{"about":{"site":"https://codewithpapers.app","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.","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"},"url":"/paper/discoverybench-towards-data-driven-discovery","title":"DiscoveryBench: Towards Data-Driven Discovery with Large Language Models","arxiv_id":"2407.01725","date":"2024-07-01","proceeding":null,"authors":["Bodhisattwa Prasad Majumder","Harshit Surana","Dhruv Agarwal","Bhavana Dalvi Mishra","Abhijeetsingh Meena","Aryan Prakhar","Tirth Vora","Tushar Khot","Ashish Sabharwal","Peter Clark"],"abstract":"Can the rapid advances in code generation, function calling, and data analysis using large language models (LLMs) help automate the search and verification of hypotheses purely from a set of provided datasets? To evaluate this question, we present DiscoveryBench, the first comprehensive benchmark that formalizes the multi-step process of data-driven discovery. The benchmark is designed to systematically assess current model capabilities in discovery tasks and provide a useful resource for improving them. Our benchmark contains 264 tasks collected across 6 diverse domains, such as sociology and engineering, by manually deriving discovery workflows from published papers to approximate the real-world challenges faced by researchers, where each task is defined by a dataset, its metadata, and a discovery goal in natural language. We additionally provide 903 synthetic tasks to conduct controlled evaluations across task complexity. Furthermore, our structured formalism of data-driven discovery enables a facet-based evaluation that provides useful insights into different failure modes. We evaluate several popular LLM-based reasoning frameworks using both open and closed LLMs as baselines on DiscoveryBench and find that even the best system scores only 25%. Our benchmark, thus, illustrates the challenges in autonomous data-driven discovery and serves as a valuable resource for the community to make progress.","url_abs":"https://arxiv.org/abs/2407.01725v1","url_pdf":"https://arxiv.org/pdf/2407.01725v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"discoverybench-towards-data-driven-discovery","repo_url":"https://github.com/allenai/discoverybench","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"NOASSERTION"}}],"tasks":[{"task_slug":"code-generation","task_name":"Code Generation"},{"task_slug":"sociology","task_name":"Sociology"}],"methods":[{"method_slug":"set","method_name":"SET"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2407.01725","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2407.01725"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/allenai/discoverybench","reach":{"status":"ok","spdx":"NOASSERTION"}}],"summary":{"ran":10,"unverified":3},"by_repo_kind":{"official":{"samples":13,"ran":10,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":13,"samples":[{"code_sha256_prefix":"61d2078e13864a0c","entry":"extract_bracket_substrings","repo":"allenai/discoverybench","repo_kind":"official","path":"utils/helpers.py","file_url":"https://github.com/allenai/discoverybench/blob/HEAD/utils/helpers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"61d2078e13864a0c"}},{"code_sha256_prefix":"1fe5884664281ae3","entry":"extract_variable","repo":"allenai/discoverybench","repo_kind":"official","path":"utils/helpers.py","file_url":"https://github.com/allenai/discoverybench/blob/HEAD/utils/helpers.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"1fe5884664281ae3"}},{"code_sha256_prefix":"11d5942be3ac53d7","entry":"get_dv_query_for_real","repo":"allenai/discoverybench","repo_kind":"official","path":"utils/autonomous_single_agent.py","file_url":"https://github.com/allenai/discoverybench/blob/HEAD/utils/autonomous_single_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"11d5942be3ac53d7"}},{"code_sha256_prefix":"15364ed46134e865","entry":"get_dv_query_for_synth","repo":"allenai/discoverybench","repo_kind":"official","path":"utils/autonomous_single_agent.py","file_url":"https://github.com/allenai/discoverybench/blob/HEAD/utils/autonomous_single_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"15364ed46134e865"}},{"code_sha256_prefix":"2d6ea20e03caf9c0","entry":"get_prompt_data","repo":"allenai/discoverybench","repo_kind":"official","path":"agents/coder_agent.py","file_url":"https://github.com/allenai/discoverybench/blob/HEAD/agents/coder_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"2d6ea20e03caf9c0"}},{"code_sha256_prefix":"3ec3bb849b4f7a1e","entry":"get_score_from_answer","repo":"allenai/discoverybench","repo_kind":"official","path":"eval/new_eval.py","file_url":"https://github.com/allenai/discoverybench/blob/HEAD/eval/new_eval.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"3ec3bb849b4f7a1e"}},{"code_sha256_prefix":"1390bd9484a06739","entry":"prepare_dataset_metadata_json","repo":"allenai/discoverybench","repo_kind":"official","path":"eval/new_eval.py","file_url":"https://github.com/allenai/discoverybench/blob/HEAD/eval/new_eval.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"1390bd9484a06739"}},{"code_sha256_prefix":"45a21e6fc93948b5","entry":"validate_metadata_options","repo":"allenai/discoverybench","repo_kind":"official","path":"discovery_agent.py","file_url":"https://github.com/allenai/discoverybench/blob/HEAD/discovery_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"45a21e6fc93948b5"}},{"code_sha256_prefix":"335a12a64e9392c2","entry":"validate_option","repo":"allenai/discoverybench","repo_kind":"official","path":"discovery_eval.py","file_url":"https://github.com/allenai/discoverybench/blob/HEAD/discovery_eval.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"335a12a64e9392c2"}},{"code_sha256_prefix":"7126075f6b70c064","entry":"validate_query","repo":"allenai/discoverybench","repo_kind":"official","path":"discovery_agent.py","file_url":"https://github.com/allenai/discoverybench/blob/HEAD/discovery_agent.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"7126075f6b70c064"}},{"code_sha256_prefix":"5ae806d9337d2727","entry":"deep_get","repo":"allenai/discoverybench","repo_kind":"official","path":"utils/helpers.py","file_url":"https://github.com/allenai/discoverybench/blob/HEAD/utils/helpers.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"5ae806d9337d2727"}},{"code_sha256_prefix":"1bb0f4227816397d","entry":"run_chatgpt_query_multi_turn","repo":"allenai/discoverybench","repo_kind":"official","path":"eval/lm_utils.py","file_url":"https://github.com/allenai/discoverybench/blob/HEAD/eval/lm_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"1bb0f4227816397d"}},{"code_sha256_prefix":"7ce491b58862e1b9","entry":"validate_model_name","repo":"allenai/discoverybench","repo_kind":"official","path":"discovery_agent.py","file_url":"https://github.com/allenai/discoverybench/blob/HEAD/discovery_agent.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NOASSERTION","inline_ok":false,"mcp_get_code":{"code_sha256":"7ce491b58862e1b9"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}