{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:M27UQP3AFMHVD6WFPILT3AK3OL","short_pith_number":"pith:M27UQP3A","schema_version":"1.0","canonical_sha256":"66bf483f602b0f51fac57a173d815b72d2fad32ffd3941c47defa8f4340ba2f1","source":{"kind":"arxiv","id":"2606.29661","version":1},"attestation_state":"computed","paper":{"title":"Diversity is the Strength of the AI Crowd","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ben Day, Matthew Aitchison, Scott Jeen, Toby Shevlane","submitted_at":"2026-06-29T00:09:49Z","abstract_excerpt":"Top AI forecasting systems are approaching superforecaster-level accuracy on future world events, but still rely primarily on off-the-shelf LLMs combined with forecasting-specific context gathering and scaffolding. We study how to improve this recipe through ensembling: given a fixed number of samples, which off-the-shelf model forecasts should be combined to maximize accuracy? On binary questions from the Metaculus AI Benchmark, we find that individual accuracy is not enough: many frontier LLMs make highly correlated predictions, limiting the value of additional forecasts from the same or sim"},"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":"2606.29661","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-29T00:09:49Z","cross_cats_sorted":[],"title_canon_sha256":"4120b84f99c263ff9c80e891479660256f113e99efab7f8fd168d0a194646a3f","abstract_canon_sha256":"fdf4986fe7b7bdb0082af51f34b41a1c21556414bd6be7d3c301bd06bf775a51"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:29.307633Z","signature_b64":"ZAsX1pldhOGADGOl8uA9KUSFIRXq+COaAcvk/YcoqFXeeekjjQHBoo31h6MeocTCBIYTMniDi2r462/nv8P1DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66bf483f602b0f51fac57a173d815b72d2fad32ffd3941c47defa8f4340ba2f1","last_reissued_at":"2026-06-30T02:17:29.307088Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:29.307088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diversity is the Strength of the AI Crowd","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ben Day, Matthew Aitchison, Scott Jeen, Toby Shevlane","submitted_at":"2026-06-29T00:09:49Z","abstract_excerpt":"Top AI forecasting systems are approaching superforecaster-level accuracy on future world events, but still rely primarily on off-the-shelf LLMs combined with forecasting-specific context gathering and scaffolding. We study how to improve this recipe through ensembling: given a fixed number of samples, which off-the-shelf model forecasts should be combined to maximize accuracy? On binary questions from the Metaculus AI Benchmark, we find that individual accuracy is not enough: many frontier LLMs make highly correlated predictions, limiting the value of additional forecasts from the same or sim"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.29661","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/2606.29661/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":"2606.29661","created_at":"2026-06-30T02:17:29.307176+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.29661v1","created_at":"2026-06-30T02:17:29.307176+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.29661","created_at":"2026-06-30T02:17:29.307176+00:00"},{"alias_kind":"pith_short_12","alias_value":"M27UQP3AFMHV","created_at":"2026-06-30T02:17:29.307176+00:00"},{"alias_kind":"pith_short_16","alias_value":"M27UQP3AFMHVD6WF","created_at":"2026-06-30T02:17:29.307176+00:00"},{"alias_kind":"pith_short_8","alias_value":"M27UQP3A","created_at":"2026-06-30T02:17:29.307176+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/M27UQP3AFMHVD6WFPILT3AK3OL","json":"https://pith.science/pith/M27UQP3AFMHVD6WFPILT3AK3OL.json","graph_json":"https://pith.science/api/pith-number/M27UQP3AFMHVD6WFPILT3AK3OL/graph.json","events_json":"https://pith.science/api/pith-number/M27UQP3AFMHVD6WFPILT3AK3OL/events.json","paper":"https://pith.science/paper/M27UQP3A"},"agent_actions":{"view_html":"https://pith.science/pith/M27UQP3AFMHVD6WFPILT3AK3OL","download_json":"https://pith.science/pith/M27UQP3AFMHVD6WFPILT3AK3OL.json","view_paper":"https://pith.science/paper/M27UQP3A","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.29661&json=true","fetch_graph":"https://pith.science/api/pith-number/M27UQP3AFMHVD6WFPILT3AK3OL/graph.json","fetch_events":"https://pith.science/api/pith-number/M27UQP3AFMHVD6WFPILT3AK3OL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M27UQP3AFMHVD6WFPILT3AK3OL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M27UQP3AFMHVD6WFPILT3AK3OL/action/storage_attestation","attest_author":"https://pith.science/pith/M27UQP3AFMHVD6WFPILT3AK3OL/action/author_attestation","sign_citation":"https://pith.science/pith/M27UQP3AFMHVD6WFPILT3AK3OL/action/citation_signature","submit_replication":"https://pith.science/pith/M27UQP3AFMHVD6WFPILT3AK3OL/action/replication_record"}},"created_at":"2026-06-30T02:17:29.307176+00:00","updated_at":"2026-06-30T02:17:29.307176+00:00"}