{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XVWEDMQ33PSSM6VXTHQXLIRZ7B","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":"61411a240af73605462fe32ae3315b900ee9a1f8ab8d3ca936170664cd5f930c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-11T13:47:48Z","title_canon_sha256":"923e4f649e9e323b741e5708b44b798a73e7ba9ea672cf389181e14941cf3f02"},"schema_version":"1.0","source":{"id":"2605.10574","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.10574","created_at":"2026-05-21T02:05:05Z"},{"alias_kind":"arxiv_version","alias_value":"2605.10574v2","created_at":"2026-05-21T02:05:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.10574","created_at":"2026-05-21T02:05:05Z"},{"alias_kind":"pith_short_12","alias_value":"XVWEDMQ33PSS","created_at":"2026-05-21T02:05:05Z"},{"alias_kind":"pith_short_16","alias_value":"XVWEDMQ33PSSM6VX","created_at":"2026-05-21T02:05:05Z"},{"alias_kind":"pith_short_8","alias_value":"XVWEDMQ3","created_at":"2026-05-21T02:05:05Z"}],"graph_snapshots":[{"event_id":"sha256:609c0556f65ceb9c5414e52335e7bf9a4c0597f9298d636fe1d62fed046797df","target":"graph","created_at":"2026-05-21T02:05:05Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Uneven capabilities across LLMs allow model combinations to generate more scientific ideas than any single model."}],"snapshot_sha256":"e619787ddb22637bc360a125dd716fb789188dbf97233fb69c627ad6566f93ee"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[{"findings_count":0,"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"}],"endpoint":"/pith/2605.10574/integrity.json","findings":[],"snapshot_sha256":"dd350d16aece251404b101e6088ffdcd522dce9507687c2833a9b2916b7257b0","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Esther H. R. Tsai, J. Anibal Boscoboinik, Kevin G. Yager, Shray Mathur","cross_cats":[],"headline":"Uneven capabilities across LLMs allow model combinations to generate more scientific ideas than any single model.","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-11T13:47:48Z","title":"LLM Jaggedness Unlocks Scientific Creativity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.10574","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-12T04:03:19.429350Z","id":"011f6e7f-8ad4-40b8-bb4a-ad3d4b38a771","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"Uneven capabilities across LLMs allow model combinations to generate more scientific ideas than any single model.","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.","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."}},"verdict_id":"011f6e7f-8ad4-40b8-bb4a-ad3d4b38a771"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:29d92c8a27b2c6c636e3bc7f34c1e2f5292c44e54e4bf03dfb19f818a9a5ffbb","target":"record","created_at":"2026-05-21T02:05:05Z","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":"61411a240af73605462fe32ae3315b900ee9a1f8ab8d3ca936170664cd5f930c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-11T13:47:48Z","title_canon_sha256":"923e4f649e9e323b741e5708b44b798a73e7ba9ea672cf389181e14941cf3f02"},"schema_version":"1.0","source":{"id":"2605.10574","kind":"arxiv","version":2}},"canonical_sha256":"bd6c41b21bdbe5267ab799e175a239f8764b42b900220339987e236e0924285f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bd6c41b21bdbe5267ab799e175a239f8764b42b900220339987e236e0924285f","first_computed_at":"2026-05-21T02:05:05.103096Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T02:05:05.103096Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"0/LvPFlfwytlmbJcMSEoVycuArMw0lEPdJNZgu+DNpJnfq3O5/4gpqN1tK3IGaEqL6aFlZOsl3jE9uUrvOo7Ag==","signature_status":"signed_v1","signed_at":"2026-05-21T02:05:05.103860Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.10574","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:29d92c8a27b2c6c636e3bc7f34c1e2f5292c44e54e4bf03dfb19f818a9a5ffbb","sha256:609c0556f65ceb9c5414e52335e7bf9a4c0597f9298d636fe1d62fed046797df"],"state_sha256":"ecddc5409760f3392756faf4349278fa5ad4817f417c72adca26f7993bcbfb88"}