{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:5JVY6J7V72XT665XRADOVIJUBZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"36aa9e5ba58fb14d3c26b6f5d75182f02c8c5bf75a9fe09b900c6774e76eeaad","cross_cats_sorted":["cs.AI","cs.CY","cs.HC","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-06T08:25:03Z","title_canon_sha256":"bc6f2331ba6b41ceab1c596dd0708f196b50b499e21b9afdefaae21da5b4c9c4"},"schema_version":"1.0","source":{"id":"2409.04109","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.04109","created_at":"2026-07-05T09:04:01Z"},{"alias_kind":"arxiv_version","alias_value":"2409.04109v1","created_at":"2026-07-05T09:04:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.04109","created_at":"2026-07-05T09:04:01Z"},{"alias_kind":"pith_short_12","alias_value":"5JVY6J7V72XT","created_at":"2026-07-05T09:04:01Z"},{"alias_kind":"pith_short_16","alias_value":"5JVY6J7V72XT665X","created_at":"2026-07-05T09:04:01Z"},{"alias_kind":"pith_short_8","alias_value":"5JVY6J7V","created_at":"2026-07-05T09:04:01Z"}],"graph_snapshots":[{"event_id":"sha256:beb9eaaf461bf26ae90a51da70d9965ee71d7a58908edbfccacc186cbcdc451e","target":"graph","created_at":"2026-07-05T09:04:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2409.04109/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in large language models (LLMs) have sparked optimism about their potential to accelerate scientific discovery, with a growing number of works proposing research agents that autonomously generate and validate new ideas. Despite this, no evaluations have shown that LLM systems can take the very first step of producing novel, expert-level ideas, let alone perform the entire research process. We address this by establishing an experimental design that evaluates research idea generation while controlling for confounders and performs the first head-to-head comparison between exp","authors_text":"Chenglei Si, Diyi Yang, Tatsunori Hashimoto","cross_cats":["cs.AI","cs.CY","cs.HC","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-06T08:25:03Z","title":"Can LLMs Generate Novel Research Ideas? A Large-Scale Human Study with 100+ NLP Researchers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.04109","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f44e18588f5c7591ecf0d6a6a380fc55fcae5f026680115e0746cba298dd129e","target":"record","created_at":"2026-07-05T09:04:01Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"36aa9e5ba58fb14d3c26b6f5d75182f02c8c5bf75a9fe09b900c6774e76eeaad","cross_cats_sorted":["cs.AI","cs.CY","cs.HC","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-06T08:25:03Z","title_canon_sha256":"bc6f2331ba6b41ceab1c596dd0708f196b50b499e21b9afdefaae21da5b4c9c4"},"schema_version":"1.0","source":{"id":"2409.04109","kind":"arxiv","version":1}},"canonical_sha256":"ea6b8f27f5feaf3f7bb78806eaa1340e41c39e671395c3d5ea30348083958e57","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ea6b8f27f5feaf3f7bb78806eaa1340e41c39e671395c3d5ea30348083958e57","first_computed_at":"2026-07-05T09:04:01.634303Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:04:01.634303Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a1gFopP5tXDPANIN572qSd8wPHJN5+P6HBzO1VvjIv1WVVXuHAtPXt/MN8wKinhilzo60RNb4rghDbyNIMeLDA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:04:01.634715Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.04109","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f44e18588f5c7591ecf0d6a6a380fc55fcae5f026680115e0746cba298dd129e","sha256:beb9eaaf461bf26ae90a51da70d9965ee71d7a58908edbfccacc186cbcdc451e"],"state_sha256":"8d32449144b8191885634b9ce2e8f6d4ca6ed3d272ec40f7dc3055d9bd9af82c"}