{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:B4R6LZWINJGNLOMI3NI33SPDFQ","short_pith_number":"pith:B4R6LZWI","schema_version":"1.0","canonical_sha256":"0f23e5e6c86a4cd5b988db51bdc9e32c18726e0aa789ce750ed52b0bc9d1a0c3","source":{"kind":"arxiv","id":"2506.20803","version":1},"attestation_state":"computed","paper":{"title":"The Ideation-Execution Gap: Execution Outcomes of LLM-Generated versus Human Research Ideas","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY","cs.HC","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chenglei Si, Diyi Yang, Tatsunori Hashimoto","submitted_at":"2025-06-25T19:47:23Z","abstract_excerpt":"Large Language Models (LLMs) have shown promise in accelerating the scientific research pipeline. A key capability for this process is the ability to generate novel research ideas, and prior studies have found settings in which LLM-generated research ideas were judged as more novel than human-expert ideas. However, a good idea should not simply appear to be novel, it should also result in better research after being executed. To test whether AI-generated ideas lead to better research outcomes, we conduct an execution study by recruiting 43 expert researchers to execute randomly-assigned ideas,"},"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":"2506.20803","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-25T19:47:23Z","cross_cats_sorted":["cs.AI","cs.CY","cs.HC","cs.LG"],"title_canon_sha256":"800fdf7346326e435780032bea20021688ab37726fb46e1b77331801b67e5108","abstract_canon_sha256":"e05d2ac4e3bc6d0f2cb27f130f0f42386bd1399139cda891286e66d513be410b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:34.305002Z","signature_b64":"C8qRYpaBy8N3Th2cD3V/3T1ZDhUVb+yZ9tv4BaU3OQ07fiyzugLuKVBi+e8Djhl9qm1aGn4Ww7DbEIi67PpfCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f23e5e6c86a4cd5b988db51bdc9e32c18726e0aa789ce750ed52b0bc9d1a0c3","last_reissued_at":"2026-07-05T11:27:34.304518Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:34.304518Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Ideation-Execution Gap: Execution Outcomes of LLM-Generated versus Human Research Ideas","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CY","cs.HC","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chenglei Si, Diyi Yang, Tatsunori Hashimoto","submitted_at":"2025-06-25T19:47:23Z","abstract_excerpt":"Large Language Models (LLMs) have shown promise in accelerating the scientific research pipeline. A key capability for this process is the ability to generate novel research ideas, and prior studies have found settings in which LLM-generated research ideas were judged as more novel than human-expert ideas. However, a good idea should not simply appear to be novel, it should also result in better research after being executed. To test whether AI-generated ideas lead to better research outcomes, we conduct an execution study by recruiting 43 expert researchers to execute randomly-assigned ideas,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.20803","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/2506.20803/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":"2506.20803","created_at":"2026-07-05T11:27:34.304571+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.20803v1","created_at":"2026-07-05T11:27:34.304571+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.20803","created_at":"2026-07-05T11:27:34.304571+00:00"},{"alias_kind":"pith_short_12","alias_value":"B4R6LZWINJGN","created_at":"2026-07-05T11:27:34.304571+00:00"},{"alias_kind":"pith_short_16","alias_value":"B4R6LZWINJGNLOMI","created_at":"2026-07-05T11:27:34.304571+00:00"},{"alias_kind":"pith_short_8","alias_value":"B4R6LZWI","created_at":"2026-07-05T11:27:34.304571+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11337","citing_title":"Can AI Agents Synthesize Scientific Conclusions?","ref_index":108,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01233","citing_title":"Measuring the Gap Between Human and LLM Research Ideas","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.30329","citing_title":"SoundnessBench: Can Your AI Scientist Really Tell Good Research Ideas from Bad Ones?","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.21491","citing_title":"Teaching Language Models to Forecast Research Success Through Comparative Idea Evaluation","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18661","citing_title":"AI for Auto-Research: Roadmap & User Guide","ref_index":185,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13450","citing_title":"Assessing the Creativity of Large Language Models: Testing, Limits, and New Frontiers","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25929","citing_title":"LLMs Generate Kitsch","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.28158","citing_title":"Intern-Atlas: A Methodological Evolution Graph as Research Infrastructure for AI Scientists","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06123","citing_title":"Back to the Beginning of Heuristic Design: Bridging Code and Knowledge with LLMs","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09793","citing_title":"GIANTS: Generative Insight Anticipation from Scientific Literature","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11009","citing_title":"From Planning to Revision: How AI Writing Support at Different Stages Alters Ownership","ref_index":51,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B4R6LZWINJGNLOMI3NI33SPDFQ","json":"https://pith.science/pith/B4R6LZWINJGNLOMI3NI33SPDFQ.json","graph_json":"https://pith.science/api/pith-number/B4R6LZWINJGNLOMI3NI33SPDFQ/graph.json","events_json":"https://pith.science/api/pith-number/B4R6LZWINJGNLOMI3NI33SPDFQ/events.json","paper":"https://pith.science/paper/B4R6LZWI"},"agent_actions":{"view_html":"https://pith.science/pith/B4R6LZWINJGNLOMI3NI33SPDFQ","download_json":"https://pith.science/pith/B4R6LZWINJGNLOMI3NI33SPDFQ.json","view_paper":"https://pith.science/paper/B4R6LZWI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.20803&json=true","fetch_graph":"https://pith.science/api/pith-number/B4R6LZWINJGNLOMI3NI33SPDFQ/graph.json","fetch_events":"https://pith.science/api/pith-number/B4R6LZWINJGNLOMI3NI33SPDFQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B4R6LZWINJGNLOMI3NI33SPDFQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B4R6LZWINJGNLOMI3NI33SPDFQ/action/storage_attestation","attest_author":"https://pith.science/pith/B4R6LZWINJGNLOMI3NI33SPDFQ/action/author_attestation","sign_citation":"https://pith.science/pith/B4R6LZWINJGNLOMI3NI33SPDFQ/action/citation_signature","submit_replication":"https://pith.science/pith/B4R6LZWINJGNLOMI3NI33SPDFQ/action/replication_record"}},"created_at":"2026-07-05T11:27:34.304571+00:00","updated_at":"2026-07-05T11:27:34.304571+00:00"}