{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XVWEDMQ33PSSM6VXTHQXLIRZ7B","short_pith_number":"pith:XVWEDMQ3","schema_version":"1.0","canonical_sha256":"bd6c41b21bdbe5267ab799e175a239f8764b42b900220339987e236e0924285f","source":{"kind":"arxiv","id":"2605.10574","version":2},"attestation_state":"computed","paper":{"title":"LLM Jaggedness Unlocks Scientific Creativity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Uneven capabilities across LLMs allow model combinations to generate more scientific ideas than any single model.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Esther H. R. Tsai, J. Anibal Boscoboinik, Kevin G. Yager, Shray Mathur","submitted_at":"2026-05-11T13:47:48Z","abstract_excerpt":"As artificial intelligence advances, models are not improving uniformly. Instead, progress unfolds in a jagged fashion, with capabilities growing unevenly across tasks, domains, and model scales. In this work, we examine this dynamic jaggedness through the lens of scientific idea generation. We introduce SciAidanBench, a benchmark of open-ended scientific questions designed to measure the scientific creativity of large language models (LLMs). Given a scientific question, models are asked to generate as many unique and coherent ideas as possible, with the total number of valid responses serving"},"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":"2605.10574","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-11T13:47:48Z","cross_cats_sorted":[],"title_canon_sha256":"923e4f649e9e323b741e5708b44b798a73e7ba9ea672cf389181e14941cf3f02","abstract_canon_sha256":"61411a240af73605462fe32ae3315b900ee9a1f8ab8d3ca936170664cd5f930c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T02:05:05.103860Z","signature_b64":"0/LvPFlfwytlmbJcMSEoVycuArMw0lEPdJNZgu+DNpJnfq3O5/4gpqN1tK3IGaEqL6aFlZOsl3jE9uUrvOo7Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bd6c41b21bdbe5267ab799e175a239f8764b42b900220339987e236e0924285f","last_reissued_at":"2026-05-21T02:05:05.103096Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T02:05:05.103096Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LLM Jaggedness Unlocks Scientific Creativity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Uneven capabilities across LLMs allow model combinations to generate more scientific ideas than any single model.","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Esther H. R. Tsai, J. Anibal Boscoboinik, Kevin G. Yager, Shray Mathur","submitted_at":"2026-05-11T13:47:48Z","abstract_excerpt":"As artificial intelligence advances, models are not improving uniformly. Instead, progress unfolds in a jagged fashion, with capabilities growing unevenly across tasks, domains, and model scales. In this work, we examine this dynamic jaggedness through the lens of scientific idea generation. We introduce SciAidanBench, a benchmark of open-ended scientific questions designed to measure the scientific creativity of large language models (LLMs). Given a scientific question, models are asked to generate as many unique and coherent ideas as possible, with the total number of valid responses serving"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"we show that this jaggedness can be harnessed. We explore mechanisms of inference-time compute, knowledge pooling, and brainstorming to combine models effectively and construct meta-model ensembles that outperform any single model.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the total number of valid responses is a reliable proxy for creative potential, and that human or automated judgment of uniqueness and coherence accurately captures scientific creativity without systematic bias.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"LLMs exhibit jagged scientific creativity across models, prompts, and domains, and this unevenness can be leveraged via model ensembles to outperform any single model on idea generation.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Uneven capabilities across LLMs allow model combinations to generate more scientific ideas than any single model.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"e619787ddb22637bc360a125dd716fb789188dbf97233fb69c627ad6566f93ee"},"source":{"id":"2605.10574","kind":"arxiv","version":2},"verdict":{"id":"011f6e7f-8ad4-40b8-bb4a-ad3d4b38a771","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-12T04:03:19.429350Z","strongest_claim":"we show that this jaggedness can be harnessed. We explore mechanisms of inference-time compute, knowledge pooling, and brainstorming to combine models effectively and construct meta-model ensembles that outperform any single model.","one_line_summary":"LLMs exhibit jagged scientific creativity across models, prompts, and domains, and this unevenness can be leveraged via model ensembles to outperform any single model on idea generation.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the total number of valid responses is a reliable proxy for creative potential, and that human or automated judgment of uniqueness and coherence accurately captures scientific creativity without systematic bias.","pith_extraction_headline":"Uneven capabilities across LLMs allow model combinations to generate more scientific ideas than any single model."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.10574/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"claim_evidence","ran_at":"2026-05-20T05:42:00.897549Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T14:41:06.809597Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T11:01:17.674593Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T09:10:30.957191Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"dd350d16aece251404b101e6088ffdcd522dce9507687c2833a9b2916b7257b0"},"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":"2605.10574","created_at":"2026-05-21T02:05:05.103196+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.10574v2","created_at":"2026-05-21T02:05:05.103196+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.10574","created_at":"2026-05-21T02:05:05.103196+00:00"},{"alias_kind":"pith_short_12","alias_value":"XVWEDMQ33PSS","created_at":"2026-05-21T02:05:05.103196+00:00"},{"alias_kind":"pith_short_16","alias_value":"XVWEDMQ33PSSM6VX","created_at":"2026-05-21T02:05:05.103196+00:00"},{"alias_kind":"pith_short_8","alias_value":"XVWEDMQ3","created_at":"2026-05-21T02:05:05.103196+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/XVWEDMQ33PSSM6VXTHQXLIRZ7B","json":"https://pith.science/pith/XVWEDMQ33PSSM6VXTHQXLIRZ7B.json","graph_json":"https://pith.science/api/pith-number/XVWEDMQ33PSSM6VXTHQXLIRZ7B/graph.json","events_json":"https://pith.science/api/pith-number/XVWEDMQ33PSSM6VXTHQXLIRZ7B/events.json","paper":"https://pith.science/paper/XVWEDMQ3"},"agent_actions":{"view_html":"https://pith.science/pith/XVWEDMQ33PSSM6VXTHQXLIRZ7B","download_json":"https://pith.science/pith/XVWEDMQ33PSSM6VXTHQXLIRZ7B.json","view_paper":"https://pith.science/paper/XVWEDMQ3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.10574&json=true","fetch_graph":"https://pith.science/api/pith-number/XVWEDMQ33PSSM6VXTHQXLIRZ7B/graph.json","fetch_events":"https://pith.science/api/pith-number/XVWEDMQ33PSSM6VXTHQXLIRZ7B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XVWEDMQ33PSSM6VXTHQXLIRZ7B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XVWEDMQ33PSSM6VXTHQXLIRZ7B/action/storage_attestation","attest_author":"https://pith.science/pith/XVWEDMQ33PSSM6VXTHQXLIRZ7B/action/author_attestation","sign_citation":"https://pith.science/pith/XVWEDMQ33PSSM6VXTHQXLIRZ7B/action/citation_signature","submit_replication":"https://pith.science/pith/XVWEDMQ33PSSM6VXTHQXLIRZ7B/action/replication_record"}},"created_at":"2026-05-21T02:05:05.103196+00:00","updated_at":"2026-05-21T02:05:05.103196+00:00"}