{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UJZWTMLPXLIU7BCLDPZAX3EZ6Q","short_pith_number":"pith:UJZWTMLP","schema_version":"1.0","canonical_sha256":"a27369b16fbad14f844b1bf20bec99f4328604e86ea3b7c6021a92b0d894b5bd","source":{"kind":"arxiv","id":"2508.11987","version":3},"attestation_state":"computed","paper":{"title":"FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Ge Zhang, Jiacheng Guo, Jianpeng Jiao, Jiashuo Liu, Jiecao Chen, Jingkai Liu, Jinpeng Wang, Jose Blanchet, Kaiyuan Zhang, Liang Hu, Lingyue Yin, Mengdi Wang, Mingren Yin, Shuang Ni, Siyuan Chen, Tianci He, Tianle Cai, Wenhao Huang, Xiang Gao, Xiangsheng Li, Xin Zhou, Xipeng Qiu, Yali Liao, Yang Yang, Yantao Du, Yixiao Tian, Zaiyuan Wang, Zehui Chen, Zhenwei Zhu, Zhiyuan Zeng, Zhoufutu Wen","submitted_at":"2025-08-16T08:54:08Z","abstract_excerpt":"Future prediction is a complex task for LLM agents, requiring a high level of analytical thinking, information gathering, contextual understanding, and decision-making under uncertainty. Agents must not only gather and interpret vast amounts of dynamic information but also integrate diverse data sources, weigh uncertainties, and adapt predictions based on emerging trends, just as human experts do in fields like politics, economics, and finance. Despite its importance, no large-scale benchmark exists for evaluating agents on future prediction, largely due to challenges in handling real-time upd"},"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":"2508.11987","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-16T08:54:08Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6c77bb37039e0d46b1258095b61ab06411b4029ab240e451d2d0d415527f049b","abstract_canon_sha256":"5b9a956d36e0039c7299d3793bd97e5ba7a4084048c35e8433029934a5522eb1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:20.042803Z","signature_b64":"Xl3GHyVRKJ4x1Oea8X7y4aSpbsaVbsWC9Rp2PghkYXmKdpcreoD4EP3sfHLnOrBpxjEa2QwxsBjKSTw6Qw+9DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a27369b16fbad14f844b1bf20bec99f4328604e86ea3b7c6021a92b0d894b5bd","last_reissued_at":"2026-07-05T12:05:20.042288Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:20.042288Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FutureX: An Advanced Live Benchmark for LLM Agents in Future Prediction","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Ge Zhang, Jiacheng Guo, Jianpeng Jiao, Jiashuo Liu, Jiecao Chen, Jingkai Liu, Jinpeng Wang, Jose Blanchet, Kaiyuan Zhang, Liang Hu, Lingyue Yin, Mengdi Wang, Mingren Yin, Shuang Ni, Siyuan Chen, Tianci He, Tianle Cai, Wenhao Huang, Xiang Gao, Xiangsheng Li, Xin Zhou, Xipeng Qiu, Yali Liao, Yang Yang, Yantao Du, Yixiao Tian, Zaiyuan Wang, Zehui Chen, Zhenwei Zhu, Zhiyuan Zeng, Zhoufutu Wen","submitted_at":"2025-08-16T08:54:08Z","abstract_excerpt":"Future prediction is a complex task for LLM agents, requiring a high level of analytical thinking, information gathering, contextual understanding, and decision-making under uncertainty. Agents must not only gather and interpret vast amounts of dynamic information but also integrate diverse data sources, weigh uncertainties, and adapt predictions based on emerging trends, just as human experts do in fields like politics, economics, and finance. Despite its importance, no large-scale benchmark exists for evaluating agents on future prediction, largely due to challenges in handling real-time upd"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.11987","kind":"arxiv","version":3},"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/2508.11987/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":"2508.11987","created_at":"2026-07-05T12:05:20.042362+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.11987v3","created_at":"2026-07-05T12:05:20.042362+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.11987","created_at":"2026-07-05T12:05:20.042362+00:00"},{"alias_kind":"pith_short_12","alias_value":"UJZWTMLPXLIU","created_at":"2026-07-05T12:05:20.042362+00:00"},{"alias_kind":"pith_short_16","alias_value":"UJZWTMLPXLIU7BCL","created_at":"2026-07-05T12:05:20.042362+00:00"},{"alias_kind":"pith_short_8","alias_value":"UJZWTMLP","created_at":"2026-07-05T12:05:20.042362+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":14,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21013","citing_title":"Agentic