{"event":{"id":"evt-hist-phase32-openproblembench-82-preprint","dedupe_key":"academic_benchmark_preprint_submission:2026-10-08:researchers-introduce-openproblembench-benchmark-of-82-open-scientific-problems","event_type":"academic_benchmark_preprint_submission","title":"Researchers introduce OpenProblemBench benchmark of 82 open scientific problems","summary":"October 8 arXiv submission proposes 82 unresolved math and physics problems evaluated without reference solutions by four evaluator models; a claimed 14 percent GPT-6-Astra judged solve rate is a model-graded score, not 14 percent independently verified solved open problems.","occurred_at":"2026-10-08T00:00:00.000Z","published_at":"2026-10-08T00:00:00.000Z","observed_at":"2026-10-18T11:05:00.000Z","reconstructed_at":"2026-10-18T11:05:00.000Z","ingest_type":"historical_backfill","locations":null,"status":"verified","confidence":0.88,"metadata":{"evidence_only":1,"global_novelty_not_proven":1,"no_production_writes":1,"original_position_1based":1192,"source_claims_not_independently_replicated":1},"created_at":"2026-10-19T06:01:51.359Z","updated_at":"2026-10-19T06:01:51.359Z"},"artifacts":[{"id":"art-hist-phase32-openproblembench-82-preprint","dedupe_key":"c9aca86d9132cbc05e25a8d2b5422448bef24a7a19a227be4136641d6c675f2d","canonical_url":"https://arxiv.org/abs/2610.11118","evidence_locator":"","artifact_type":"original_publication","title":"Researchers introduce OpenProblemBench benchmark of 82 open scientific problems","summary":"","creator_entities":[],"released_at":"2026-10-08T00:00:00.000Z","content_hash":null,"metadata":[],"created_at":"2026-10-19T06:01:51.359Z","updated_at":"2026-10-19T06:01:51.359Z","relation":"documented_by"}],"signals":[]}