{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5D7HVATC7BN6NG34FO6PLN4X3N","short_pith_number":"pith:5D7HVATC","schema_version":"1.0","canonical_sha256":"e8fe7a8262f85be69b7c2bbcf5b797db7921f5b881dd73a590ef4abada736247","source":{"kind":"arxiv","id":"2404.07738","version":2},"attestation_state":"computed","paper":{"title":"ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jinheon Baek, Silviu Cucerzan, Sujay Kumar Jauhar, Sung Ju Hwang","submitted_at":"2024-04-11T13:36:29Z","abstract_excerpt":"The pace of scientific research, vital for improving human life, is complex, slow, and needs specialized expertise. Meanwhile, novel, impactful research often stems from both a deep understanding of prior work, and a cross-pollination of ideas across domains and fields. To enhance the productivity of researchers, we propose ResearchAgent, which leverages the encyclopedic knowledge and linguistic reasoning capabilities of Large Language Models (LLMs) to assist them in their work. This system automatically defines novel problems, proposes methods and designs experiments, while iteratively refini"},"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":"2404.07738","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-04-11T13:36:29Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"a83cad876b0f261a6fb064f02c555e858168bccba06bc1c994fefbd9986f7b20","abstract_canon_sha256":"d8717463e088d40eb34116896153fc2c29b582ef503c16993d8f0443b70cae19"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:18.407627Z","signature_b64":"3qi1BS5CqJ7AbLt27XZ22vxSYf7Vl18qKd36uhOWd9Ay/OQGojpQxJmZW7CAWKjHcGjGEzizR4K+E6bDMh/FBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e8fe7a8262f85be69b7c2bbcf5b797db7921f5b881dd73a590ef4abada736247","last_reissued_at":"2026-07-05T10:11:18.407109Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:18.407109Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ResearchAgent: Iterative Research Idea Generation over Scientific Literature with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Jinheon Baek, Silviu Cucerzan, Sujay Kumar Jauhar, Sung Ju Hwang","submitted_at":"2024-04-11T13:36:29Z","abstract_excerpt":"The pace of scientific research, vital for improving human life, is complex, slow, and needs specialized expertise. Meanwhile, novel, impactful research often stems from both a deep understanding of prior work, and a cross-pollination of ideas across domains and fields. To enhance the productivity of researchers, we propose ResearchAgent, which leverages the encyclopedic knowledge and linguistic reasoning capabilities of Large Language Models (LLMs) to assist them in their work. This system automatically defines novel problems, proposes methods and designs experiments, while iteratively refini"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.07738","kind":"arxiv","version":2},"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/2404.07738/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":"2404.07738","created_at":"2026-07-05T10:11:18.407174+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.07738v2","created_at":"2026-07-05T10:11:18.407174+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.07738","created_at":"2026-07-05T10:11:18.407174+00:00"},{"alias_kind":"pith_short_12","alias_value":"5D7HVATC7BN6","created_at":"2026-07-05T10:11:18.407174+00:00"},{"alias_kind":"pith_short_16","alias_value":"5D7HVATC7BN6NG34","created_at":"2026-07-05T10:11:18.407174+00:00"},{"alias_kind":"pith_short_8","alias_value":"5D7HVATC","created_at":"2026-07-05T10:11:18.407174+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":19,"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":59,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17628","citing_title":"OPD-Evolver: Cultivating Holistic Agent Evolver via On-Policy Distillation","ref_index":105,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30775","citing_title":"A Single Rewrite Suffices: Empirical Lessons from Production Skill Description Optimization","ref_index":100,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31651","citing_title":"FARS: A Fully Automated Research System Deployed at Scale","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14790","citing_title":"Graphs of Research: Citation Evolution Graphs as Supervision for Research Idea Generation","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2409.14634","citing_title":"Human-LLM Compound System for Scientific Ideation through Facet Recombination and Novelty Evaluation","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2509.06503","citing_title":"An AI system to help scientists write expert-level empirical software","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2507.21035","citing_title":"GenoMAS: A Multi-Agent Framework for Scientific Discovery via Code-Driven Gene Expression Analysis","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2509.06503","citing_title":"An AI system to help scientists write expert-level empirical software","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2507.02212","citing_title":"SciGA: A Comprehensive Dataset for Designing Graphical Abstracts in Academic Papers","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2504.19678","citing_title":"From LLM Reasoning to Autonomous AI Agents: A Comprehensive Review","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2504.13958","citing_title":"ToolRL: Reward is All Tool Learning Needs","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11258","citing_title":"Unlocking LLM Creativity in Science through Analogical Reasoning","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11532","citing_title":"Read, Grep, and Synthesize: Diagnosing Cross-Domain Seed Exposure for LLM Research Ideation","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.12144","citing_title":"VERITAS: A Multi-Agent Co-Scientist for Verifiable Image-Derived Hypothesis Testing","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2408.06292","citing_title":"The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05854","citing_title":"Deep Researcher Agent: An Autonomous Framework for 24/7 Deep Learning Experimentation with Zero-Cost Monitoring","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.05587","citing_title":"ResearchEVO: An End-to-End Framework for Automated Scientific Discovery and Documentation","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11538","citing_title":"ResearchCube: Multi-Dimensional Trade-off Exploration for Research Ideation","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5D7HVATC7BN6NG34FO6PLN4X3N","json":"https://pith.science/pith/5D7HVATC7BN6NG34FO6PLN4X3N.json","graph_json":"https://pith.science/api/pith-number/5D7HVATC7BN6NG34FO6PLN4X3N/graph.json","events_json":"https://pith.science/api/pith-number/5D7HVATC7BN6NG34FO6PLN4X3N/events.json","paper":"https://pith.science/paper/5D7HVATC"},"agent_actions":{"view_html":"https://pith.science/pith/5D7HVATC7BN6NG34FO6PLN4X3N","download_json":"https://pith.science/pith/5D7HVATC7BN6NG34FO6PLN4X3N.json","view_paper":"https://pith.science/paper/5D7HVATC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.07738&json=true","fetch_graph":"https://pith.science/api/pith-number/5D7HVATC7BN6NG34FO6PLN4X3N/graph.json","fetch_events":"https://pith.science/api/pith-number/5D7HVATC7BN6NG34FO6PLN4X3N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5D7HVATC7BN6NG34FO6PLN4X3N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5D7HVATC7BN6NG34FO6PLN4X3N/action/storage_attestation","attest_author":"https://pith.science/pith/5D7HVATC7BN6NG34FO6PLN4X3N/action/author_attestation","sign_citation":"https://pith.science/pith/5D7HVATC7BN6NG34FO6PLN4X3N/action/citation_signature","submit_replication":"https://pith.science/pith/5D7HVATC7BN6NG34FO6PLN4X3N/action/replication_record"}},"created_at":"2026-07-05T10:11:18.407174+00:00","updated_at":"2026-07-05T10:11:18.407174+00:00"}