Time Machine as an Infrastructure for Future-Event Forecasting","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2607.01661","citing_title":"Diverse Evidence, Better Forecasts: Multi-Agent Deliberation Under Information Asymmetry","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11816","citing_title":"WorldReasoner: Evaluating Whether Language Model Agents Forecast Events with Valid Reasoning","ref_index":45,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00644","citing_title":"ForeSci: Evaluating LLM Agents for Forward-Looking AI Research Judgment","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22681","citing_title":"Forecasting Scientific Progress with Artificial Intelligence","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2512.00417","citing_title":"CryptoBench: A Dynamic Benchmark for Expert-Level Evaluation of LLM Agents in Cryptocurrency","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14199","citing_title":"PolyBench: Benchmarking LLM Forecasting and Trading Capabilities on Live Prediction Market Data","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26235","citing_title":"LATTICE: Evaluating Decision Support Utility of Crypto Agents","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03762","citing_title":"OracleProto: A Reproducible Framework for Benchmarking LLM Native Forecasting via Knowledge Cutoff and Temporal Masking","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23072","citing_title":"Analytica: Soft Propositional Reasoning for Robust and Scalable LLM-Driven Analysis","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18576","citing_title":"Agentic Forecasting using Sequential Bayesian Updating of Linguistic Beliefs","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15719","citing_title":"Harnessing Pre-Resolution Signals for Future Prediction Agents","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15719","citing_title":"Harnessing Pre-Resolution Signals for Future Prediction Agents","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27865","citing_title":"KellyBench: A Benchmark for Long-Horizon Sequential Decision Making","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UJZWTMLPXLIU7BCLDPZAX3EZ6Q","json":"https://pith.science/pith/UJZWTMLPXLIU7BCLDPZAX3EZ6Q.json","graph_json":"https://pith.science/api/pith-number/UJZWTMLPXLIU7BCLDPZAX3EZ6Q/graph.json","events_json":"https://pith.science/api/pith-number/UJZWTMLPXLIU7BCLDPZAX3EZ6Q/events.json","paper":"https://pith.science/paper/UJZWTMLP"},"agent_actions":{"view_html":"https://pith.science/pith/UJZWTMLPXLIU7BCLDPZAX3EZ6Q","download_json":"https://pith.science/pith/UJZWTMLPXLIU7BCLDPZAX3EZ6Q.json","view_paper":"https://pith.science/paper/UJZWTMLP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.11987&json=true","fetch_graph":"https://pith.science/api/pith-number/UJZWTMLPXLIU7BCLDPZAX3EZ6Q/graph.json","fetch_events":"https://pith.science/api/pith-number/UJZWTMLPXLIU7BCLDPZAX3EZ6Q/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UJZWTMLPXLIU7BCLDPZAX3EZ6Q/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UJZWTMLPXLIU7BCLDPZAX3EZ6Q/action/storage_attestation","attest_author":"https://pith.science/pith/UJZWTMLPXLIU7BCLDPZAX3EZ6Q/action/author_attestation","sign_citation":"https://pith.science/pith/UJZWTMLPXLIU7BCLDPZAX3EZ6Q/action/citation_signature","submit_replication":"https://pith.science/pith/UJZWTMLPXLIU7BCLDPZAX3EZ6Q/action/replication_record"}},"created_at":"2026-07-05T12:05:20.042362+00:00","updated_at":"2026-07-05T12:05:20.042362+00:00"}