title":"O1 Replication Journey: A Strategic Progress Report -- Part 1","date":"2024-10-08","arxiv_id":"2410.18982","repositories_listed":1,"syntology":null},{"url":"/paper/scienceagentbench-toward-rigorous-assessment","slug":"scienceagentbench-toward-rigorous-assessment","title":"ScienceAgentBench: Toward Rigorous Assessment of Language Agents for Data-Driven Scientific Discovery","date":"2024-10-07","arxiv_id":"2410.05080","repositories_listed":1,"syntology":{"n":2,"n_ran":2,"n_constructed":0,"n_ran_checked":0,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"2 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/scienceagentbench-toward-rigorous-assessment#ran","syntology_url":"https://syntology.ai/paper/2410.05080","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.05080"}},"official":null}},{"url":"/paper/synthesizing-interpretable-control-policies","slug":"synthesizing-interpretable-control-policies","title":"Synthesizing Interpretable Control Policies through Large Language Model Guided Search","date":"2024-10-07","arxiv_id":"2410.05406","repositories_listed":1,"syntology":null},{"url":"/paper/geometric-representation-condition-improves","slug":"geometric-representation-condition-improves","title":"Geometric Representation Condition Improves Equivariant Molecule Generation","date":"2024-10-04","arxiv_id":"2410.03655","repositories_listed":1,"syntology":{"n":13,"n_ran":11,"n_constructed":0,"n_ran_checked":7,"n_instrument":4,"n_unverified":2,"n_honours":2,"n_violates":4,"n_no_contract":1,"n_pointer_only":13,"phrase":"11 ran (of which 0 constructed an object rather than computing a result; 7 with no instrument failure: 2 honoured, 4 violated, 1 with no contract checked; 4 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/geometric-representation-condition-improves#ran","syntology_url":"https://syntology.ai/paper/2410.03655","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.03655"}},"official":{"repos":["GraphPKU/GeoRCG"],"state":"official (archive's flag): 11 ran","n_ran":11,"n_constructed":0,"n_ran_no_instrument_failure":7,"n_unverified":2,"ran_from_kinds":["official"]}}},{"url":"/paper/on-the-limits-of-agency-in-agent-based-models","slug":"on-the-limits-of-agency-in-agent-based-models","title":"On the limits of agency in agent-based models","date":"2024-09-14","arxiv_id":"2409.10568","repositories_listed":1,"syntology":null},{"url":"/paper/hypothesizing-missing-causal-variables-with","slug":"hypothesizing-missing-causal-variables-with","title":"Hypothesizing Missing Causal Variables with LLMs","date":"2024-09-04","arxiv_id":"2409.02604","repositories_listed":1,"syntology":null},{"url":"/paper/active-symbolic-discovery-of-ordinary","slug":"active-symbolic-discovery-of-ordinary","title":"Active Symbolic Discovery of Ordinary Differential Equations via Phase Portrait Sketching","date":"2024-09-02","arxiv_id":"2409.01416","repositories_listed":1,"syntology":null},{"url":"/paper/scilitllm-how-to-adapt-llms-for-scientific","slug":"scilitllm-how-to-adapt-llms-for-scientific","title":"SciLitLLM: How to Adapt LLMs for Scientific Literature Understanding","date":"2024-08-28","arxiv_id":"2408.15545","repositories_listed":1,"syntology":{"n":13,"n_ran":13,"n_constructed":0,"n_ran_checked":4,"n_instrument":9,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":3,"n_pointer_only":0,"phrase":"13 ran (of which 0 constructed an object rather than computing a result; 4 with no instrument failure: 1 honoured, 0 violated, 3 with no contract checked; 9 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/scilitllm-how-to-adapt-llms-for-scientific#ran","syntology_url":"https://syntology.ai/paper/2408.15545","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.15545"}},"official":{"repos":["dptech-corp/Uni-SMART"],"state":"official (archive's flag): 13 ran","n_ran":13,"n_constructed":0,"n_ran_no_instrument_failure":4,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/can-transformers-do-enumerative-geometry","slug":"can-transformers-do-enumerative-geometry","title":"Can Transformers Do Enumerative Geometry?","date":"2024-08-27","arxiv_id":"2408.14915","repositories_listed":1,"syntology":{"n":3,"n_ran":3,"n_constructed":0,"n_ran_checked":1,"n_instrument":2,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"3 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 2 