{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:X5QGPPJJMIJVBV343QB75MM6YK","short_pith_number":"pith:X5QGPPJJ","schema_version":"1.0","canonical_sha256":"bf6067bd29621350d77cdc03feb19ec2b27894e9ef72c832c3a1f8254aa21e17","source":{"kind":"arxiv","id":"2310.13014","version":1},"attestation_state":"computed","paper":{"title":"Large Language Model Prediction Capabilities: Evidence from a Real-World Forecasting Tournament","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CY","authors_text":"Peter S. Park, Philipp Schoenegger","submitted_at":"2023-10-17T17:58:17Z","abstract_excerpt":"Accurately predicting the future would be an important milestone in the capabilities of artificial intelligence. However, research on the ability of large language models to provide probabilistic predictions about future events remains nascent. To empirically test this ability, we enrolled OpenAI's state-of-the-art large language model, GPT-4, in a three-month forecasting tournament hosted on the Metaculus platform. The tournament, running from July to October 2023, attracted 843 participants and covered diverse topics including Big Tech, U.S. politics, viral outbreaks, and the Ukraine conflic"},"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":"2310.13014","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CY","submitted_at":"2023-10-17T17:58:17Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"ac5a13cc74ce91023529135b2b5021aa7bc47f526b15bbec576e894d5b16b9a8","abstract_canon_sha256":"41d046bd9dd6d291eb3bde280845239cb57892c39e12b5c0729b56df7ccd340d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:02:55.706570Z","signature_b64":"adwx7D+mlSijjonFdYNJugM+sEuN8vMp0kSrzYWeKnKjMj2TeXAkxfYzStFaFCCke+I7WiPPsAcF2uRfDyHTBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf6067bd29621350d77cdc03feb19ec2b27894e9ef72c832c3a1f8254aa21e17","last_reissued_at":"2026-07-05T07:02:55.705831Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:02:55.705831Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Model Prediction Capabilities: Evidence from a Real-World Forecasting Tournament","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CY","authors_text":"Peter S. Park, Philipp Schoenegger","submitted_at":"2023-10-17T17:58:17Z","abstract_excerpt":"Accurately predicting the future would be an important milestone in the capabilities of artificial intelligence. However, research on the ability of large language models to provide probabilistic predictions about future events remains nascent. To empirically test this ability, we enrolled OpenAI's state-of-the-art large language model, GPT-4, in a three-month forecasting tournament hosted on the Metaculus platform. The tournament, running from July to October 2023, attracted 843 participants and covered diverse topics including Big Tech, U.S. politics, viral outbreaks, and the Ukraine conflic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.13014","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/2310.13014/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":"2310.13014","created_at":"2026-07-05T07:02:55.705894+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.13014v1","created_at":"2026-07-05T07:02:55.705894+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.13014","created_at":"2026-07-05T07:02:55.705894+00:00"},{"alias_kind":"pith_short_12","alias_value":"X5QGPPJJMIJV","created_at":"2026-07-05T07:02:55.705894+00:00"},{"alias_kind":"pith_short_16","alias_value":"X5QGPPJJMIJVBV34","created_at":"2026-07-05T07:02:55.705894+00:00"},{"alias_kind":"pith_short_8","alias_value":"X5QGPPJJ","created_at":"2026-07-05T07:02:55.705894+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.01661","citing_title":"Diverse Evidence, Better Forecasts: Multi-Agent Deliberation Under Information Asymmetry","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11482","citing_title":"Building Social World Models with Large Language Models","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03310","citing_title":"Coordination as an Architectural Layer for LLM-Based Multi-Agent Systems","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00420","citing_title":"Foresight Arena: An On-Chain Benchmark for Evaluating AI Forecasting Agents","ref_index":11,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X5QGPPJJMIJVBV343QB75MM6YK","json":"https://pith.science/pith/X5QGPPJJMIJVBV343QB75MM6YK.json","graph_json":"https://pith.science/api/pith-number/X5QGPPJJMIJVBV343QB75MM6YK/graph.json","events_json":"https://pith.science/api/pith-number/X5QGPPJJMIJVBV343QB75MM6YK/events.json","paper":"https://pith.science/paper/X5QGPPJJ"},"agent_actions":{"view_html":"https://pith.science/pith/X5QGPPJJMIJVBV343QB75MM6YK","download_json":"https://pith.science/pith/X5QGPPJJMIJVBV343QB75MM6YK.json","view_paper":"https://pith.science/paper/X5QGPPJJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.13014&json=true","fetch_graph":"https://pith.science/api/pith-number/X5QGPPJJMIJVBV343QB75MM6YK/graph.json","fetch_events":"https://pith.science/api/pith-number/X5QGPPJJMIJVBV343QB75MM6YK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X5QGPPJJMIJVBV343QB75MM6YK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X5QGPPJJMIJVBV343QB75MM6YK/action/storage_attestation","attest_author":"https://pith.science/pith/X5QGPPJJMIJVBV343QB75MM6YK/action/author_attestation","sign_citation":"https://pith.science/pith/X5QGPPJJMIJVBV343QB75MM6YK/action/citation_signature","submit_replication":"https://pith.science/pith/X5QGPPJJMIJVBV343QB75MM6YK/action/replication_record"}},"created_at":"2026-07-05T07:02:55.705894+00:00","updated_at":"2026-07-05T07:02:55.705894+00:00"}