{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ABW2GBMEMDA2VC7L5U42DXSZH6","short_pith_number":"pith:ABW2GBME","schema_version":"1.0","canonical_sha256":"006da3058460c1aa8bebed39a1de593f8cd1f44b8c4d91d6dc44a11900e866a6","source":{"kind":"arxiv","id":"2506.21558","version":1},"attestation_state":"computed","paper":{"title":"Bench to the Future: A Pastcasting Benchmark for Forecasting Agents","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Daniel Hnyk, Dan Schwarz, Finn Hambly, FutureSearch: Jack Wildman, Jon Evans, Lawrence Phillips, Nikos I. Bosse, Peter M\\\"uhlbacher","submitted_at":"2025-06-11T16:18:40Z","abstract_excerpt":"Forecasting is a challenging task that offers a clearly measurable way to study AI systems. Forecasting requires a large amount of research on the internet, and evaluations require time for events to happen, making the development of forecasting benchmarks challenging. To date, no forecasting benchmark provides a realistic, hermetic, and repeatable environment for LLM forecasters. We introduce Bench To the Future (BTF), a \"pastcasting\" benchmark with hundreds of high-quality questions for which the resolution is already known. Each question is accompanied by a large offline corpus of tens of t"},"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":"2506.21558","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2025-06-11T16:18:40Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"514b6d3aedc69f73eaf5b812368c8223b8ec2e67399a1ac8583db9270b9c17cb","abstract_canon_sha256":"3a16473805d2ebb63c815a17167bc409c9286f2a222e337a6e22f11157c920c8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:27:56.341670Z","signature_b64":"Se4TkoYNj3lMuwwjDlvZ0x29hfIqf8aIhWINarmISgo/PNAeFWICVTNePTrkBfM35HEBCkubZySuvIGd34QoBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"006da3058460c1aa8bebed39a1de593f8cd1f44b8c4d91d6dc44a11900e866a6","last_reissued_at":"2026-07-05T11:27:56.341171Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:27:56.341171Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bench to the Future: A Pastcasting Benchmark for Forecasting Agents","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Daniel Hnyk, Dan Schwarz, Finn Hambly, FutureSearch: Jack Wildman, Jon Evans, Lawrence Phillips, Nikos I. Bosse, Peter M\\\"uhlbacher","submitted_at":"2025-06-11T16:18:40Z","abstract_excerpt":"Forecasting is a challenging task that offers a clearly measurable way to study AI systems. Forecasting requires a large amount of research on the internet, and evaluations require time for events to happen, making the development of forecasting benchmarks challenging. To date, no forecasting benchmark provides a realistic, hermetic, and repeatable environment for LLM forecasters. We introduce Bench To the Future (BTF), a \"pastcasting\" benchmark with hundreds of high-quality questions for which the resolution is already known. Each question is accompanied by a large offline corpus of tens of t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.21558","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/2506.21558/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":"2506.21558","created_at":"2026-07-05T11:27:56.341229+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.21558v1","created_at":"2026-07-05T11:27:56.341229+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.21558","created_at":"2026-07-05T11:27:56.341229+00:00"},{"alias_kind":"pith_short_12","alias_value":"ABW2GBMEMDA2","created_at":"2026-07-05T11:27:56.341229+00:00"},{"alias_kind":"pith_short_16","alias_value":"ABW2GBMEMDA2VC7L","created_at":"2026-07-05T11:27:56.341229+00:00"},{"alias_kind":"pith_short_8","alias_value":"ABW2GBME","created_at":"2026-07-05T11:27:56.341229+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21013","citing_title":"Agentic Time Machine as an Infrastructure for Future-Event Forecasting","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.18686","citing_title":"ForecastBench-Sim: A Simulated-World Forecasting Benchmark","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.11816","citing_title":"WorldReasoner: Evaluating Whether Language Model Agents Forecast Events with Valid Reasoning","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22672","citing_title":"Is Capability a Liability? More Capable Language Models Make Worse Forecasts When It Matters Most","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22672","citing_title":"Is Capability a Liability? More Capable Language Models Make Worse Forecasts When It Matters Most","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2602.00758","citing_title":"Temporal Leakage in Search-Engine Date-Filtered Web Retrieval: A Retrospective Forecasting Case Study","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26106","citing_title":"Evaluating Strategic Reasoning in Forecasting Agents","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15719","citing_title":"Harnessing Pre-Resolution Signals for Future Prediction Agents","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15719","citing_title":"Harnessing Pre-Resolution Signals for Future Prediction Agents","ref_index":2,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ABW2GBMEMDA2VC7L5U42DXSZH6","json":"https://pith.science/pith/ABW2GBMEMDA2VC7L5U42DXSZH6.json","graph_json":"https://pith.science/api/pith-number/ABW2GBMEMDA2VC7L5U42DXSZH6/graph.json","events_json":"https://pith.science/api/pith-number/ABW2GBMEMDA2VC7L5U42DXSZH6/events.json","paper":"https://pith.science/paper/ABW2GBME"},"agent_actions":{"view_html":"https://pith.science/pith/ABW2GBMEMDA2VC7L5U42DXSZH6","download_json":"https://pith.science/pith/ABW2GBMEMDA2VC7L5U42DXSZH6.json","view_paper":"https://pith.science/paper/ABW2GBME","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.21558&json=true","fetch_graph":"https://pith.science/api/pith-number/ABW2GBMEMDA2VC7L5U42DXSZH6/graph.json","fetch_events":"https://pith.science/api/pith-number/ABW2GBMEMDA2VC7L5U42DXSZH6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ABW2GBMEMDA2VC7L5U42DXSZH6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ABW2GBMEMDA2VC7L5U42DXSZH6/action/storage_attestation","attest_author":"https://pith.science/pith/ABW2GBMEMDA2VC7L5U42DXSZH6/action/author_attestation","sign_citation":"https://pith.science/pith/ABW2GBMEMDA2VC7L5U42DXSZH6/action/citation_signature","submit_replication":"https://pith.science/pith/ABW2GBMEMDA2VC7L5U42DXSZH6/action/replication_record"}},"created_at":"2026-07-05T11:27:56.341229+00:00","updated_at":"2026-07-05T11:27:56.341229+00:00"}