{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:OLFXYVWLQCU3A5ASGP7BZDK5AN","short_pith_number":"pith:OLFXYVWL","schema_version":"1.0","canonical_sha256":"72cb7c56cb80a9b0741233fe1c8d5d035954d210213abd4f725ace336593c492","source":{"kind":"arxiv","id":"2506.22026","version":1},"attestation_state":"computed","paper":{"title":"Literature-Grounded Novelty Assessment of Scientific Ideas","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Daniel S. Weld, Marissa Radensky, Pao Siangliulue, Raymond Fok, Simra Shahid, Tom Hope","submitted_at":"2025-06-27T08:47:28Z","abstract_excerpt":"Automated scientific idea generation systems have made remarkable progress, yet the automatic evaluation of idea novelty remains a critical and underexplored challenge. Manual evaluation of novelty through literature review is labor-intensive, prone to error due to subjectivity, and impractical at scale. To address these issues, we propose the Idea Novelty Checker, an LLM-based retrieval-augmented generation (RAG) framework that leverages a two-stage retrieve-then-rerank approach. The Idea Novelty Checker first collects a broad set of relevant papers using keyword and snippet-based retrieval, "},"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":"2506.22026","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.IR","submitted_at":"2025-06-27T08:47:28Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"34b9ec3b0bcc646628dcb9fb454a7d6a23308e4a27f5e57d3a92628e831793cd","abstract_canon_sha256":"32e4fe1d1195245251f581d94844ceb4b7145261fe2d7f6a0c346ec87d9dd29f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:28:20.694134Z","signature_b64":"ka3YE/DJcGUHdWWKWwxizn5m7eP3TjlqX0E8K9pDO6yIgOicziEvwTGdpl6EeZHBcjM3fPx9PzOGyQ8T2f1zAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72cb7c56cb80a9b0741233fe1c8d5d035954d210213abd4f725ace336593c492","last_reissued_at":"2026-07-05T11:28:20.693652Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:28:20.693652Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Literature-Grounded Novelty Assessment of Scientific Ideas","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Daniel S. Weld, Marissa Radensky, Pao Siangliulue, Raymond Fok, Simra Shahid, Tom Hope","submitted_at":"2025-06-27T08:47:28Z","abstract_excerpt":"Automated scientific idea generation systems have made remarkable progress, yet the automatic evaluation of idea novelty remains a critical and underexplored challenge. Manual evaluation of novelty through literature review is labor-intensive, prone to error due to subjectivity, and impractical at scale. To address these issues, we propose the Idea Novelty Checker, an LLM-based retrieval-augmented generation (RAG) framework that leverages a two-stage retrieve-then-rerank approach. The Idea Novelty Checker first collects a broad set of relevant papers using keyword and snippet-based retrieval, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.22026","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/2506.22026/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":"2506.22026","created_at":"2026-07-05T11:28:20.693710+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.22026v1","created_at":"2026-07-05T11:28:20.693710+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.22026","created_at":"2026-07-05T11:28:20.693710+00:00"},{"alias_kind":"pith_short_12","alias_value":"OLFXYVWLQCU3","created_at":"2026-07-05T11:28:20.693710+00:00"},{"alias_kind":"pith_short_16","alias_value":"OLFXYVWLQCU3A5AS","created_at":"2026-07-05T11:28:20.693710+00:00"},{"alias_kind":"pith_short_8","alias_value":"OLFXYVWL","created_at":"2026-07-05T11:28:20.693710+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.22878","citing_title":"SciAtlas: A Large-Scale Knowledge Graph for Automated Scientific Research","ref_index":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11258","citing_title":"Unlocking LLM Creativity in Science through Analogical Reasoning","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OLFXYVWLQCU3A5ASGP7BZDK5AN","json":"https://pith.science/pith/OLFXYVWLQCU3A5ASGP7BZDK5AN.json","graph_json":"https://pith.science/api/pith-number/OLFXYVWLQCU3A5ASGP7BZDK5AN/graph.json","events_json":"https://pith.science/api/pith-number/OLFXYVWLQCU3A5ASGP7BZDK5AN/events.json","paper":"https://pith.science/paper/OLFXYVWL"},"agent_actions":{"view_html":"https://pith.science/pith/OLFXYVWLQCU3A5ASGP7BZDK5AN","download_json":"https://pith.science/pith/OLFXYVWLQCU3A5ASGP7BZDK5AN.json","view_paper":"https://pith.science/paper/OLFXYVWL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.22026&json=true","fetch_graph":"https://pith.science/api/pith-number/OLFXYVWLQCU3A5ASGP7BZDK5AN/graph.json","fetch_events":"https://pith.science/api/pith-number/OLFXYVWLQCU3A5ASGP7BZDK5AN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OLFXYVWLQCU3A5ASGP7BZDK5AN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OLFXYVWLQCU3A5ASGP7BZDK5AN/action/storage_attestation","attest_author":"https://pith.science/pith/OLFXYVWLQCU3A5ASGP7BZDK5AN/action/author_attestation","sign_citation":"https://pith.science/pith/OLFXYVWLQCU3A5ASGP7BZDK5AN/action/citation_signature","submit_replication":"https://pith.science/pith/OLFXYVWLQCU3A5ASGP7BZDK5AN/action/replication_record"}},"created_at":"2026-07-05T11:28:20.693710+00:00","updated_at":"2026-07-05T11:28:20.693710+00:00"}