{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WQ66NAS7QRJQWP4HPYLRQ2N4ST","short_pith_number":"pith:WQ66NAS7","schema_version":"1.0","canonical_sha256":"b43de6825f84530b3f877e171869bc94eab8d04bd392bd457dcb524b154deb46","source":{"kind":"arxiv","id":"2605.15188","version":1},"attestation_state":"computed","paper":{"title":"FutureSim: Replaying World Events to Evaluate Adaptive Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"FutureSim evaluates AI agents by replaying real historical events in order and shows even the best achieve only 25 percent accuracy on future predictions.","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Ameya Prabhu, Arvindh Arun, Jonas Geiping, Maksym Andriushchenko, Moritz Hardt, Nikhil Chandak, Shashwat Goel, Steffen Staab","submitted_at":"2026-05-14T17:59:28Z","abstract_excerpt":"AI agents are being increasingly deployed in dynamic, open-ended environments that require adapting to new information as it arrives. To efficiently measure this capability for realistic use-cases, we propose building grounded simulations that replay real-world events in the order they occurred. We build FutureSim, where agents forecast world events beyond their knowledge cutoff while interacting with a chronological replay of the world: real news articles arriving and questions resolving over the simulated period. We evaluate frontier agents in their native harness, testing their ability to p"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.15188","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T17:59:28Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"131de9b90c4210166213f7230b50e3513bf7fc6742b5a6d98d95edbdd3897002","abstract_canon_sha256":"f79f3e8bfe083d3301c4d1dae9a620b2c49a6264f13323f074fd97ad4e825d76"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.2","canonical_sha256":"b43de6825f84530b3f877e171869bc94eab8d04bd392bd457dcb524b154deb46","last_reissued_at":"2026-05-17T21:57:18.480573Z","signature_status":"unsigned_v0","first_computed_at":"2026-05-17T21:40:25.093331Z"},"graph_snapshot":{"paper":{"title":"FutureSim: Replaying World Events to Evaluate Adaptive Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"FutureSim evaluates AI agents by replaying real historical events in order and shows even the best achieve only 25 percent accuracy on future predictions.","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.LG","authors_text":"Ameya Prabhu, Arvindh Arun, Jonas Geiping, Maksym Andriushchenko, Moritz Hardt, Nikhil Chandak, Shashwat Goel, Steffen Staab","submitted_at":"2026-05-14T17:59:28Z","abstract_excerpt":"AI agents are being increasingly deployed in dynamic, open-ended environments that require adapting to new information as it arrives. To efficiently measure this capability for realistic use-cases, we propose building grounded simulations that replay real-world events in the order they occurred. We build FutureSim, where agents forecast world events beyond their knowledge cutoff while interacting with a chronological replay of the world: real news articles arriving and questions resolving over the simulated period. We evaluate frontier agents in their native harness, testing their ability to p"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"FutureSim reveals a clear separation in their capabilities, with the best agent's accuracy being 25%, and many having worse Brier skill score than making no prediction at all.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That replaying real historical events chronologically without future knowledge leakage accurately measures an agent's adaptive capabilities in open-ended real-world settings.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"FutureSim is a benchmark that replays real news from January to March 2026 for AI agents to forecast events, with top accuracy at 25% and some agents worse than no-prediction baselines on Brier skill score.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"FutureSim evaluates AI agents by replaying real historical events in order and shows even the best achieve only 25 percent accuracy on future predictions.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"162a363276cac9ee69424ab8967097dedc85f9a09d938c5ff0d36ca3518e1ce7"},"source":{"id":"2605.15188","kind":"arxiv","version":1},"verdict":{"id":"ee187d39-2dbe-4949-9514-d3edbd034f12","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T03:08:02.403868Z","strongest_claim":"FutureSim reveals a clear separation in their capabilities, with the best agent's accuracy being 25%, and many having worse Brier skill score than making no prediction at all.","one_line_summary":"FutureSim is a benchmark that replays real news from January to March 2026 for AI agents to forecast events, with top accuracy at 25% and some agents worse than no-prediction baselines on Brier skill score.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That replaying real historical events chronologically without future knowledge leakage accurately measures an agent's adaptive capabilities in open-ended real-world settings.","pith_extraction_headline":"FutureSim evaluates AI agents by replaying real historical events in order and shows even the best achieve only 25 percent accuracy on future predictions."},"references":{"count":25,"sample":[{"doi":"10.5281/zenodo.1207631","year":2018,"title":"World models","work_id":"74007479-6f51-4839-ae30-4d6122d21c36","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2026,"title":"Lost in simulation: Llm-simulated users are unreliable proxies for human users in agentic evaluations","work_id":"1e07215b-a63b-418a-8387-6f3ccef28361","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"just give the model shell and tool access","work_id":"d4881466-cfe9-4f1b-95d7-3b358380ab45","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"Context consumption feedback:After each tool call, the agent receives feedback about remaining context budget and approximate context occupancy. This is useful because the task spans thousands of turn","work_id":"c90e391d-d088-4e4f-880f-346a36ccc7cb","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":null,"title":"The goal is to make memory writing and retrieval deliberate actions rather than accidental byproducts of shell usage","work_id":"335abbb3-e733-4812-972b-67211b25b759","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":25,"snapshot_sha256":"98adbddef2b0d635a05aa2a0371620041f76819bc33f8144f0c8c6d153cc870f","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":"2605.15188","created_at":"2026-05-17T21:18:32.780863+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15188v1","created_at":"2026-05-17T21:18:32.780863+00:00"},{"alias_kind":"pith_short_12","alias_value":"WQ66NAS7QRJQ","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"WQ66NAS7QRJQWP4H","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"WQ66NAS7","created_at":"2026-05-18T12:33:37.589309+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/WQ66NAS7QRJQWP4HPYLRQ2N4ST","json":"https://pith.science/pith/WQ66NAS7QRJQWP4HPYLRQ2N4ST.json","graph_json":"https://pith.science/api/pith-number/WQ66NAS7QRJQWP4HPYLRQ2N4ST/graph.json","events_json":"https://pith.science/api/pith-number/WQ66NAS7QRJQWP4HPYLRQ2N4ST/events.json","paper":"https://pith.science/paper/WQ66NAS7"},"agent_actions":{"view_html":"https://pith.science/pith/WQ66NAS7QRJQWP4HPYLRQ2N4ST","download_json":"https://pith.science/pith/WQ66NAS7QRJQWP4HPYLRQ2N4ST.json","view_paper":"https://pith.science/paper/WQ66NAS7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15188&json=true","fetch_graph":"https://pith.science/api/pith-number/WQ66NAS7QRJQWP4HPYLRQ2N4ST/graph.json","fetch_events":"https://pith.science/api/pith-number/WQ66NAS7QRJQWP4HPYLRQ2N4ST/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WQ66NAS7QRJQWP4HPYLRQ2N4ST/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WQ66NAS7QRJQWP4HPYLRQ2N4ST/action/storage_attestation","attest_author":"https://pith.science/pith/WQ66NAS7QRJQWP4HPYLRQ2N4ST/action/author_attestation","sign_citation":"https://pith.science/pith/WQ66NAS7QRJQWP4HPYLRQ2N4ST/action/citation_signature","submit_replication":"https://pith.science/pith/WQ66NAS7QRJQWP4HPYLRQ2N4ST/action/replication_record"}},"created_at":"2026-05-17T21:18:32.780863+00:00","updated_at":"2026-05-17T21:57:18.480660+00:00"}