{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:R7N4E4K34XK7RS2QDN5MDJZCWM","short_pith_number":"pith:R7N4E4K3","schema_version":"1.0","canonical_sha256":"8fdbc2715be5d5f8cb501b7ac1a722b326910ca005c3dfad1b3c69198e63468d","source":{"kind":"arxiv","id":"2606.18686","version":1},"attestation_state":"computed","paper":{"title":"ForecastBench-Sim: A Simulated-World Forecasting Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Ezra Karger, Jaeho Lee, Nick Merrill","submitted_at":"2026-06-17T04:52:41Z","abstract_excerpt":"Forecasting benchmarks for general-purpose AI systems usually inherit the constraints of the real world: outcomes resolve slowly, tail events are rare, and counterfactual questions are difficult to score. We introduce ForecastBench-Sim, a simulated-world forecasting benchmark built on game rollouts from Freeciv, a turn-based strategy game modelled on the Civilization series. Forecasters receive a fixed world report (a structured snapshot of the current game state) and answer questions about hidden future states; the benchmark then continues the simulation and scores forecasts. Because the worl"},"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":"2606.18686","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-17T04:52:41Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"684f94585d2c31c7554a814820a5f935f03ea75b53597f97c2fbe37c57426da1","abstract_canon_sha256":"0f767cb0b10eb19f6d00dabdd5e844926beec6d9b32939224141a4a0d2303f62"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:11:44.539093Z","signature_b64":"KixpnyrIOGSZwA4E4AWlH76mFLtzYneZ++vBAx31+QcPZ/UIbU89HAHE/zi89xMvZxzLWJ5Jv6GvxpIMQ7EtBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8fdbc2715be5d5f8cb501b7ac1a722b326910ca005c3dfad1b3c69198e63468d","last_reissued_at":"2026-06-19T16:11:44.538756Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:11:44.538756Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ForecastBench-Sim: A Simulated-World Forecasting Benchmark","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Ezra Karger, Jaeho Lee, Nick Merrill","submitted_at":"2026-06-17T04:52:41Z","abstract_excerpt":"Forecasting benchmarks for general-purpose AI systems usually inherit the constraints of the real world: outcomes resolve slowly, tail events are rare, and counterfactual questions are difficult to score. We introduce ForecastBench-Sim, a simulated-world forecasting benchmark built on game rollouts from Freeciv, a turn-based strategy game modelled on the Civilization series. Forecasters receive a fixed world report (a structured snapshot of the current game state) and answer questions about hidden future states; the benchmark then continues the simulation and scores forecasts. Because the worl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18686","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/2606.18686/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":"2606.18686","created_at":"2026-06-19T16:11:44.538816+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.18686v1","created_at":"2026-06-19T16:11:44.538816+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18686","created_at":"2026-06-19T16:11:44.538816+00:00"},{"alias_kind":"pith_short_12","alias_value":"R7N4E4K34XK7","created_at":"2026-06-19T16:11:44.538816+00:00"},{"alias_kind":"pith_short_16","alias_value":"R7N4E4K34XK7RS2Q","created_at":"2026-06-19T16:11:44.538816+00:00"},{"alias_kind":"pith_short_8","alias_value":"R7N4E4K3","created_at":"2026-06-19T16:11:44.538816+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/R7N4E4K34XK7RS2QDN5MDJZCWM","json":"https://pith.science/pith/R7N4E4K34XK7RS2QDN5MDJZCWM.json","graph_json":"https://pith.science/api/pith-number/R7N4E4K34XK7RS2QDN5MDJZCWM/graph.json","events_json":"https://pith.science/api/pith-number/R7N4E4K34XK7RS2QDN5MDJZCWM/events.json","paper":"https://pith.science/paper/R7N4E4K3"},"agent_actions":{"view_html":"https://pith.science/pith/R7N4E4K34XK7RS2QDN5MDJZCWM","download_json":"https://pith.science/pith/R7N4E4K34XK7RS2QDN5MDJZCWM.json","view_paper":"https://pith.science/paper/R7N4E4K3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.18686&json=true","fetch_graph":"https://pith.science/api/pith-number/R7N4E4K34XK7RS2QDN5MDJZCWM/graph.json","fetch_events":"https://pith.science/api/pith-number/R7N4E4K34XK7RS2QDN5MDJZCWM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/R7N4E4K34XK7RS2QDN5MDJZCWM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/R7N4E4K34XK7RS2QDN5MDJZCWM/action/storage_attestation","attest_author":"https://pith.science/pith/R7N4E4K34XK7RS2QDN5MDJZCWM/action/author_attestation","sign_citation":"https://pith.science/pith/R7N4E4K34XK7RS2QDN5MDJZCWM/action/citation_signature","submit_replication":"https://pith.science/pith/R7N4E4K34XK7RS2QDN5MDJZCWM/action/replication_record"}},"created_at":"2026-06-19T16:11:44.538816+00:00","updated_at":"2026-06-19T16:11:44.538816+00:00"}