{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5K7DRPJSUWHOT5FPUYXD33BYGH","short_pith_number":"pith:5K7DRPJS","schema_version":"1.0","canonical_sha256":"eabe38bd32a58ee9f4afa62e3dec3831e051b4671ca91218744eb95190f7c08b","source":{"kind":"arxiv","id":"2407.01725","version":1},"attestation_state":"computed","paper":{"title":"DiscoveryBench: Towards Data-Driven Discovery with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Abhijeetsingh Meena, Aryan Prakhar, Ashish Sabharwal, Bhavana Dalvi Mishra, Bodhisattwa Prasad Majumder, Dhruv Agarwal, Harshit Surana, Peter Clark, Tirth Vora, Tushar Khot","submitted_at":"2024-07-01T18:58:22Z","abstract_excerpt":"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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2407.01725","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-07-01T18:58:22Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"c85b9ff9b63a9edf2ebc11fad6f250e179f751451c722ad0bfd4af892f715329","abstract_canon_sha256":"4251f808dbd3f28c729e87a8e9df2d26db2a1160a13da5f3fea310235ee9f799"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:04.226962Z","signature_b64":"mM6hB0lDkn/WFLMBcuW0wd6U6haW/vhrEMMlD2Tde+VoE2r0rnfCUYH0/n3uGBfFhUoXpxCxMC+fYHsFOloRCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eabe38bd32a58ee9f4afa62e3dec3831e051b4671ca91218744eb95190f7c08b","last_reissued_at":"2026-07-05T08:39:04.226513Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:04.226513Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DiscoveryBench: Towards Data-Driven Discovery with Large Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Abhijeetsingh Meena, Aryan Prakhar, Ashish Sabharwal, Bhavana Dalvi Mishra, Bodhisattwa Prasad Majumder, Dhruv Agarwal, Harshit Surana, Peter Clark, Tirth Vora, Tushar Khot","submitted_at":"2024-07-01T18:58:22Z","abstract_excerpt":"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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01725","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2407.01725/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2407.01725","created_at":"2026-07-05T08:39:04.226570+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.01725v1","created_at":"2026-07-05T08:39:04.226570+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01725","created_at":"2026-07-05T08:39:04.226570+00:00"},{"alias_kind":"pith_short_12","alias_value":"5K7DRPJSUWHO","created_at":"2026-07-05T08:39:04.226570+00:00"},{"alias_kind":"pith_short_16","alias_value":"5K7DRPJSUWHOT5FP","created_at":"2026-07-05T08:39:04.226570+00:00"},{"alias_kind":"pith_short_8","alias_value":"5K7DRPJS","created_at":"2026-07-05T08:39:04.226570+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22610","citing_title":"PaperClaw: Harnessing Agents for Autonomous Research and Human-in-the-Loop Refinement","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17628","citing_title":"OPD-Evolver: Cultivating Holistic Agent Evolver via On-Policy Distillation","ref_index":92,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11926","citing_title":"Toward Generalist Autonomous Research via Hypothesis-Tree Refinement","ref_index":82,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26087","citing_title":"DiscoverPhysics: Benchmarking LLMs for Out-of-the-Box Scientific Thinking","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.02258","citing_title":"Matter to Mechanism: A Benchmark for AI Co-Scientists in Materials and Battery Research","ref_index":57,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18854","citing_title":"Evaluating Memory Condensation Strategies for Coding Agents in Data-Driven Scientific Discovery","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2507.11810","citing_title":"Evolving Roles of LLMs in Scientific Innovation: Assistant, Collaborator, Scientist, and Evaluator","ref_index":124,"is_internal_anchor":false},{"citing_arxiv_id":"2509.20374","citing_title":"CFDLLMBench: A Benchmark Suite for Evaluating Large Language Models in Computational Fluid Dynamics","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2602.11354","citing_title":"ReplicatorBench: Benchmarking LLM Agents for Replicability in Social and Behavioral Sciences","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14033","citing_title":"Sheaf-Theoretic Transport and Obstruction for Detecting Scientific Theory Shift in AI Agents","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12808","citing_title":"Neurodata Without Boredom: Benchmarking Agentic AI for Data Reuse","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2504.19678","citing_title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","ref_index":100,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12808","citing_title":"Neurodata Without Boredom: Benchmarking Agentic AI for Data Reuse","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2408.06292","citing_title":"The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery","ref_index":73,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5K7DRPJSUWHOT5FPUYXD33BYGH","json":"https://pith.science/pith/5K7DRPJSUWHOT5FPUYXD33BYGH.json","graph_json":"https://pith.science/api/pith-number/5K7DRPJSUWHOT5FPUYXD33BYGH/graph.json","events_json":"https://pith.science/api/pith-number/5K7DRPJSUWHOT5FPUYXD33BYGH/events.json","paper":"https://pith.science/paper/5K7DRPJS"},"agent_actions":{"view_html":"https://pith.science/pith/5K7DRPJSUWHOT5FPUYXD33BYGH","download_json":"https://pith.science/pith/5K7DRPJSUWHOT5FPUYXD33BYGH.json","view_paper":"https://pith.science/paper/5K7DRPJS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.01725&json=true","fetch_graph":"https://pith.science/api/pith-number/5K7DRPJSUWHOT5FPUYXD33BYGH/graph.json","fetch_events":"https://pith.science/api/pith-number/5K7DRPJSUWHOT5FPUYXD33BYGH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5K7DRPJSUWHOT5FPUYXD33BYGH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5K7DRPJSUWHOT5FPUYXD33BYGH/action/storage_attestation","attest_author":"https://pith.science/pith/5K7DRPJSUWHOT5FPUYXD33BYGH/action/author_attestation","sign_citation":"https://pith.science/pith/5K7DRPJSUWHOT5FPUYXD33BYGH/action/citation_signature","submit_replication":"https://pith.science/pith/5K7DRPJSUWHOT5FPUYXD33BYGH/action/replication_record"}},"created_at":"2026-07-05T08:39:04.226570+00:00","updated_at":"2026-07-05T08:39:04.226570+00:00"}