{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UHUYKZA5DQ32SOUEXA4QLQ2PVE","short_pith_number":"pith:UHUYKZA5","schema_version":"1.0","canonical_sha256":"a1e985641d1c37a93a84b83905c34fa92d052f4f501cd9495bf5f7cd53076d2b","source":{"kind":"arxiv","id":"2501.04306","version":1},"attestation_state":"computed","paper":{"title":"LLM4SR: A Survey on Large Language Models for Scientific Research","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DL"],"primary_cat":"cs.CL","authors_text":"Wei Yang, Xinya Du, Zexin Xu, Ziming Luo, Zonglin Yang","submitted_at":"2025-01-08T06:44:02Z","abstract_excerpt":"In recent years, the rapid advancement of Large Language Models (LLMs) has transformed the landscape of scientific research, offering unprecedented support across various stages of the research cycle. This paper presents the first systematic survey dedicated to exploring how LLMs are revolutionizing the scientific research process. We analyze the unique roles LLMs play across four critical stages of research: hypothesis discovery, experiment planning and implementation, scientific writing, and peer reviewing. Our review comprehensively showcases the task-specific methodologies and evaluation b"},"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":"2501.04306","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-08T06:44:02Z","cross_cats_sorted":["cs.DL"],"title_canon_sha256":"474770f3a7f7005a55b26887a373f2e6a29b77a115b264d491b3c4beb518424c","abstract_canon_sha256":"f7ccb0d5def74454051b0f5414a77cb06ac03caa419058417c3b24bb98d841b7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:58:33.075120Z","signature_b64":"UW6hsX5GlGIF8LsbfmY3o0u38EEFbtjPN2lcbWecaRRK3RhJb+MvrQ0UTF+j9QQ8OqaNwl1WKNGbeJqiXjrZAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a1e985641d1c37a93a84b83905c34fa92d052f4f501cd9495bf5f7cd53076d2b","last_reissued_at":"2026-07-05T09:58:33.074673Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:58:33.074673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM4SR: A Survey on Large Language Models for Scientific Research","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DL"],"primary_cat":"cs.CL","authors_text":"Wei Yang, Xinya Du, Zexin Xu, Ziming Luo, Zonglin Yang","submitted_at":"2025-01-08T06:44:02Z","abstract_excerpt":"In recent years, the rapid advancement of Large Language Models (LLMs) has transformed the landscape of scientific research, offering unprecedented support across various stages of the research cycle. This paper presents the first systematic survey dedicated to exploring how LLMs are revolutionizing the scientific research process. We analyze the unique roles LLMs play across four critical stages of research: hypothesis discovery, experiment planning and implementation, scientific writing, and peer reviewing. Our review comprehensively showcases the task-specific methodologies and evaluation b"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.04306","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/2501.04306/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":"2501.04306","created_at":"2026-07-05T09:58:33.074728+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.04306v1","created_at":"2026-07-05T09:58:33.074728+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.04306","created_at":"2026-07-05T09:58:33.074728+00:00"},{"alias_kind":"pith_short_12","alias_value":"UHUYKZA5DQ32","created_at":"2026-07-05T09:58:33.074728+00:00"},{"alias_kind":"pith_short_16","alias_value":"UHUYKZA5DQ32SOUE","created_at":"2026-07-05T09:58:33.074728+00:00"},{"alias_kind":"pith_short_8","alias_value":"UHUYKZA5","created_at":"2026-07-05T09:58:33.074728+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":19,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25057","citing_title":"LLM-Based Scientific Peer Review: Methods, Benchmarks, and Reliability Challenges","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2606.26728","citing_title":"Scientific discovery as meta-optimization: a combinatorial optimization case study","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20897","citing_title":"PeerCheck: Enhancing LLM-Generated Academic Reviews Towards Human-Level Quality","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2606.20873","citing_title":"SciLens: Multi-modal Scientific Claim Verification with Agentic Entailment and Grounding","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09105","citing_title":"Graph2Idea:Retrieval-Augmented Scientific Idea Generation with Graph-Structured Contexts","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08036","citing_title":"GIScholarBench: Benchmarking LLM Overconfidence in GIS Research","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29981","citing_title":"Hephaestus: Toward a Cybersecurity AI Scientist","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30961","citing_title":"EvoGens: A Population-Based Heuristic Search Framework for Scientific Idea Generation","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23204","citing_title":"AutoResearch AI: Towards AI-Powered Research Automation for Scientific Discovery","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2510.10129","citing_title":"CacheClip: Accelerating RAG with Effective KV Cache Reuse","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18661","citing_title":"AI for Auto-Research: Roadmap & User Guide","ref_index":126,"is_internal_anchor":false},{"citing_arxiv_id":"2506.22598","citing_title":"RExBench: Can coding agents autonomously implement AI research extensions?","ref_index":33,"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":118,"is_internal_anchor":false},{"citing_arxiv_id":"2602.11354","citing_title":"ReplicatorBench: Benchmarking LLM Agents for Replicability in Social and Behavioral Sciences","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01489","citing_title":"SciResearcher: Scaling Deep Research Agents for Frontier Scientific Reasoning","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06505","citing_title":"MedConclusion: A Benchmark for Biomedical Conclusion Generation from Structured Abstracts","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2506.13131","citing_title":"AlphaEvolve: A coding agent for scientific and algorithmic discovery","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11184","citing_title":"Taking a Pulse on How Generative AI is Reshaping the Software Engineering Research Landscape","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23593","citing_title":"When AI reviews science: Can we trust the referee?","ref_index":6,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UHUYKZA5DQ32SOUEXA4QLQ2PVE","json":"https://pith.science/pith/UHUYKZA5DQ32SOUEXA4QLQ2PVE.json","graph_json":"https://pith.science/api/pith-number/UHUYKZA5DQ32SOUEXA4QLQ2PVE/graph.json","events_json":"https://pith.science/api/pith-number/UHUYKZA5DQ32SOUEXA4QLQ2PVE/events.json","paper":"https://pith.science/paper/UHUYKZA5"},"agent_actions":{"view_html":"https://pith.science/pith/UHUYKZA5DQ32SOUEXA4QLQ2PVE","download_json":"https://pith.science/pith/UHUYKZA5DQ32SOUEXA4QLQ2PVE.json","view_paper":"https://pith.science/paper/UHUYKZA5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.04306&json=true","fetch_graph":"https://pith.science/api/pith-number/UHUYKZA5DQ32SOUEXA4QLQ2PVE/graph.json","fetch_events":"https://pith.science/api/pith-number/UHUYKZA5DQ32SOUEXA4QLQ2PVE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UHUYKZA5DQ32SOUEXA4QLQ2PVE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UHUYKZA5DQ32SOUEXA4QLQ2PVE/action/storage_attestation","attest_author":"https://pith.science/pith/UHUYKZA5DQ32SOUEXA4QLQ2PVE/action/author_attestation","sign_citation":"https://pith.science/pith/UHUYKZA5DQ32SOUEXA4QLQ2PVE/action/citation_signature","submit_replication":"https://pith.science/pith/UHUYKZA5DQ32SOUEXA4QLQ2PVE/action/replication_record"}},"created_at":"2026-07-05T09:58:33.074728+00:00","updated_at":"2026-07-05T09:58:33.074728+00:00"}