{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:TNEVT3YRPDJO5QP5E7HXVNLW2V","short_pith_number":"pith:TNEVT3YR","schema_version":"1.0","canonical_sha256":"9b4959ef1178d2eec1fd27cf7ab576d54d66a7d666e76253ad63bbe488f3b2f5","source":{"kind":"arxiv","id":"2606.10587","version":1},"attestation_state":"computed","paper":{"title":"Towards Diverse Scientific Hypothesis Search with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chandan K. Reddy, Chao Zhang, Haorui Wang, Jiajun He, Jos\\'e Miguel Hern\\'andez-Lobato, Kazem Meidani, Kunyang Sun, Parshin Shojaee, Teresa Head-Gordon, Yuanqi Du","submitted_at":"2026-06-09T08:52:49Z","abstract_excerpt":"Large language models (LLMs) are on the rise for accelerating scientific discovery, most recently in advanced tasks such as generating valid scientific hypotheses. Yet in many discovery settings, the goal is not to identify a single best hypothesis since validation can be noisy and expensive, and scientists benefit from a set of high-quality alternative hypotheses that hedge against downstream uncertainty for the best solutions. Nevertheless, commonly used evolutionary search recipes tend to prioritize optimization over exploration in hypothesis generation, and the resulting selection pressure"},"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":"2606.10587","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-06-09T08:52:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2eda80b09a4320ae3ecc4cc2a6983350cb620ffb8c78ef4c8d66fd4c6638ef95","abstract_canon_sha256":"116bed223cbdffba29aa4f5015b41aea96f39a6867555919f043422ed2180d55"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:10:28.201109Z","signature_b64":"2/GN2LVMvckAYRDloWvQ+MqL7ahbkpbYdvl84unwRTG30rOO7X1oAt6qS1sNcLYuRT3WlUAvdgmzg8WilNJRBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9b4959ef1178d2eec1fd27cf7ab576d54d66a7d666e76253ad63bbe488f3b2f5","last_reissued_at":"2026-06-10T01:10:28.200289Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:10:28.200289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Diverse Scientific Hypothesis Search with Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chandan K. Reddy, Chao Zhang, Haorui Wang, Jiajun He, Jos\\'e Miguel Hern\\'andez-Lobato, Kazem Meidani, Kunyang Sun, Parshin Shojaee, Teresa Head-Gordon, Yuanqi Du","submitted_at":"2026-06-09T08:52:49Z","abstract_excerpt":"Large language models (LLMs) are on the rise for accelerating scientific discovery, most recently in advanced tasks such as generating valid scientific hypotheses. Yet in many discovery settings, the goal is not to identify a single best hypothesis since validation can be noisy and expensive, and scientists benefit from a set of high-quality alternative hypotheses that hedge against downstream uncertainty for the best solutions. Nevertheless, commonly used evolutionary search recipes tend to prioritize optimization over exploration in hypothesis generation, and the resulting selection pressure"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.10587","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/2606.10587/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":"2606.10587","created_at":"2026-06-10T01:10:28.200442+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.10587v1","created_at":"2026-06-10T01:10:28.200442+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.10587","created_at":"2026-06-10T01:10:28.200442+00:00"},{"alias_kind":"pith_short_12","alias_value":"TNEVT3YRPDJO","created_at":"2026-06-10T01:10:28.200442+00:00"},{"alias_kind":"pith_short_16","alias_value":"TNEVT3YRPDJO5QP5","created_at":"2026-06-10T01:10:28.200442+00:00"},{"alias_kind":"pith_short_8","alias_value":"TNEVT3YR","created_at":"2026-06-10T01:10:28.200442+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TNEVT3YRPDJO5QP5E7HXVNLW2V","json":"https://pith.science/pith/TNEVT3YRPDJO5QP5E7HXVNLW2V.json","graph_json":"https://pith.science/api/pith-number/TNEVT3YRPDJO5QP5E7HXVNLW2V/graph.json","events_json":"https://pith.science/api/pith-number/TNEVT3YRPDJO5QP5E7HXVNLW2V/events.json","paper":"https://pith.science/paper/TNEVT3YR"},"agent_actions":{"view_html":"https://pith.science/pith/TNEVT3YRPDJO5QP5E7HXVNLW2V","download_json":"https://pith.science/pith/TNEVT3YRPDJO5QP5E7HXVNLW2V.json","view_paper":"https://pith.science/paper/TNEVT3YR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.10587&json=true","fetch_graph":"https://pith.science/api/pith-number/TNEVT3YRPDJO5QP5E7HXVNLW2V/graph.json","fetch_events":"https://pith.science/api/pith-number/TNEVT3YRPDJO5QP5E7HXVNLW2V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TNEVT3YRPDJO5QP5E7HXVNLW2V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TNEVT3YRPDJO5QP5E7HXVNLW2V/action/storage_attestation","attest_author":"https://pith.science/pith/TNEVT3YRPDJO5QP5E7HXVNLW2V/action/author_attestation","sign_citation":"https://pith.science/pith/TNEVT3YRPDJO5QP5E7HXVNLW2V/action/citation_signature","submit_replication":"https://pith.science/pith/TNEVT3YRPDJO5QP5E7HXVNLW2V/action/replication_record"}},"created_at":"2026-06-10T01:10:28.200442+00:00","updated_at":"2026-06-10T01:10:28.200442+00:00"}