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/can-transformers-do-enumerative-geometry#ran","syntology_url":"https://syntology.ai/paper/2408.14915","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.14915"}},"official":{"repos":["Baran-phys/DynamicFormer"],"state":"official (archive's flag): 3 ran","n_ran":3,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/recent-advances-on-machine-learning-for","slug":"recent-advances-on-machine-learning-for","title":"Recent Advances on Machine Learning for Computational Fluid Dynamics: A Survey","date":"2024-08-22","arxiv_id":"2408.12171","repositories_listed":1,"syntology":null},{"url":"/paper/blade-benchmarking-language-model-agents-for","slug":"blade-benchmarking-language-model-agents-for","title":"BLADE: Benchmarking Language Model Agents for Data-Driven Science","date":"2024-08-19","arxiv_id":"2408.09667","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/blade-benchmarking-language-model-agents-for#ran","syntology_url":"https://syntology.ai/paper/2408.09667","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2408.09667"}},"official":{"repos":["behavioral-data/blade"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/kan-2-0-kolmogorov-arnold-networks-meet","slug":"kan-2-0-kolmogorov-arnold-networks-meet","title":"KAN 2.0: Kolmogorov-Arnold Networks Meet Science","date":"2024-08-19","arxiv_id":"2408.10205","repositories_listed":1,"syntology":null},{"url":"/paper/large-language-models-as-biomedical","slug":"large-language-models-as-biomedical","title":"Large Language Models as Biomedical Hypothesis Generators: A Comprehensive Evaluation","date":"2024-07-12","arxiv_id":"2407.08940","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-large-language-models-for-nano","slug":"leveraging-large-language-models-for-nano","title":"Leveraging large language models for nano synthesis mechanism explanation: solid foundations or mere conjectures?","date":"2024-07-12","arxiv_id":"2407.08922","repositories_listed":1,"syntology":null}],"syntology_records":35,"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"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"since_archive_judged":{"papers":0,"papers_placed":0,"judged_by":{"model":"a model","models_as_recorded":[],"from":"lb_rows_run_verified.jsonl: each record's `model` field (the extractor's call that wrote decisions[])"},"note":"a model's judgement from the paper's own tables that they report on this leaderboard, not a result: no value from a paper that was not placed is printed or carried here; papers counts each paper once over these leaderboards","backfill":"8,886 of 18,637 newer papers checked so far (733 more had nothing to place; 41 could not be read)","backfill_complete":false,"leaderboards":[]},"papers_where_code_ran":58,"papers_where_code_ran_first_page":"/task/scientific-discovery/papers/ran/1","papers_where_code_ran_caption":"We ran code from the paper's repository; we did not run it on this task or check it against the task's benchmarks.","pages":[{"order":"archive","page":2,"of":5,"url":"/task/scientific-discovery/papers/2","json":"/task/scientific-discovery/papers/2.json","rows":100},{"order":"archive","page":3,"of":5,"url":"/task/scientific-discovery/papers/3","json":"/task/scientific-discovery/papers/3.json","rows":100},{"order":"archive","page":4,"of":5,"url":"/task/scientific-discovery/papers/4","json":"/task/scientific-discovery/papers/4.json","rows":100},{"order":"archive","page":5,"of":5,"url":"/task/scientific-discovery/papers/5","json":"/task/scientific-discovery/papers/5.json","rows":64},{"order":"ran","page":1,"of":1,"url":"/task/scientific-discovery/papers/ran/1","json":"/task/scientific-discovery/papers/ran/1.json","rows":58}],"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":"2026-10-05T00:36:11+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; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"},"row_route":"each syntology object on a benchmark's first row and on a paper carries sample_list (this site's paper page, #ran), syntology_url (syntology.ai's page for the paper, only when that route probed live) and mcp (the agent call that lists the paper's harvested samples; not a verdict on the paper)","developers":"https://syntology.ai/developers"},"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"},"record_sha256":"2c38b9c218af6bcab670b074dcd568c5410b0db7fa18417b5333fb25d725ad7c","record_changed_at":"2026-10-05","record_changed_at_basis":"changed"}